Showing papers in "BME frontiers in 2022"

Ultrasound-Mediated Drug Delivery: Sonoporation Mechanisms, Biophysics, and Critical Factors

Abstract: Sonoporation, or the use of ultrasound in the presence of cavitation nuclei to induce plasma membrane perforation, is well considered as an emerging physical approach to facilitate the delivery of drugs and genes to living cells. Nevertheless, this emerging drug delivery paradigm has not yet reached widespread clinical use, because the efficiency of sonoporation is often deemed to be mediocre due to the lack of detailed understanding of the pertinent scientific mechanisms. Here, we summarize the current observational evidence available on the notion of sonoporation, and we discuss the prevailing understanding of the physical and biological processes related to sonoporation. To facilitate systematic understanding, we also present how the extent of sonoporation is dependent on a multitude of factors related to acoustic excitation parameters (ultrasound frequency, pressure, cavitation dose, exposure time), microbubble parameters (size, concentration, bubble-to-cell distance, shell composition), and cellular properties (cell type, cell cycle, biochemical contents). By adopting a science-backed approach to the realization of sonoporation, ultrasound-mediated drug delivery can be more controllably achieved to viably enhance drug uptake into living cells with high sonoporation efficiency. This drug delivery approach, when coupled with concurrent advances in ultrasound imaging, has potential to become an effective therapeutic paradigm.

Recent Advancements in Ultrasound Transducer: From Material Strategies to Biomedical Applications

Abstract: Ultrasound is extensively studied for biomedical engineering applications. As the core part of the ultrasonic system, the ultrasound transducer plays a significant role. For the purpose of meeting the requirement of precision medicine, the main challenge for the development of ultrasound transducer is to further enhance its performance. In this article, an overview of recent developments in ultrasound transducer technologies that use a variety of material strategies and device designs based on both the piezoelectric and photoacoustic mechanisms is provided. Practical applications are also presented, including ultrasound imaging, ultrasound therapy, particle/cell manipulation, drug delivery, and nerve stimulation. Finally, perspectives and opportunities are also highlighted.

A Review of Deep Learning Applications in Lung Ultrasound Imaging of COVID-19 Patients

Abstract: The massive and continuous spread of COVID-19 has motivated researchers around the world to intensely explore, understand, and develop new techniques for diagnosis and treatment. Although lung ultrasound imaging is a less established approach when compared to other medical imaging modalities such as X-ray and CT, multiple studies have demonstrated its promise to diagnose COVID-19 patients. At the same time, many deep learning models have been built to improve the diagnostic efficiency of medical imaging. The integration of these initially parallel efforts has led multiple researchers to report deep learning applications in medical imaging of COVID-19 patients, most of which demonstrate the outstanding potential of deep learning to aid in the diagnosis of COVID-19. This invited review is focused on deep learning applications in lung ultrasound imaging of COVID-19 and provides a comprehensive overview of ultrasound systems utilized for data acquisition, associated datasets, deep learning models, and comparative performance.

A Low-Cost High-Performance Data Augmentation for Deep Learning-Based Skin Lesion Classification

Abstract: Objective and Impact Statement. There is a need to develop high-performance and low-cost data augmentation strategies for intelligent skin cancer screening devices that can be deployed in rural or underdeveloped communities. The proposed strategy can not only improve the classification performance of skin lesions but also highlight the potential regions of interest for clinicians’ attention. This strategy can also be implemented in a broad range of clinical disciplines for early screening and automatic diagnosis of many other diseases in low resource settings. Methods. We propose a high-performance data augmentation strategy of search space 101, which can be combined with any model through a plug-and-play mode and search for the best argumentation method for a medical database with low resource cost. Results. With EfficientNets as a baseline, the best BACC of HAM10000 is 0.853, outperforming the other published models of “single-model and no-external-database” for ISIC 2018 Lesion Diagnosis Challenge (Task 3). The best average AUC performance on ISIC 2017 achieves 0.909 (±0.015), exceeding most of the ensembling models and those using external datasets. Performance on Derm7pt archives the best BACC of 0.735 (±0.018) ahead of all other related studies. Moreover, the model-based heatmaps generated by Grad-CAM++ verify the accurate selection of lesion features in model judgment, further proving the scientific rationality of model-based diagnosis. Conclusion. The proposed data augmentation strategy greatly reduces the computational cost for clinically intelligent diagnosis of skin lesions. It may also facilitate further research in low-cost, portable, and AI-based mobile devices for skin cancer screening and therapeutic guidance.

Impedance Imaging of Cells and Tissues: Design and Applications

Abstract: Due to their label-free and noninvasive nature, impedance measurements have attracted increasing interest in biological research. Advances in microfabrication and integrated-circuit technology have opened a route to using large-scale microelectrode arrays for real-time, high-spatiotemporal-resolution impedance measurements of biological samples. In this review, we discuss different methods and applications of measuring impedance for cell and tissue analysis with a focus on impedance imaging with microelectrode arrays in in vitro applications. We first introduce how electrode configurations and the frequency range of the impedance analysis determine the information that can be extracted. We then delve into relevant circuit topologies that can be used to implement impedance measurements and their characteristic features, such as resolution and data-acquisition time. Afterwards, we detail design considerations for the implementation of new impedance-imaging devices. We conclude by discussing future fields of application of impedance imaging in biomedical research, in particular applications where optical imaging is not possible, such as monitoring of ex vivo tissue slices or microelectrode-based brain implants.

Noninvasive Ultrasound Retinal Stimulation for Vision Restoration at High Spatiotemporal Resolution

Abstract: Objective . Retinal degeneration involving progressive deterioration and loss of function of photoreceptors is a major cause of permanent vision loss worldwide. Strategies to treat these incurable conditions incorporate retinal prostheses via electrically stimulating surviving retinal neurons with implanted devices in the eye, optogenetic therapy, and sonogenetic therapy. Existing challenges of these strategies include invasive manner, complex implantation surgeries, and risky gene therapy. Methods and Results . Here, we show that direct ultrasound stimulation on the retina can evoke neuron activities from the visual centers including the superior colliculus and the primary visual cortex (V1), in either normal-sighted or retinal degenerated blind rats in vivo . The neuron activities induced by the customized spherically focused 3.1 MHz ultrasound transducer have shown both good spatial resolution of 250 μ m and temporal resolution of 5 Hz in the rat visual centers. An additional customized 4.4 MHz helical transducer was further implemented to generate a static stimulation pattern of letter forms. Conclusion . Our findings demonstrate that ultrasound stimulation of the retina in vivo is a safe and effective approach with high spatiotemporal resolution, indicating a promising future of ultrasound stimulation as a novel and noninvasive visual prosthesis for translational applications in blind patients.

Highly Integrated Multiplexing and Buffering Electronics for Large Aperture Ultrasonic Arrays

Abstract: Large aperture ultrasonic arrays can be implemented by tiling together multiple pretested modules of high-density acoustic arrays with closely integrated multiplexing and buffering electronics to form a larger aperture with high yield. These modular arrays can be used to implement large 1.75D array apertures capable of focusing in elevation for uniform slice thickness along the axial direction which can improve image contrast. An important goal for large array tiling is obtaining high yield and sensitivity while reducing extraneous image artifacts. We have been developing tileable acoustic-electric modules for the implementation of large array apertures utilizing Application Specific Integrated Circuits (ASICs) implemented using 0.35 μm high voltage (50 V) CMOS. Multiple generations of ASICs have been designed and tested. The ASICs were integrated with high-density transducer arrays for acoustic testing and imaging. The modules were further interfaced to a Verasonics Vantage imaging system and were used to image industry standard ultrasound phantoms. The first-generation modules comprise ASICs with both multiplexing and buffering electronics on-chip and have demonstrated a switching artifact which was visible in the images. A second-generation ASIC design incorporates low switching injection circuits which effectively mitigate the artifacts observed with the first-generation devices. Here, we present the architecture of the two ASIC designs and module types as well imaging results that demonstrate reduction in switching artifacts for the second-generation devices.

Endoscopic Coregistered Ultrasound Imaging and Precision Histotripsy: Initial In Vivo Evaluation

Abstract: Objective. Initial performance evaluation of a system for simultaneous high-resolution ultrasound imaging and focused mechanical submillimeter histotripsy ablation in rat brains. Impact Statement. This study used a novel combination of high-resolution imaging and histotripsy in an endoscopic form. This would provide neurosurgeons with unprecedented accuracy in targeting and executing nonthermal ablations in minimally invasive surgeries. Introduction. Histotripsy is a safe and effective nonthermal focused ablation technique. However, neurosurgical applications, such as brain tumor ablation, are difficult due to the presence of the skull. Current devices are too large to use in the minimally invasive approaches surgeons prefer. We have developed a combined imaging and histotripsy endoscope to provide neurosurgeons with a new tool for this application. Methods. The histotripsy component had a 10 mm diameter, operating at 6.3 MHz. Affixed within a cutout hole in its center was a 30 MHz ultrasound imaging array. This coregistered pair was used to ablate brain tissue of anesthetized rats while imaging. Histological sections were examined, and qualitative descriptions of ablations and basic shape descriptive statistics were generated. Results. Complete ablations with submillimeter area were produced in seconds, including with a moving device. Ablation progress could be monitored in real time using power Doppler imaging, and B-mode was effective for monitoring post-ablation bleeding. Collateral damage was minimal, with a 100 μm maximum distance of cellular damage from the ablation margin. Conclusion. The results demonstrate a promising hardware suite to enable precision ablations in endoscopic procedures or fundamental preclinical research in histotripsy, neuroscience, and cancer.

A Review of Imaging Methods to Assess Ultrasound-Mediated Ablation

Abstract: Ultrasound ablation techniques are minimally invasive alternatives to surgical resection and have rapidly increased in use. The response of tissue to HIFU ablation differs based on the relative contributions of thermal and mechanical effects, which can be varied to achieve optimal ablation parameters for a given tissue type and location. In tumor ablation, similar to surgical resection, it is desirable to include a safety margin of ablated tissue around the entirety of the tumor. A factor in optimizing ablative techniques is minimizing the recurrence rate, which can be due to incomplete ablation of the target tissue. Further, combining focal ablation with immunotherapy is likely to be key for effective treatment of metastatic cancer, and therefore characterizing the impact of ablation on the tumor microenvironment will be important. Thus, visualization and quantification of the extent of ablation is an integral component of ablative procedures. The aim of this review article is to describe the radiological findings after ultrasound ablation across multiple imaging modalities. This review presents readers with a general overview of the current and emerging imaging methods to assess the efficacy of ultrasound ablative treatments.

High-Frequency 3D Photoacoustic Computed Tomography Using an Optical Microring Resonator.

Abstract: 3D photoacoustic computed tomography (3D-PACT) has made great advances in volumetric imaging of biological tissues, with high spatial-temporal resolutions and large penetration depth. The development of 3D-PACT requires high-performance acoustic sensors with a small size, large detection bandwidth, and high sensitivity. In this work, we present a new high-frequency 3D-PACT system that uses a micro-ring resonator (MRR) as the acoustic sensor. The MRR sensor has a size of 80 μm in diameter, and was fabricated using the nanoimprint lithography technology. Using the MRR sensor, we have developed a transmission-mode 3D-PACT system that has achieved a detection bandwidth of ~23 MHz, an imaging depth of ~8 mm, a lateral resolution of 114 μm, and an axial resolution of 57 μm. We have demonstrated the 3D PACT's performance on in vitro phantoms, ex vivo mouse brain, and in vivo mouse ear and tadpole. The MRR-based 3D-PACT system can be a promising tool for structural, functional, and molecular imaging of biological tissues at depths.

Blood-Brain Barrier Opening by Individualized Closed-Loop Feedback Control of Focused Ultrasound

Abstract: Objective and Impact Statement. To develop an approach for individualized closed-loop feedback control of microbubble cavitation to achieve safe and effective focused ultrasound in combination with microbubble-induced blood-brain barrier opening (FUS-BBBO). Introduction. FUS-BBBO is a promising strategy for noninvasive and localized brain drug delivery with a growing number of clinical studies currently ongoing. Real-time cavitation monitoring and feedback control are critical to achieving safe and effective FUS-BBBO. However, feedback control algorithms used in the past were either open-loop or without consideration of baseline cavitation level difference among subjects. Methods. This study performed feedback-controlled FUS-BBBO by defining the target cavitation level based on the baseline stable cavitation level of an individual subject with “dummy” FUS sonication. The dummy FUS sonication applied FUS with a low acoustic pressure for a short duration in the presence of microbubbles to define the baseline stable cavitation level that took into consideration of individual differences in the detected cavitation emissions. FUS-BBBO was then achieved through two sonication phases: ramping-up phase to reach the target cavitation level and maintaining phase to control the stable cavitation level at the target cavitation level. Results. Evaluations performed in wild-type mice demonstrated that this approach achieved effective and safe trans-BBB delivery of a model drug. The drug delivery efficiency increased as the target cavitation level increased from 0.5 dB to 2 dB without causing vascular damage. Increasing the target cavitation level to 3 dB and 4 dB increased the probability of tissue damage. Conclusions. Safe and effective brain drug delivery was achieved using the individualized closed-loop feedback-controlled FUS-BBBO.

A Deep Learning Approach for Detecting Colorectal Cancer via Raman Spectra

Abstract: Objective and Impact Statement. Distinguishing tumors from normal tissues is vital in the intraoperative diagnosis and pathological examination. In this work, we propose to utilize Raman spectroscopy as a novel modality in surgery to detect colorectal cancer tissues. Introduction. Raman spectra can reflect the substance components of the target tissues. However, the feature peak is slight and hard to detect due to environmental noise. Collecting a high-quality Raman spectroscopy dataset and developing effective deep learning detection methods are possibly viable approaches. Methods. First, we collect a large Raman spectroscopy dataset from 26 colorectal cancer patients with the Raman shift ranging from 385 to 1545 cm −1. Second, a one-dimensional residual convolutional neural network (1D-ResNet) architecture is designed to classify the tumor tissues of colorectal cancer. Third, we visualize and interpret the fingerprint peaks found by our deep learning model. Results. Experimental results show that our deep learning method achieves 98.5% accuracy in the detection of colorectal cancer and outperforms traditional methods. Conclusion. Overall, Raman spectra are a novel modality for clinical detection of colorectal cancer. Our proposed ensemble 1D-ResNet could effectively classify the Raman spectra obtained from colorectal tumor tissues or normal tissues.

Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer with Deep Learning

Abstract: Objective. To develop an artificial intelligence method predicting lymph node metastasis (LNM) for patients with colorectal cancer (CRC). Impact Statement. A novel interpretable multimodal AI-based method to predict LNM for CRC patients by integrating information of pathological images and serum tumor-specific biomarkers. Introduction. Preoperative diagnosis of LNM is essential in treatment planning for CRC patients. Existing radiology imaging and genomic tests approaches are either unreliable or too costly. Methods. A total of 1338 patients were recruited, where 1128 patients from one centre were included as the discovery cohort and 210 patients from other two centres were involved as the external validation cohort. We developed a Multimodal Multiple Instance Learning (MMIL) model to learn latent features from pathological images and then jointly integrated the clinical biomarker features for predicting LNM status. The heatmaps of the obtained MMIL model were generated for model interpretation. Results. The MMIL model outperformed preoperative radiology-imaging diagnosis and yielded high area under the curve (AUCs) of 0.926, 0.878, 0.809, and 0.857 for patients with stage T1, T2, T3, and T4 CRC, on the discovery cohort. On the external cohort, it obtained AUCs of 0.855, 0.832, 0.691, and 0.792, respectively (T1-T4), which indicates its prediction accuracy and potential adaptability among multiple centres. Conclusion. The MMIL model showed the potential in the early diagnosis of LNM by referring to pathological images and tumor-specific biomarkers, which is easily accessed in different institutes. We revealed the histomorphologic features determining the LNM prediction indicating the model ability to learn informative latent features.

Multicontrast Pocket Colposcopy Cervical Cancer Diagnostic Algorithm for Referral Populations

Abstract: Objective and Impact Statement. We use deep learning models to classify cervix images—collected with a low-cost, portable Pocket colposcope—with biopsy-confirmed high-grade precancer and cancer. We boost classification performance on a screened-positive population by using a class-balanced loss and incorporating green-light colposcopy image pairs, which come at no additional cost to the provider. Introduction. Because the majority of the 300,000 annual deaths due to cervical cancer occur in countries with low- or middle-Human Development Indices, an automated classification algorithm could overcome limitations caused by the low prevalence of trained professionals and diagnostic variability in provider visual interpretations. Methods. Our dataset consists of cervical images (n=1,760) from 880 patient visits. After optimizing the network architecture and incorporating a weighted loss function, we explore two methods of incorporating green light image pairs into the network to boost the classification performance and sensitivity of our model on a test set. Results. We achieve an area under the receiver-operator characteristic curve, sensitivity, and specificity of 0.87, 75%, and 88%, respectively. The addition of the class-balanced loss and green light cervical contrast to a Resnet-18 backbone results in a 2.5 times improvement in sensitivity. Conclusion. Our methodology, which has already been tested on a prescreened population, can boost classification performance and, in the future, be coupled with Pap smear or HPV triaging, thereby broadening access to early detection of precursor lesions before they advance to cancer.

Three-Dimensional Shear Wave Elastography Using a 2D Row Column Addressing (RCA) Array

Abstract: Objective . To develop a 3D shear wave elastography (SWE) technique using a 2D row column addressing (RCA) array, with either external vibration or acoustic radiation force (ARF) as the shear wave source. Impact Statement . The proposed method paves the way for clinical translation of 3D SWE based on the 2D RCA, providing a low-cost and high volume rate solution that is compatible with existing clinical systems. Introduction . SWE is an established ultrasound imaging modality that provides a direct and quantitative assessment of tissue stiffness, which is significant for a wide range of clinical applications including cancer and liver fibrosis. SWE requires high frame rate imaging for robust shear wave tracking. Due to the technical challenges associated with high volume rate imaging in 3D, current SWE techniques are typically confined to 2D. Advancing SWE from 2D to 3D is significant because of the heterogeneous nature of tissue, which demands 3D imaging for accurate and comprehensive evaluation. Methods . A 3D SWE method using a RCA array was developed with a volume rate up to 2000 Hz. The performance of the proposed method was systematically evaluated on tissue-mimicking elasticity phantoms and in an in vivo case study. Results . 3D shear wave motion induced by either external vibration or ARF was successfully detected with the proposed method. Robust 3D shear wave speed maps were reconstructed for phantoms and in vivo . Conclusion . The high volume rate 3D imaging provided by the 2D RCA array provides a robust and practical solution for 3D SWE with a clear pathway for future clinical translation.

Label-Free Virtual HER2 Immunohistochemical Staining of Breast Tissue using Deep Learning

Abstract: The immunohistochemical (IHC) staining of the human epidermal growth factor receptor 2 (HER2) biomarker is widely practiced in breast tissue analysis, preclinical studies, and diagnostic decisions, guiding cancer treatment and investigation of pathogenesis. HER2 staining demands laborious tissue treatment and chemical processing performed by a histotechnologist, which typically takes one day to prepare in a laboratory, increasing analysis time and associated costs. Here, we describe a deep learning-based virtual HER2 IHC staining method using a conditional generative adversarial network that is trained to rapidly transform autofluorescence microscopic images of unlabeled/label-free breast tissue sections into bright-field equivalent microscopic images, matching the standard HER2 IHC staining that is chemically performed on the same tissue sections. The efficacy of this virtual HER2 staining framework was demonstrated by quantitative analysis, in which three board-certified breast pathologists blindly graded the HER2 scores of virtually stained and immunohistochemically stained HER2 whole slide images (WSIs) to reveal that the HER2 scores determined by inspecting virtual IHC images are as accurate as their immunohistochemically stained counterparts. A second quantitative blinded study performed by the same diagnosticians further revealed that the virtually stained HER2 images exhibit a comparable staining quality in the level of nuclear detail, membrane clearness, and absence of staining artifacts with respect to their immunohistochemically stained counterparts. This virtual HER2 staining framework bypasses the costly, laborious, and time-consuming IHC staining procedures in laboratory and can be extended to other types of biomarkers to accelerate the IHC tissue staining used in life sciences and biomedical workflow.

Automatic Detection of Atrial Fibrillation from Single-Lead ECG Using Deep Learning of the Cardiac Cycle

Abstract: Objective and Impact Statement. Atrial fibrillation (AF) is a serious medical condition that requires effective and timely treatment to prevent stroke. We explore deep neural networks (DNNs) for learning cardiac cycles and reliably detecting AF from single-lead electrocardiogram (ECG) signals. Introduction. Electrocardiograms are widely used for diagnosis of various cardiac dysfunctions including AF. The huge amount of collected ECGs and recent algorithmic advances to process time-series data with DNNs substantially improve the accuracy of the AF diagnosis. DNNs, however, are often designed as general purpose black-box models and lack interpretability of their decisions. Methods. We design a three-step pipeline for AF detection from ECGs. First, a recording is split into a sequence of individual heartbeats based on R-peak detection. Individual heartbeats are then encoded using a DNN that extracts interpretable features of a heartbeat by disentangling the duration of a heartbeat from its shape. Second, the sequence of heartbeat codes is passed to a DNN to combine a signal-level representation capturing heart rhythm. Third, the signal representations are passed to a DNN for detecting AF. Results. Our approach demonstrates a superior performance to existing ECG analysis methods on AF detection. Additionally, the method provides interpretations of the features extracted from heartbeats by DNNs and enables cardiologists to study ECGs in terms of the shapes of individual heartbeats and rhythm of the whole signals. Conclusion. By considering ECGs on two levels and employing DNNs for modelling of cardiac cycles, this work presents a method for reliable detection of AF from single-lead ECGs.

High-Performance Magnetic-core Coils for Targeted Rodent Brain Stimulations

Abstract: Objective and Impact Statement. There is a need to develop rodent coils capable of targeted brain stimulation for treating neuropsychiatric disorders and understanding brain mechanisms. We describe a novel rodent coil design to improve the focality for targeted stimulations in small rodent brains. Introduction. Transcranial magnetic stimulation (TMS) is becoming increasingly important for treating neuropsychiatric disorders and understanding brain mechanisms. Preclinical studies permit invasive manipulations and are essential for the mechanistic understanding of TMS effects and explorations of therapeutic outcomes in disease models. However, existing TMS tools lack focality for targeted stimulations. Notably, there has been limited fundamental research on developing coils capable of focal stimulation at deep brain regions on small animals like rodents. Methods. In this study, ferromagnetic cores are added to a novel angle-tuned coil design to enhance the coil performance regarding penetration depth and focality. Numerical simulations and experimental electric field measurements were conducted to optimize the coil design. Results. The proposed coil system demonstrated a significantly smaller stimulation spot size and enhanced electric field decay rate in comparison to existing coils. Adding the ferromagnetic core reduces the energy requirements up to 60% for rodent brain stimulation. The simulated results are validated with experimental measurements and demonstration of suprathreshold rodent limb excitation through targeted motor cortex activation. Conclusion. The newly developed coils are suitable tools for focal stimulations of the rodent brain due to their smaller stimulation spot size and improved electric field decay rate.

Virtual Staining, Segmentation, and Classification of Blood Smears for Label-Free Hematology Analysis

Abstract: Objective and Impact Statement. We present a fully automated hematological analysis framework based on single-channel (single-wavelength), label-free deep-ultraviolet (UV) microscopy that serves as a fast, cost-effective alternative to conventional hematology analyzers. Introduction. Hematological analysis is essential for the diagnosis and monitoring of several diseases but requires complex systems operated by trained personnel, costly chemical reagents, and lengthy protocols. Label-free techniques eliminate the need for staining or additional preprocessing and can lead to faster analysis and a simpler workflow. In this work, we leverage the unique capabilities of deep-UV microscopy as a label-free, molecular imaging technique to develop a deep learning-based pipeline that enables virtual staining, segmentation, classification, and counting of white blood cells (WBCs) in single-channel images of peripheral blood smears. Methods. We train independent deep networks to virtually stain and segment grayscale images of smears. The segmented images are then used to train a classifier to yield a quantitative five-part WBC differential. Results. Our virtual staining scheme accurately recapitulates the appearance of cells under conventional Giemsa staining, the gold standard in hematology. The trained cellular and nuclear segmentation networks achieve high accuracy, and the classifier can achieve a quantitative five-part differential on unseen test data. Conclusion. This proposed automated hematology analysis framework could greatly simplify and improve current complete blood count and blood smear analysis and lead to the development of a simple, fast, and low-cost, point-of-care hematology analyzer.

Breast Cancer Induced Bone Osteolysis Prediction Using Temporal Variational Autoencoders

Abstract: Objective and Impact Statement . We adopt a deep learning model for bone osteolysis prediction on computed tomography (CT) images of murine breast cancer bone metastases. Given the bone CT scans at previous time steps, the model incorporates the bone-cancer interactions learned from the sequential images and generates future CT images. Its ability of predicting the development of bone lesions in cancer-invading bones can assist in assessing the risk of impending fractures and choosing proper treatments in breast cancer bone metastasis. Introduction . Breast cancer often metastasizes to bone, causes osteolytic lesions, and results in skeletal-related events (SREs) including severe pain and even fatal fractures. Although current imaging techniques can detect macroscopic bone lesions, predicting the occurrence and progression of bone lesions remains a challenge. Methods . We adopt a temporal variational autoencoder (T-VAE) model that utilizes a combination of variational autoencoders and long short-term memory networks to predict bone lesion emergence on our micro-CT dataset containing sequential images of murine tibiae. Given the CT scans of murine tibiae at early weeks, our model can learn the distribution of their future states from data. Results . We test our model against other deep learning-based prediction models on the bone lesion progression prediction task. Our model produces much more accurate predictions than existing models under various evaluation metrics. Conclusion . We develop a deep learning framework that can accurately predict and visualize the progression of osteolytic bone lesions. It will assist in planning and evaluating treatment strategies to prevent SREs in breast cancer patients.

A Transparent Ultrasound Array for Real-Time Optical, Ultrasound, and Photoacoustic Imaging

Abstract: Objective and Impact Statement. Simultaneous imaging of ultrasound and optical contrasts can help map structural, functional, and molecular biomarkers inside living subjects with high spatial resolution. There is a need to develop a platform to facilitate this multimodal imaging capability to improve diagnostic sensitivity and specificity. Introduction . Currently, combining ultrasound, photoacoustic, and optical imaging modalities is challenging because conventional ultrasound transducer arrays are optically opaque. As a result, complex geometries are used to coalign both optical and ultrasound waves in the same field of view. Methods . One elegant solution is to make the ultrasound transducer transparent to light. Here, we demonstrate a novel transparent ultrasound transducer (TUT) linear array fabricated using a transparent lithium niobate piezoelectric material for real-time multimodal imaging. Results . The TUT-array consists of 64 elements and centered at ~6 MHz frequency. We demonstrate a quad-mode ultrasound, Doppler ultrasound, photoacoustic, and fluorescence imaging in real-time using the TUT-array directly coupled to the tissue mimicking phantoms. Conclusion . The TUT-array successfully showed a multimodal imaging capability and has potential applications in diagnosing cancer, neurological, and vascular diseases, including image-guided endoscopy and wearable imaging.

Molecular Computational Anatomy: Unifying the Particle to Tissue Continuum via Measure Representations of the Brain

Abstract: Objective. The objective of this research is to unify the molecular representations of spatial transcriptomics and cellular scale histology with the tissue scales of computational anatomy for brain mapping. Impact Statement. We present a unified representation theory for brain mapping based on geometric varifold measures of the microscale deterministic structure and function with the statistical ensembles of the spatially aggregated tissue scales. Introduction. Mapping across coordinate systems in computational anatomy allows us to understand structural and functional properties of the brain at the millimeter scale. New measurement technologies in digital pathology and spatial transcriptomics allow us to measure the brain molecule by molecule and cell by cell based on protein and transcriptomic functional identity. We currently have no mathematical representations for integrating consistently the tissue limits with the molecular particle descriptions. The formalism derived here demonstrates the methodology for transitioning consistently from the molecular scale of quantized particles—using mathematical structures as first introduced by Dirac as the class of generalized functions—to the tissue scales with methods originally introduced by Euler for fluids. Methods. We introduce two mathematical methods based on notions of generalized functions and statistical mechanics. We use geometric varifolds, a product measure on space and function, to represent functional states at the micro-scales—electrophysiology, molecular histology—integrated with a Boltzmann-like program to pass from deterministic particle descriptions to empirical probabilities on the functional states at the tissue scales. Results. Our space-function varifold representation provides a recipe for traversing from molecular to tissue scales in terms of a cascade of linear space scaling composed with nonlinear functional feature mapping. Following the cascade implies every scale is a geometric measure so that a universal family of measure norms can be introduced which quantifies the geodesic connection between brains in the orbit independent of the probing technology, whether it be RNA identities, Tau or amyloid histology, spike trains, or dense MR imagery. Conclusions. We demonstrate a unified brain mapping theory for molecular and tissue scales based on geometric measure representations. We call the consistent aggregation of tissue scales from particle and cellular scales, molecular computational anatomy.

Breast Cancer Induced Bone Osteolysis Prediction Using Temporal Variational Auto-Encoders

Abstract: Objective and Impact Statement. We adopt a deep learning model for bone osteolysis prediction on computed tomography (CT) images of murine breast cancer bone metastases. Given the bone CT scans at previous time steps, the model incorporates the bone-cancer interactions learned from the sequential images and generates future CT images. Its ability of predicting the development of bone lesions in cancer-invading bones can assist in assessing the risk of impending fractures and choosing proper treatments in breast cancer bone metastasis. Introduction. Breast cancer often metastasizes to bone, causes osteolytic lesions, and results in skeletal-related events (SREs) including severe pain and even fatal fractures. Although current imaging techniques can detect macroscopic bone lesions, predicting the occurrence and progression of bone lesions remains a challenge. Methods. We adopt a temporal variational autoencoder (T-VAE) model that utilizes a combination of variational autoencoders and long short-term memory networks to predict bone lesion emergence on our micro-CT dataset containing sequential images of murine tibiae. Given the CT scans of murine tibiae at early weeks, our model can learn the distribution of their future states from data. Results. We test our model against other deep learning-based prediction models on the bone lesion progression prediction task. Our model produces much more accurate predictions than existing models under various evaluation metrics. Conclusion. We develop a deep learning framework that can accurately predict and visualize the progression of osteolytic bone lesions. It will assist in planning and evaluating treatment strategies to prevent SREs in breast cancer patients.

Deep UV Microscopy Identifies Prostatic Basal Cells: An Important Biomarker for Prostate Cancer Diagnostics

Abstract: Objective and Impact Statement. Identifying benign mimics of prostatic adenocarcinoma remains a significant diagnostic challenge. In this work, we developed an approach based on label-free, high-resolution molecular imaging with multispectral deep ultraviolet (UV) microscopy which identifies important prostate tissue components, including basal cells. This work has significant implications towards improving the pathologic assessment and diagnosis of prostate cancer. Introduction. One of the most important indicators of prostate cancer is the absence of basal cells in glands and ducts. However, identifying basal cells using hematoxylin and eosin (H&E) stains, which is the standard of care, can be difficult in a subset of cases. In such situations, pathologists often resort to immunohistochemical (IHC) stains for a definitive diagnosis. However, IHC is expensive and time-consuming and requires more tissue sections which may not be available. In addition, IHC is subject to false-negative or false-positive stains which can potentially lead to an incorrect diagnosis. Methods. We leverage the rich molecular information of label-free multispectral deep UV microscopy to uniquely identify basal cells, luminal cells, and inflammatory cells. The method applies an unsupervised geometrical representation of principal component analysis to separate the various components of prostate tissue leading to multiple image representations of the molecular information. Results. Our results show that this method accurately and efficiently identifies benign and malignant glands with high fidelity, free of any staining procedures, based on the presence or absence of basal cells. We further use the molecular information to directly generate a high-resolution virtual IHC stain that clearly identifies basal cells, even in cases where IHC stains fail. Conclusion. Our simple, low-cost, and label-free deep UV method has the potential to improve and facilitate prostate cancer diagnosis by enabling robust identification of basal cells and other important prostate tissue components.

Particle-Mediated Histotripsy for the Targeted Treatment of Intraluminal Biofilms in Catheter-Based Medical Devices

Abstract: Objective. This paper is an initial work towards developing particle-mediated histotripsy (PMH) as a novel method of treating catheter-based medical device (CBMD) intraluminal biofilms. Impact Statement. CBMDs commonly become infected with bacterial biofilms leading to medical device failure, infection, and adverse patient outcomes. Introduction. Histotripsy is a noninvasive focused ultrasound ablation method that was recently proposed as a novel method to remove intraluminal biofilms. Here, we explore the potential of combining histotripsy with acoustically active particles to develop a PMH approach that can noninvasively remove biofilms without the need for high acoustic pressures or real-time image guidance for targeting. Methods. Histotripsy cavitation thresholds in catheters containing either gas-filled microbubbles (MBs) or fluid-filled nanocones (NCs) were determined. The ability of these particles to sustain cavitation over multiple ultrasound pulses was tested after a series of histotripsy exposures. Next, the ability of PMH to generate selective intraluminal cavitation without generating extraluminal cavitation was tested. Finally, the biofilm ablation and bactericidal capabilities of PMH were tested using both MBs and NCs. Results. PMH significantly reduced the histotripsy cavitation threshold, allowing for selective luminal cavitation for both MBs and NCs. Results further showed PMH successfully removed intraluminal biofilms in Tygon catheters. Finally, results from bactericidal experiments showed minimal reduction in bacteria viability. Conclusion. The results of this study demonstrate the potential for PMH to provide a new modality for removing bacterial biofilms from CBMDs and suggest that additional work is warranted to develop histotripsy and PMH for treatment of CBMD intraluminal biofilms.

Connectivity-based Cortical Parcellation via Contrastive Learning on Spatial-Graph Convolution

Abstract: Objective. Objective of this work is the development and evaluation of a cortical parcellation framework based on tractography-derived brain structural connectivity. Impact Statement. The proposed framework utilizes novel spatial-graph representation learning methods for solving the task of cortical parcellation, an important medical image analysis and neuroscientific problem. Introduction. The concept of “connectional fingerprint” has motivated many investigations on the connectivity-based cortical parcellation, especially with the technical advancement of diffusion imaging. Previous studies on multiple brain regions have been conducted with promising results. However, performance and applicability of these models are limited by the relatively simple computational scheme and the lack of effective representation of brain imaging data. Methods. We propose the Spatial-graph Convolution Parcellation (SGCP) framework, a two-stage deep learning-based modeling for the graph representation brain imaging. In the first stage, SGCP learns an effective embedding of the input data through a self-supervised contrastive learning scheme with the backbone encoder of a spatial-graph convolution network. In the second stage, SGCP learns a supervised classifier to perform voxel-wise classification for parcellating the desired brain region. Results. SGCP is evaluated on the parcellation task for 5 brain regions in a 15-subject DWI dataset. Performance comparisons between SGCP, traditional parcellation methods, and other deep learning-based methods show that SGCP can achieve superior performance in all the cases. Conclusion. Consistent good performance of the proposed SGCP framework indicates its potential to be used as a general solution for investigating the regional/subregional composition of human brain based on one or more connectivity measurements.

Deep Segmentation Feature-Based Radiomics Improves Recurrence Prediction of Hepatocellular Carcinoma

Abstract: Objective and Impact Statement. This study developed and validated a deep semantic segmentation feature-based radiomics (DSFR) model based on preoperative contrast-enhanced computed tomography (CECT) combined with clinical information to predict early recurrence (ER) of single hepatocellular carcinoma (HCC) after curative resection. ER prediction is of great significance to the therapeutic decision-making and surveillance strategy of HCC. Introduction. ER prediction is important for HCC. However, it cannot currently be adequately determined. Methods. Totally, 208 patients with single HCC after curative resection were retrospectively recruited into a model-development cohort (n=180) and an independent validation cohort (n=28). DSFR models based on different CT phases were developed. The optimal DSFR model was incorporated with clinical information to establish a DSFR-C model. An integrated nomogram based on the Cox regression was established. The DSFR signature was used to stratify high- and low-risk ER groups. Results. A portal phase-based DSFR model was selected as the optimal model (area under receiver operating characteristic curve (AUC): development cohort, 0.740; validation cohort, 0.717). The DSFR-C model achieved AUCs of 0.782 and 0.744 in the development and validation cohorts, respectively. In the development and validation cohorts, the integrated nomogram achieved C-index of 0.748 and 0.741 and time-dependent AUCs of 0.823 and 0.822, respectively, for recurrence-free survival (RFS) prediction. The RFS difference between the risk groups was statistically significant (P<0.0001 and P=0.045 in the development and validation cohorts, respectively). Conclusion. CECT-based DSFR can predict ER in single HCC after curative resection, and its combination with clinical information further improved the performance for ER prediction.

Development of Moderate Intensity Focused Ultrasound (MIFU) for Ocular Drug Delivery

Abstract: The purpose of this study is to develop a method for delivering antiinflammatory agents of high molecular weight (e.g., Avastin) into the posterior segment that does not require injections into the eye (i.e., intravitreal injections; IVT). Diseases affecting the posterior segment of the eye are currently treated with monthly to bimonthly intravitreal injections, which can predispose patients to severe albeit rare complications like endophthalmitis, retinal detachment, traumatic cataract, and/or increased intraocular. In this study, we show that one time moderate intensity focused ultrasound (MIFU) treatment can facilitate the penetration of large molecules across the scleral barrier, showing promising evidence that this is a viable method to deliver high molecular weight medications not invasively. To validate the efficacy of the drug delivery system, IVT injections of vascular endothelial growth factor (VEGF) were used to create an animal model of retinopathy. The creation of this model allowed us to test anti-VEGF medications and evaluate the efficacy of the treatment. In vivo testing showed that animals treated with our MIFU device improved on the retinal tortuosity and clinical dilation compared to the control group while evaluating fluorescein angiogram (FA) Images.

Simulated MRI Artifacts: Testing Machine Learning Failure Modes

Abstract: Objective. Seven types of MRI artifacts, including acquisition and preprocessing errors, were simulated to test a machine learning brain tumor segmentation model for potential failure modes. Introduction. Real-world medical deployments of machine learning algorithms are less common than the number of medical research papers using machine learning. Part of the gap between the performance of models in research and deployment comes from a lack of hard test cases in the data used to train a model. Methods. These failure modes were simulated for a pretrained brain tumor segmentation model that utilizes standard MRI and used to evaluate the performance of the model under duress. These simulated MRI artifacts consisted of motion, susceptibility induced signal loss, aliasing, field inhomogeneity, sequence mislabeling, sequence misalignment, and skull stripping failures. Results. The artifact with the largest effect was the simplest, sequence mislabeling, though motion, field inhomogeneity, and sequence misalignment also caused significant performance decreases. The model was most susceptible to artifacts affecting the FLAIR (fluid attenuation inversion recovery) sequence. Conclusion. Overall, these simulated artifacts could be used to test other brain MRI models, but this approach could be used across medical imaging applications.

Recent Advances in the Science of Burst Wave Lithotripsy and Ultrasonic Propulsion

Abstract: Nephrolithiasis is a common, painful condition that requires surgery in many patients whose stones do not pass spontaneously. Recent technologic advances have enabled the use of ultrasonic propulsion to reposition stones within the urinary tract, either to relieve symptoms or facilitate treatment. Burst wave lithotripsy (BWL) has emerged as a noninvasive technique to fragment stones in awake patients without significant pain or renal injury. We review the preclinical and human studies that have explored the use of these two technologies. We envision that BWL will fill an unmet need for the noninvasive treatment of patients with nephrolithiasis.