Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Vascular and non-vascular UNet systems dominated with sUNet classes with attention. Most of the studies suffered from a low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09999432.pdf

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

https://doi.org/10.1016/j.aej.2023.02.020

Smart IoMT-based segmentation of coronavirus infections using lung CT scans

PURPOSE
Delineation of the clinical target volume (CTV) and organs-at-risk (OARs) is important in cervical cancer radiotherapy. But it is generally labor-intensive, time-consuming, and subjective. This paper proposes a parallel-path attention fusion network (PPAF-net) to overcome these disadvantages in the delineation task.


METHODS
The PPAF-net utilizes both the texture and structure information of CTV and OARs by employing a U-Net network to capture the high-level texture information, and an up-sampling and down-sampling (USDS) network to capture the low-level structure information to accentuate the boundaries of CTV and OARs. Multi-level features extracted from both networks are then fused together through an attention module to generate the delineation result.


RESULTS
The dataset contains 276 computed tomography (CT) scans of patients with cervical cancer of staging IB-IIA. The images are provided by the West China Hospital of Sichuan University. Simulation results demonstrate that PPAF-net performs favorably on the delineation of the CTV and OARs (e.g., rectum, bladder and etc.) and achieves the state-of-the-art delineation accuracy, respectively, for the CTV and OARs. In terms of the Dice Similarity Coefficient (DSC) and the Hausdorff Distance (HD), 88.61% and 2.25 cm for the CTV, 92.27% and 0.73 cm for the rectum, 96.74% and 0.68 cm for the bladder, 96.38% and 0.65 cm for the left kidney, 96.79% and 0.63 cm for the right kidney, 93.42% and 0.52 cm for the left femoral head, 93.69% and 0.51 cm for the right femoral head, 87.53% and 1.07 cm for the small intestine, and 91.50% and 0.84 cm for the spinal cord.


CONCLUSIONS
The proposed automatic delineation network PPAF-net performs well on CTV and OARs segmentation tasks, which has great potential for reducing the burden of radiation oncologists and increasing the accuracy of delineation. In future, radiation oncologists from the West China Hospital of Sichuan University will further evaluate the results of network delineation, making this method helpful in clinical practice.

Delineation of clinical target volume and organs at risk in cervical cancer radiotherapy by deep learning networks.

Coronary artery segmentation has great significance in providing morphological information and treatment guidance in clinics. However, the complex structures with tiny and narrow branches of the coronary artery bring it a great challenge. Limited by the low resolution and poor contrast of medical images, voxel-based segmentation methods could potentially lead to fragmentations of segmented vessels and surface voids are commonly found in the reconstructed mesh. Therefore, we propose a geometry-based end-to-end segmentation method for the coronary artery in computed tomography angiography. A U-shaped network is applied to extract image features, which are projected to mesh space, driving the geometrybased network to deform the mesh. Integrating the ability of geometric deformation, the proposed network could output mesh results of the coronary artery directly. Besides, the centerline-based approach is utilized to produce the ground truth of the mesh instead of the traditional marching cube method. Extensive experiments on our collected dataset CCA-520 demonstrate the feasibility and robustness of our method. Quantitatively, our model achieves Dice of 0.779 and HD of 0.299, exceeding other methods in our dataset. Especially, our geometrybased model generates an accurate, intact and smooth mesh of the coronary artery, devoid of any fragmentations of segmented vessels.

Coronary artery in computed tomography angiography

Segmentation of the coronary artery is an important task for the quantitative analysis of coronary computed tomography angiography (CCTA) images and is being stimulated by the field of deep learning. However, the complex structures with tiny and narrow branches of the coronary artery bring it a great challenge. Coupled with the medical image limitations of low resolution and poor contrast, fragmentations of segmented vessels frequently occur in the prediction. Therefore, a geometry-based cascaded segmentation method is proposed for the coronary artery, which has the following innovations: 1) Integrating geometric deformation networks, we design a cascaded network for segmenting the coronary artery and vectorizing results. The generated meshes of the coronary artery are continuous and accurate for twisted and sophisticated coronary artery structures, without fragmentations. 2) Different from mesh annotations generated by the traditional marching cube method from voxel-based labels, a finer vectorized mesh of the coronary artery is reconstructed with the regularized morphology. The novel mesh annotation benefits the geometry-based segmentation network, avoiding bifurcation adhesion and point cloud dispersion in intricate branches. 3) A dataset named CCA-200 is collected, consisting of 200 CCTA images with coronary artery disease. The ground truths of 200 cases are coronary internal diameter annotations by professional radiologists. Extensive experiments verify our method on our collected dataset CCA-200 and public ASOCA dataset, with a Dice of 0.778 on CCA-200 and 0.895 on ASOCA, showing superior results. Especially, our geometry-based model generates an accurate, intact and smooth coronary artery, devoid of any fragmentations of segmented vessels.

Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network

https://kclpure.kcl.ac.uk/portal/files/171263078/Manuscript_20211003_Final_PURE.pdf

Estimation of central pulse wave velocity from radial pulse wave analysis

Automatic coronary artery segmentation is of great value in diagnosing coronary disease. In this paper, we propose an automatic coronary artery segmentation method for coronary computerized tomography angiography (CCTA) images based on a deep convolutional neural network. The proposed method consists of three steps. First, to improve the efficiency and effectiveness of the segmentation, a 2D DenseNet classification network is utilized to screen out the non-coronary-artery slices. Second, we propose a coronary artery segmentation network based on the 3D-UNet, which is capable of extracting, fusing and rectifying features efficiently for accurate coronary artery segmentation. Specifically, in the encoding process of the 3D-UNet network, we adapt the dense block into the 3D-UNet so that it can extract rich and representative features for coronary artery segmentation; In the decoding process, 3D residual blocks with feature rectification capability are applied to improve the segmentation quality further. Third, we introduce a Gaussian weighting method to obtain the final segmentation results. This operation can highlight the more reliable segmentation results at the center of the 3D data blocks while weakening the less reliable segmentations at the block boundary when merging the segmentation results of spatially overlapping data blocks. Experiments demonstrate that our proposed method achieves a Dice Similarity Coefficient (DSC) value of 0.826 on a CCTA dataset constructed by us. The code of the proposed method is available at https://github.com/alongsong/3D_CAS.

Automatic Coronary Artery Segmentation of CCTA Images With an Efficient Feature-Fusion-and-Rectification 3D-UNet

Background Low back pain is a common medical condition among the general population that is associated with many adverse health effects when comorbid with depressive symptoms. However, little is known about depressive symptoms in the population with low back pain in China. Our study evaluated the prevalence of depressive symptoms and analyzed the factors associated with this condition in the Chinese population with low back pain. Methods We conducted a cross-sectional analysis of data from the 2018 China Health and Retirement Longitudinal Study. We collected low back pain information for each participant and identified depressive symptoms using the brief version of the Center for Epidemiologic Studies Depression Scale. A wide range of sociodemographic and health-related characteristics of the subjects were extracted. We measured the prevalence of depressive symptoms comorbid with low back pain and analyzed the associated factors by multiple logistic regression. Results A total of 5,779 respondents aged 45 and over with low back pain formed the sample, 41.8% of whom reported depressive symptoms. Multiple logistic regression analysis indicated greater vulnerability to depressive symptoms among females (OR = 1.41, 95% CI, 1.16–1.73), relatively younger persons (60–74 years: OR = 0.72, 95% CI, 0.63–0.83; ≥ 75 years: OR = 0.62, 95% CI, 0.49–0.79, reference: 45–59 years), those from the central and western regions (central: OR = 1.39, 95% CI, 1.18–1.64; western: OR = 1.56, 95% CI, 1.33–1.83), participants with extremely short sleep duration (OR = 2.74, 95% CI, 2.33–3.23), those with poor self-perceived health status (OR = 2.91, 95% CI, 2.34–3.63,), multisite pain (OR = 1.54, 95% CI, 1.20–1.98) and disability in activities of daily living (Basic: OR = 1.70, 95% CI, 1.47–1.98; Instrumental: OR = 1.95, 95% CI, 1.70–2.24). Conclusion Depressive symptoms were highly prevalent in the Chinese population ≥ 45 years with low back pain. More attention should be paid to the individuals at high-risk confirmed by this study to facilitate early identification and intervention against depressive symptoms.

/pdf/prevalence-and-factors-associated-with-comorbid-depressive-64wycj9q.pdf

Prevalence and factors associated with comorbid depressive symptoms among people with low back pain in China: A cross-sectional study

Ballistocardiography (BCG) is considered a good alternative to HRV analysis with its non-contact and unobtrusive acquisition characteristics. However, consensus about its validity has not yet been established. In this study, 50 healthy subjects (26.2 ± 5.5 years old, 22 females, 28 males) were invited. Comprehensive statistical analysis, including Coefficients of Variation (CV), Lin’s Concordance Correlation Coefficient (LCCC), and Bland-Altman analysis (BA ratio), were utilized to analyze the consistency of BCG and ECG signals in HRV analysis. If the methods gave different answers, the worst case was taken as the result. Measures of consistency such as Mean, SDNN, LF gave good agreement (the absolute value of CV difference < 2%, LCCC > 0.99, BA ratio < 0.1) between J-J (BCG) and R-R intervals (ECG). pNN50 showed moderate agreement (the absolute value of CV difference < 5%, LCCC > 0.95, BA ratio < 0.2), while RMSSD, HF, LF/HF indicated poor agreement (the absolute value of CV difference ≥ 5% or LCCC ≤ 0.95 or BA ratio ≥ 0.2). Additionally, the R-R intervals were compared with P-P intervals extracted from the pulse wave (PW). Except for pNN50, which exhibited poor agreement in this comparison, the performances of the HRV indices estimated from the PW and the BCG signals were similar.

/pdf/statistical-analysis-of-the-consistency-of-hrv-analysis-39imjdcw.pdf

Lisheng Xu

Papers

Estimation of central pulse wave velocity from radial pulse wave analysis

Automatic Coronary Artery Segmentation of CCTA Images With an Efficient Feature-Fusion-and-Rectification 3D-UNet

Prevalence and factors associated with comorbid depressive symptoms among people with low back pain in China: A cross-sectional study

Statistical Analysis of the Consistency of HRV Analysis Using BCG or Pulse Wave Signals

Feasibility of waveform separation of central aortic pressure pulse based on lognormal flow wave approximation