Crystalline thin films of organic semiconductors are a good candidate for field effect transistor (FET) materials in printed electronics. However, there are currently two main problems, which are associated with inhomogeneity and poor thermal durability of these films. Here we report that liquid crystalline materials exhibiting a highly ordered liquid crystal phase of smectic E (SmE) can solve both these problems. We design a SmE liquid crystalline material, 2-decyl-7-phenyl-[1]benzothieno[3,2-b][1]benzothiophene (Ph-BTBT-10), for FETs and synthesize it. This material provides uniform and molecularly flat polycrystalline thin films reproducibly when SmE precursor thin films are crystallized, and also exhibits high durability of films up to 200 °C. In addition, the mobility of FETs is dramatically enhanced by about one order of magnitude (over 10 cm2 V−1 s−1) after thermal annealing at 120 °C in bottom-gate-bottom-contact FETs. We anticipate the use of SmE liquid crystals in solution-processed FETs may help overcome upcoming difficulties with novel technologies for printed electronics.

液晶物質の有機トランジスタへの展開 ; Liquid Crystals for Organic Thin Film Transistors

Objective: Accurate diagnosis and prognosis are essential in lung cancer treatment selection and planning. With the rapid advance of medical imaging technology, whole slide imaging (WSI) in pathology is becoming a routine clinical procedure. An interplay of needs and challenges exists for computer-aided diagnosis based on accurate and efficient analysis of pathology images. Recently, artificial intelligence, especially deep learning, has shown great potential in pathology image analysis tasks such as tumor region identification, prognosis prediction, tumor microenvironment characterization, and metastasis detection. Materials and Methods: In this review, we aim to provide an overview of current and potential applications for AI methods in pathology image analysis, with an emphasis on lung cancer. Results: We outlined the current challenges and opportunities in lung cancer pathology image analysis, discussed the recent deep learning developments that could potentially impact digital pathology in lung cancer, and summarized the existing applications of deep learning algorithms in lung cancer diagnosis and prognosis. Discussion and Conclusion: With the advance of technology, digital pathology could have great potential impacts in lung cancer patient care. We point out some promising future directions for lung cancer pathology image analysis, including multi-task learning, transfer learning, and model interpretation.

Artificial Intelligence in Lung Cancer Pathology Image Analysis.

The 3D image segmentation is the process of partitioning a digital 3D volumes into multiple segments. This paper presents a fully automatic method for high resolution 3D volumetric segmentation of medical image data using modern supervised deep learning approach. We introduce 3D Dense-U-Net neural network architecture implementing densely connected layers. It has been optimized for graphic process unit accelerated high resolution image processing on currently available hardware (Nvidia GTX 1080ti). The method has been evaluated on MRI brain 3D volumetric dataset and CT thoracic scan dataset for spine segmentation. In contrast with many previous methods, our approach is capable of precise segmentation of the input image data in the original resolution, without any pre-processing of the input image. It can process image data in 3D and has achieved accuracy of 99.72% on MRI brain dataset, which outperformed results achieved by human expert. On lumbar and thoracic vertebrae CT dataset it has achieved the accuracy of 99.80%. The architecture proposed in this paper can also be easily applied to any task already using U-Net network as a segmentation algorithm to enhance its results. Complete source code was released online under open-source license.

Optimized High Resolution 3D Dense-U-Net Network for Brain and Spine Segmentation

A survey on applications of deep learning in microscopy image analysis.

There have been many recently published studies exploring machine learning (ML) and deep learning applications within neuroradiology. The improvement in performance of these techniques has resulted in an ever-increasing number of commercially available tools for the neuroradiologist. In this narrative review, recent publications exploring ML in neuroradiology are assessed with a focus on several key clinical domains. In particular, major advances are reviewed in the context of: (1) intracranial hemorrhage detection, (2) stroke imaging, (3) intracranial aneurysm screening, (4) multiple sclerosis imaging, (5) neuro-oncology, (6) head and tumor imaging, and (7) spine imaging.

Artificial Intelligence and Deep Learning in Neuroradiology: Exploring the New Frontier:

Segmenting vertebrae and disks in medical images using algorithmic methods promises to improve diagnostics and treatment selection for lower back pain. While most existing spinal segmentation methods are model-based, we propose a deep learning approach that uses a series of four pixel-wise segmentation networks. Each network segments MR images at a different scale. Results from one network in the chain are fed as input to the next network in the chain. By using both the original image and results from the previous network as input, each successive network produces an increasingly refined segmentation result. This approach improves vertebrae and disk segmentations results by 1.3% and 4.9%, respectively, when compared to a state-of-the-art deep-learning segmentation method—the U-net. It also provides additional benefits over U-net architectures by simplifying simultaneous multi-class segmentation, streamlining the overall use of the network, and removing the need for post-processing to filter erroneous classifications from the output.

A deep learning approach to spine segmentation using a feed-forward chain of pixel-wise convolutional networks

A flexible fan-out wafer-level packaging (FOWLP) process for heterogeneous integration of high performance dies in a flexible and biocompatible elastomeric package (FlexTrateTM) was used to assemble >600 dies with co-planarity and tilt <1µm, average die-shift of 3.28 µm with ? < 2.23 µm. We have also engineered a novel corrugated topography of a stress buffer layer for metal interconnects on FlexTrateTM to mitigate the buckling phenomenon of metal films deposited on elastomeric substrates. Corrugated interconnects were then tested for their mechanical bending reliability and have shown less than 0.4% change in resistance after bending at 1 mm radius for 1,000 cycles. Finally, we demonstrate integration of an array of 25 dielets interconnected in a daisy chain configuration at 40 µm interconnect pitch.

/pdf/extremely-flexible-1mm-bending-radius-biocompatible-3s813pj3wc.pdf

Extremely Flexible (1mm Bending Radius) Biocompatible Heterogeneous Fan-Out Wafer-Level Platform with the Lowest Reported Die-Shift (<6 µm) and Reliable Flexible Cu-Based Interconnects

Estimation of cell nuclei in images stained for the c-fos protein using immunohistochemistry (IHC) is infeasible in large image sets. Use of multiple human raters to increase throughput often creates variance in the data analysis. Machine learning techniques for biomedical image analysis have been explored for cell-counting in pathology, but their performance on IHC staining, especially to label activated cells in the spinal cord is unknown. In this study, we evaluate different machine learning techniques to segment and count spinal cord neurons that have been active during stepping. We present a qualitative as well as quantitative comparison of algorithmic performance versus two human raters. Quantitative ratings are presented with cell-count statistics and Dice (DSI) scores. We also show the degree of variability between multiple human raters’ segmentations and observe that there is a higher degree of variability in segmentations produced by classic machine learning techniques (SVM and Random forest) as compared to the newer deep learning techniques. The work presented here, represents the first steps towards addressing the analysis time bottleneck of large image data sets generated by c-fos IHC staining techniques, a task that would be impossible to do manually.

Cell Counting and Segmentation of Immunohistochemical Images in the Spinal Cord: Comparing Deep Learning and Traditional Approaches

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the ∼1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

Massively parallel annealing processors may oﬀer superior performance for a wide range of sampling and optimization problems. A key component dictating the size of these processors is the neuron update circuit, ideally implemented using special stochastic nanodevices. We leverage photon statistics using single photon avalanche diodes (SPADs) and temporal ﬁltering to generate stochastic states. This method is a powerful alternative oﬀering unique features not currently seen in annealing processors: the ability to continuously control the computational temperature and the seamless extension to the Potts model, a n -state generalization of the two-state Ising model. SPADs also oﬀer a considerable practical advantage since they are readily manufacturable in current standard CMOS processes. As a ﬁrst step towards realiz-ing a CMOS SPAD-based annealer, we have designed Ising and Potts models driven by an array of discrete SPADs and show they accurately sample from their theoretical distributions. variable-rate SPAD transfer function measurements. The uncertainty depends on how many pulses were recorded during the sampling period, with higher pulse rates resulting in lower uncertainty. The table lists the lowest measured pulse rates and associated number of detected pulses, from which a worst-case relative measurement error is determined. The measurement quantity (number of pulses over the measurement timeframe) is modeled as a Poisson distribution.

William Whitehead

Papers

A deep learning approach to spine segmentation using a feed-forward chain of pixel-wise convolutional networks

Extremely Flexible (1mm Bending Radius) Biocompatible Heterogeneous Fan-Out Wafer-Level Platform with the Lowest Reported Die-Shift (<6 µm) and Reliable Flexible Cu-Based Interconnects

Cell Counting and Segmentation of Immunohistochemical Images in the Spinal Cord: Comparing Deep Learning and Traditional Approaches

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

CMOS-compatible Ising and Potts Annealing Using Single Photon Avalanche Diodes