Avi Ben-Cohen

Fully Convolutional Network for Liver Segmentation and Lesions Detection

In this work we explore a fully convolutional network (FCN) for the task of liver segmentation and liver metastases detection in computed tomography (CT) examinations. FCN has proven to be a very powerful tool for semantic segmentation. We explore the FCN performance on a relatively small dataset and compare it to patch based CNN and sparsity based classification schemes. Our data contains CT examinations from 20 patients with overall 68 lesions and 43 livers marked in one slice and 20 different patients with a full 3D liver segmentation. We ran 3-fold cross-validation and results indicate superiority of the FCN over all other methods tested. Using our fully automatic algorithm we achieved true positive rate of 0.86 and 0.6 false positive per case which are very promising and clinically relevant results.

Virtual PET Images from CT Data Using Deep Convolutional Networks: Initial Results

In this work we present a novel system for PET estimation using CT scans. We explore the use of fully convolutional networks (FCN) and conditional generative adversarial networks (GAN) to export PET data from CT data. Our dataset includes 25 pairs of PET and CT scans where 17 were used for training and 8 for testing. The system was tested for detection of malignant tumors in the liver region. Initial results look promising showing high detection performance with a TPR of 92.3% and FPR of 0.25 per case. Future work entails expansion of the current system to the entire body using a much larger dataset. Such a system can be used for tumor detection and drug treatment evaluation in a CT-only environment instead of the expansive and radioactive PET-CT scan.

Automated method for detection and segmentation of liver metastatic lesions in follow-up CT examinations

Abstract. This paper presents a fully automated method for detection and segmentation of liver metastases in serial computed tomography (CT) examinations. Our method uses a given two-dimensional baseline segmentation mask for identifying the lesion location in the follow-up CT and locating surrounding tissues, using nonrigid image registration and template matching, in order to reduce the search area for segmentation. Adaptive region growing and mean-shift clustering are used to obtain the lesion segmentation. Our database contains 127 cases from the CT abdomen unit at Sheba Medical Center. Development of the methodology was conducted using 22 of the cases, and testing was conducted on the remaining 105 cases. Results show that 94 of the 105 lesions were detected, for an overall matching rate of 90% making the correct RECIST 1.1 assessment in 88% of the cases. The average Dice index was 0.83±0.08, the average sensitivity was 0.82±0.13, and the positive predictive value was 0.87±0.11. In 92% of the rated cases, the results were classified by the radiologists as acceptable or better. The segmentation performance, matching rate, and RECIST assessment results hence appear promising.

Sparsity-based liver metastases detection using learned dictionaries

In this work we explore sparsity-based approaches for the task of liver metastases detection in liver computed-tomography (CT) examinations. Sparse signal representation has proven to be a very powerful tool for robustly acquiring, representing, and compressing high-dimensional signals that can be accurately constructed from a compact, fixed set basis. We explore different sparsity based classification techniques and compare them to state of the art classification schemes. These methods were tested on CT examinations from 20 patients taken in different times, with overall 68 lesions. Best performance was achieved using the label consistent K-SVD (LC-KSVD) method, with detection rate of 91%, 0.9 false positive (FP) rate and classification accuracy (ACC) of 96%. The detection rates as well as the classification results are promising. Future work entails expanding the method to 3D analysis as well as testing it on a larger database.

Improving the Segmentation of Anatomical Structures in Chest Radiographs Using U-Net with an ImageNet Pre-trained Encoder

Accurate segmentation of anatomical structures in chest radiographs is essential for many computer-aided diagnosis tasks. In this paper we investigate the latest fully-convolutional architectures for the task of multi-class segmentation of the lungs field, heart and clavicles in a chest radiograph. In addition, we explore the influence of using different loss functions in the training process of a neural network for semantic segmentation. We evaluate all models on a common benchmark of 247 X-ray images from the JSRT database and ground-truth segmentation masks from the SCR dataset. Our best performing architecture, is a modified U-Net that benefits from pre-trained encoder weights. This model outperformed the current state-of-the-art methods tested on the same benchmark, with Jaccard overlap scores of 96.1% for lung fields, 90.6% for heart and 85.5% for clavicles.

Left Atria Reconstruction from a Series of Sparse Catheter Paths Using Neural Networks.

Modeling and reconstructing the shape of a heart chamber from partial or noisy data is useful in many (minimally) invasive heart procedures. We propose a method to reconstruct the shape of the left atria during the electrophysiology procedure from a series of simple catheter maneuvers. We use left atria shapes generated from a statistical based physical model and approximate traversal locations of catheter maneuvers inside the left atria. These paths mimic realistic ones doable in a lab phantom. We demonstrate the ability of a deep neural network to approximate the atria shape solely based on the given paths. We compare the results against training from partial data generated by the intersection of a randomly generated sphere and the atria. We test the presented network on actual lab phantoms and show promising results.

Electrostatic Selectivity of Volatile Organic Compounds Using Electrostatically Formed Nanowire Sensor

For the past several decades, there is growing demand for the development of low-power gas sensing technology for the selective detection of volatile organic compounds (VOCs), important for monitoring safety, pollution, and healthcare. Here we report the selective detection of homologous alcohols and different functional groups containing VOCs using the electrostatically formed nanowire (EFN) sensor without any surface modification of the device. Selectivity toward specific VOC is achieved by training machine-learning based classifiers using the calculated changes in the threshold voltage and the drain-source on current, obtained from systematically controlled biasing of the surrounding gates (junction and back gates) of the field-effect transistors (FET). This work paves the way for a Si complementary metal-oxide-semiconductor (CMOS)-based FET device as an electrostatically selective sensor suitable for mass production and low-power sensing technology.