Synthetic-Aperture-Radar (SAR) is a commonly used modality in mission-critical remote-sensing applications, including battlefield intelligence, surveillance, and reconnaissance (ISR). Processing SAR sensory inputs with deep learning is challenging because deep learning methods generally require large training datasets and high- quality labels, which are expensive for SAR. In this paper, we introduce a new approach for learning from SAR images in the absence of abundant labeled SAR data. We demonstrate that our geometrically-inspired neural architecture, together with our proposed self-supervision scheme, enables us to leverage the unlabeled SAR data and learn compelling image features with few labels. Finally, we show the test results of our proposed algorithm on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset.
Modern advancements in imaging devices have enabled us to explore the subcellular structure of living organisms and extract vast amounts of information. However, interpreting the biological information mined in the captured images is not a trivial task. Utilizing predetermined numerical features is usually the only hope for quantifying this information. Nonetheless, direct visual or biological interpretation of results obtained from these selected features is non-intuitive and difficult. In this paper, we describe an automatic method for modeling visual variations in a set of images, which allows for direct visual interpretation of the most significant differences, without the need for predefined features. The method is based on a linearized version of the continuous optimal transport (OT) metric, which provides a natural linear embedding for the image data set, in which linear combination of images leads to a visually meaningful image. This enables us to apply linear geometric data analysis techniques such as principal component analysis and linear discriminant analysis in the linearly embedded space and visualize the most prominent modes, as well as the most discriminant modes of variations, in the dataset. Using the continuous OT framework, we are able to analyze variations in shape and texture in a set of images utilizing each image at full resolution, that otherwise cannot be done by existing methods. The proposed method is applied to a set of nuclei images segmented from Feulgen stained liver tissues in order to investigate the major visual differences in chromatin distribution of Fetal-Type Hepatoblastoma (FHB) cells compared to the normal cells.
diagnostic standard is a pleural biopsy with subsequent histologic examination of the tissue demonstrating invasion by
the tumor. The diagnostic tissue is obtained through thoracoscopy or open thoracotomy, both being highly invasive
procedures. Thoracocenthesis, or removal of effusion fluid from the pleural space, is a far less invasive procedure that
can provide material for cytological examination. However, it is insufficient to definitively confirm or exclude the
diagnosis of malignant mesothelioma, since tissue invasion cannot be determined. In this study, we present a
computerized method to detect and classify malignant mesothelioma based on the nuclear chromatin distribution from
digital images of mesothelial cells in effusion cytology specimens. Our method aims at determining whether a set of
nuclei belonging to a patient, obtained from effusion fluid images using image segmentation, is benign or malignant, and
has a potential to eliminate the need for tissue biopsy. This method is performed by quantifying chromatin morphology
of cells using the optimal transportation (Kantorovich–Wasserstein) metric in combination with the modified Fisher
discriminant analysis, a k-nearest neighborhood classification, and a simple voting strategy. Our results show that we can
classify the data of 10 different human cases with 100% accuracy after blind cross validation. We conclude that nuclear
structure alone contains enough information to classify the malignant mesothelioma. We also conclude that the
distribution of chromatin seems to be a discriminating feature between nuclei of benign and malignant mesothelioma