RICE: A method for quantitative mammographic image enhancement.

We introduce Region of Interest Contrast Enhancement (RICE) to identify focal densities in mammograms. It aims to help radiologists: 1) enhancing the contrast of mammographic images; and 2) detecting regions of interest (such as focal densities) that are candidate masses potentially masked behind dense parenchyma. Cancer masking is an unsolved issue, particularly in breast density categories BI-RADS C and D. RICE suppresses normal breast parenchyma in order to highlight focal densities. Unlike methods that enhance mammograms by modifying the dynamic range of an image; RICE relies on the actual tissue composition of the breast. It segments Volumetric Breast Density (VBD) maps into smaller regions and then applies a recursive mechanism to estimate the 'neighbourhood' for each segment. The method then subtracts and updates the neighbourhood, or the encompassing tissue, from each piecewise constant component of the breast image. This not only enhances the appearance of a candidate mass but also helps in estimating the mass density. In extensive experiments, RICE enhances focal densities in all breast density types including the most challenging category BI-RADS D. Suitably adapted, RICE can be used as a precursor to any computer-aided diagnostics and detection system.

Learning Spatiotemporal Features for Esophageal Abnormality Detection From Endoscopic Videos.

Esophageal cancer is categorized as a type of disease with a high mortality rate. Early detection of esophageal abnormalities (i.e. precancerous and early cancerous) can improve the survival rate of the patients. Recent deep learning-based methods for selected types of esophageal abnormality detection from endoscopic images have been proposed. However, no methods have been introduced in the literature to cover the detection from endoscopic videos, detection from challenging frames and detection of more than one esophageal abnormality type. In this paper, we present an efficient method to automatically detect different types of esophageal abnormalities from endoscopic videos. We propose a novel 3D Sequential DenseConvLstm network that extracts spatiotemporal features from the input video. Our network incorporates 3D Convolutional Neural Network (3DCNN) and Convolutional Lstm (ConvLstm) to efficiently learn short and long term spatiotemporal features. The generated feature map is utilized by a region proposal network and ROI pooling layer to produce a bounding box that detects abnormality regions in each frame throughout the video. Finally, we investigate a post-processing method named Frame Search Conditional Random Field (FS-CRF) that improves the overall performance of the model by recovering the missing regions in neighborhood frames within the same clip. We extensively validate our model on an endoscopic video dataset that includes a variety of esophageal abnormalities. Our model achieved high performance using different evaluation metrics showing 93.7% recall, 92.7% precision, and 93.2% F-measure. Moreover, as no results have been reported in the literature for the esophageal abnormality detection from endoscopic videos, to validate the robustness of our model, we have tested the model on a publicly available colonoscopy video dataset, achieving the polyp detection performance in a recall of 81.18%, precision of 96.45% and F-measure 88.16%, compared to the state-of-the-art results of 78.84% recall, 90.51% precision and 84.27% F-measure using the same dataset. This demonstrates that the proposed method can be adapted to different gastrointestinal endoscopic video applications with a promising performance.

ResDUnet: Residual Dilated UNet for Left Ventricle Segmentation from Echocardiographic Images.

Echocardiography is the modality of choice for the assessment of left ventricle function. Left ventricle is responsible for pumping blood rich in oxygen to all body parts. Segmentation of this chamber from echocardiographic images is a challenging task, due to the ambiguous boundary and inhomogeneous intensity distribution. In this paper we propose a novel deep learning model named ResDUnet. The model is based on U-net incorporated with dilated convolution, where residual blocks are employed instead of the basic U-net units to ease the training process. Each block is enriched with squeeze and excitation unit for channel-wise attention and adaptive feature re-calibration. To tackle the problem of left ventricle shape and size variability, we chose to enrich the process of feature concatenation in U-net by integrating feature maps generated by cascaded dilation. Cascaded dilation broadens the receptive field size in comparison with traditional convolution, which allows the generation of multi-scale information which in turn results in a more robust segmentation. Performance measures were evaluated on a publicly available dataset of 500 patients with large variability in terms of quality and patients pathology. The proposed model shows a dice similarity increase of 8.4% when compared to deeplabv3 and 1.2% when compared to the basic U-net architecture. Experimental results demonstrate the potential use in clinical domain.

Integral invariants for image enhancement.

Medical images pose a major challenge for image analysis: often they have poor signal-to-noise, necessitating smoothing; yet such smoothing needs to preserve the boundaries of regions of interest and small features such as mammogram microcalcifications. We show how circular integral invariants (II) may be adapted for feature-preserving smoothing to facilitate segmentation. Though II is isotropic, we show that it leads to considerably less feature deterioration than Gaussian blurring and it improves segmentation of regions of interest as compared to anisotropic diffusion, particularly for hierarchical contour based segmentation methods.

Shape matching by integral invariants on eccentricity transformed images.

Matching occluded and noisy shapes is a frequently encountered problem in vision and medical image analysis and more generally in computer vision. To keep track of changes inside breast, it is important for a computer aided diagnosis system (CAD) to establish correspondences between regions of interest. Shape transformations, computed both with integral invariants and geodesic distance yield signatures that are invariant to isometric deformations, such as bending and articulations. Integral invariants are used on 2D planar shapes to describe the shape boundary. However, they provide no information about where a particular feature on the boundary lies with regard to overall shape structure. On the other hand, eccentricity transforms can be used to match shapes by signatures of geodesic distance histograms based on information from inside the shape; but they ignore the boundary information. We describe a method that combines both the boundary signature of shape obtained from integral invariants and structural information from the eccentricity transform to yield improved results.