Abstract
This chapter surveys methodologies for the segmentation of carotid ultrasound images and describes a method for the semiautomatic detection of the lumen-intima and the media-adventitia interfaces of the near and far common carotid wall. The approach is based on feature extraction, fitting of cubic splines, dynamic programming, smooth intensity thresholding surfaces, and geometric snakes. A set of 47 B-mode images of the common carotid were used to assess the performance of the method. The detection errors are similar to the ones observed in manual segmentations for 95% of the far wall interfaces and 73% of the near wall interfaces. © 2014 Springer Science+Business Media, LLC. All rights are reserved.

Abstract
Synthesizing images of the eye fundus is a challenging task that has been previously approached by formulating complex models of the anatomy of the eye. New images can then be generated by sampling a suitable parameter space. Here we propose a method that learns to synthesize eye fundus images directly from data. For that, we pair true eye fundus images with their respective vessel trees, by means of a vessel segmentation technique. These pairs are then used to learn a mapping from a binary vessel tree to a new retinal image. For this purpose, we use a recent image-to-image translation technique, based on the idea of adversarial learning. Experimental results show that the original and the generated images are visually different in terms of their global appearance, in spite of sharing the same vessel tree. Additionally, a quantitative quality analysis of the synthetic retinal images confirms that the produced images retain a high proportion of the true image set quality. © Springer International Publishing AG 2017.

Abstract
The Arteriolar-to-Venular Ratio (AVR) is a popular dimensionless measure which allows the assessment of patients' condition for the early diagnosis of different diseases, including hypertension and diabetic retinopathy. This paper presents two new approaches for AVR computation in retinal photographs which include a sequence of automated processing steps: vessel segmentation, caliber measurement, optic disc segmentation, artery/vein classification, region of interest delineation, and AVR calculation. Both approaches have been tested on the INSPIRE-AVR dataset, and compared with a ground-truth provided by two medical specialists. The obtained results demonstrate the reliability of the fully automatic approach which provides AVR ratios very similar to at least one of the observers. Furthermore, the semi-automatic approach, which includes the manual modification of the artery/vein classification if needed, allows to significantly reduce the error to a level below the human error.

Abstract
Microcalcifications are early indicators of breast cancer that appear on mammograms as small bright regions within the breast tissue. To assist screening radiologists in reading mammograms, supervised learning techniques have been found successful to detect micro-calcifications automatically. Among them, Convolutional Neural Networks (CNNs) can automatically learn and extract low-level features that capture contrast and spatial information, and use these features to build robust classifiers. Therefore, spatial enhancement that enhances local contrast based on spatial context is expected to positively influence the learning task of the CNN and, as a result, its classification performance. In this work, we propose a novel spatial enhancement technique for microcalcifications based on the removal of haze, an apparently unrelated phenomenon that causes image degradation due to atmospheric absorption and scattering. We tested the influence of dehazing of digital mammograms on the microcalcification detection performance of two CNNs inspired by the popular AlexNet and VGGnet. Experiments were performed on 1, 066 mammograms acquired with GE Senographe systems. Statistically significantly better microcalcification detection performance was obtained when dehazing was used as preprocessing. Results of dehazing were superior also to those obtained with Contrast Limited Adaptive Histogram Equalization (CLAHE).

Abstract

Abstract
In order to assess the atherosclerotic plaque disruption risk from B-mode ultrasound images of the carotid, an appropriate normalization of the plaque regions is required. This is usually achieved through the manual selection of two sample regions in the image containing blood and adventitia tissues, which are used as reference. In this work, we propose a new plaque region normalization method that takes advantage of multiple blood and adventitia reference samples per image, and a method for the automatic selection of these reference samples. Several preliminary results are provided in order to demonstrate the possible capabilities of the proposed methods.