Mitotic nuclei estimation in breast tumour samples has a prognostic significance in analysing tumour aggressiveness and grading system. The automated assessment of mitotic nuclei is challenging because of their high similarity with non-mitotic nuclei and heteromorphic appearance. In this work, we have proposed a new Deep Convolutional Neural Network (CNN) based Heterogeneous Ensemble technique "DHE-Mit-Classifier" for analysis of mitotic nuclei in breast histopathology images. The proposed technique in the first step detects candidate mitotic patches from the histopathological biopsy regions, whereas, in the second step, these patches are classified into mitotic and non-mitotic nuclei using the proposed DHE-Mit-Classifier. For the development of a heterogeneous ensemble, five different deep CNNs are designed and used as base-classifiers. These deep CNNs have varying architectural designs to capture the structural, textural, and morphological properties of the mitotic nuclei. The developed base-classifiers exploit different ideas, including (i) region homogeneity and feature invariance, (ii) asymmetric split-transform-merge, (iii) dilated convolution based multi-scale transformation, (iv) spatial and channel attention, and (v) residual learning. Multi-layer-perceptron is used as a meta-classifier to develop a robust and accurate classifier for providing the final decision. The performance of the proposed ensemble "DHE-Mit-Classifier" is evaluated against state-of-the-art CNNs. The performance evaluation on the test set suggests the superiority of the proposed ensemble with an F-score (0.77), recall (0.71), precision (0.83), and area under the precision-recall curve (0.80). The good generalisation of the proposed ensemble with a considerably high F-score and precision suggests its potential use in the development of an assistance tool for pathologists.
Automated left ventricular (LV) segmentation is crucial for efficient quantification of cardiac function and morphology to aid subsequent management of cardiac pathologies. In this paper, we parameterize the complete (all short axis slices and phases) LV segmentation task in terms of the radial distances between the LV centerpoint and the endo- and epicardial contours in polar space. We then utilize convolutional neural network regression to infer these parameters. Utilizing parameter regression, as opposed to conventional pixel classification, allows the network to inherently reflect domain-specific physical constraints. We have benchmarked our approach primarily against the publicly-available left ventricle segmentation challenge (LVSC) dataset, which consists of 100 training and 100 validation cardiac MRI cases representing a heterogeneous mix of cardiac pathologies and imaging parameters across multiple centers. Our approach attained a .77 Jaccard index, which is the highest published overall result in comparison to other automated algorithms. To test general applicability, we also evaluated against the Kaggle Second Annual Data Science Bowl, where the evaluation metric was the indirect clinical measures of LV volume rather than direct myocardial contours. Our approach attained a Continuous Ranked Probability Score (CRPS) of .0124, which would have ranked tenth in the original challenge. With this we demonstrate the effectiveness of convolutional neural network regression paired with domain-specific features in clinical segmentation.
Diabetic Retinopathy (DR) is the most common cause of avoidable vision loss, predominantly affecting the working-age population across the globe. Screening for DR, coupled with timely consultation and treatment, is a globally trusted policy to avoid vision loss. However, implementation of DR screening programs is challenging due to the scarcity of medical professionals able to screen a growing global diabetic population at risk for DR. Computer-aided disease diagnosis in retinal image analysis could provide a sustainable approach for such large-scale screening effort. The recent scientific advances in computing capacity and machine learning approaches provide an avenue for biomedical scientists to reach this goal. Aiming to advance the state-of-the-art in automatic DR diagnosis, a grand challenge on "Diabetic Retinopathy - Segmentation and Grading" was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI - 2018). In this paper, we report the set-up and results of this challenge that is primarily based on Indian Diabetic Retinopathy Image Dataset (IDRiD). There were three principal sub-challenges: lesion segmentation, disease severity grading, and localization of retinal landmarks and segmentation. These multiple tasks in this challenge allow to test the generalizability of algorithms, and this is what makes it different from existing ones. It received a positive response from the scientific community with 148 submissions from 495 registrations effectively entered in this challenge. This paper outlines the challenge, its organization, the dataset used, evaluation methods and results of top-performing participating solutions. The top-performing approaches utilized a blend of clinical information, data augmentation, and an ensemble of models. These findings have the potential to enable new developments in retinal image analysis and image-based DR screening in particular.