This paper presents and evaluates a deep learning architecture for automated basal cell carcinoma cancer detection that integrates (1) image representation learning, (2) image classification and (3) result interpretability. A novel characteristic of this approach is that it extends the deep learning architecture to also include an interpretable layer that highlights the visual patterns that contribute to discriminate between cancerous and normal tissues patterns, working akin to a digital staining which spotlights image regions important for diagnostic decisions. Experimental evaluation was performed on set of 1,417 images from 308 regions of interest of skin histopathology slides, where the presence of absence of basal cell carcinoma needs to be determined. Different image representation strategies, including bag of features (BOF), canonical (discrete cosine transform (DCT) and Haar-based wavelet transform (Haar)) and proposed learned-from-data representations, were evaluated for comparison. Experimental results show that the representation learned from a large histology image data set has the best overall performance (89.4% in F-measure and 91.4% in balanced accuracy), which represents an improvement of around 7% over canonical representations and 3% over the best equivalent BOF representation.

/pdf/a-deep-learning-architecture-for-image-representation-visual-386rd4801w.pdf

A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detection.

Image analysis and machine learning for detecting malaria

Data-driven methods in structural health monitoring (SHM) is gaining popularity due to recent technological advancements in sensors, as well as high-speed internet and cloud-based computation. Since the introduction of deep learning (DL) in civil engineering, particularly in SHM, this emerging and promising tool has attracted significant attention among researchers. The main goal of this paper is to review the latest publications in SHM using emerging DL-based methods and provide readers with an overall understanding of various SHM applications. After a brief introduction, an overview of various DL methods (e.g., deep neural networks, transfer learning, etc.) is presented. The procedure and application of vibration-based, vision-based monitoring, along with some of the recent technologies used for SHM, such as sensors, unmanned aerial vehicles (UAVs), etc. are discussed. The review concludes with prospects and potential limitations of DL-based methods in SHM applications.

Data-Driven Structural Health Monitoring and Damage Detection through Deep Learning: State-of-the-Art Review.

The number of mitoses per tissue area gives an important aggressiveness indication of the invasive breast carcinoma. However, automatic mitosis detection in histology images remains a challenging problem. Traditional methods either employ hand-crafted features to discriminate mitoses from other cells or construct a pixel-wise classifier to label every pixel in a sliding window way. While the former suffers from the large shape variation of mitoses and the existence of many mimics with similar appearance, the slow speed of the later prohibits its use in clinical practice. In order to overcome these shortcomings, we propose a fast and accurate method to detect mitosis by designing a novel deep cascaded convolutional neural network, which is composed of two components. First, by leveraging the fully convolutional neural network, we propose a coarse retrieval model to identify and locate the candidates of mitosis while preserving a high sensitivity. Based on these candidates, a fine discrimination model utilizing knowledge transferred from cross-domain is developed to further single out mitoses from hard mimics. Our approach outperformed other methods by a large margin in 2014 ICPR MITOS-ATYPIA challenge in terms of detection accuracy. When compared with the state-of-the-art methods on the 2012 ICPR MITOSIS data (a smaller and less challenging dataset), our method achieved comparable or better results with a roughly 60 times faster speed.

/pdf/mitosis-detection-in-breast-cancer-histology-images-via-deep-43jpc8jf6q.pdf

Mitosis detection in breast cancer histology images via deep cascaded networks

Automated image analysis of histopathology specimens could potentially provide support for early detection and improved characterization of breast cancer. Automated segmentation of the cells comprising imaged tissue microarrays (TMAs) is a prerequisite for any subsequent quantitative analysis. Unfortunately, crowding and overlapping of cells present significant challenges for most traditional segmentation algorithms. In this paper, we propose a novel algorithm that can reliably separate touching cells in hematoxylin-stained breast TMA specimens that have been acquired using a standard RGB camera. The algorithm is composed of two steps. It begins with a fast, reliable object center localization approach that utilizes single-path voting followed by mean-shift clustering. Next, the contour of each cell is obtained using a level set algorithm based on an interactive model. We compared the experimental results with those reported in the most current literature. Finally, performance was evaluated by comparing the pixel-wise accuracy provided by human experts with that produced by the new automated segmentation algorithm. The method was systematically tested on 234 image patches exhibiting dense overlap and containing more than 2200 cells. It was also tested on whole slide images including blood smears and TMAs containing thousands of cells. Since the voting step of the seed detection algorithm is well suited for parallelization, a parallel version of the algorithm was implemented using graphic processing units (GPU) that resulted in significant speedup over the C/C++ implementation.

Robust Segmentation of Overlapping Cells in Histopathology Specimens Using Parallel Seed Detection and Repulsive Level Set

A semi-automatic method for quantification and classification of erythrocytes infected with malaria parasites in microscopic images

Malaria is an infectious disease which is mainly diagnosed by visual microscopical evaluation of Giemsa-stained thin blood films using a differential analysis of color features. This paper presents the evaluation of a color segmentation technique, based on standard supervised classification algorithms. The whole approach uses a general purpose classifier, which is parameterized and adapted to the problem of separating image pixels into three different classes: parasite, blood red cells and background. Assessment included not only four different supervised classification techniques - KNN, Naive Bayes, SVM and MLP - but different color spaces -RGB, normalized RGB, HSV and YCbCr-. Results show better performance for the KNN classifiers along with an improving feature characterization in the normalized RGB color space.

/pdf/infected-cell-identification-in-thin-blood-images-based-on-47hggy4gac.pdf

Infected cell identification in thin blood images based on color pixel classification: comparison and analysis

Automatic annotation of histopathological images using a latent topic model based on non-negative matrix factorization.

This article presents a new approach for extracting high level semantic concepts from digital histopathological images. This strategy provides not only annotation of several biologi- cal concepts, but also a coarse location of these concepts. The proposed approach is composed of five main steps: (1) a stain decomposition stage, which separates the contribution of hematoxylin and eosin dyes, (2) a color standardization that corrects color image differences, (3) a part-based repre- sentation, which describes the image in terms of the conditional probability of relevant local patches, selected by their stain contributions, (4) a discriminative classification model, which bridges out the found patterns and the biological concepts, (5) a block-based annotation strategy that identifies the multiple biological concepts within an image. A set of 655 skin images, contain- ing 10 biological concepts of skin tissues were used for assessing the proposed approach, obtaining a sensitivity of 84% and a specificity of 67% when annotating images with multiple concepts. Microsc. Res. Tech. 00:000-000, 2011. V C 2011 Wiley-Liss, Inc.

Gloria M. Díaz

Papers

A semi-automatic method for quantification and classification of erythrocytes infected with malaria parasites in microscopic images

Infected cell identification in thin blood images based on color pixel classification: comparison and analysis

Automatic annotation of histopathological images using a latent topic model based on non-negative matrix factorization.

Micro‐structural tissue analysis for automatic histopathological image annotation

Abbreviated magnetic resonance imaging in breast cancer: A systematic review of literature.