BACH: Grand challenge on breast cancer histology images.

Deep neural network models for computational histopathology: A survey

Breast cancer histopathological image classification using a hybrid deep neural network.

There has been an exponential growth in the application of AI in health and in pathology. This is resulting in the innovation of deep learning technologies that are specifically aimed at cellular imaging and practical applications that could transform diagnostic pathology. This paper reviews the different approaches to deep learning in pathology, the public grand challenges that have driven this innovation and a range of emerging applications in pathology. The translation of AI into clinical practice will require applications to be embedded seamlessly within digital pathology workflows, driving an integrated approach to diagnostics and providing pathologists with new tools that accelerate workflow and improve diagnostic consistency and reduce errors. The clearance of digital pathology for primary diagnosis in the US by some manufacturers provides the platform on which to deliver practical AI. AI and computational pathology will continue to mature as researchers, clinicians, industry, regulatory organizations and patient advocacy groups work together to innovate and deliver new technologies to health care providers: technologies which are better, faster, cheaper, more precise, and safe.

/pdf/translational-ai-and-deep-learning-in-diagnostic-pathology-4gxgwy8rd6.pdf

Translational AI and Deep Learning in Diagnostic Pathology

The widespread adoption of whole slide imaging has increased the demand for effective and efficient gigapixel image analysis. Deep learning is at the forefront of computer vision, showcasing significant improvements over previous methodologies on visual understanding. However, whole slide images have billions of pixels and suffer from high morphological heterogeneity as well as from different types of artifacts. Collectively, these impede the conventional use of deep learning. For the clinical translation of deep learning solutions to become a reality, these challenges need to be addressed. In this paper, we review work on the interdisciplinary attempt of training deep neural networks using whole slide images, and highlight the different ideas underlying these methodologies.

/pdf/deep-learning-for-whole-slide-image-analysis-an-overview-koor8f72sr.pdf

Deep Learning for Whole Slide Image Analysis: An Overview.

Convolutional neural networks (CNN) have shown to be effective in medical image processing and analysis. Herein, we propose a CNN approach to perform patch- and pixel-wise histology labeling on breast microscopy and whole slide images (WSI), respectively. We devise a processing block that is capable of extracting compact features in an efficient manner. Based upon the processing block, classification and segmentation networks are built. Two networks share an encoder via partial transformation and transfer learning to maximally utilize the trained network and available dataset. 400 microscopy images and 10 WSI were employed to evaluate the proposed approach. For patch classification, an accuracy of 71% and 65% were obtained on the training and testing dataset, respectively. As for segmentation, we achieved an overall score of 0.7343 and 0.4945 on the training and testing dataset, respectively.

Micro and Macro Breast Histology Image Analysis by Partial Network Re-use

Background Diseases and pests have a profound effect on a yearly harvest and productivity in agriculture. A precise and accurate detection of the diseases and pests could facilitate timely treatment and management of the diseases and pests and lessen the resultant loss in economy and health. Herein, we propose an improved design of the disease detection system for plant images. Methods Built upon the two-stage framework of object detection neural networks such as Mask R-CNN, the proposed network involves three types of extensions, including the addition of additional level of feature pyramids to improve the exploration and proposal of candidate regions, the aggregation of feature maps from all levels of feature pyramids per candidate region to fully exploit the information from feature pyramids, and the introduction of a squeeze-and-excitation block to the construction of feature pyramids and the aggregated feature maps to improve the representation of feature maps. Results The proposed network was evaluated using 74 images of infected apple fruits. In 3-fold cross-validation, the proposed network achieved averaged precision (AP) of 72.26, AP at 0.5 threshold of 88.51 and AP at 0.75 threshold of 82.30. In the comparative experiments, the proposed network outperformed the other competing networks. The utility of the three extensions was also demonstrated in comparison to Mask R-CNN. Conclusions The experimental results suggest that the proposed network could identify and localize the symptom of the disease with high accuracy, leading to an early diagnosis and treatment of the disease, and thus holding the potential for improving crop yield and quality.

/pdf/region-aggregated-attention-cnn-for-disease-detection-in-4iw6s5iejn.pdf

Region-aggregated attention CNN for disease detection in fruit images.

In this study, we propose a deep learning method to segment plants in images. The deep learning method is composed of a contracting path and expanding path. The contracting path learns high level feature representation of images and the expanding path interprets the high level features and generates segmentation maps. The proposed method is trained and validated, via five-fold cross validation, using images of radish seedlings. The method achieved 99.15% accuracy and 0.9790 Dice coefficient, suggesting that deep learning could play a significant role in processing and analyzing plant images.

Eal Kim

Papers

BACH: Grand challenge on breast cancer histology images.

Micro and Macro Breast Histology Image Analysis by Partial Network Re-use

Region-aggregated attention CNN for disease detection in fruit images.

Deep convolution and up-convolution network for plant segmentation