A multi-resolution model for histopathology image classification and localization with multiple instance learning. (April 2021)

• Record Type: Journal Article
• Authors: Li, Jiayun; Li, Wenyuan; Sisk, Anthony; Ye, Huihui; Wallace, W. Dean; Speier, William; Arnold, Corey W.
• Is Part Of: Computers in biology and medicine. Volume 131(2021)
• Publication Date: 2021-04
• Subjects: Whole slide images -- Multiple instance learning -- Convolutional neural network -- Image classification prostate cancer; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2021.104253
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Large numbers of histopathological images have been digitized into high resolution whole slide images, opening opportunities in developing computational image analysis tools to reduce pathologists' workload and potentially improve inter- and intra-observer agreement. Most previous work on whole slide image analysis has focused on classification or segmentation of small pre-selected regions-of-interest, which requires fine-grained annotation and is non-trivial to extend for large-scale whole slide analysis. In this paper, we proposed a multi-resolution multiple instance learning model that leverages saliency maps to detect suspicious regions for fine-grained grade prediction. Instead of relying on expensive region- or pixel-level annotations, our model can be trained end-to-end with only slide-level labels. The model is developed on a large-scale prostate biopsy dataset containing 20, 229 slides from 830 patients. The model achieved 92.7% accuracy, 81.8% Cohen's Kappa for benign, low grade ( i.e. Grade group 1) and high grade ( i.e. Grade group ≥ 2) prediction, an area under the receiver operating characteristic curve (AUROC) of 98.2% and an average precision (AP) of 97.4% for differentiating malignant and benign slides. The model obtained an AUROC of 99.4% and an AP of 99.8% for cancer detection on an external dataset. Graphical abstract: Image 1 Highlights: A multi-resolution multiple instance learning model is developed for Gleason grade group classification. The model can localize suspicious regions, and then classify cancer grade at a higher magnification with selected tiles. The model doesn't require fine-grained annotations and can be trained with slide-level labels from pathology reports. The model was evaluated on a large independent test set and an external dataset, and achieved promising results.