A promising deep learning-assistive algorithm for histopathological screening of colorectal cancer

Abstract

Colorectal cancer is one of the most common cancers worldwide, accounting for an annual estimated 1.8 million incident cases. With the increasing number of colonoscopies being performed, colorectal biopsies make up a large proportion of any histopathology laboratory workload. We trained and validated a unique artificial intelligence (AI) deep learning model as an assistive tool to screen for colonic malignancies in colorectal specimens, in order to improve cancer detection and classification; enabling busy pathologists to focus on higher order decision-making tasks. The study cohort consists of Whole Slide Images (WSI) obtained from 294 colorectal specimens. Qritive’s unique composite algorithm comprises both a deep learning model based on a Faster Region Based Convolutional Neural Network (Faster-RCNN) architecture for instance segmentation with a ResNet-101 feature extraction backbone that provides glandular segmentation, and a classical machine learning classifier. The initial training used pathologists’ annotations on a cohort of 66,191 image tiles extracted from 39 WSIs. A subsequent application of a classical machine learning-based slide classifier sorted the WSIs into ‘low risk’ (benign, inflammation) and ‘high risk’ (dysplasia, malignancy) categories. We further trained the composite AI-model’s performance on a larger cohort of 105 resections WSIs and then validated our findings on a cohort of 150 biopsies WSIs against the classifications of two independently blinded pathologists. We evaluated the area under the receiver-operator characteristic curve (AUC) and other performance metrics. The AI model achieved an AUC of 0.917 in the validation cohort, with excellent sensitivity (97.4%) in detection of high risk features of dysplasia and malignancy. We demonstrate an unique composite AI-model incorporating both a glandular segmentation deep learning model and a classical machine learning classifier, with excellent sensitivity in picking up high risk colorectal features. As such, AI plays a role as a potential screening tool in assisting busy pathologists by outlining the dysplastic and malignant glands.

AI based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images

“…To deploy in practical histopathological diagnostic workflow system for screening colon biopsies, a recent study (20) modeled the classification of epithelial tumors (adenocarcinoma and adenoma) with a large development cohort (n=4 036) and small validation cohorts (n=500, and TCGA-COAD: n=547). A more recent study (21) used gland segmentation and classification to model categorization of ‘low risk’ (benign, inflammation) and ‘high risk’ (dysplasia, malignancy) slides with a small cohort (n=294). However, these models do not cater for early diagnosis and lack high sensitivity.…”

A Deep Learning System to Predict the Histopathological Results From Urine Cytopathological Images

“…It extracts features, makes detections through these features, and quantifies the degree of fit at each detection using a value of possibility ranging from the worst of 0 to the optimum of 100. Evidence has shown that Faster-RCNN is especially good at detecting objects at multiple scales and aspect ratios, such as abnormal cervical cells in cytology images and cancer regions in colorectal biopsies ( 17 , 18 ).…”

Deep Neural Network Models for Colon Cancer Screening

“…The sliding-window technique was used to break these down into smaller images. Other studies used various images, such as endoscopic and whole slide images (WSI) for the detection of colon cancer [ 46 , 47 ]. Another study used a larger image size (768 × 768 pixels) to preserve tissue architecture information and reduce computational cost, as opposed to a smaller patch size (384 × 384 pixels), which produced the same result but had a higher computational cost [ 48 ].…”