June 2, 2023
Created by
Neo Yin
In Progress
Reading Notes
Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study

Objective To develop an interpretable artificial intelligence algorithm to rule out normal large bowel endoscopic biopsies, saving pathologist resources and helping with early diagnosis. Design A graph neural network was developed incorporating pathologist domain knowledge to classify 6591 whole-slides images (WSIs) of endoscopic large bowel biopsies from 3291 patients (approximately 54% female, 46% male) as normal or abnormal (non-neoplastic and neoplastic) using clinically driven interpretable features. One UK National Health Service (NHS) site was used for model training and internal validation. External validation was conducted on data from two other NHS sites and one Portuguese site. Results Model training and internal validation were performed on 5054 WSIs of 2080 patients resulting in an area under the curve-receiver operating characteristic (AUC-ROC) of 0.98 (SD=0.004) and AUC-precision-recall (PR) of 0.98 (SD=0.003). The performance of the model, named Interpretable Gland-Graphs using a Neural Aggregator (IGUANA), was consistent in testing over 1537 WSIs of 1211 patients from three independent external datasets with mean AUC-ROC=0.97 (SD=0.007) and AUC-PR=0.97 (SD=0.005). At a high sensitivity threshold of 99%, the proposed model can reduce the number of normal slides to be reviewed by a pathologist by approximately 55%. IGUANA also provides an explainable output highlighting potential abnormalities in a WSI in the form of a heatmap as well as numerical values associating the model prediction with various histological features. Conclusion The model achieved consistently high accuracy showing its potential in optimising increasingly scarce pathologist resources. Explainable predictions can guide pathologists in their diagnostic decision-making and help boost their confidence in the algorithm, paving the way for its future clinical adoption. WSIs from University Hospitals Coventry and Warwickshire NHS Trust, East Suffolk and North Essex NHS Foundation Trust, and South Warwickshire NHS Foundation Trust will be made available upon successful application to the PathLAKE data access committee. Relevant information on obtaining the data from the IMP cohort can be found in the original publication.

Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study
The goal of this reading notes is to jot down the main ideas and architecture choices behind the IGUANA model.
I can’t summarize this model better than the illustration from the paper

In words, IGUANA performs a segmentation task, a graph construction task, a feature extraction task (in a non-graphical fashion as the graph-node level), and finally a global graph classification task. Each one of these parts of the architecture require some deliberation.

IGUANA Segmentation
IGUANA Gland Graph Construction
IGUANA Feature Extraction
IGUANA Global Graph Classification

IGUANA may work well for tissue slices where the orignally structure information are preserved. It might not be good for things like

because the BMA preparation procedure means that lots of celluar structural relations are destroyed.