Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Prototype-based Interpretable Grading of Prostate Cancer

Riddhasree Bhattacharyya, Pallabi Dutta, Sushmita Mitra

TL;DR

A novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images that can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows is proposed.

Abstract

Prostate cancer being one of the frequently diagnosed malignancy in men, the rising demand for biopsies places a severe workload on pathologists. The grading procedure is tedious and subjective, motivating the development of automated systems. Although deep learning has made inroads in terms of performance, its limited interpretability poses challenges for widespread adoption in high-stake applications like medicine. Existing interpretability techniques for prostate cancer classifiers provide a coarse explanation but do not reveal why the highlighted regions matter. In this scenario, we propose a novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images. These networks can prove to be more trustworthy since their explicit reasoning procedure mirrors the workflow of a pathologist in comparing suspicious regions with clinically validated examples. The network is initially pre-trained at patch-level to learn robust prototypical features associated with each grade. In order to adapt it to a weakly-supervised setup for prostate cancer grading, the network is fine-tuned with a new prototype-aware loss function. Finally, a new attention-based dynamic pruning mechanism is introduced to handle inter-sample heterogeneity, while selectively emphasizing relevant prototypes for optimal performance. Extensive validation on the benchmark PANDA and SICAP datasets confirms that the framework can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows.

Adaptive Prototype-based Interpretable Grading of Prostate Cancer

TL;DR

A novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images that can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows is proposed.

Abstract

Prostate cancer being one of the frequently diagnosed malignancy in men, the rising demand for biopsies places a severe workload on pathologists. The grading procedure is tedious and subjective, motivating the development of automated systems. Although deep learning has made inroads in terms of performance, its limited interpretability poses challenges for widespread adoption in high-stake applications like medicine. Existing interpretability techniques for prostate cancer classifiers provide a coarse explanation but do not reveal why the highlighted regions matter. In this scenario, we propose a novel prototype-based weakly-supervised framework for an interpretable grading of prostate cancer from histopathology images. These networks can prove to be more trustworthy since their explicit reasoning procedure mirrors the workflow of a pathologist in comparing suspicious regions with clinically validated examples. The network is initially pre-trained at patch-level to learn robust prototypical features associated with each grade. In order to adapt it to a weakly-supervised setup for prostate cancer grading, the network is fine-tuned with a new prototype-aware loss function. Finally, a new attention-based dynamic pruning mechanism is introduced to handle inter-sample heterogeneity, while selectively emphasizing relevant prototypes for optimal performance. Extensive validation on the benchmark PANDA and SICAP datasets confirms that the framework can serve as a reliable assistive tool for pathologists in their routine diagnostic workflows.
Paper Structure (10 sections, 2 theorems, 18 equations, 8 figures, 4 tables)

This paper contains 10 sections, 2 theorems, 18 equations, 8 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Problem statement
  4. Stage 1: Patch-level pretraining
  5. Stage 2: WSI-level fine-tuning
  6. Stage 3: Attention-based dynamic prototype pruning
  7. Experimental Results and Discussion
  8. Quantitative analysis
  9. Qualitative analysis
  10. Conclusion

Key Result

Lemma 1

Let $\epsilon \ge 0$ be the convergence value of the classwise loss function such that $\mathcal{L}_c \le \epsilon$. The mean attention responses for positive and negative WSIs have disjoint support quantified by the bound on their inner product $\langle \boldsymbol{\mu}_c^+, \boldsymbol{\mu}_c^- \r

Figures (8)

  • Figure 1: Schematic representation of the workflow of the ADAPT framework
  • Figure 2: The architecture of the ADAPT framework. During stage 1 patch-level pretraining, the attention and WSI-level prediction modules are not needed. For stage 2 WSI-level fine-tuning, the attention module is not required. Stage 3 uses all the modules.
  • Figure 3: Training strategy for WSI-level fine-tuning
  • Figure 4: Ablation study evaluating the impact of the training stages and prototype counts on WSI-level Gleason grading performance over the PANDA dataset w.r.t. (a) Macro F1 score, and corresponding (b) Hamming loss
  • Figure 5: Fraction of low-attention prototypes, for configurations having prototypes per class as (a) 4, (b) 5, and (c) 6, over the PANDA dataset
  • ...and 3 more figures

Theorems & Definitions (4)

  • Lemma 1
  • proof
  • Lemma 2
  • proof