Primary Tumor and Inter-Organ Augmentations for Supervised Lymph Node Colon Adenocarcinoma Metastasis Detection

TL;DR

This paper investigates data augmentation strategies using primary tumor and inter-organ data to improve lymph node metastasis detection in histopathology, especially when labeled data is scarce, enhancing accuracy and robustness.

Contribution

It introduces and evaluates inter-organ and intra-organ augmentation methods that require minimal additional annotation for better metastasis detection.

Findings

Augmentation improves detection accuracy.

Augmentation enhances model robustness.

Inter-organ and intra-organ methods are effective with limited data.

Abstract

The scarcity of labeled data is a major bottleneck for developing accurate and robust deep learning-based models for histopathology applications. The problem is notably prominent for the task of metastasis detection in lymph nodes, due to the tissue's low tumor-to-non-tumor ratio, resulting in labor- and time-intensive annotation processes for the pathologists. This work explores alternatives on how to augment the training data for colon carcinoma metastasis detection when there is limited or no representation of the target domain. Through an exhaustive study of cross-validated experiments with limited training data availability, we evaluate both an inter-organ approach utilizing already available data for other tissues, and an intra-organ approach, utilizing the primary tumor. Both these approaches result in little to no extra annotation effort. Our results show that these data augmentation strategies can be an efficient way of increasing accuracy on metastasis detection, but fore-most increase robustness.