One-by-One Stainer: A Fast and Hallucination Resilient Domain Adaptation Method for Histopathology

Karel Moens, Jonas De Vylder, Tinne Tuytelaars, Matthew B. Blaschko

Keywords: domain adaptation, medical image analysis, histopathology, information loss

TL;DR: Histological stain normalization corrects data drift. AI based methods risk image hallucinations that affect the diagnosis. Constraints on the network lead to resilience to hallucinations.

Abstract: Histological staining is a crucial step in the analysis of tissue samples, enabling pathologists to identify and diagnose diseases. However, variations in staining protocols and equipment can lead to inconsistencies in image quality, making it challenging to compare samples across different conditions. Histological stain normalization remains an active area of research with increasing demand for AI driven diagnosis support. Unlike other domain adaptation problems, in pathology, the consequences of image hallucinations, removing or inserting information, are much greater. We propose a method that mitigates the risk of hallucinations by simplifying the network architecture and training process. Our model does not need supervision from CycleGAN based models. It is trained directly and leverages target domain color distribution information for better convergence without requiring any paired images. As a result, our method can be trained concurrently on images at varying scales, showing differing anatomical structures or dyes. This simplifies the data set collection, facilitates the adoption at new centers, and reduces the number of models needed at inference.

Primary Subject Area: Transfer Learning and Domain Adaptation

Secondary Subject Area: Safe and Trustworthy Learning-assisted Solutions for Medical Imaging

Registration Requirement: Yes

Visa & Travel: No

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 121