Fidelity-Imposed Displacement Editing for the Learn2Reg 2024 SHG-BF Challenge

TL;DR

This paper introduces a novel multi-modal registration framework with fidelity-imposed displacement editing, improving alignment of SHG and BF microscopy images, validated by winning the Learn2Reg 2024 challenge.

Contribution

It presents a new registration method combining contrastive learning, feature pre-alignment, and instance-level optimization for multi-modal microscopy images.

Findings

Achieved 1st place in the Learn2Reg 2024 SHG-BF Challenge.

Outperformed existing methods in multi-modal image registration.

Validated effectiveness through extensive experiments.

Abstract

Co-examination of second-harmonic generation (SHG) and bright-field (BF) microscopy enables the differentiation of tissue components and collagen fibers, aiding the analysis of human breast and pancreatic cancer tissues. However, large discrepancies between SHG and BF images pose challenges for current learning-based registration models in aligning SHG to BF. In this paper, we propose a novel multi-modal registration framework that employs fidelity-imposed displacement editing to address these challenges. The framework integrates batch-wise contrastive learning, feature-based pre-alignment, and instance-level optimization. Experimental results from the Learn2Reg COMULISglobe SHG-BF Challenge validate the effectiveness of our method, securing the 1st place on the online leaderboard.