ZeroReg3D: A Zero-shot Registration Pipeline for 3D Consecutive Histopathology Image Reconstruction

TL;DR

ZeroReg3D is a novel zero-shot registration pipeline that enables accurate 3D reconstruction of histological tissue from 2D slices, overcoming deformation and variability issues without retraining.

Contribution

It combines zero-shot deep learning keypoint matching with optimization-based registration, eliminating the need for retraining and improving 3D histopathology reconstruction.

Findings

Effective handling of tissue deformation and artifacts.

No retraining required, suitable for diverse datasets.

Open-source implementation available.

Abstract

Histological analysis plays a crucial role in understanding tissue structure and pathology. While recent advancements in registration methods have improved 2D histological analysis, they often struggle to preserve critical 3D spatial relationships, limiting their utility in both clinical and research applications. Specifically, constructing accurate 3D models from 2D slices remains challenging due to tissue deformation, sectioning artifacts, variability in imaging techniques, and inconsistent illumination. Deep learning-based registration methods have demonstrated improved performance but suffer from limited generalizability and require large-scale training data. In contrast, non-deep-learning approaches offer better generalizability but often compromise on accuracy. In this study, we introduced ZeroReg3D, a novel zero-shot registration pipeline tailored for accurate 3D reconstruction from serial histological sections. By combining zero-shot deep learning-based keypoint matching with optimization-based affine and non-rigid registration techniques, ZeroReg3D effectively addresses critical challenges such as tissue deformation, sectioning artifacts, staining variability, and inconsistent illumination without requiring retraining or fine-tuning. The code has been made publicly available at https://github.com/hrlblab/ZeroReg3D