2D-3D Deformable Image Registration of Histology Slide and Micro-CT with ML-based Initialization

TL;DR

A novel 2D-3D multi-modal deformable image registration method that demonstrates superior performance compared to the other two methods and is evaluated on datasets acquired from tonsil and tumor tissues.

Abstract

Recent developments in the registration of histology and micro-computed tomography (μCT) have broadened the perspective of pathological applications such as virtual histology based on μCT. This topic remains challenging because of the low image quality of soft tissue CT. Additionally, soft tissue samples usually deform during the histology slide preparation, making it difficult to correlate the structures between histology slide and μCT. In this work, we propose a novel 2D-3D multi-modal deformable image registration method. The method uses a machine learning (ML) based initialization followed by the registration. The registration is finalized by an analytical out-of-plane deformation refinement. The method is evaluated on datasets acquired from tonsil and tumor tissues. μCTs of both phase-contrast and conventional absorption modalities are investigated. The registration results from the proposed method are compared with those from intensity- and keypoint-based methods. The comparison is conducted using both visual and fiducial-based evaluations. The proposed method demonstrates superior performance compared to the other two methods.

Figures (4)

• Figure 1: The demonstration of the workflow of the proposed registration algorithm. (A) Image preprocessing with grayscale conversion and percentile normalization. (B) Initialization of the plane pose using 2D-3D registration on the feature maps of CT and histology. The original feature maps contain 16 channels, but only the first 3 channels are extracted for better visualization. (C) Sampling plane refinement by optimizing over the plane pose parameters and the out-of-plane deformation. Control point pairs are displayed as yellow markers above and under the CT volume.
• Figure 2: Preprocessed histology slides and the registered CT slices of different tissues and imaging modalities. (A) and (B) Tonsil tissues and phase-contrast CTs. (C) Tumor tissue and phase-contrast CT. (D) Tonsil tissue and absorption CT.
• Figure 3: Comparison of registration results from different initialization approaches. (A) Preprocessed histology image. (B) Registration using intensity-based initialization. (C) Registration using keypoint-based initialization. (D) Registration using DISA initialization. (E) Registration using manual initialization.
• Figure 4: The selected 20 fiducial pairs on the sample shown in Figure \ref{['fig:result_images']}A and the plot of the computed FRE values. (A) 20 manually annotated fiducials on the 2D histology. (B) Corresponding 20 fiducials on the CT volume. (C) FRE values of the registration results from four different initialization approaches