Extracting and analyzing 3D histomorphometric features related to perineural and lymphovascular invasion in prostate cancer

TL;DR

This study develops a 3D histomorphometric analysis pipeline to extract features related to nerve and vessel invasion in prostate cancer, demonstrating improved prognostic value over traditional 2D features.

Contribution

The paper introduces a novel 3D feature extraction pipeline for PNI and LVI in prostate cancer, utilizing advanced imaging and segmentation techniques to enhance prognostic assessments.

Findings

3D PNI features outperform 2D features in prognosis (AUC = 0.71 vs. 0.52).

A deep learning model accurately segments nerves and vessels in 3D prostate tissue.

3D analysis provides more comprehensive spatial information for cancer invasion assessment.

Abstract

Diagnostic grading of prostate cancer (PCa) relies on the examination of 2D histology sections. However, the limited sampling of specimens afforded by 2D histopathology, and ambiguities when viewing 2D cross-sections, can lead to suboptimal treatment decisions. Recent studies have shown that 3D histomorphometric analysis of glands and nuclei can improve PCa risk assessment compared to analogous 2D features. Here, we expand on these efforts by developing an analytical pipeline to extract 3D features related to perineural invasion (PNI) and lymphovascular invasion (LVI), which correlate with poor prognosis for a variety of cancers. A 3D segmentation model (nnU-Net) was trained to segment nerves and vessels in 3D datasets of archived prostatectomy specimens that were optically cleared, labeled with a fluorescent analog of H&E, and imaged with open-top light-sheet (OTLS) microscopy. PNI- and LVI-related features, including metrics describing cancer-nerve and cancer-vessel proximity, were then extracted based on the 3D nerve/vessel segmentation masks in conjunction with 3D masks of cancer-enriched regions. As a preliminary exploration of the prognostic value of these features, we trained a supervised machine learning classifier to predict 5-year biochemical recurrence (BCR) outcomes, finding that 3D PNI-related features are moderately prognostic and outperform 2D PNI-related features (AUC = 0.71 vs. 0.52). Source code is available at https://github.com/sarahrahsl/SegCIA.git.