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

2026-03-06

AI Summary

Traditional two-dimensional histopathology struggles to accurately assess perineural invasion (PNI) and lymphovascular invasion (LVI)—features associated with poor prognosis in prostate cancer. This study leverages light-sheet microscopy of optically cleared, whole-mount prostatectomy specimens labeled with fluorescent H&E and imaged using an open-top light-sheet (OTLS) microscope. Employing nnU-Net for segmentation of nerves and vasculature, the authors extract three-dimensional morphometric features of PNI and LVI from tumor-enriched regions. For the first time, they systematically validate the prognostic value of these 3D features, demonstrating significantly superior performance over conventional 2D metrics in predicting 5-year biochemical recurrence (AUC = 0.71 vs. 0.52), thereby overcoming key limitations of standard pathological assessment.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

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.

Problem

• prostate cancer
• perineural invasion
• lymphovascular invasion
• 3D histomorphometry
• diagnostic grading

Innovation

• 3D histomorphometry
• perineural invasion
• lymphovascular invasion
• light-sheet microscopy
• nnU-Net segmentation