MRI-based habitat analysis of vascular and nerve invasion in the tumor microenvironment: an advanced approach for prostate cancer diagnosis

TL;DR

This study uses MRI and radiomic features to improve the detection of vascular and nerve invasion in prostate cancer, enhancing diagnosis and prognosis.

Contribution

A novel radiomic model combining tumor habitat analysis and Gleason scores improves diagnostic accuracy for prostate cancer.

Findings

The habitat-based model achieved an AUC of 0.882 in training and 0.860 in testing for detecting invasion.

Combining habitat scores with Gleason scores improved AUC to 0.889 in training and 0.886 in testing.

The approach outperformed traditional radiomic models in predicting vascular and nerve invasion.

Abstract

This study aims to detect vascular and neural invasion in prostate cancer through MRI, utilize habitat analysis of the tumor microenvironment, construct a radiomic feature model, thereby enhancing diagnostic accuracy and prognostic assessment for prostate cancer, ultimately improving patients’ quality of life.

We retrospectively collected records of 400 patients with pathologically verified prostate cancer from January to December 2023. We developed a radiomic features model within the tumor habitat using MRI data and identified independent risk factors through multivariate analysis to construct a clinical model. Finally, we assessed the performance of these features using the DeLong test (through the area under the receiver operating characteristic curve, AUC), evaluated the calibration curve with the Hosmer-Lemeshow test, and performed decision curve analysis.

In the training set, the optimal algorithm based on the intratumoral heterogeneity score had an AUC value of 0.882 (CI: 0.843-0.921); in the test set, the AUC value was 0.860 (CI: 0.792-0.928). The traditional radiomics model (considering the entire tumor) had an AUC value of 0.761 (CI: 0.695-0.827) in the training set and 0.732 (CI: 0.630-0.834) in the test set. The combined model that integrates habitat scores and Gleason scores had an AUC value of 0.889 (CI: 0.8509-0.9276) in the training set and 0.886 (CI: 0.8183-0.9533) in the test set, outperforming the single models.

By deeply analyzing the tumor microenvironment and combining radiomics models, the diagnostic precision and predictive accuracy of vascular and nerve invasion in prostate cancer can be significantly improved. This approach provides a valuable tool for optimizing treatment plans, improving patient prognosis, and reducing unnecessary medical interventions.

Figures