# A retrospective study on predicting clinically significant prostate cancer via a bi-parametric ultrasound-based deep learning radiomics model

## TL;DR

This study developed a new model combining ultrasound-based deep learning with clinical data to better predict significant prostate cancer, especially where MRI is not available.

## Contribution

The first nomogram integrating ultrasound-based deep learning radiomics with clinical factors for predicting clinically significant prostate cancer.

## Key findings

- The bi-parametric ultrasound-based DLR model achieved an AUC of 0.80 in predicting csPCa.
- The composite model combining DLR and clinical factors achieved an AUC of 0.87, outperforming individual models.
- The composite model showed greater net benefit across high-risk thresholds compared to standalone models.

## Abstract

This study aimed to establish and evaluate a model utilizing bi-parametric ultrasound-based deep learning radiomics (DLR) in conjunction with clinical factors to anticipate clinically significant prostate cancer (csPCa).

We retrospectively analyzed 232 participants from our institution who underwent both B-mode ultrasound and shear wave elastography (SWE) prior to prostate biopsy between June 2022 and December 2023. A random allocation placed the participants into training and test cohorts with a 7:3 distribution. We developed a nomogram that integrates DLR with clinical factors within the training cohort, which was subsequently validated using the test cohort. The diagnostic performance and clinical applicability were evaluated with receiver operating characteristic (ROC) curve analysis and decision curve analysis.

In our study, the bi-parametric ultrasound-based DLR model demonstrated an area under the curve (AUC) of 0.80 (95%CI: 0.70-0.91) in the test set, surpassing the performance of both the radiomics and deep learning models individually. By integrating clinical factors, a composite model, presented as the nomogram, was developed and exhibited superior diagnostic performance, achieving an AUC of 0.87 (95%CI: 0.77-0.95) in the test set. The performance exceeded that of the DLR (P = 0.049) and the clinical model (AUC = 0.79, 95%CI: 0.69-0.86, P = 0.041). Furthermore, the decision curve analysis indicated that the composite model provided a greater net benefit across a various high-risk threshold than the DLR or the clinical model alone.

To our knowledge, this is the first proposal of a nomogram integrating ultrasound-based DLR with clinical indicators for predicting csPCa. This nomogram can improve the accuracy of csPCa prediction and may help physicians make more confident decisions regarding interventions, particularly in settings where MRI is unavailable.