Development and internal validation of transrectal ultrasound radiomics models for patient- and needle-level prostate cancer prediction in biopsy-naive men.
- 1Department of Ultrasound, Huashan Hospital, Fudan University, Shanghai, China.
- 2Department of Urology, Huashan Hospital, Fudan University, Shanghai, China.
- 3Department of Electronic Engineering, College of Biomedical Engineering, Fudan University, Shanghai, China.
Abstract
Current prostate cancer (PCa) assessment uses clinical findings, prostate-specific antigen (PSA), and multiparametric magnetic resonance imaging (mp-MRI), while transrectal ultrasound (TRUS) mainly provides real-time biopsy guidance. We developed zone-specific TRUS radiomics models for patient-level and planned needle-level PCa prediction. This retrospective single-center study included 247 biopsy-naive men undergoing freehand transperineal 10-core systematic biopsy from August 2023 to April 2024. Each patient contributed two transition zone (TZ) cores and eight peripheral zone (PZ) cores. A blinded sonographer delineated whole-zone and pre-firing needle-target regions of interest (ROIs), visually matched to post-firing images acquired seconds later. From each ROI, 513 radiomic features were extracted, sparsely selected, and classified with a two-layer RNN. Models were evaluated using an 80:20 split. A patient or core was positive when pathology showed Gleason score (GS) ≥6. The cohort included 116 patients with PCa and 131 with benign findings; 545 of 2,470 cores were positive. Without PSA, the combined TZ + PZ patient-level model had the highest patient-level area under the receiver operating characteristic curve (AUC) (0.828), whereas needle-level AUCs were 0.699, 0.698, and 0.680 for TZ, PZ, and TZ + PZ models. With PSA, the combined patient-level model reached an AUC of 0.876, and the needle-level TZ + PSA model reached 0.826. The findings support further investigation of zone-specific TRUS radiomics, particularly for patient-level prediction. Needle-level results are exploratory and do not establish real-time biopsy guidance. External validation, confidence intervals, comparator models, prospective registration, and patient-grouped evaluation are required before clinical use.
Related
- Development and internal validation of a clinicopathological and CT radiomics based prediction model for extracranial distant metastasis after radical resection in early-stage non-small cell lung cancer
- MRI-Based Radiomics Model for Pretreatment Prediction of Pathological Lymph Node Metastasis in Neuroendocrine Carcinoma of the Cervix: Dual-Center Development and External Validation.
- Development and Patient-Level Internal Validation of an MRI-Based Radiomics Machine Learning Model for Preoperative Prediction of Cervical Lymph Node Metastasis in Oral Squamous Cell Carcinoma: A Pilot Study.
- Multimodal integration of carotid plaque ultrasound radiomics and dynamic systemic immune-inflammation trajectories for subacute risk stratification after stroke thrombectomy: development and internal validation of an exploratory prognostic model
- Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma
BibTeX
@article{chen2026development,
title = {{Development and internal validation of transrectal ultrasound radiomics models for patient- and needle-level prostate cancer prediction in biopsy-naive men.}},
author = {Jizhao Chen and Guanxiong Ding and Guoqing Wu and Weibin Zhang},
journal = {Translational andrology and urology},
year = {2026},
month = sep,
doi = {10.21037/tau-2026-0354},
url = {https://europepmc.org/article/MED/42997186},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Development and internal validation of transrectal ultrasound radiomics models for patient- and needle-level prostate cancer prediction in biopsy-naive men.
AU - Jizhao Chen
AU - Guanxiong Ding
AU - Guoqing Wu
AU - Weibin Zhang
PY - 2026
DA - 2026/09/29
JO - Translational andrology and urology
DO - 10.21037/tau-2026-0354
UR - https://europepmc.org/article/MED/42997186
AB - Current prostate cancer (PCa) assessment uses clinical findings, prostate-specific antigen (PSA), and multiparametric magnetic resonance imaging (mp-MRI), while transrectal ultrasound (TRUS) mainly provides real-time biopsy guidance. We developed zone-specific TRUS radiomics models for patient-level and planned needle-level PCa prediction. This retrospective single-center study included 247 biopsy-naive men undergoing freehand transperineal 10-core systematic biopsy from August 2023 to April 2024. Each patient contributed two transition zone (TZ) cores and eight peripheral zone (PZ) cores. A blinded sonographer delineated whole-zone and pre-firing needle-target regions of interest (ROIs), visually matched to post-firing images acquired seconds later. From each ROI, 513 radiomic features were extracted, sparsely selected, and classified with a two-layer RNN. Models were evaluated using an 80:20 split. A patient or core was positive when pathology showed Gleason score (GS) ≥6. The cohort included 116 patients with PCa and 131 with benign findings; 545 of 2,470 cores were positive. Without PSA, the combined TZ + PZ patient-level model had the highest patient-level area under the receiver operating characteristic curve (AUC) (0.828), whereas needle-level AUCs were 0.699, 0.698, and 0.680 for TZ, PZ, and TZ + PZ models. With PSA, the combined patient-level model reached an AUC of 0.876, and the needle-level TZ + PSA model reached 0.826. The findings support further investigation of zone-specific TRUS radiomics, particularly for patient-level prediction. Needle-level results are exploratory and do not establish real-time biopsy guidance. External validation, confidence intervals, comparator models, prospective registration, and patient-grouped evaluation are required before clinical use.
SN - 2223-4691
ER -