MUSeg‐PSV: A Real‐Time Deep‐Learning Segmentation of the Prostate Gland and Seminal Vesicles on 29‐MHz Micro‐Ultrasound
Fuente:
Wiley Open Access
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Artículo Open Access |
| Publié: |
Wiley
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1867004988764454912 |
|---|---|
| author | Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi |
| author_facet | Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi |
| collection | Wiley Open Access |
| contents | MUSeg‐PSV: A Real‐Time Deep‐Learning Segmentation of the Prostate Gland and Seminal Vesicles on 29‐MHz Micro‐Ultrasound Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi BJUI Compass Abstract Objectives This study aimed to develop and evaluate MUSeg‐PSV, a real‐time deep‐learning framework for segmentation of the prostate gland and seminal vesicles on 29‐MHz micro‐ultrasound (MicroUS), intended to support anatomical orientation during MicroUS‐guided prostate biopsy and local staging of prostate cancer. Patients and methods MicroUS data from 14 patients (21 full‐length videos; 2588 annotated frames) were used to train and test MUSeg‐PSV, a lightweight single‐stage convolutional model based on YOLOv11s‐seg. Two training strategies were compared: a standard configuration with basic augmentations and an augmentation‐rich configuration incorporating advanced spatial and photometric transformations. Model performance was assessed on a held‐out test set using mean average precision (mAP), dice similarity coefficient (DSC), expected calibration error (ECE) and Brier score. Real‐time feasibility was evaluated through inference latency and qualitative assessment of temporal consistency on unseen videos. Results The augmentation‐rich model outperformed the standard configuration, yielding a 21% relative increase in mAP and a 4.6‐fold improvement in seminal vesicle AP (0.183 → 0.842). Prostate DSC increased from 0.675 to 0.770 ( p = 4.4 × 10 −5 ), while seminal vesicle DSC remained robust (0.892 vs. 0.876), reflecting a controlled trade‐off with substantially improved SV detection (AP: 0.183 → 0.842). Calibration improved markedly, with ECE decreasing from 0.558 to 0.156 and Brier score from 1.000 to 0.196 ( p < 0.01). Qualitative evaluation confirmed smooth, temporally coherent overlays and consistent delineation of challenging anatomical regions. End‐to‐end latency (28–35 ms/frame; ~35 fps) demonstrated compatibility with real‐time clinical deployment. Conclusion MUSeg‐PSV enables reliable, real‐time multiclass segmentation of high‐frequency MicroUS, providing stable delineation of the prostate and seminal vesicles at clinically viable frame rates. These results support the potential of AI‐assisted MicroUS to enhance operator orientation during MicroUS‐guided prostate biopsy and local staging, and to promote standardised identification of seminal vesicles within prostate cancer diagnostic and staging workflows. 10.1002/bco2.70211 http://creativecommons.org/licenses/by/4.0/ |
| doi_str_mv | 10.1002/bco2.70211 |
| format | Artículo Open Access |
| id | wiley_oa_10_1002_bco2_70211 |
| institution | Wiley Open Access |
| license_str_mv | http://creativecommons.org/licenses/by/4.0/ |
| publishDate | 2026 |
| publisher | Wiley |
| record_format | wiley_oa |
| spellingShingle | MUSeg‐PSV: A Real‐Time Deep‐Learning Segmentation of the Prostate Gland and Seminal Vesicles on 29‐MHz Micro‐Ultrasound Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi BJUI Compass MUSeg‐PSV: A Real‐Time Deep‐Learning Segmentation of the Prostate Gland and Seminal Vesicles on 29‐MHz Micro‐Ultrasound Ludovica Cella Marco Paciotti Giacomo Cavadini Luca Di Stefano Pier Paolo Avolio Vittorio Fasulo Andrea Piccolini Cesare Saitta Edoardo Beatrici Rafal Kocielnik Andrew J. Hung Alberto Saita Paolo Casale Massimo Lazzeri Giovanni Lughezzani Nicolò Maria Buffi BJUI Compass Abstract Objectives This study aimed to develop and evaluate MUSeg‐PSV, a real‐time deep‐learning framework for segmentation of the prostate gland and seminal vesicles on 29‐MHz micro‐ultrasound (MicroUS), intended to support anatomical orientation during MicroUS‐guided prostate biopsy and local staging of prostate cancer. Patients and methods MicroUS data from 14 patients (21 full‐length videos; 2588 annotated frames) were used to train and test MUSeg‐PSV, a lightweight single‐stage convolutional model based on YOLOv11s‐seg. Two training strategies were compared: a standard configuration with basic augmentations and an augmentation‐rich configuration incorporating advanced spatial and photometric transformations. Model performance was assessed on a held‐out test set using mean average precision (mAP), dice similarity coefficient (DSC), expected calibration error (ECE) and Brier score. Real‐time feasibility was evaluated through inference latency and qualitative assessment of temporal consistency on unseen videos. Results The augmentation‐rich model outperformed the standard configuration, yielding a 21% relative increase in mAP and a 4.6‐fold improvement in seminal vesicle AP (0.183 → 0.842). Prostate DSC increased from 0.675 to 0.770 ( p = 4.4 × 10 −5 ), while seminal vesicle DSC remained robust (0.892 vs. 0.876), reflecting a controlled trade‐off with substantially improved SV detection (AP: 0.183 → 0.842). Calibration improved markedly, with ECE decreasing from 0.558 to 0.156 and Brier score from 1.000 to 0.196 ( p < 0.01). Qualitative evaluation confirmed smooth, temporally coherent overlays and consistent delineation of challenging anatomical regions. End‐to‐end latency (28–35 ms/frame; ~35 fps) demonstrated compatibility with real‐time clinical deployment. Conclusion MUSeg‐PSV enables reliable, real‐time multiclass segmentation of high‐frequency MicroUS, providing stable delineation of the prostate and seminal vesicles at clinically viable frame rates. These results support the potential of AI‐assisted MicroUS to enhance operator orientation during MicroUS‐guided prostate biopsy and local staging, and to promote standardised identification of seminal vesicles within prostate cancer diagnostic and staging workflows. 10.1002/bco2.70211 http://creativecommons.org/licenses/by/4.0/ |
| title | MUSeg‐PSV: A Real‐Time Deep‐Learning Segmentation of the Prostate Gland and Seminal Vesicles on 29‐MHz Micro‐Ultrasound |
| topic | BJUI Compass |
| url | https://bjui-journals.onlinelibrary.wiley.com/doi/10.1002/bco2.70211 |