EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Uncertainty‐aware hybrid model for reliable navigation guidance in prostate biopsy

Chloé Soormally, Clément Beitone, Jocelyne Troccaz, Sandrine Voros

Medical Physics · 2026

DOI: 10.1002/mp.70718 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2026. Verfasst von Chloé Soormally und 3 weiteren Autor:innen. Beteiligte Einrichtung: UMR 5525, TIMC, Univ. Grenoble Alpes, CNRS, VetAgro Sup, Grenoble INP, INSERM, Grenoble, France. Hauptthemen laut MEDLINE: Prostate, Image-Guided Biopsy, Prostatic Neoplasms. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: GRANT PSPC DIANA n°9, GRANT MIAI@GRENOBLE-ALPES, CAMI LABEX.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Prostate biopsy – performed under ultrasound (US) guidance ‐ is the only confirmatory procedure for diagnosing prostate cancer. If several systems aiming at improving the accuracy of tissue sampling for histopathological analysis exist, they often fail to adequately account for patient / tissue motion and deformation during the procedure or are not suitable for real‐time guidance towards a pre‐defined target.

Purpose

This work proposes a real‐time assistance method to help urologists navigate between biopsy sites leveraging both 2D US and 3D US information.

Methods

The proposed hybrid framework combines three ResNet‐18‐based sub‐networks with a Kalman filter to track the pose of the current 2D US frame within a reference 3D US volume acquired during the intervention. Two of the networks predict relative rigid transformations from pairs of US frames or frame/slice combinations extracted from the 3D volume. A third network predicts the registration error from a frame/slice pair and acts as a large‐error detector. This error prediction module is integrated directly into the iterative registration process, to ensure robust tracking in the presence of tissue deformation or image artifacts, while also providing an uncertainty estimate of registration quality at each time step. The proposed framework was trained and evaluated on complex biopsy trajectories generated from a dataset of 847 3D US volumes acquired during real transrectal prostate biopsy procedures from 97 patients. The dataset was divided into training (78 patients, 669 volumes), validation (10 patients, 115 volumes), and test (9 patients, 63 volumes) sets. Performance was compared with an image‐correlation‐based baseline method using clinically relevant evaluation metrics, including the mean surface registration error ( mean SRE ) over 25‐s trajectories, as well as the percentage of registered frames with an SRE below 2.5 mm and 5 mm. Statistical significance was assessed using Wilcoxon signed‐rank tests (adjusted with Holm–Bonferroni correction) and 95% confidence bootstrap intervals (CI 95%) across the test cohort. Effect sizes were quantified with rank‐biserial correlation (RBC).

Results

Compared with the baseline method, the proposed approach achieved a significant reduction in the mean SRE over 25‐s trajectories, decreasing from to mm (median [CI 95%], p = 0.016, RBC = 0.96). In addition, the proposed large‐error detector ‐ used for uncertainty estimation ‐ achieved a balanced accuracy score of 0.81 for classifying registration errors above or below a given threshold of 5 mm.

Conclusions

These results demonstrate the potential of the proposed framework to improve the accuracy and robustness of real‐time prostate biopsy navigation guidance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ProstateImage-Guided BiopsyProstatic NeoplasmsHumansMaleUncertaintyUltrasonographyImaging, Three-Dimensional

Stichwörter der Autor:innen

2D/3D registrationdeep learningmodel uncertaintynavigation assistanceprostate biopsyultrasound

Autor:innen und Institutionen

  • UMR 5525, TIMC, Univ. Grenoble Alpes, CNRS, VetAgro Sup, Grenoble INP, INSERM, Grenoble, France.

Förderung

  • GRANT PSPC DIANA n°9
  • GRANT MIAI@GRENOBLE-ALPES
  • CAMI LABEX

Zitieren

APA

Soormally, C., Beitone, C., Troccaz, J., & Voros, S. (2026). Uncertainty‐aware hybrid model for reliable navigation guidance in prostate biopsy. Medical Physics. https://doi.org/10.1002/mp.70718

Vancouver

Soormally C, Beitone C, Troccaz J, Voros S. Uncertainty‐aware hybrid model for reliable navigation guidance in prostate biopsy. Medical Physics. 2026. doi:10.1002/mp.70718

BibTeX
@article{Soormally2026,
  author = {Soormally, Chloé and Beitone, Clément and Troccaz, Jocelyne and Voros, Sandrine},
  title = {Uncertainty‐aware hybrid model for reliable navigation guidance in prostate biopsy},
  journal = {Medical Physics},
  year = {2026},
  doi = {10.1002/mp.70718}
}
Kostenlos starten →