A Light, 3D UNet-based Architecture for Fully Automatic Segmentation of Prostate Lesions from T2-MRI Images

Larisa Gabriela Coroama; Laura Diosan; Teodora Telecan; Iulia Andras; Nicolae Crisan; Anca Andreica; Cosmin Caraiani; Andrei Lebovici; Zoltán Bálint; Bianca Boca

doi:10.2174/1573405620666230522151445

A Light, 3D UNet-based Architecture for Fully Automatic Segmentation of Prostate Lesions from T2-MRI Images

Curr Med Imaging. 2023 May 22. doi: 10.2174/1573405620666230522151445. Online ahead of print.

Authors

Larisa Gabriela Coroama¹, Laura Diosan¹, Teodora Telecan^{2

3}, Iulia Andras^{2

3}, Nicolae Crisan^{2

3}, Anca Andreica¹, Cosmin Caraiani⁴, Andrei Lebovici^{5

6}, Zoltán Bálint⁷, Bianca Boca^{3

8}

Affiliations

¹ Faculty of Mathematics and Computer Science, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania.
² Department of Urology, Faculty of Medicine, Iuliu Hațieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania.
³ Department of Urology, Municipal Clinical Hospital, 400139 Cluj-Napoca, Romania.
⁴ Department of Medical Imaging, Iuliu Hațieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania.
⁵ Department of Radiology, Faculty of Medicine, Iuliu Hațieganu University of Medicine and Pharmacy, 400012 Cluj-Napoca, Romania.
⁶ Department of Radiology, Emergency Clinical County Hospital of Cluj-Napoca, 400006 Cluj-Napoca, Romania.
⁷ Department of Biomolecular Physics, Faculty of Physics, Babeș-Bolyai University, 400084 Cluj-Napoca, Romania.
⁸ Department of Radiology and Medical Imaging, Faculty of Medicine, George Emil Palade University of Medicine, Pharmacy, Science and Technology of Târgu Mureș, 540139 Târgu Mureș, Romania.

PMID: 37218191
DOI: 10.2174/1573405620666230522151445

Abstract

Introduction: Prostate magnetic resonance imaging (MRI) has been recently integrated into the pathway of diagnosis of prostate cancer (PCa). However, the lack of an optimal contrast-to-noise ratio hinders automatic recognition of suspicious lesions, thus developing a solution for proper delimitation of the tumour and its separation from the healthy parenchyma, which is of primordial importance.

Method: As a solution to this unmet medical need, we aimed to develop a decision support system based on artificial intelligence, which automatically segments the prostate and any suspect area from the 3D MRI images. We assessed retrospective data from all patients diagnosed with PCa by MRI-US fusion prostate biopsy, who underwent prostate MRI in our department due to a clinical or biochemical suspicion of PCa (n=33). All examinations were performed using a 1.5 Tesla MRI scanner. All images were reviewed by two radiologists, who performed manual segmentation of the prostate and all lesions. A total of 145 augmented datasets were generated. The performance of our fully automated end-to-end segmentation model based on a 3D UNet architecture and trained in two learning scenarios (on 14 or 28 patient datasets) was evaluated by two loss functions.

Results: Our model had an accuracy of over 90% for automatic segmentation of prostate and PCa nodules, as compared to manual segmentation. We have shown low complexity networks, UNet architecture with less than five layers, as feasible and to show good performance for automatic 3D MRI image segmentation. A larger training dataset could further improve the results.

Conclusion: Therefore, herein, we propose a less complex network, a slim 3D UNet with superior performance, being faster than the original five-layer UNet architecture.

Keywords: T2 MRI images; UNet architecture; convolutional neuronal network; fully automatic 3D image segmentation; prostate cancer characterization; slim 3D UNet.