Deep learning algorithms for bladder cancer segmentation on multi-parametric MRI

Gumus, Kazim Z., Nicolas, Julien, Gopireddy, Dheeraj R., Dolz, Jose, Jazayeri, Seyed Behzad et Bandyk, Mark. 2024. « Deep learning algorithms for bladder cancer segmentation on multi-parametric MRI ». Cancers, vol. 16, nº 13.

Prévisualisation

PDF Dolz-J-2024-29086.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (2MB) | Prévisualisation

Résumé

Background: Bladder cancer (BC) segmentation on MRI images is the first step to determining the presence of muscular invasion. This study aimed to assess the tumor segmentation performance of three deep learning (DL) models on multi-parametric MRI (mp-MRI) images. Methods: We studied 53 patients with bladder cancer. Bladder tumors were segmented on each slice of T2-weighted (T2WI), diffusion-weighted imaging/apparent diffusion coefficient (DWI/ADC), and T1-weighted contrast-enhanced (T1WI) images acquired at a 3Tesla MRI scanner. We trained Unet, MAnet, and PSPnet using three loss functions: cross-entropy (CE), dice similarity coefficient loss (DSC), and focal loss (FL). We evaluated the model performances using DSC, Hausdorff distance (HD), and expected calibration error (ECE). Results: The MAnet algorithm with the CE+DSC loss function gave the highest DSC values on the ADC, T2WI, and T1WI images. PSPnet with CE+DSC obtained the smallest HDs on the ADC, T2WI, and T1WI images. The segmentation accuracy overall was better on the ADC and T1WI than on the T2WI. The ECEs were the smallest for PSPnet with FL on the ADC images, while they were the smallest for MAnet with CE+DSC on the T2WI and T1WI. Conclusions: Compared to Unet, MAnet and PSPnet with a hybrid CE+DSC loss function displayed better performances in BC segmentation depending on the choice of the evaluation metric.

Type de document:	Article publié dans une revue, révisé par les pairs
Professeur:	Professeur Dolz, José
Affiliation:	Génie logiciel et des technologies de l'information
Date de dépôt:	05 août 2024 14:16
Dernière modification:	08 août 2024 15:48
URI:	https://espace2.etsmtl.ca/id/eprint/29086

Actions (Authentification requise)

Dernière vérification avant le dépôt