Fully automated bladder tumor segmentation from T2 MRI images using 3D U-Net algorithm

Abstract

IntroductionBladder magnetic resonance imaging (MRI) has been recently integrated in the diagnosis pathway of bladder cancer. However, automatic recognition of suspicious lesions is still challenging. Thus, development of a solution for proper delimitation of the tumor and its separation from the healthy tissue is of primordial importance. As a solution to this unmet medical need, we aimed to develop an artificial intelligence-based decision support system, which automatically segments the bladder wall and the tumor as well as any suspect area from the 3D MRI images.MaterialsWe retrospectively assessed all patients diagnosed with bladder cancer, who underwent MRI at our department (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 bladder wall and all lesions. First, the performance of our fully automated end-to-end segmentation model based on a 3D U-Net architecture (by considering various depths of 4, 5 or 6 blocks) trained in two data augmentation scenarios (on 5 and 10 augmentation datasets per original data, respectively) was tested. Second, two learning setups were analyzed by training the segmentation algorithm with 7 and 14 MRI original volumes, respectively.ResultsWe obtained a Dice-based performance over 0.878 for automatic segmentation of bladder wall and tumors, as compared to manual segmentation. A larger training dataset using 10 augmentations for 7 patients could further improve the results of the U-Net-5 model (0.902 Dice coefficient at image level). This model performed best in terms of automated segmentation of bladder, as compared to U-Net-4 and U-Net-6. However, in this case increased time for learning was needed as compared to U-Net-4. We observed that an extended dataset for training led to significantly improved segmentation of the bladder wall, but not of the tumor.ConclusionWe developed an intelligent system for bladder tumors automated diagnostic, that uses a deep learning model to segment both the bladder wall and the tumor. As a conclusion, low complexity networks, with less than five-layers U-Net architecture are feasible and show good performance for automatic 3D MRI image segmentation in patients with bladder tumors.

Multiparametric MRI in Era of Artificial Intelligence for Bladder Cancer Therapies

“…The autosegmentation of bladder walls and tumors using mpMRI is challenging due to bladder shape variations; weak boundaries; diverse intensity and inhomogeneity in urine; and variability across the population, particularly in tumor appearance [122]. A few studies from Table 4 used various DL-based autosegmentation and denoising methods for T 2 w MR images [122][123][124][125][126][127]. Dolz et al used a deep CNN model with progressive dilated convolutional modules to segment multiple regions in T 2 w images of 60 bladder cancer patients [123].…”

Radiomics Prediction of Muscle Invasion in Bladder Cancer Using Semi-Automatic Lesion Segmentation of MRI Compared with Manual Segmentation

“…However, the accurate automatic segmentation of medical images remains a challenge, which can be attributed to the ambiguous, low-contrast, and heterogeneous boundary of the segmented area [24]. Several BCa radiomics segmentation methods have been shown to perform well [25][26][27][28]. The shape prior constrained particle swarm optimization (SPCPSO) model was proposed for automatic segmentation of the inner and outer boundaries of the bladder wall with good performance [25].…”

“…This method only required a small database size to achieve a preferable segmentation performance compared with the conventional U-Net model. Our study utilized a twodimensional U-Net network and a combination of the focal loss function and the soft Dice loss function, instead of a three-dimensional structure and categorical cross-entropy function in modelling, as in the work conducted by Coroama, D. M. et al [28].…”