Abstract
The manual delineation of region of interest (RoI) in 3D magnetic resonance imaging (MRI) of the prostate is time-consuming and subjective. Correct identification of prostate tissue is helpful to define a precise RoI to be used in CAD systems in clinical practice during diagnostic imaging, radiotherapy and monitoring the progress of disease. Conditional GAN (cGAN), cycleGAN and U-Net models and their performances were studied for the detection and segmentation of prostate tissue in 3D multi-parametric MRI scans. These models were trained and evaluated on MRI data from 40 patients with biopsy-proven prostate cancer. Due to the limited amount of available training data, three augmentation schemes were proposed to artificially increase the training samples. These models were tested on a clinical dataset annotated for this study and on a public dataset (PROMISE12). The cGAN model outperformed the U-Net and cycleGAN predictions owing to the inclusion of paired image supervision. Based on our quantitative results, cGAN gained a Dice score of 0.78 and 0.75 on the private and the PROMISE12 public datasets, respectively.
Highlights
Prostate cancer is the most common type of cancer in men
Our qualitative and quantitative results show that the Conditional Generative Adversarial Networks (GANs) (cGAN) outperformed the other two models (U-Net and cycleGAN) which implies that the proposed detection and segmentation model has the potential to be utilised as an alternative to double reading by clinicians [24]
Based on our evaluation metrics, we conclude that the best segmentation performance in all modalities is achieved by the cGAN model, followed by the U-Net model
Summary
In 2017, there were nearly 48,500 new cases and 11,700 prostate cancer deaths in the UK [1]. Bray et al [2] reported 1,276,106 new global cases in 2018, and 358,989 prostate cancer deaths worldwide. Delineation of prostate tissue is based on manual localisation of the prostate from multi-parametric MRI. Due to the inter-reader variability, this subjective identification of prostate tissue is limited in reproducibility, time consuming and often requires clinical expertise. Accurate segmentation of the prostate could enable radiologists to more quickly demarcate the prostate gland. It can improve the determination of clinical markers such as prostate-specific antigen (PSA) density, which depends on MRI prostate volume estimation [3].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
