Robust Resolution-Enhanced Prostate Segmentation in Magnetic Resonance and Ultrasound Images through Convolutional Neural Networks
| Autor: | Paula Pelechano Gómez, Juan Casanova Ramón-Borja, Victor Gonzalez-Perez, Oscar J. Pellicer-Valero, José D. Martín-Guerrero, María Barrios Benito, José Rubio-Briones, Isabel Martín García, M. J. Rupérez |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
MR prostate imaging US prostate imaging INGENIERIA MECANICA convolutional neural network lcsh:Technology Convolutional neural network 030218 nuclear medicine & medical imaging lcsh:Chemistry 03 medical and health sciences 0302 clinical medicine medicine General Materials Science lcsh:QH301-705.5 Instrumentation 030304 developmental biology Fluid Flow and Transfer Processes 0303 health sciences medicine.diagnostic_test lcsh:T business.industry Process Chemistry and Technology Convolutional Neural Networks Ultrasound Resolution (electron density) General Engineering Magnetic resonance imaging Pattern recognition Prostate Segmentation lcsh:QC1-999 Computer Science Applications Neural resolution enhancement lcsh:Biology (General) lcsh:QD1-999 lcsh:TA1-2040 Christian ministry Artificial intelligence lcsh:Engineering (General). Civil engineering (General) Magnetic Resonance and Ultrasound Images business lcsh:Physics Prostate segmentation |
| Zdroj: | Applied Sciences, Vol 11, Iss 844, p 844 (2021) Applied Sciences Volume 11 Issue 2 RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia instname |
| ISSN: | 2076-3417 |
| Popis: | [EN] Prostate segmentations are required for an ever-increasing number of medical applications, such as image-based lesion detection, fusion-guided biopsy and focal therapies. However, obtaining accurate segmentations is laborious, requires expertise and, even then, the inter-observer variability remains high. In this paper, a robust, accurate and generalizable model for Magnetic Resonance (MR) and three-dimensional (3D) Ultrasound (US) prostate image segmentation is proposed. It uses a densenet-resnet-based Convolutional Neural Network (CNN) combined with techniques such as deep supervision, checkpoint ensembling and Neural Resolution Enhancement. The MR prostate segmentation model was trained with five challenging and heterogeneous MR prostate datasets (and two US datasets), with segmentations from many different experts with varying segmentation criteria. The model achieves a consistently strong performance in all datasets independently (mean Dice Similarity Coefficient -DSC- above 0.91 for all datasets except for one), outperforming the inter-expert variability significantly in MR (mean DSC of 0.9099 vs. 0.8794). When evaluated on the publicly available Promise12 challenge dataset, it attains a similar performance to the best entries. In summary, the model has the potential of having a significant impact on current prostate procedures, undercutting, and even eliminating, the need of manual segmentations through improvements in terms of robustness, generalizability and output resolution This work has been partially supported by a doctoral grant of the Spanish Ministry of Innovation and Science, with reference FPU17/01993 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|