Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  Applied Sciences  /  Vol: 10 Par: 3 (2020)  /  Artículo
ARTÍCULO
TITULO

Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT

Jean Léger    
Eliott Brion    
Paul Desbordes    
Christophe De Vleeschouwer    
John A. Lee and Benoit Macq    

Resumen

For prostate cancer patients, large organ deformations occurring between radiotherapy treatment sessions create uncertainty about the doses delivered to the tumor and surrounding healthy organs. Segmenting those regions on cone beam CT (CBCT) scans acquired on treatment day would reduce such uncertainties. In this work, a 3D U-net deep-learning architecture was trained to segment bladder, rectum, and prostate on CBCT scans. Due to the scarcity of contoured CBCT scans, the training set was augmented with CT scans already contoured in the current clinical workflow. Our network was then tested on 63 CBCT scans. The Dice similarity coefficient (DSC) increased significantly with the number of CBCT and CT scans in the training set, reaching 0.874" role="presentation">0.8740.874 0.874 ± 0.096" role="presentation">0.0960.096 0.096 , 0.814" role="presentation">0.8140.814 0.814 ± 0.055" role="presentation">0.0550.055 0.055 , and 0.758" role="presentation">0.7580.758 0.758 ± 0.101" role="presentation">0.1010.101 0.101 for bladder, rectum, and prostate, respectively. This was about 10% better than conventional approaches based on deformable image registration between planning CT and treatment CBCT scans, except for prostate. Interestingly, adding 74 CT scans to the CBCT training set allowed maintaining high DSCs, while halving the number of CBCT scans. Hence, our work showed that although CBCT scans included artifacts, cross-domain augmentation of the training set was effective and could rely on large datasets available for planning CT scans.

 Artículos similares

       
 
Jianyuan Li, Xiaochun Lu, Ping Zhang and Qingquan Li    
The timely identification and detection of surface cracks in concrete dams, an important public safety infrastructure, is of great significance in predicting engineering hazards and ensuring dam safety. Due to their low efficiency and accuracy, manual de... ver más
Revista: Water

 
Vangelis Malamas, George Palaiologos, Panayiotis Kotzanikolaou, Mike Burmester and Dimitris Glynos    
Although there are several access control systems in the literature for flexible policy management in multi-authority and multi-domain environments, achieving interoperability and scalability, without relying on strong trust assumptions, is still an open... ver más
Revista: Applied Sciences

 
Isabel Rio-Torto, Ana Teresa Campaniço, Pedro Pinho, Vitor Filipe and Luís F. Teixeira    
The still prevalent use of paper conformity lists in the automotive industry has a serious negative impact on the performance of quality control inspectors. We propose instead a hybrid quality inspection system, where we combine automated detection with ... ver más
Revista: Applied Sciences

 
Jaekyung Kim, Jungwoo Huh, Ingu Park, Junhyeong Bak, Donggeon Kim and Sanghoon Lee    
Deep learning-based object detection is one of the most popular research topics. However, in cases where large-scale datasets are unavailable, the training of detection models remains challenging due to the data-driven characteristics of deep learning. S... ver más
Revista: Applied Sciences

 
Yunliang Li, Zhiqiang Du, Yanfang Fu and Liangxin Liu    
Information service platforms or management information systems of various institutions or sectors of enterprises are gradually interconnected to form a multi-domain environment. A multi-domain environment is convenient for managers to supervise and mana... ver más
Revista: Applied Sciences