A convolutional neural network algorithm for automatic segmentation of head and neck organs at risk using deep lifelong learning
| Autor: | Sue S. Yom, Jason Chan, Atchar Sudhyadhom, Samuel Haaf, Madeleine Bogdanov, Mariah Reddick, Nayha Dixit, Susan Wu, V. Kearney, Timothy D. Solberg, Josephine Chen |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Organs at Risk
Risk Computer science Squamous Cell Carcinoma of Head and Neck Multi-task learning General Medicine Convolutional neural network 030218 nuclear medicine & medical imaging Set (abstract data type) 03 medical and health sciences Automation 0302 clinical medicine Deep Learning 030220 oncology & carcinogenesis Test set Image Processing Computer-Assisted Humans Transfer of learning Tomography X-Ray Computed Algorithm Radiotherapy Image-Guided |
| Zdroj: | Medical physics. 46(5) |
| ISSN: | 2473-4209 |
| Popis: | Purpose This study suggests a lifelong learning-based convolutional neural network (LL-CNN) algorithm as a superior alternative to single-task learning approaches for automatic segmentation of head and neck (OARs) organs at risk. Methods and materials Lifelong learning-based convolutional neural network was trained on twelve head and neck OARs simultaneously using a multitask learning framework. Once the weights of the shared network were established, the final multitask convolutional layer was replaced by a single-task convolutional layer. The single-task transfer learning network was trained on each OAR separately with early stoppage. The accuracy of LL-CNN was assessed based on Dice score and root-mean-square error (RMSE) compared to manually delineated contours set as the gold standard. LL-CNN was compared with 2D-UNet, 3D-UNet, a single-task CNN (ST-CNN), and a pure multitask CNN (MT-CNN). Training, validation, and testing followed Kaggle competition rules, where 160 patients were used for training, 20 were used for internal validation, and 20 in a separate test set were used to report final prediction accuracies. Results On average contours generated with LL-CNN had higher Dice coefficients and lower RMSE than 2D-UNet, 3D-Unet, ST- CNN, and MT-CNN. LL-CNN required ~72 hrs to train using a distributed learning framework on 2 Nvidia 1080Ti graphics processing units. LL-CNN required 20 s to predict all 12 OARs, which was approximately as fast as the fastest alternative methods with the exception of MT-CNN. Conclusions This study demonstrated that for head and neck organs at risk, LL-CNN achieves a prediction accuracy superior to all alternative algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text