Yu-Chun Lin1,2, Chia-Hung Lin1, Hsin-Ying Lu1,2,3, Hsin-Ju Chiang1,2,3, Ho-Kai Wang1, Yu-Ting Huang1,4, Shu-Hang Ng1,2, Ji-Hong Hong2,4,5, Tzu-Chen Yen4,6, Chyong-Huey Lai2,7, Gigin Lin8,9,10,11. 1. Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 2. Imaging Core Laboratory, Institute for Radiological Research, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 3. Clinical Metabolomics Core Laboratory, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 4. Department of Obstetrics and Gynecology and Gynecologic Cancer Research Center, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 5. Department of Radiation Oncology, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 6. Department of Nuclear Medicine and Center for Advanced Molecular Imaging and Translation, Chang Gung Memorial Hospital and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 7. Clinical Trial Center, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. 8. Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. giginlin@cgmh.org.tw. 9. Imaging Core Laboratory, Institute for Radiological Research, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. giginlin@cgmh.org.tw. 10. Clinical Metabolomics Core Laboratory, Chang Gung Memorial Hospital at Linkou, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. giginlin@cgmh.org.tw. 11. Department of Obstetrics and Gynecology and Gynecologic Cancer Research Center, Chang Gung Memorial Hospital at Linkou and Chang Gung University, 5 Fuhsing St., Guishan, Taoyuan, Taiwan, 33382. giginlin@cgmh.org.tw.
Abstract
OBJECTIVE: To develop and evaluate the performance of U-Net for fully automated localization and segmentation of cervical tumors in magnetic resonance (MR) images and the robustness of extracting apparent diffusion coefficient (ADC) radiomics features. METHODS: This retrospective study involved analysis of MR images from 169 patients with cervical cancer stage IB-IVA captured; among them, diffusion-weighted (DW) images from 144 patients were used for training, and another 25 patients were recruited for testing. A U-Net convolutional network was developed to perform automated tumor segmentation. The manually delineated tumor region was used as the ground truth for comparison. Segmentation performance was assessed for various combinations of input sources for training. ADC radiomics were extracted and assessed using Pearson correlation. The reproducibility of the training was also assessed. RESULTS: Combining b0, b1000, and ADC images as a triple-channel input exhibited the highest learning efficacy in the training phase and had the highest accuracy in the testing dataset, with a dice coefficient of 0.82, sensitivity 0.89, and a positive predicted value 0.92. The first-order ADC radiomics parameters were significantly correlated between the manually contoured and fully automated segmentation methods (p < 0.05). Reproducibility between the first and second training iterations was high for the first-order radiomics parameters (intraclass correlation coefficient = 0.70-0.99). CONCLUSION: U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. First-order radiomics features extracted from whole tumor volume demonstrate the potential robustness for longitudinal monitoring of tumor responses in broad clinical settings. U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. KEY POINTS: • U-Net-based deep learning can perform accurate fully automated localization and segmentation of cervical cancer in diffusion-weighted MR images. • Combining b0, b1000, and apparent diffusion coefficient (ADC) images exhibited the highest accuracy in fully automated localization. • First-order radiomics feature extraction from whole tumor volume was robust and could thus potentially be used for longitudinal monitoring of treatment responses.
OBJECTIVE: To develop and evaluate the performance of U-Net for fully automated localization and segmentation of cervical tumors in magnetic resonance (MR) images and the robustness of extracting apparent diffusion coefficient (ADC) radiomics features. METHODS: This retrospective study involved analysis of MR images from 169 patients with cervical cancer stage IB-IVA captured; among them, diffusion-weighted (DW) images from 144 patients were used for training, and another 25 patients were recruited for testing. A U-Net convolutional network was developed to perform automated tumor segmentation. The manually delineated tumor region was used as the ground truth for comparison. Segmentation performance was assessed for various combinations of input sources for training. ADC radiomics were extracted and assessed using Pearson correlation. The reproducibility of the training was also assessed. RESULTS: Combining b0, b1000, and ADC images as a triple-channel input exhibited the highest learning efficacy in the training phase and had the highest accuracy in the testing dataset, with a dice coefficient of 0.82, sensitivity 0.89, and a positive predicted value 0.92. The first-order ADC radiomics parameters were significantly correlated between the manually contoured and fully automated segmentation methods (p < 0.05). Reproducibility between the first and second training iterations was high for the first-order radiomics parameters (intraclass correlation coefficient = 0.70-0.99). CONCLUSION:U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. First-order radiomics features extracted from whole tumor volume demonstrate the potential robustness for longitudinal monitoring of tumor responses in broad clinical settings. U-Net-based deep learning can perform accurate localization and segmentation of cervical cancer in DW MR images. KEY POINTS: • U-Net-based deep learning can perform accurate fully automated localization and segmentation of cervical cancer in diffusion-weighted MR images. • Combining b0, b1000, and apparent diffusion coefficient (ADC) images exhibited the highest accuracy in fully automated localization. • First-order radiomics feature extraction from whole tumor volume was robust and could thus potentially be used for longitudinal monitoring of treatment responses.
Authors: Jose Dolz; Xiaopan Xu; Jérôme Rony; Jing Yuan; Yang Liu; Eric Granger; Christian Desrosiers; Xi Zhang; Ismail Ben Ayed; Hongbing Lu Journal: Med Phys Date: 2018-11-08 Impact factor: 4.071
Authors: Akshay Goel; George Shih; Sadjad Riyahi; Sunil Jeph; Hreedi Dev; Rejoice Hu; Dominick Romano; Kurt Teichman; Jon D Blumenfeld; Irina Barash; Ines Chicos; Hanna Rennert; Martin R Prince Journal: Radiol Artif Intell Date: 2022-02-16