Fan Liang1, Pengjiang Qian2, Kuan-Hao Su3, Atallah Baydoun4, Asha Leisser5, Steven Van Hedent6, Jung-Wen Kuo7, Kaifa Zhao8, Parag Parikh9, Yonggang Lu10, Bryan J Traughber11, Raymond F Muzic12. 1. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA; Tianjin Key Laboratory of Information Sensing & Intelligent Control, Tianjin University of Technology and Education, Tianjin, China. Electronic address: bachelormd10@163.com. 2. School of Digital Media, Jiangnan University, Wuxi, Jiangsu, China. Electronic address: qianpjiang@jiangnan.edu.cn. 3. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA. Electronic address: kuan-hao.su@case.edu. 4. Department of Internal Medicine, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Department of Internal Medicine, Louis Stokes VA Medical Center, Cleveland, OH, USA; Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA. Electronic address: atallah.baydoun@case.edu. 5. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA; Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria. Electronic address: asha.leisser@meduniwien.ac.at. 6. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA; Department of Radiology, UZ Brussel (VUB), Brussels, Belgium. Electronic address: steven.vanhedent@case.edu. 7. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA. Electronic address: jung-wen.kuo@case.edu. 8. School of Digital Media, Jiangnan University, Wuxi, Jiangsu, China. Electronic address: zhaokaifa@qq.com. 9. Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA. Electronic address: pparikh@radonc.wustl.edu. 10. Department of Radiation Oncology, Washington University School of Medicine, St. Louis, MO, USA. Electronic address: yonggang.lu@wustl.edu. 11. Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA; Department of Radiation Oncology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Department of Radiation Oncology, University Hospitals Seidman Cancer Center, Cleveland, OH, USA. Electronic address: bryan.traughber@case.edu. 12. Department of Radiology, Case Western Reserve University School of Medicine, Cleveland, OH, USA; Case Center for Imaging Research, University Hospitals Case Medical Center, Case Western Reserve University, Cleveland, OH, USA; Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA; Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA. Electronic address: raymond.muzic@case.edu.
Abstract
BACKGROUND: Manual contouring remains the most laborious task in radiation therapy planning and is a major barrier to implementing routine Magnetic Resonance Imaging (MRI) Guided Adaptive Radiation Therapy (MR-ART). To address this, we propose a new artificial intelligence-based, auto-contouring method for abdominal MR-ART modeled after human brain cognition for manual contouring. METHODS/MATERIALS: Our algorithm is based on two types of information flow, i.e. top-down and bottom-up. Top-down information is derived from simulation MR images. It grossly delineates the object based on its high-level information class by transferring the initial planning contours onto daily images. Bottom-up information is derived from pixel data by a supervised, self-adaptive, active learning based support vector machine. It uses low-level pixel features, such as intensity and location, to distinguish each target boundary from the background. The final result is obtained by fusing top-down and bottom-up outputs in a unified framework through artificial intelligence fusion. For evaluation, we used a dataset of four patients with locally advanced pancreatic cancer treated with MR-ART using a clinical system (MRIdian, Viewray, Oakwood Village, OH, USA). Each set included the simulation MRI and onboard T1 MRI corresponding to a randomly selected treatment session. Each MRI had 144 axial slices of 266 × 266 pixels. Using the Dice Similarity Index (DSI) and the Hausdorff Distance Index (HDI), we compared the manual and automated contours for the liver, left and right kidneys, and the spinal cord. RESULTS: The average auto-segmentation time was two minutes per set. Visually, the automatic and manual contours were similar. Fused results achieved better accuracy than either the bottom-up or top-down method alone. The DSI values were above 0.86. The spinal canal contours yielded a low HDI value. CONCLUSION: With a DSI significantly higher than the usually reported 0.7, our novel algorithm yields a high segmentation accuracy. To our knowledge, this is the first fully automated contouring approach using T1 MRI images for adaptive radiotherapy.
BACKGROUND: Manual contouring remains the most laborious task in radiation therapy planning and is a major barrier to implementing routine Magnetic Resonance Imaging (MRI) Guided Adaptive Radiation Therapy (MR-ART). To address this, we propose a new artificial intelligence-based, auto-contouring method for abdominal MR-ART modeled after human brain cognition for manual contouring. METHODS/MATERIALS: Our algorithm is based on two types of information flow, i.e. top-down and bottom-up. Top-down information is derived from simulation MR images. It grossly delineates the object based on its high-level information class by transferring the initial planning contours onto daily images. Bottom-up information is derived from pixel data by a supervised, self-adaptive, active learning based support vector machine. It uses low-level pixel features, such as intensity and location, to distinguish each target boundary from the background. The final result is obtained by fusing top-down and bottom-up outputs in a unified framework through artificial intelligence fusion. For evaluation, we used a dataset of four patients with locally advanced pancreatic cancer treated with MR-ART using a clinical system (MRIdian, Viewray, Oakwood Village, OH, USA). Each set included the simulation MRI and onboard T1 MRI corresponding to a randomly selected treatment session. Each MRI had 144 axial slices of 266 × 266 pixels. Using the Dice Similarity Index (DSI) and the Hausdorff Distance Index (HDI), we compared the manual and automated contours for the liver, left and right kidneys, and the spinal cord. RESULTS: The average auto-segmentation time was two minutes per set. Visually, the automatic and manual contours were similar. Fused results achieved better accuracy than either the bottom-up or top-down method alone. The DSI values were above 0.86. The spinal canal contours yielded a low HDI value. CONCLUSION: With a DSI significantly higher than the usually reported 0.7, our novel algorithm yields a high segmentation accuracy. To our knowledge, this is the first fully automated contouring approach using T1 MRI images for adaptive radiotherapy.
Authors: Pengjiang Qian; Yangyang Chen; Jung-Wen Kuo; Yu-Dong Zhang; Yizhang Jiang; Kaifa Zhao; Rose Al Helo; Harry Friel; Atallah Baydoun; Feifei Zhou; Jin Uk Heo; Norbert Avril; Karin Herrmann; Rodney Ellis; Bryan Traughber; Robert S Jones; Shitong Wang; Kuan-Hao Su; Raymond F Muzic Journal: IEEE Trans Med Imaging Date: 2019-08-16 Impact factor: 10.048
Authors: Alba Magallon-Baro; Maaike T W Milder; Patrick V Granton; Wilhelm den Toom; Joost J Nuyttens; Mischa S Hoogeman Journal: Front Oncol Date: 2022-06-08 Impact factor: 5.738
Authors: Lixun Xian; Guangjun Li; Qing Xiao; Zhibin Li; Xiangbin Zhang; Li Chen; Zhenyao Hu; Sen Bai Journal: Technol Cancer Res Treat Date: 2021 Jan-Dec
Authors: José S Enriquez; Yan Chu; Shivanand Pudakalakatti; Kang Lin Hsieh; Duncan Salmon; Prasanta Dutta; Niki Zacharias Millward; Eugene Lurie; Steven Millward; Florencia McAllister; Anirban Maitra; Subrata Sen; Ann Killary; Jian Zhang; Xiaoqian Jiang; Pratip K Bhattacharya; Shayan Shams Journal: JMIR Med Inform Date: 2021-06-17