Abdominal, multi-organ, auto-contouring method for online adaptive magnetic resonance guided radiotherapy: An intelligent, multi-level fusion approach

• Published in: Artificial intelligence in medicine Vol. 90; pp. 34 - 41
• Main Authors: Liang, Fan, Qian, Pengjiang, Su, Kuan-Hao, Baydoun, Atallah, Leisser, Asha, Van Hedent, Steven, Kuo, Jung-Wen, Zhao, Kaifa, Parikh, Parag, Lu, Yonggang, Traughber, Bryan J., Muzic, Raymond F.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.08.2018
• Subjects: Adaptive radiotherapy; Auto-Contouring; Humans; Image Interpretation, Computer-Assisted - methods; Image-guided; Machine learning; Magnetic Resonance Imaging - methods; Multimodal Imaging; Pancreatic Neoplasms - diagnostic imaging; Pancreatic Neoplasms - pathology; Pancreatic Neoplasms - radiotherapy; Radiotherapy; Radiotherapy Planning, Computer-Assisted - methods; Radiotherapy, Image-Guided - methods; Support Vector Machine; Tomography, X-Ray Computed; Workflow; Auto-Contouring; Image-guided; Radiotherapy; Machine learning; Adaptive radiotherapy
• ISSN: 0933-3657; 1873-2860; 1873-2860
• DOI: 10.1016/j.artmed.2018.07.001

•MR-ART consists of daily modification of the radiation therapy plan.•Manual contouring is laborious, subject to variability and inconvenient for MR-ART.•An auto-contouring method based on the human processing model is proposed.•The algorithm couples multi-level top-down and bottom-up information.•To our knowledge, this is the first automated contouring approach for T1 MR-ART. 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. 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. 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. 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.