PURPOSE: Manual contouring of gross tumor volumes (GTV) is a crucial and time-consuming process in rectum cancer radiotherapy. This study aims to develop a simple deep learning-based autosegmentation algorithm to segment rectal tumors on T2-weighted MR images. MATERIAL AND METHODS: MRI scans (3T, T2-weighted) of 93 patients with locally advanced (cT3-4 and/or cN1-2) rectal cancer treated with neoadjuvant chemoradiotherapy followed by surgery were enrolled in this study. A 2D U-net similar network was established as a training model. The model was trained in two phases to increase efficiency. These phases were tumor recognition and tumor segmentation. An opening (erosion and dilation) process was implemented to smooth contours after segmentation. Data were randomly separated into training (90%) and validation (10%) datasets for a 10-folder cross-validation. Additionally, 20 patients were double contoured for performance evaluation. Four indices were calculated to evaluate the similarity of automated and manual segmentation, including Hausdorff distance (HD), average surface distance (ASD), Dice index (DSC), and Jaccard index (JSC). RESULTS: The DSC, JSC, HD, and ASD (mean ± SD) were 0.74 ± 0.14, 0.60 ± 0.16, 20.44 ± 13.35, and 3.25 ± 1.69 mm for validation dataset; and these indices were 0.71 ± 0.13, 0.57 ± 0.15, 14.91 ± 7.62, and 2.67 ± 1.46 mm between two human radiation oncologists, respectively. No significant difference has been observed between automated segmentation and manual segmentation considering DSC (P = 0.42), JSC (P = 0.35), HD (P = 0.079), and ASD (P = 0.16). However, significant difference was found for HD (P = 0.0027) without opening process. CONCLUSION: This study showed that a simple deep learning neural network can perform segmentation for rectum cancer based on MRI T2 images with results comparable to a human.
PURPOSE: Manual contouring of gross tumor volumes (GTV) is a crucial and time-consuming process in rectum cancer radiotherapy. This study aims to develop a simple deep learning-based autosegmentation algorithm to segment rectal tumors on T2-weighted MR images. MATERIAL AND METHODS: MRI scans (3T, T2-weighted) of 93 patients with locally advanced (cT3-4 and/or cN1-2) rectal cancer treated with neoadjuvant chemoradiotherapy followed by surgery were enrolled in this study. A 2D U-net similar network was established as a training model. The model was trained in two phases to increase efficiency. These phases were tumor recognition and tumor segmentation. An opening (erosion and dilation) process was implemented to smooth contours after segmentation. Data were randomly separated into training (90%) and validation (10%) datasets for a 10-folder cross-validation. Additionally, 20 patients were double contoured for performance evaluation. Four indices were calculated to evaluate the similarity of automated and manual segmentation, including Hausdorff distance (HD), average surface distance (ASD), Dice index (DSC), and Jaccard index (JSC). RESULTS: The DSC, JSC, HD, and ASD (mean ± SD) were 0.74 ± 0.14, 0.60 ± 0.16, 20.44 ± 13.35, and 3.25 ± 1.69 mm for validation dataset; and these indices were 0.71 ± 0.13, 0.57 ± 0.15, 14.91 ± 7.62, and 2.67 ± 1.46 mm between two human radiation oncologists, respectively. No significant difference has been observed between automated segmentation and manual segmentation considering DSC (P = 0.42), JSC (P = 0.35), HD (P = 0.079), and ASD (P = 0.16). However, significant difference was found for HD (P = 0.0027) without opening process. CONCLUSION: This study showed that a simple deep learning neural network can perform segmentation for rectum cancer based on MRI T2 images with results comparable to a human.