This paper introduces a novel approach to automate the segmentation of gastrointestinal (GI) tract regions in magnetic resonance imaging (MRI) scans for radiotherapy planning. The proposed model integrates advanced deep learning architectures, including Inception-V4 for initial classification, UNet++ with a VGG19 encoder for 2.5D data processing, and Edge UNet for grayscale data segmentation. The model employs meticulous data preprocessing techniques, such as spatial and intensity augmentation, to enhance adaptability and robustness. The overall architecture consists of three distinct pathways: Inception-V4 for initial classification, 2.5D U-Net++ for detailed segmentation, and Edge U-Net for edge-aware segmentation. The model's performance is evaluated using the Dice Coefficient and 3D Hausdorff Distance, with Edge UNet showing superior performance in grayscale image segmentation and UNet++ with VGG19 excelling in 2.5D images. The experimental results demonstrate the effectiveness and versatility of the proposed model, offering a valuable tool for clinicians to streamline radiotherapy planning and improve patient care.This paper introduces a novel approach to automate the segmentation of gastrointestinal (GI) tract regions in magnetic resonance imaging (MRI) scans for radiotherapy planning. The proposed model integrates advanced deep learning architectures, including Inception-V4 for initial classification, UNet++ with a VGG19 encoder for 2.5D data processing, and Edge UNet for grayscale data segmentation. The model employs meticulous data preprocessing techniques, such as spatial and intensity augmentation, to enhance adaptability and robustness. The overall architecture consists of three distinct pathways: Inception-V4 for initial classification, 2.5D U-Net++ for detailed segmentation, and Edge U-Net for edge-aware segmentation. The model's performance is evaluated using the Dice Coefficient and 3D Hausdorff Distance, with Edge UNet showing superior performance in grayscale image segmentation and UNet++ with VGG19 excelling in 2.5D images. The experimental results demonstrate the effectiveness and versatility of the proposed model, offering a valuable tool for clinicians to streamline radiotherapy planning and improve patient care.