Abstract
Spinal cord segmentation is the process of identifying and delineating the boundaries of the spinal cord in medical images such as magnetic resonance imaging (MRI) or computed tomography (CT) scans. This process is important for many medical applications, including the diagnosis, treatment planning, and monitoring of spinal cord injuries and diseases. The segmentation process involves using image processing techniques to identify the spinal cord in the medical image and differentiate it from other structures, such as the vertebrae, cerebrospinal fluid, and tumors. There are several approaches to spinal cord segmentation, including manual segmentation by a trained expert, semi-automated segmentation using software tools that require some user input, and fully automated segmentation using deep learning algorithms. Researchers have proposed a wide range of system models for segmentation and tumor classification in spinal cord scans, but the majority of these models are designed for a specific segment of the spine. As a result, their performance is limited when applied to the entire lead, limiting their deployment scalability. This paper proposes a novel augmented model for spinal cord segmentation and tumor classification using deep nets to overcome this limitation. The model initially segments all five spinal cord regions and stores them as separate datasets. These datasets are manually tagged with cancer status and stage based on observations from multiple radiologist experts. Multiple Mask Regional Convolutional Neural Networks (MRCNNs) were trained on various datasets for region segmentation. The results of these segmentations were combined using a combination of VGGNet 19, YoLo V2, ResNet 101, and GoogLeNet models. These models were selected via performance validation on each segment. It was observed that VGGNet-19 was capable of classifying the thoracic and cervical regions, while YoLo V2 was able to efficiently classify the lumbar region, ResNet 101 exhibited better accuracy for sacral-region classification, and GoogLeNet was able to classify the coccygeal region with high performance accuracy. Due to use of specialized CNN models for different spinal cord segments, the proposed model was able to achieve a 14.5% better segmentation efficiency, 98.9% tumor classification accuracy, and a 15.6% higher speed performance when averaged over the entire dataset and compared with various state-of-the art models. This performance was observed to be better, due to which it can be used for various clinical deployments. Moreover, this performance was observed to be consistent across multiple tumor types and spinal cord regions, which makes the model highly scalable for a wide variety of spinal cord tumor classification scenarios.