Joint Vertebrae Identification And Localization In Spinal Ct Images

CTSpine1K is a large-scale and comprehensive dataset for research in spinal image analysis. CTSpine1K is curated from the following four open sources, totalling 1,005 CT volumes (over 500,000 labeled slices and over 11,000 vertebrae) of diverse appearance variations. * COLONOG. This is a subset of the CT COLONOGRAPHY dataset related to a CT colonography trial12. * HNSCC-3DCT-RT. This sub-dataset contains three dimensional (3D) high-resolution fan-beam CT scans collected during pre-treatment, mid-treatment, and post-treatment using a Siemens 16-slice CT scanner with the standard clinical protocol for head-and-neck squamous cell carcinoma (HNSCC) patients13. These images are in DICOM format. * MSD T10. This sub-dataset comes from the 10th Medical Segmentation Decathlon14. To attain more slices containing the spine, we select the task03_liver dataset consisting of 201 cases. These images are in Neuroimaging Informatics Technology Initiative (NIfTI) format (https://nifti.nimh.nih.gov/nifti-1). * COVID-19. This sub-dataset consists of non-enhanced chest CTs from 632 patients with COVID-19 infections. The images were acquired at the point of care in an outbreak setting from patients with Reverse Transcription Polymerase Chain Reaction(RT-PCR) confirmation for the presence of SARS-CoV-215. We pick 40 scans with the images stored in NIfTI format.

Description: <a href="https://gts.ai/dataset-download/spinal-vertebrae-segmentation-dataset/" target="_blank">👉 Download the dataset here</a> This dataset is comprised of high-resolution MRI scans of the spine, showcasing various degenerative and dystrophic changes, including vertebral fractures, osteophytes, and disc protrusions. It’s an invaluable resource for the development of machine learning models aimed at classifying and segmenting spinal abnormalities. Download Dataset Key Features: Comprehensive Imaging: The dataset includes 5 studies, captured from different angles, covering a range of spinal anomalies such as a focal mass in the Th7 vertebral body, fluid masses, and spondyloarthrosis. Clinical Annotations: All images are thoroughly labeled by experienced medical professionals and come with corresponding PDF reports, allowing for accurate diagnosis and reference. Diverse Conditions: The scans highlight both common and complex conditions like osteophytes, fluid masses on the anterior contour of the vertebrae, and dorsal protrusions of the Th11-Th12 disc. These features make it highly applicable for detecting fractures and classifying various spine-related abnormalities. Applications in AI and Healthcare: Fracture Detection Models: This dataset is particularly useful for training deep learning algorithms to detect vertebral fractures, nerve compression, and other dystrophic changes. Segmentation and Classification: The detailed imaging of vertebrae, intervertebral discs, and surrounding tissues enables the segmentation of critical regions for AI-driven diagnostic tools. Training Data for Degenerative Disease Detection: With a focus on conditions like spondyloarthrosis, the dataset provides robust training material for detecting degenerative spinal diseases, enhancing the accuracy of automated systems. Use Case for AI Training: Researchers and healthcare professionals can leverage this dataset to develop machine learning models for improved diagnostics in spinal health, particularly focusing on dystrophic conditions and spine anomaly classification. This dataset is sourced from Kaggle.