Check out the guide about loading medical data guide first.
In order to have a taste all the features of Sethealth, you probably need some medical data to play with.
Sethealth can load
png and even raw buffers.
Sethealth distributes some public URLs to download datasets of Computed Tomographies (CT), radiographies (CR) and magnetic resonance images (MRI).
The DeepLesion dataset contains 32,120 axial computed tomography (CT) slices from 10,594 CT scans (studies) of 4,427 unique patients. There are 1–3 lesions in each image with accompanying bounding boxes and size measurements, adding up to 32,735 lesions altogether.
NIH compiled the dataset of scans from more than 30,000 patients, including many with advanced lung disease. Patients at the NIH Clinical Center, the nation’s largest hospital devoted entirely to clinical research, are partners in research and voluntarily enroll to participate in clinical trials. With patient privacy being paramount, the dataset was rigorously screened to remove all personally identifiable information before release.
The LIDC/IDRI data set is publicly available, including the annotations of nodules by four radiologists. The LUNA16 challenge is therefore a completely open challenge. We have tracks for complete systems for nodule detection, and for systems that use a list of locations of possible nodules. We provide this list to also allow teams to participate with an algorithm that only determines the likelihood for a given location in a CT scan to contain a pulmonary nodule.
Four research institutions provided large volumes of de-identified CT studies that were assembled to create the challenge dataset: Stanford University, Thomas Jefferson University, Unity Health Toronto and Universidade Federal de São Paulo (UNIFESP), The American Society of Neuroradiology (ASNR) organized a cadre of more than 60 volunteers to label over 25,000 exams for the challenge dataset. ASNR is the world’s leading organization for the future of neuroradiology representing more than 5,300 radiologists, researchers, interventionalists, and imaging scientists. MD.ai provided tooling and support for the data annotation process.
These datasets are exclusively available for research and teaching. You are not authorized to redistribute or sell them, or use them for commercial purposes.
The scans in the CQ500 dataset were generously provided by Centre for Advanced Research in Imaging, Neurosciences and Genomics(CARING), New Delhi, IN. The reads were done by three radiologists with an experience of 8, 12 and 20 years in cranial CT interpretation respectively.
We are always looking for new datasets, please feel free to submit a PR adding any dataset that we are missing. We also offer free storage and bandwidth for non-profit projects, reach us at firstname.lastname@example.org if we need help publishing a dataset.