Browse » Medical

Top Medical Datasets

Medical datasets, computer vision models, and APIs can be used to automatically identify anomalies, estimate the size of areas of interest, visualize issues, medical imaging, health monitoring, disease detection, diagnosis assistance, research, and more.

More information: https://blog.roboflow.com/computer-vision-in-healthcare/

Case study: https://blog.roboflow.com/cancer-research-computer-vision/

This dataset was originally created by Adrian Rodriguez. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/tfg-2nmge/axial-dataset.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

cavity
4

This dataset was originally created by NhiNguyen, DƯƠNG ĐỨC CƯỜNG. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/duong-duc-cuong/cavity-n3ioq.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

pills
7

This dataset was originally created by Mohamed Attia. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/mohamed-attia-e2mor/pill-detection-llp4r.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

drugs
1
phages
2

This dataset was originally created by Danish. To see the current project, which may have been updated since this version, please go here.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Anonymous. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/new-workspace-fditd/stomata02.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Joao Paulo Martins. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/graduao/sistema-para-analise-de-ovos-de-parasitas-em-amostra-de-agua-e-sangue.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

Here are a few use cases for this project:

  1. Elderly Care Monitoring: The Fall Detection model can be integrated into smart home systems or camera-assisted monitoring services to promptly identify when elderly individuals fall, enabling caregivers or family members to respond quickly to potential injuries or medical emergencies.

  2. Workplace Safety: In high-risk work environments like construction sites or factories, the Fall Detection model can be implemented to monitor employees and detect any accidents, alerting supervisors or emergency medical services immediately to provide assistance.

  3. Public Safety: Security cameras in public spaces such as parks, streets, or shopping centers can utilize the Fall Detection model to detect falls and possible criminal activities or accidents, allowing law enforcement or emergency services to respond in a timely manner.

  4. Assisted Living Facilities: The Fall Detection model can help improve the safety of residents in assisted living facilities, nursing homes, or rehabilitation centers by monitoring common areas for falls and automatically notifying staff members when incidents occur.

  5. Sports Injury Detection: The Fall Detection model can be used in gyms or sports centers to monitor athletes during training sessions, helping to quickly identify falls or injuries and enabling coaches or medical staff to intervene if necessary.

This dataset was originally created by Abhishek Dada. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/liver-t5yvf/liver-diseases.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Yuanyu Anpei. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/yuanyuanpei7/5-8w.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Yousef Ghanem. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/yousef-ghanem-jzj4y/brain-tumor-detection-fpf1f.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

cells
3

This dataset was originally created by Miguel Fernández Cruchaga. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/new-workspace-86q1t/t03-proyecto-celula-dataset-ampliado.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Anonymous. To see the current project, which may have been updated since this version, please go here.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Xingwei He. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/xinweihe/circle-3train.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Thuan Phat Nguyen. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/objectdetection-9lu9z/detectron2-acl.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Jason Zhang, Caden Li. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/science-research/science-research-2022:-bone-fracture-detection.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Simeon Marlokov. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/publictestsite/xray-rheumatology-images-public.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

This dataset was originally created by Terada Shoma. To see the current project, which may have been updated since this version, please go here: https://universe.roboflow.com/terada-shoma/gram-positive-bacteria.

This dataset is part of RF100, an Intel-sponsored initiative to create a new object detection benchmark for model generalizability.

Access the RF100 Github repo: https://github.com/roboflow-ai/roboflow-100-benchmark

Hands
1

Here are a few use cases for this project:

  1. Medical Imaging Analysis: Radiologists could use this model to detect and identify specific Hand-joint abnormalities in women, aiding diagnosis of rheumatoid arthritis, osteoarthritis, fractures, or other hand joint disorders.

  2. Physical Therapy Assistance: Therapists could utilize this model to monitor the progress of patients' hand and joint rehabilitation. By assessing the condition of the joints over time, therapists can tailor their rehabilitation plans based on results.

  3. Sports Medicine: Coaches and sports therapists could use this technology to help athletes understand their hand and finger joint health, prevent injuries or help heal after an injury has occurred.

  4. Bionic Prosthesis Development: Researchers and developers creating prosthetic limbs could use the model to better understand the functionalities of human hand joints, aiding in the development of more realistic and functional artificial hands.

  5. Educational Purpose: The model could be used in medical schools for teaching anatomy and radiology, allowing students to identify and understand the various complexities of female hand joints.

DASH-DIET-101


About DASH-DIET-101

DASH-DIET-101 is created by Bhavya Bansal, Nikunj Bansal, Dhruv Sehgal, Yogita Gehani and Ayush Rai with a goal of building a creating a model to detect food items that reduce Hypertension. It contains more than 16900 images of 101 popular food items.

Data collection

We used search engines (Google and Bing) to crawl and look for suitable images using JavaScript queries for each food item from the list created. The images with incomplete RGB channels were removed, and the images collected from different search engines were compiled. When downloading images from search engines, many images were irrelevant to the purpose, especially the ones with a lot of text in them. We deployed the EAST text detector to segregate such images. Finally, a comprehensive manual inspection was conducted to ensure the relevancy of images in the dataset.

Fair use

This dataset contains some copyrighted material whose use has not been specifically authorized by the copyright owners. In an effort to advance scientific research, we make this material available for academic research. If you wish to use copyrighted material in our dataset for purposes of your own that go beyond non-commercial research and academic purposes, you must obtain permission directly from the copyright owner. We believe this constitutes a 'fair use' of any such copyrighted material as provided for in section 107 of the US Copyright Law. In accordance with Title 17 U.S.C. Section 107, the material on this site is distributed without profit to those who have expressed a prior interest in receiving the included information for non-commercial research and educational purposes.(adapted from Christopher Thomas).

Citation

If you find our dataset useful, please cite us as:

@article{bansal2023dashdiet101,
                              title={DASH-DIET-101: Detecting Food Items that lowers Blood Pressure Using Deep Learning-Based Computer Vision},
                              author={Bansal, Bhavya and Bansal, Nikunj and Sehgal, Dhruv and Gehani, Yogita and Rai, Ayush},
                              journal={---},
                              pages={1--36},
                              year={2023},
                              publisher={Springer}
                            }
                            

Overview
This is the largest Gastrointestinal dataset generously provided by Simula Research Laboratory in Norway

You can read their research paper here in Nature

In total, the dataset contains 10,662 labeled images stored using the JPEG format. The images can be found in the images folder. The classes, which each of the images belong to, correspond to the folder they are stored in (e.g., the ’polyp’ folder contains all polyp images, the ’barretts’ folder contains all images of Barrett’s esophagus, etc.). Each class-folder is located in a subfolder describing the type of finding, which again is located in a folder describing wheter it is a lower GI or upper GI finding. The number of images per class are not balanced, which is a general challenge in the medical field due to the fact that some findings occur more often than others. This adds an additional challenge for researchers, since methods applied to the data should also be able to learn from a small amount of training data. The labeled images represent 23 different classes of findings.

The data is collected during real gastro- and colonoscopy examinations at a Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists.

Use Cases

"Artificial intelligence is currently a hot topic in medicine. The fact that medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel to perform the cumbersome and tedious labeling of the data, leads to technical limitations. In this respect, we share the Hyper-Kvasir dataset, which is the largest image and video dataset from the gastrointestinal tract available today."

"We have used the labeled data to research the classification and segmentation of GI findings using both computer vision and ML approaches to potentially be used in live and post-analysis of patient examinations. Areas of potential utilization are analysis, classification, segmentation, and retrieval of images and videos with particular findings or particular properties from the computer science area. The labeled data can also be used for teaching and training in medical education. Having expert gastroenterologists providing the ground truths over various findings, HyperKvasir provides a unique and diverse learning set for future clinicians. Moreover, the unlabeled data is well suited for semi-supervised and unsupervised methods, and, if even more ground truth data is needed, the users of the data can use their own local medical experts to provide the needed labels. Finally, the videos can in addition be used to simulate live endoscopies feeding the video into the system like it is captured directly from the endoscopes enable developers to do image classification."

Borgli, H., Thambawita, V., Smedsrud, P.H. et al. HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci Data 7, 283 (2020). https://doi.org/10.1038/s41597-020-00622-y

Using this Dataset

Hyper-Kvasir is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source. This means that in all documents and papers that use or refer to the Hyper-Kvasir dataset or report experimental results based on the dataset, a reference to the related article needs to be added: PREPRINT: https://osf.io/mkzcq/. Additionally, one should provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

About Roboflow

Roboflow makes managing, preprocessing, augmenting, and versioning datasets for computer vision seamless.

Developers reduce 50% of their boilerplate code when using Roboflow's workflow, automate annotation quality assurance, save training time, and increase model reproducibility.

  • [Y] Import 1079 images (full set) from Google Drive
  • [ ] Label right and left eye as one class and name as "eyes"
  • [ ] Remove the images with no anatomy and artifacts
  • [ ] Show Sam
  • [ ] Invite Shuhadah to inter-rate
  • [ ] Export labelling and measure IoU