You can try MIMIC III dataset available in physione. It has huge number of medical image.

https://healthitanalytics.com/news/nih-makes-largest-set-of-medical-imaging-data-available-to-public .

https://github.com/sfikas/medical-imaging-datasets .

https://www.kaggle.com/kmader/siim-medical-images .

https://www.cs.cmu.edu/~cil/v-images.html .

http://www.aylward.org/notes/open-access-medical-image-repositories

Dear Pascal

the following datasets released by National Institute of Health (NIH) can be helpful (more details are found here) https://www.nih.gov/news-events/news-releases/nih-clinical-center-releases-dataset-32000-ct-images.

The datasets are located in the following address:

https://nihcc.app.box.com/v/DeepLesion

You can try MIMIC III dataset available in physione. It has huge number of medical image.

https://healthitanalytics.com/news/nih-makes-largest-set-of-medical-imaging-data-available-to-public.

like a piece of cake; go to github.com and search for the related topics; you will find related data sets.

Have a look at Article An overview of deep learning in medical imaging focusing on MRI

https://openaccess.thecvf.com/content_cvpr_2018/papers/Balakrishnan_An_Unsupervised_Learning_CVPR_2018_paper.pdf

Well prepared datasets can be found at:

https://grand-challenge.org/challenges/

https://www.kaggle.com/datasets

in particular: https://www.kaggle.com/datasets?search=histopathology

You can try using MURA dataset:

https://stanfordmlgroup.github.io/competitions/mura/

MURA is a dataset of musculoskeletal radiographs consisting of 14,863 studies from 12,173 patients, with a total of 40,561 multi-view radiographic images. Each belongs to one of seven standard upper extremity radiographic study types: elbow, finger, forearm, hand, humerus, shoulder, and wrist. Each study was manually labeled as normal or abnormal by board-certified radiologists from the Stanford Hospital at the time of clinical radiographic interpretation in the diagnostic radiology environment between 2001 and 2012.

Here is another public datset for COVID-19:

https://github.com/mr7495/COVID-CTset

I suggest to visit the site web very famous for getting the new datasets

https://www.kaggle.com

https://www.kaggle.com/

https://github.com/beamandrew/medical-data

Have a look at

http://www.aylward.org/notes/open-access-medical-image-repositories

https://healthitanalytics.com/news/nih-makes-largest-set-of-medical-imaging-data-available-to-public

Dear;

You can read it in the following link:

https://openaccess.thecvf.com/content_cvpr_2018/papers/Balakrishnan_An_Unsupervised_Learning_CVPR_2018_paper.pdf

Regards