Skin Cancer Recognition
This scenario focuses on the collaboration between a machine learning expert and a clinician to build a skin lesion classifier. The machine learning expert, trains models with Python and logs the training to a Marcelle data store. She develops two dashboards for monitoring the training and assessing the performance of various models. She can share particular models with a clinician who can test the classifier with his own images, correcting the predictions if necessary.
For testing, example data from the HAM10000 dataset can be downloaded from Harvard Dataverse.
Privacy Notice: Cookies are necessary to run the demo. In this demo, all training sets are public and synchronized across clients. The data you provide we will uploaded to a server and available publicly. Dataset browsers provide controls for deleting instances and classes.
ML Expert's Dashboard
medical-ml-dashboard
ML Expert's Comparison Dashboard
medical-ml-comparison
Clinician's Interface
medical-clinician