Microsoft software to "replace" radiologists - recognizes organs and structures in medical images

Microsoft Research, Mar 8, 2011: InnerEye focuses on the analysis of patient scans using machine learning techniques for automatic detection and segmentation of healthy anatomy as well as anomalies:

Antonio Criminisi is the the researcher shown in the video above.

The InnerEye research project focuses on the automatic analysis of patients' scans by using machine learning techniques for:

- Automatic detection and segmentation of healthy anatomy, as well as anomalies
- Semantic navigation and visualization

Microsoft Research methods aim to combine medical expertise and modern machine learning theory in the design of tools for computer-aided diagnosis, personalized medicine, and natural user interfaces for surgical intervention.

The InnerEye project has a host of famous collaborators, including Johns Hopkins Medical Institute, The University of Oxford, Cornell Medical School, Massachusetts General Hospital, the University of Washington, Kings College London, and Cambridge University Hospitals.

High-Performance Cancer Screening: See how a high--performance, 3-D rendering engine can be transformed into a real-world, life-saving medical application:


Comments from Twitter:

@hrana (Hisham Rana, MD): No thanks. RT @DrVes: Microsoft software to "replace" radiologists - recognizes organs and structures in medical images

@doctorwhitecoat (Vamsi Balakrishnan): Definitely not a replacement... but cool tool in development.

@DrVes: Well, of course it's not a replacement... :) Just as "Watson" supercomputer won't replace PCPs/specialists...

@doctorwhitecoat (Vamsi Balakrishnan): Watson can't replace 3rd year Med students either; it can't do scutwork...:)

@ILoveOrthopedix (Orthopaedic Resident): MS Radiology! very interesting - the ECG machines recognise patterns & give diagnoses, but all the doctors make their own diagnosis.

@drcrosby (Bradley Dick): Reminiscent of Robin Cook's "Brain"?! (

No comments:

Post a Comment

Blog Widget by LinkWithin