3 minute read
Rama Asuri - Homework 6 AI in Health and Medicine
AI in health and medicine is achieving expert level performance. In this paper, we examine two different examples where AI was able to detect cancer and explore current status of AI in cancer diagnosis 1.
In the first example, we will cover Cervical cancer. Cervical cancer kills more women in India than in any other country. It is a preventable disease which kills 67000 women in India. Screening and detection can help reduce the number of deaths but the challenge is the testing process which takes enormous time. SRL diagnostics partnered with Microsoft to co create an AI Network of Pathology to reduce the burden of cytopathologists and histopathologists. Cytopathologists at SRL Diagnostics manually marked their observations. These observations were used as training data for Cervical Cancer Image Detection. But there was a different challenge, the way cytopathologists examine different elements are very unique even though they all have come to the same conclusion. This was because of these experts may approach a problem from a different direction. The AI model able to differentiate between normal and abnormal smear slides with accuracy 1.
The second example is about detecting lung cancer. The survival rate is really high if lung cancer is detected during the early stages. but the problem is that is difficult to do it manually when there millions of 3D X-rays. Reviewing scans is done by highly trained specialist and majority of the reviews results in no detection. Moreover this is also monotonous work which might lead to errors by the reviewers. The LUNA Grand Challenge is an open dataset with high-quality labels of patient CT scans. The gLUNA Grand Challenge encourages improvements in nodule detection by making it easy for teams to compete for high positions on the leader board. A project team can test the efficacy of their detection methods against standardized criteria 3.
Emerging AI Applications in Oncology
Improving Cancer Screening and Diagnosis
The MRI-guided biopsy was developed by National Cancer Institute (NCI) researchers works without a need for clinics because of the AI tool 4.
Aiding the Genomic Characterization of Tumors
Identifying mutations using noninvasive techniques is a particularly challenging problem when it comes to brain tumors 4. NCI and other partners concluded that AI could help identify gene mutations in innovative ways.
Accelerating Drug Discovery
Using AI, scientists were able to target mutations in the KRAS gene, one of the most frequently mutated oncogenes in tumors 4.
Improving Cancer Surveillance
AI will help predicting treatment response, recurrence and survival based on the detection from the images.