AI model identifies certain breast tumour stages likely to progress to invasive cancer

MIT News reports that research supported in part by the MIT Jameel Clinic, leads a team from MIT and ETH Zurich to develop an AI model for identifying different stages of ductal carcinoma in situ (DCIS), a form of breast cancer that accounts for 25% of all breast cancer diagnoses, and can progress into an aggressive form of cancer, but whose stages are difficult for physicians to determine. The research identified the importance of not only the state, but also the arrangement of cells, which can be examined via inexpensive tissue images, enabling the the team to build an extensive dataset to train and test the model with promising results.

Caroline Uhler, a principal investigator at MIT Jameel Clinic, tells MIT News: "We took the first step in understanding that we should be looking at the spatial organisation of cells when diagnosing DCIS, and now we have developed a technique that is scalable. From here, we really need a prospective study. Working with a hospital and getting this all the way to the clinic will be an important step forward.”