Category: DataS

Machine Learning Reduces Uncertainty in Breast Cancer Diagnoses

Researchers at Michigan Tech have developed a machine learning model for detecting breast cancer from histopathology images — tissues and cells examined under microscope. The model can classify benign and malignant tumors from these images — and it can also evaluate the uncertainty in its predictions.

In their paper recently published in the journal IEEE Transactions on Medical Imaging, graduate students Ponkrshnan Thiagarajan and Pushkar Khairnar and Susanta Ghosh (ME-EM) outline their novel probabilistic machine learning model, which outperforms similar models.

Read the full story at

Thomas Oommen is PI on $188K DoT Project

Thomas Oommen (GMES/MTTI/ICC-DataS) is the principal investigator (PI) on a project that has received a $188,433 research and development contract from the U.S. Department of Transportation, Federal Railroad Administration.

The project is titled “An Integrated Automated Decision Support System for Ground Hazard Risk Mitigation for Railway using Remote Sensing and Traditional Condition Monitoring Data.”

Pasi Lautala and Melanie Kueber Watkins (CEE/MTTI) and Colin Brooks (MTRI/MTTI) are co-PIs on this potential three-year project.