Case study title

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nullam laoreet vestibulum efficitur. Fusce lacus augue, mollis id convallis eget, varius in est. Etiam feugiat risus eu felis ullamcorper feugiat. Morbi vel vulputate justo. Aliquam diam lectus, mollis ut auctor a, euismod non turpis. Quisque vulputate bibendum consequat. Nulla in mauris sapien.

A large database of 1000+ chest CT scans from a failed phase-III study was available to extract useful insights for future studies. The dataset included information about patient outcomes, such as treatment response and overall survival. The biopharma partner engaged in a value-based strategic collaboration with Quibim to design and create an AI model that could predict treatment response from pre-treatment CT scans.

Quibim performed an initial feasibility analysis, finding a high variability in the image quality across the 50+ sites involved in the study. The image quality of a few sites was not enough to qualify. All the images were transformed into a standard image quality by GAN-based image harmonization algorithms implemented by Quibim.

After the image quality harmonization of the entire dataset, Quibim developed and validated an AI algorithm based on radiomics, deep features, and deep learning techniques, predicting whether the patient will respond to immunotherapy in 80% of cases.