Fujitsu  announced the development of explainable AI technology that automatically draws on data in multiple formats, including text, images, and numerical data, to create knowledge graphs that will help users to more easily draw meaning from large-scale data sets with high accuracy for areas including medicine.

The company's latest innovations were put to the test in the classification of lung cancer types and the prediction of survival rates for breast cancer patients. These trials have confirmed the potential of Fujitsu’s AI to improve diagnostic accuracy by identifying critical visual cues for lung cancer and enhancing survival prediction models for breast cancer.

Fujitsu's new AI technology excels in analyzing images with differing visual depictions, making it possible to train algorithms for highly accurate evaluations of pathological images, even with limited training data. This technological breakthrough is poised to revolutionize the way AI supports medical diagnostics by allowing for more precise assessments without the reliance on extensive data sets.

The potential applications of Fujitsu’s technology extend beyond medical diagnostics. The company plans to utilize these advancements across various sectors, promising enhancements in data center failure prediction and fraud detection. As part of its future plans, Fujitsu will make these technologies available on the Fujitsu Research Portal by the end of fiscal 2024, providing a platform for broader access and testing of these innovative solutions.

This progress is part of a broader collaboration with the Barcelona Supercomputing Center in Spain, focusing on personalized medicine and other cutting-edge research areas. The partnership aims to refine these AI technologies further and expand their application globally, reinforcing Fujitsu's commitment to pioneering the integration of multimodal data for advanced problem-solving in healthcare and beyond.