AI-Powered Platform to Advance Lung Cancer Diagnosis and Treatment

A team of researchers at the University of Cologne’s Faculty of Medicine and University Hospital Cologne have carried out a study that unveils a cutting-edge AI-powered pathology platform that can help doctors accurately diagnose and evaluate lung cancer in patients. The AI tool provides entirely automated and in-depth analysis of benign and cancerous tissues for faster and more personalized.

The researchers developed a deep-learning-based multi-class tissue segmentation platform that automatically analyzes digitized lung tissue samples. It screens for cancer and provides cellular details of the region. 

Notably, the AI model was trained and validated on a large dataset from six institutions, totaling 4,097 annotated slides from 1,527 patients. 

According to study senior author Yuri Tolkach, “The algorithm can differentiate between 11 tissue types, ranging from tumor tissue, tumor-associated classes (e.g., tumor stroma, necrotic debris, mucin), to cartilage and lymphatic tissue. It showed very high pixel-wise accuracy for segmentation of different classes with an average Dice Score of 0.893.”

The researchers used the University of Cologne’s high-performance computing cluster equipped with 12 NVIDIA V100 GPUs, four NVIDIA A100 GPUs on the pathology institute’s AI server, and PC stations equipped with NVIDIA GeForce RTX 3090 and NVIDIA RTX 4090 GPUs. 

The setup facilitates quick analysis of entire slide images. Evidently, it takes about 1 to 5 minutes to analyze each whole-slide image ranging from 200 to 2000 Mb. 

Further, the study states that the AI tool can also reveal detailed characteristics of tumor and immune cells in the cellular environment, revealing how the cancer is interacting within the body.