A collaborative research team led by POSTECH Professor Chulhong Kim and Professor Chan Kwon Jung of Seoul St. Mary’s Hospital, Catholic University of Korea, has developed an artificial intelligence (AI) system to analyse the label-free photoacoustic histological images of human liver cancer tissues.
Its research was recently published in Light: Science and Applications, an international journal of optics and photonics.
Photoacoustic histology (PAH) technology generates images by detecting sound (ultrasound) signals produced by biomolecules when illuminated with light (laser), thus eliminating the need for staining and labelling. However, PAH was initially unfamiliar to pathologists, complicating interpretation and diagnosis, and resulting in relatively low accuracy. In this study, the researchers at Pohang University of Science and Technology (POSTECH), integrated PAH with cutting-edge deep learning models capable of virtual staining, segmentation, and classification of human tissue images.
Initially, the ‘virtual staining’ step transforms black-and-white, unlabelled images - containing cell nuclei and cytoplasm - into images that mimic stained samples. This step is designed to produce images similar to actual stained samples while preserving tissue structures and uses explainable deep learning methods to increase the reliability of the virtual staining results.
Next, during the ‘segmentation’ phase, the unlabelled image and the virtual staining data are used to segment features of the sample such as cell area, cell count, and intercellular distances. Finally, in the ‘classification’ phase, the model uses the unlabelled image, virtual staining image, and segmentation data to classify whether the tissues are cancerous or not.
The researchers applied their deep learning model to the PAH images of human liver cancer tissues. The AI model, which integrates the three stages, achieved a high accuracy of 98% in distinguishing between cancerous and non-cancerous liver cells. Notably, the model demonstrated a 100% sensitivity when evaluated by three pathologists, underscoring its potential for clinical application.
- Yoon C, Park E, Misra S, et al. Deep learning-based virtual staining, segmentation, and classification in label-free photoacoustic histology of human specimens. Light Sci Appl. 2024;13(1):226. Published 2024 Sep 2. doi:10.1038/s41377-024-01554-7