Japanese researchers developed an AI system using light scattering spectra to improve cancer cell identification in cytology.
Key Details
- 1The machine learning system leverages white-light scattering spectra of cells, captured by dark-field microscopy.
- 2Achieved approximately 91% accuracy for distinguishing mesothelioma cancer cells from similar non-cancerous cells in patient-based validation.
- 3Showed potential to differentiate other cancer types, such as gastric, urothelial, and several thoracic cancers.
- 4Method detects differences at submicron scale, beyond conventional microscopic resolution or standard image analysis.
- 5The system uses principal component analysis and support vector machine for classification.
- 6Study published August 2026 in Scientific Reports by NAIST and collaborators.
Why It Matters
This proof-of-concept demonstrates a new dimension of cytological diagnostic information using AI, potentially improving cancer screening accuracy, especially in ambiguous cases. It may offer radiology and pathology labs a valuable adjunct to traditional visual assessment and image-based AI tools.
Source
EurekAlert
Related News
•EurekAlert
UVA's $4M NIH Grant Backs AI to Optimize Cardiac MRI Therapies
UVA secures $4 million NIH funding to develop GenStrain, an AI model using MRI data to personalize cardiac pacing therapies.
•EurekAlert
Machine Learning Models Predict Cancer Risk with Routine Health Data
Researchers developed machine learning models using routinely collected health data to predict individual risk for 20 common cancers, outperforming traditional methods for several cancer types.
•EurekAlert
Duke Receives $25M to Lead National Trustworthy AI Hub for Dementia and Aging
Duke University has launched a $25 million national center to make AI for aging and dementia clinically robust and trustworthy.