Back to Search
Start Over
Improving Interpretability of Leucocyte Classification with Multimodal Network.
- Source :
-
Studies in health technology and informatics [Stud Health Technol Inform] 2024 Aug 22; Vol. 316, pp. 1098-1102. - Publication Year :
- 2024
-
Abstract
- White blood cell classification plays a key role in the diagnosis of hematologic diseases. Models can perform classification either from images or based on morphological features. Image-based classification generally yields higher performance, but feature-based classification is more interpretable for clinicians. In this study, we employed a Multimodal neural network to classify white blood cells, utilizing a combination of images and morphological features. We compared this approach with image-only and feature-only training. While the highest performance was achieved with image-only training, the Multimodal model provided enhanced interpretability by the computation of SHAP values, and revealed crucial morphological features for biological characterization of the cells.
- Subjects :
- Humans
Leukocytes classification
Leukocytes cytology
Neural Networks, Computer
Subjects
Details
- Language :
- English
- ISSN :
- 1879-8365
- Volume :
- 316
- Database :
- MEDLINE
- Journal :
- Studies in health technology and informatics
- Publication Type :
- Academic Journal
- Accession number :
- 39176573
- Full Text :
- https://doi.org/10.3233/SHTI240602