Comprehensive benchmarking of deep learning architectures for multiclass histopathological classification of oral epithelial lesions
Achla Bharti, Nikita Kashyap, Mala Kamboj, Kamaldeep Joshi, Sahil Hooda, Deepika Mishra, Harpreet Singh, Debnath Pal · 2026
Read Comprehensive benchmarking of deep learning architectures for multiclass histopathological classification of oral epithelial lesions by Achla Bharti, Nikita Kashyap, Mala Kamboj, Kamaldeep Joshi, Sahil Hooda, Deepika Mishra, Harpreet Singh, Debnath Pal (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13266174.txt.
Description
Achla Bharti and colleagues benchmark deep learning models for classifying mouth tissue images, published in 2026. Separating normal lining, precancerous change, and cancer by eye is slow and variable. A curated set held more than two thousand images across the three classes. Seven model architectures trained under standard conditions.
Augmentation expanded training data to handle class imbalance. One model, EfficientNet-B0, reached the highest validation accuracy and best test scores. Three other models performed nearly as well. Errors clustered at transition zones between normal, precancer, and early cancer. The authors support automated classification as a diagnostic aid.
Catalog record
| CREATOR | Achla Bharti, Nikita Kashyap, Mala Kamboj, Kamaldeep Joshi, Sahil Hooda, Deepika Mishra, Harpreet Singh, Debnath Pal |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 68 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |