What the study found
A multislide, weakly supervised deep learning model performed best for classifying three fibro-osseous lesions of the jaw: fibrous dysplasia, cemento-ossifying fibroma, and cemento-osseous dysplasia. The model’s performance was reported as higher than that of experienced oral pathologists when only histology slides were considered.
Why the authors say this matters
The authors say distinguishing these lesions is important because they have different prognoses and affect clinical management. The study suggests the model could serve as a supportive tool alongside clinical, radiologic, and molecular data.
What the researchers tested
The researchers developed and validated a deep learning model using 1,218 hematoxylin and eosin whole-slide images from 338 cases across 3 institutions. They compared 4 training strategies using a ResNet-50 backbone with loss functions and multiple-instance learning, including weakly and fully supervised models on single or multiple slides.
What worked and what didn't
The weakly supervised multislide model had the best test-set performance, with an area under the curve of 0.86 and accuracy of 0.71. Other models performed less well, and probability heat maps showed the model identified histomorphologic patterns relevant to distinguishing the three lesion types.
What to keep in mind
The test cohort was limited in sample size and geographic diversity. The authors note that further expansion and more diverse cohorts are needed to better support generalizability.
Key points
- The best-performing model was a weakly supervised multislide deep learning approach.
- The model classified fibrous dysplasia, cemento-ossifying fibroma, and cemento-osseous dysplasia from histology slides.
- Reported test performance was an area under the curve of 0.86 and accuracy of 0.71.
- The authors say the model outperformed experienced oral pathologists when only slides were used.
- The test cohort was limited in sample size and geographic diversity.
Disclosure
- Research title:
- Deep learning improved classification of jaw fibro-osseous lesions
- Authors:
- A.B. Zhang, P.Y. Li, J. Xue, J H Zhang, Z. You, S H Ge, Z Xu, Z.P. Sun, D.X. Chang, L.S. Sun, T.J. Li
- Institutions:
- Shandong University, Chinese Academy of Medical Sciences & Peking Union Medical College, National Clinical Research, Beijing Jiaotong University, Shandong Provincial Hospital, Shandong First Medical University, Peking University
- Publication date:
- 2026-02-24
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.