SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging

Wang, Jie; Jin, Xin Yan; Zhang, Yi Fan; Yuan, Jie; Lin, Zi Tong; Chen, Ying

doi:10.3390/diagnostics16050710

Open AccessArticle

SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging

by

Jie Wang

¹,

Xin Yan Jin

¹,

Yi Fan Zhang

¹,

Jie Yuan

¹,

Zi Tong Lin

^2,*

and

Ying Chen

^1,*

¹

School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China

²

Department of Dentomaxillofacial Radiology, Nanjing Stomatological Hospital, Medical School of Nanjing University, Nanjing 210008, China

^*

Authors to whom correspondence should be addressed.

Diagnostics 2026, 16(5), 710; https://doi.org/10.3390/diagnostics16050710

Submission received: 12 January 2026 / Revised: 30 January 2026 / Accepted: 12 February 2026 / Published: 27 February 2026

(This article belongs to the Special Issue Application of Artificial Intelligence to Oral Diseases)

Download

Browse Figures

Versions Notes

Abstract

Background/Objectives: Medical image analysis of vertical root fractures (VRFs) is challenged by limited annotated data, class imbalance, and subtle inter-class differences. To address these issues, we propose an SBMN: a Similarity-Based Memory Network that integrates Category Memory with the Basic SBMN Module and a similarity-based classifier. Methods: An SBMN stores representative features for each class and leverages similarity-based gating to enhance feature discrimination. Experiments were conducted on a CBCT dataset of fractured and non-fractured teeth to evaluate performance. Results: The SBMN achieved up to 97.1% and 99.7% classification accuracy on automatically and manually segmented images, respectively. Memory manipulation experiments confirm the critical role of Category Memory in controlling classification outcomes. Conclusions: These results indicate that SBMNs offer an effective and interpretable approach for small-sample medical image classification and diagnosis.

Keywords: vertical root fracture; dental diagnostics; AI; CBCT; similarity-based memory network; category memory

Share and Cite

MDPI and ACS Style

Wang, J.; Jin, X.Y.; Zhang, Y.F.; Yuan, J.; Lin, Z.T.; Chen, Y. SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging. Diagnostics 2026, 16, 710. https://doi.org/10.3390/diagnostics16050710

AMA Style

Wang J, Jin XY, Zhang YF, Yuan J, Lin ZT, Chen Y. SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging. Diagnostics. 2026; 16(5):710. https://doi.org/10.3390/diagnostics16050710

Chicago/Turabian Style

Wang, Jie, Xin Yan Jin, Yi Fan Zhang, Jie Yuan, Zi Tong Lin, and Ying Chen. 2026. "SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging" Diagnostics 16, no. 5: 710. https://doi.org/10.3390/diagnostics16050710

APA Style

Wang, J., Jin, X. Y., Zhang, Y. F., Yuan, J., Lin, Z. T., & Chen, Y. (2026). SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging. Diagnostics, 16(5), 710. https://doi.org/10.3390/diagnostics16050710

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

SBMN: Similarity-Based Memory Network for the Diagnosis of Vertical Root Fracture in Dental Imaging

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI