Paper
Deep Learning-based Assessment of the Relation Between the Third Molar and Mandibular Canal on Panoramic Radiographs using Local, Centralized, and Federated Learning
Authors
Johan Andreas Balle Rubak, Sara Haghighat, Sanyam Jain, Mostafa Aldesoki, Akhilanand Chaurasia, Sarah Sadat Ehsani, Faezeh Dehghan Ghanatkaman, Ahmad Badruddin Ghazali, Julien Issa, Basel Khalil, Rishi Ramani, Ruben Pauwels
Abstract
Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar-canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while federated learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy = 0.782), FL showed intermediate performance (AUC 0.757; accuracy = 0.703), and LL generalized poorly across clients (AUC range = 0.619-0.734; mean = 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL.
Metadata
Related papers
Fractal universe and quantum gravity made simple
Fabio Briscese, Gianluca Calcagni • 2026-03-25
POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan
Marta Moscati, Muhammad Saad Saeed, Marina Zanoni, Mubashir Noman, Rohan Kuma... • 2026-03-25
LensWalk: Agentic Video Understanding by Planning How You See in Videos
Keliang Li, Yansong Li, Hongze Shen, Mengdi Liu, Hong Chang, Shiguang Shan • 2026-03-25
Orientation Reconstruction of Proteins using Coulomb Explosions
Tomas André, Alfredo Bellisario, Nicusor Timneanu, Carl Caleman • 2026-03-25
The role of spatial context and multitask learning in the detection of organic and conventional farming systems based on Sentinel-2 time series
Jan Hemmerling, Marcel Schwieder, Philippe Rufin, Leon-Friedrich Thomas, Mire... • 2026-03-25
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.11850v1</id>\n <title>Deep Learning-based Assessment of the Relation Between the Third Molar and Mandibular Canal on Panoramic Radiographs using Local, Centralized, and Federated Learning</title>\n <updated>2026-03-12T12:17:17Z</updated>\n <link href='https://arxiv.org/abs/2603.11850v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.11850v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar-canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while federated learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy = 0.782), FL showed intermediate performance (AUC 0.757; accuracy = 0.703), and LL generalized poorly across clients (AUC range = 0.619-0.734; mean = 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='eess.IV'/>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-12T12:17:17Z</published>\n <arxiv:primary_category term='eess.IV'/>\n <author>\n <name>Johan Andreas Balle Rubak</name>\n </author>\n <author>\n <name>Sara Haghighat</name>\n </author>\n <author>\n <name>Sanyam Jain</name>\n </author>\n <author>\n <name>Mostafa Aldesoki</name>\n </author>\n <author>\n <name>Akhilanand Chaurasia</name>\n </author>\n <author>\n <name>Sarah Sadat Ehsani</name>\n </author>\n <author>\n <name>Faezeh Dehghan Ghanatkaman</name>\n </author>\n <author>\n <name>Ahmad Badruddin Ghazali</name>\n </author>\n <author>\n <name>Julien Issa</name>\n </author>\n <author>\n <name>Basel Khalil</name>\n </author>\n <author>\n <name>Rishi Ramani</name>\n </author>\n <author>\n <name>Ruben Pauwels</name>\n </author>\n </entry>"
}