# Impact of Labeling Inaccuracy and Image Noise on Tooth Segmentation in Panoramic Radiographs using Federated, Centralized and Local Learning

arXiv: https://arxiv.org/abs/2509.06553 · HTML: https://mlsanity.com/paper/2509.06553/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [The Future of Digital Health with Federated Learning](https://mlsanity.com/paper/2003.08119/) (2020)
- [Federated Optimization:Distributed Optimization Beyond the Datacenter](https://mlsanity.com/paper/1511.03575/) (2015)
- [FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2207.09653/) (2022)
- [Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks](https://mlsanity.com/paper/2209.15595/) (2022)
- [FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation](https://mlsanity.com/paper/2205.01840/) (2022)
- [FedA3I: Annotation Quality-Aware Aggregation for Federated Medical Image Segmentation against Heterogeneous Annotation Noise](https://mlsanity.com/paper/2312.12838/) (2023)
- [FedIA: Federated Medical Image Segmentation with Heterogeneous Annotation Completeness](https://mlsanity.com/paper/2407.02280/) (2024)
- [Supercharging Federated Learning with Flower and NVIDIA FLARE](https://mlsanity.com/paper/2407.00031/) (2024)

## Built on by (most cited first, 3 of 3)

- [DinoDental: Benchmarking DINOv3 as a Unified Vision Encoder for Dental Image Analysis](https://mlsanity.com/paper/2603.28297/) (2026)
- [Deep Learning-based Assessment of the Relation Between the Third Molar and Mandibular Canal on Panoramic Radiographs using Local, Centralized, and Federated Learning](https://mlsanity.com/paper/2603.11850/) (2026)
- [Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation](https://mlsanity.com/paper/2605.04201/) (2026)

## Abstract (arXiv)

Objectives: Federated learning (FL) may mitigate privacy constraints, heterogeneous data quality, and inconsistent labeling in dental diagnostic AI. We compared FL with centralized (CL) and local learning (LL) for tooth segmentation in panoramic radiographs across multiple data corruption scenarios. Methods: An Attention U-Net was trained on 2066 radiographs from six institutions across four settings: baseline (unaltered data); label manipulation (dilated/missing annotations); image-quality manipulation (additive Gaussian noise); and exclusion of a faulty client with corrupted data. FL was implemented via the Flower AI framework. Per-client training- and validation-loss trajectories were monitored for anomaly detection and a set of metrics (Dice, IoU, HD, HD95 and ASSD) was evaluated on a hold-out test set. From these metrics significance results were reported through Wilcoxon signed-rank test. CL and LL served as comparators. Results: Baseline: FL achieved a median Dice of 0.94889 (ASSD: 1.33229), slightly better than CL at 0.94706 (ASSD: 1.37074) and LL at 0.93557-0.94026 (ASSD: 1.51910-1.69777). Label manipulation: FL maintained the best median Dice score at 0.94884 (ASSD: 1.46487) versus CL's 0.94183 (ASSD: 1.75738) and LL's 0.93003-0.94026 (ASSD: 1.51910-2.11462). Image noise: FL led with Dice at 0.94853 (ASSD: 1.31088); CL scored 0.94787 (ASSD: 1.36131); LL ranged from 0.93179-0.94026 (ASSD: 1.51910-1.77350). Faulty-client exclusion: FL reached Dice at 0.94790 (ASSD: 1.33113) better than CL's 0.94550 (ASSD: 1.39318). Loss-curve monitoring reliably flagged the corrupted site. Conclusions: FL matches or exceeds CL and outperforms LL across corruption scenarios while preserving privacy. Per-client loss trajectories provide an effective anomaly-detection mechanism and support FL as a practical, privacy-preserving approach for scalable clinical AI deployment.