Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation

• URL: http://arxiv.org/abs/2605.04201v1
• Date: Tue, 05 May 2026 18:42:15 GMT
• Title: Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation
• Abstract summary: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation.<n>The proposed method integrates a novel tooth-specific topological loss into quantization-aware training.<n> Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models.
• Score: 1.9336815376402718
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.

Related papers

• Practical Lossless Volumetric Medical Image Compression via Tri-plane Context Tree Learning [44.4636106590074]
  Traditional compression methods are often limited in efficiency due to rigid, handcrafted models.<n>Deep neural network (DNN)-based compression methods, while effective, demand substantial computational resources.<n>We propose a novel tri-plane context tree (TCT)-based method for lossless volumetric medical image compression.
  arXiv  Detail & Related papers  (2026-08-14T03:01:44Z)
• Efficient Neural Architectures for Real-Time ECG Interpretation on Limited Hardware [0.0]
  We present an empirical study of convolutional neural network (CNN) architectures, exploring tradeoffs between diagnostic accuracy and computational efficiency.<n>We propose three lightweight models: ParallelCNN, ParallelCNNew, and SimpleNet.<n>Our experiments span three publicly available 12-lead ECG datasets from Germany, China, and the United States.
  arXiv  Detail & Related papers  (2026-05-11T01:02:28Z)
• CAHAL: Clinically Applicable resolution enHAncement for Low-resolution MRI scans [29.281962308908195]
  Large-scale automated morphometric analysis of brain MRI is limited by the thick-slice.<n>Existing generative super-resolution methods produce visually compelling isotropic volumes but often introduce anatomical hallucinations.<n>We propose CAHAL (Clinically Applicable resolution enHAncement for Low-resolution MRI scans), a hallucination-robust, physics-informed resolution enhancement framework.
  arXiv  Detail & Related papers  (2026-04-20T19:45:11Z)
• BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Classification [1.3909285316906435]
  BEAT-Net is a Biomimetic ECG Analysis with Tokenization framework.<n>It decomposes cardiac physiology through specialized encoders that extract local beat morphology.<n>It exhibits exceptional data efficiency, recovering fully supervised performance using only 30 to 35 percent of annotated data.
  arXiv  Detail & Related papers  (2026-01-12T08:37:47Z)
• Enhanced SegNet with Integrated Grad-CAM for Interpretable Retinal Layer Segmentation in OCT Images [0.0]
  This study proposes an improved SegNet-based deep learning framework for automated and interpretable retinal layer segmentation.<n> Architectural innovations, including modified pooling strategies, enhance feature extraction from noisy OCT images.<n>Grad-CAM visualizations highlighted anatomically relevant regions, aligning segmentation with clinical biomarkers.
  arXiv  Detail & Related papers  (2025-09-09T14:31:51Z)
• A Multi-Resolution Benchmark Framework for Spatial Reasoning Assessment in Neural Networks [40.69150418258213]
  This paper presents preliminary results in the definition of a comprehensive benchmark framework designed to evaluate spatial reasoning capabilities in neural networks.<n>The framework is currently being used to study the capabilities of nnU-Net.
  arXiv  Detail & Related papers  (2025-08-18T09:04:13Z)
• An Efficient Approach for Muscle Segmentation and 3D Reconstruction Using Keypoint Tracking in MRI Scan [8.089892147270529]
  This study proposes a training-free segmentation approach based on keypoint tracking, which integrates keypoint selection with Lucas-Kanade optical flow.<n>The proposed method achieves a mean Dice similarity coefficient (DSC) ranging from 0.6 to 0.7, depending on the keypoint selection strategy.
  arXiv  Detail & Related papers  (2025-07-11T15:39:28Z)
• Skelite: Compact Neural Networks for Efficient Iterative Skeletonization [38.6452617345504]
  Skeletonization extracts thin representations from images that compactly encode their geometry and topology.<n>We propose a novel framework for training iterative skeletonization algorithms with a learnable component.<n>Our method demonstrates a 100 times speedup over topology-constrained algorithms.
  arXiv  Detail & Related papers  (2025-03-10T14:27:25Z)
• Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression [44.35542987414442]
  Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs)<n>Applying these techniques jointly via co-optimization has the potential to produce smaller, high-quality models.<n>We present the framework GETA, which automatically and efficiently performs joint structured pruning and quantization-aware training on any DNNs.
  arXiv  Detail & Related papers  (2025-02-23T16:28:18Z)
• Leveraging Frequency Domain Learning in 3D Vessel Segmentation [50.54833091336862]
  In this study, we leverage Fourier domain learning as a substitute for multi-scale convolutional kernels in 3D hierarchical segmentation models. We show that our novel network achieves remarkable dice performance (84.37% on ASACA500 and 80.32% on ImageCAS) in tubular vessel segmentation tasks.
  arXiv  Detail & Related papers  (2024-01-11T19:07:58Z)
• Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network [51.44506007844284]
  We propose a shape-aware relation network for accurate and real-time landmark detection in endoscopic submucosal dissection surgery. We first devise an algorithm to automatically generate relation keypoint heatmaps, which intuitively represent the prior knowledge of spatial relations among landmarks. We then develop two complementary regularization schemes to progressively incorporate the prior knowledge into the training process.
  arXiv  Detail & Related papers  (2021-11-08T07:57:30Z)
• An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation [53.425900196763756]
  We propose a segmentation refinement method based on uncertainty analysis and graph convolutional networks. We employ the uncertainty levels of the convolutional network in a particular input volume to formulate a semi-supervised graph learning problem. We show that our method outperforms the state-of-the-art CRF refinement method by improving the dice score by 1% for the pancreas and 2% for spleen.
  arXiv  Detail & Related papers  (2020-12-06T18:55:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.