Related papers: Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis

Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis

URL: http://arxiv.org/abs/2606.08364v1
Date: Sat, 06 Jun 2026 22:42:17 GMT
Title: Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis
Abstract summary: Temporomandibular joint osteoarthritis (TMJ OA) is a prevalent degenerative condition whose osseous changes are often subtle on cone-beam CT (CBCT)<n>We study how well the DINO family of self-supervised vision transformers transfers to CBCT.<n>We propose a simple slice-based pipeline using Vision Transformer (ViT) backbones.
Score: 0.0
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
Abstract: Temporomandibular joint osteoarthritis (TMJ OA) is a prevalent degenerative condition whose osseous changes are often subtle on cone-beam CT (CBCT), making automated detection challenging. We study how well the DINO family of self-supervised vision transformers -- DINOv1, DINOv2, DINOv2+reg, and RAD-DINO (a radiology-pretrained variant) -- transfers to CBCT, asking how much backbone adaptation is needed and of what kind. We propose a simple slice-based pipeline using Vision Transformer (ViT) backbones: axial CBCT slices are encoded per-slice by a frozen or partially adapted ViT and aggregated via attention-based multiple instance learning (MIL) for patient-level binary OA/Normal classification. Through systematic ablation across unfreezing strategies and aggregation designs on a multi-source CBCT dataset, we find that partial unfreezing of the final two transformer blocks is the decisive factor, improving AUC from 0.671 (fully frozen DINOv2) to 0.902. This outperforms DINOv1 (0.867), DINOv2+reg (0.774), and a supervised ImageNet ViT-B/16 baseline (0.843). Our results provide practical guidance for adapting DINO-family foundation models in low-data medical imaging settings, showing that adaptation strategy is a stronger driver of performance than backbone choice alone.

Related papers

Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention [46.03321798937855]
We show that the standard Generalized Dice Loss (GDL) is unstable under domain shift.<n>We propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8%.
arXiv Detail & Related papers (2026-07-23T09:59:30Z)
A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans [0.39998518782208775]
We present a heterogeneous ensemble of nine models spanning three inference paradigms.<n>The ensemble achieves an average macro F1 of 0.9280 across four hospital centres, outperforming the best single model.
arXiv Detail & Related papers (2026-03-15T21:34:59Z)
ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification [0.7495002546468839]
We introduce ZACH-ViT (Zero- parameter Adaptive Compact Hierarchical Vision Transformer), a 0.25 M-Hierarchical Vision Transformer that removes both positional embeddings and variant token.<n>ZACH-ViT was evaluated on 380 LUS videos from 95 critically ill patients against nine state-of-the-art baselines.<n>It achieved the highest validation and test ROC-AUC (0.80 and 0.79) with balanced sensitivity (0.60) and specificity (0.91), while all competing models collapsed to trivial classification.
arXiv Detail & Related papers (2025-10-20T15:26:38Z)
EqDiff-CT: Equivariant Conditional Diffusion model for CT Image Synthesis from CBCT [43.92108185590778]
Cone-beam computed tomography (CBCT) is widely used for imageguided radiotherapy (IGRT)<n>We propose a novel diffusion-based conditional generative model, coined EqDiff-CT, to synthesize high-quality CT images from CBCT.
arXiv Detail & Related papers (2025-09-26T05:51:59Z)
A Novel Attention-Augmented Wavelet YOLO System for Real-time Brain Vessel Segmentation on Transcranial Color-coded Doppler [49.03919553747297]
We propose an AI-powered, real-time CoW auto-segmentation system capable of efficiently capturing cerebral arteries.<n>No prior studies have explored AI-driven cerebrovascular segmentation using Transcranial Color-coded Doppler (TCCD)<n>The proposed AAW-YOLO demonstrated strong performance in segmenting both ipsilateral and contralateral CoW vessels.
arXiv Detail & Related papers (2025-08-19T14:41:22Z)
ViT-2SPN: Vision Transformer-based Dual-Stream Self-Supervised Pretraining Networks for Retinal OCT Classification [0.10241134756773226]
Vision Transformer-based Dual-Stream Self-Supervised Pretraining Network (ViT-2SPN) is a novel framework designed to enhance feature extraction and improve diagnostic accuracy.<n>ViT-2SPN employs a three-stage workflow: Supervised Pretraining, Self-Supervised Pretraining, and Supervised Fine-Tuning.<n>ViT-2SPN achieves a mean AUC of 0.93, accuracy of 0.77, precision of 0.81, recall of 0.75, and an F1 score of 0.76, outperforming existing SSP-based methods.
arXiv Detail & Related papers (2025-01-28T19:41:38Z)
KaLDeX: Kalman Filter based Linear Deformable Cross Attention for Retina Vessel Segmentation [46.57880203321858]
We propose a novel network (KaLDeX) for vascular segmentation leveraging a Kalman filter based linear deformable cross attention (LDCA) module. Our approach is based on two key components: Kalman filter (KF) based linear deformable convolution (LD) and cross-attention (CA) modules. The proposed method is evaluated on retinal fundus image datasets (DRIVE, CHASE_BD1, and STARE) as well as the 3mm and 6mm of the OCTA-500 dataset.
arXiv Detail & Related papers (2024-10-28T16:00:42Z)
A Two-Stage Generative Model with CycleGAN and Joint Diffusion for MRI-based Brain Tumor Detection [41.454028276986946]
We propose a novel framework Two-Stage Generative Model (TSGM) to improve brain tumor detection and segmentation. CycleGAN is trained on unpaired data to generate abnormal images from healthy images as data prior. VE-JP is implemented to reconstruct healthy images using synthetic paired abnormal images as a guide.
arXiv Detail & Related papers (2023-11-06T12:58:26Z)
Learned Local Attention Maps for Synthesising Vessel Segmentations [43.314353195417326]
We present an encoder-decoder model for synthesising segmentations of the main cerebral arteries in the circle of Willis (CoW) from only T2 MRI. It uses learned local attention maps generated by dilating the segmentation labels, which forces the network to only extract information from the T2 MRI relevant to synthesising the CoW.
arXiv Detail & Related papers (2023-08-24T15:32:27Z)
Spatiotemporal Feature Learning Based on Two-Step LSTM and Transformer for CT Scans [2.3682456328966115]
We propose a novel, effective, two-step-wise approach to tickle this issue for COVID-19 symptom classification thoroughly. First, the semantic feature embedding of each slice for a CT scan is extracted by conventional backbone networks. Then, we proposed a long short-term memory (LSTM) and Transformer-based sub-network to deal with temporal feature learning.
arXiv Detail & Related papers (2022-07-04T16:59:05Z)
Multiple Time Series Fusion Based on LSTM An Application to CAP A Phase Classification Using EEG [56.155331323304]
Deep learning based electroencephalogram channels' feature level fusion is carried out in this work. Channel selection, fusion, and classification procedures were optimized by two optimization algorithms.
arXiv Detail & Related papers (2021-12-18T14:17:49Z)
Multi-Slice Net: A novel light weight framework for COVID-19 Diagnosis [38.32234937094937]
This paper presents a novel lightweight COVID-19 diagnosis framework using CT scans. We use a powerful backbone network as a feature extractor to capture discriminative slice-level features. These features are aggregated by a lightweight network to obtain a patient level diagnosis.
arXiv Detail & Related papers (2021-08-09T02:46:11Z)

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