# DINO-LG: Enhancing Vision Transformers with Label Guidance for Coronary Artery Calcium Detection

arXiv: https://arxiv.org/abs/2411.07976 · HTML: https://mlsanity.com/paper/2411.07976/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 50 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology Benchmarks](https://mlsanity.com/paper/2312.02366/) (2023)
- [Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification](https://mlsanity.com/paper/2402.07595/) (2024)
- [Pretrained ViTs Yield Versatile Representations For Medical Images](https://mlsanity.com/paper/2303.07034/) (2023)
- [Anatomy-aware Self-supervised Learning for Anomaly Detection in Chest Radiographs](https://mlsanity.com/paper/2205.04282/) (2022)
- [Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class](https://mlsanity.com/paper/2304.05163/) (2023)
- [Shifting to Machine Supervision: Annotation-Efficient Semi and Self-Supervised Learning for Automatic Medical Image Segmentation and Classification](https://mlsanity.com/paper/2311.10319/) (2023)
- [DINO-CXR: A self supervised method based on vision transformer for chest X-ray classification](https://mlsanity.com/paper/2308.00475/) (2023)
- [USL-Net: Uncertainty Self-Learning Network for Unsupervised Skin Lesion Segmentation](https://mlsanity.com/paper/2309.13289/) (2023)
- [Automated Coronary Calcium Scoring using U-Net Models through Semi-supervised Learning on Non-Gated CT Scans](https://mlsanity.com/paper/2206.10455/) (2022)
- [Coronary artery segmentation in non-contrast calcium scoring CT images using deep learning](https://mlsanity.com/paper/2403.02544/) (2024)

## Built on by (most cited first, 1 of 1)

- [DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT](https://mlsanity.com/paper/2606.07775/) (2026)

## Abstract (arXiv)

Coronary artery disease (CAD), one of the leading causes of mortality worldwide, necessitates effective risk assessment strategies, with coronary artery calcium (CAC) scoring via computed tomography (CT) being a key method for prevention. Traditional methods, primarily based on UNET architectures implemented on pre-built models, face challenges like the scarcity of annotated CT scans containing CAC and imbalanced datasets, leading to reduced performance in segmentation and scoring tasks. In this study, we address these limitations by introducing DINO-LG, a novel label-guided extension of DINO (self-distillation with no labels) that incorporates targeted augmentation on annotated calcified regions during self-supervised pre-training. Our three-stage pipeline integrates Vision Transformer (ViT-Base/8) feature extraction via DINO-LG trained on 914 CT scans comprising 700 gated and 214 non-gated acquisitions, linear classification to identify calcified slices, and U-NET segmentation for CAC quantification and Agatston scoring. DINO-LG achieved 89% sensitivity and 90% specificity for detecting CAC-containing CT slices, compared to standard DINO's 79% sensitivity and 77% specificity, reducing false-negative and false-positive rates by 49% and 57% respectively. The integrated system achieves 90% accuracy in CAC risk classification on 45 test patients, outperforming standalone U-NET segmentation (76% accuracy) while processing only the relevant subset of CT slices. This targeted approach enhances CAC scoring accuracy by feeding the UNET model with relevant slices, improving diagnostic precision while lowering healthcare costs by minimizing unnecessary tests and treatments.