# Localizing Anatomical Landmarks in Ocular Images using Zoom-In Attentive Networks

arXiv: https://arxiv.org/abs/2210.02445 · HTML: https://mlsanity.com/paper/2210.02445/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 25 Sep 2022.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [Hierarchical Question-Image Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1606.00061/) (2016)
- [REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs](https://mlsanity.com/paper/1910.03667/) (2019)
- [See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks](https://mlsanity.com/paper/2001.06810/) (2020)
- [Integrating Spatial Configuration into Heatmap Regression Based CNNs for Landmark Localization](https://mlsanity.com/paper/1908.00748/) (2019)
- [Multi-Head Attention: Collaborate Instead of Concatenate](https://mlsanity.com/paper/2006.16362/) (2020)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Medical Image Segmentation Using Squeeze-and-Expansion Transformers](https://mlsanity.com/paper/2105.09511/) (2021)
- [Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering](https://mlsanity.com/paper/1804.00775/) (2018)
- [A Survey on Deep Learning for Localization and Mapping: Towards the Age of Spatial Machine Intelligence](https://mlsanity.com/paper/2006.12567/) (2020)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [Deep Learning-Based Regression and Classification for Automatic Landmark Localization in Medical Images](https://mlsanity.com/paper/2007.05295/) (2020)
- [Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports](https://mlsanity.com/paper/2110.03094/) (2021)
- [AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography](https://mlsanity.com/paper/2005.02258/) (2020)
- [Spine Landmark Localization with combining of Heatmap Regression and Direct Coordinate Regression](https://mlsanity.com/paper/2007.05355/) (2020)

## Abstract (arXiv)

Localizing anatomical landmarks are important tasks in medical image analysis. However, the landmarks to be localized often lack prominent visual features. Their locations are elusive and easily confused with the background, and thus precise localization highly depends on the context formed by their surrounding areas. In addition, the required precision is usually higher than segmentation and object detection tasks. Therefore, localization has its unique challenges different from segmentation or detection. In this paper, we propose a zoom-in attentive network (ZIAN) for anatomical landmark localization in ocular images. First, a coarse-to-fine, or "zoom-in" strategy is utilized to learn the contextualized features in different scales. Then, an attentive fusion module is adopted to aggregate multi-scale features, which consists of 1) a co-attention network with a multiple regions-of-interest (ROIs) scheme that learns complementary features from the multiple ROIs, 2) an attention-based fusion module which integrates the multi-ROIs features and non-ROI features. We evaluated ZIAN on two open challenge tasks, i.e., the fovea localization in fundus images and scleral spur localization in AS-OCT images. Experiments show that ZIAN achieves promising performances and outperforms state-of-the-art localization methods. The source code and trained models of ZIAN are available at https://github.com/leixiaofeng-astar/OMIA9-ZIAN.