Minuscule Cell Detection in AS-OCT Images with Progressive Field-of-View Focusing

2025-03-15

AI Summary

This work addresses the challenging problem of automatically detecting extremely small inflammatory cells (occupying <0.005% of image area) in anterior segment optical coherence tomography (AS-OCT) images—hampered by severe pixel-level noise and extreme scale imbalance. To this end, we propose a progressive field-of-view focusing framework: (1) a three-stage spatial contraction mechanism to localize candidate regions; (2) a micro-region proposal module coupled with a noise-robust spatial attention network for single-cell-level detection; and (3) integration of segmentation priors from vision foundation models into an end-to-end jointly optimized architecture. Evaluated on a clinical AS-OCT dataset, our method achieves substantial improvements over state-of-the-art approaches, with 12.6% higher precision and 18.3% higher recall. The source code is publicly available, demonstrating strong potential for clinical deployment.

Technology Category

• Computer Vision: Segmentation
• Search and Optimization: Learning to Search
• Machine Learning: Optimization

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Anterior Segment Optical Coherence Tomography (AS-OCT) is an emerging imaging technique with great potential for diagnosing anterior uveitis, a vision-threatening ocular inflammatory condition. A hallmark of this condition is the presence of inflammatory cells in the eye's anterior chamber, and detecting these cells using AS-OCT images has attracted research interest. While recent efforts aim to replace manual cell detection with automated computer vision approaches, detecting extremely small (minuscule) objects in high-resolution images, such as AS-OCT, poses substantial challenges: (1) each cell appears as a minuscule particle, representing less than 0.005% of the image, making the detection difficult, and (2) OCT imaging introduces pixel-level noise that can be mistaken for cells, leading to false positive detections. To overcome these challenges, we propose a minuscule cell detection framework through a progressive field-of-view focusing strategy. This strategy systematically refines the detection scope from the whole image to a target region where cells are likely to be present, and further to minuscule regions potentially containing individual cells. Our framework consists of two modules. First, a Field-of-Focus module uses a vision foundation model to segment the target region. Subsequently, a Fine-grained Object Detection module introduces a specialized Minuscule Region Proposal followed by a Spatial Attention Network to distinguish individual cells from noise within the segmented region. Experimental results demonstrate that our framework outperforms state-of-the-art methods for cell detection, providing enhanced efficacy for clinical applications. Our code is publicly available at: https://github.com/joeybyc/MCD.

Problem

• Detecting minuscule inflammatory cells in AS-OCT images.
• Overcoming challenges of small object detection and noise.
• Proposing a progressive field-of-view focusing strategy.

Innovation

• Progressive field-of-view focusing strategy
• Minuscule Region Proposal for cell detection
• Spatial Attention Network to reduce noise