CAF-YOLO: A Robust Framework for Multi-Scale Lesion Detection in Biomedical Imagery

TL;DR

CAF-YOLO is a novel multi-scale lesion detection framework combining CNNs and transformers, enhancing the detection of tiny biomedical entities with improved global and local feature modeling.

Contribution

The paper introduces CAF-YOLO, integrating an attention-convolution fusion module and multi-scale neural network to improve detection accuracy of minute lesions in biomedical images.

Findings

Outperforms existing methods on BCCD and LUNA16 datasets.

Effectively detects micro-lesions with high precision.

Enhances global and local feature interaction in biomedical object detection.

Abstract

Object detection is of paramount importance in biomedical image analysis, particularly for lesion identification. While current methodologies are proficient in identifying and pinpointing lesions, they often lack the precision needed to detect minute biomedical entities (e.g., abnormal cells, lung nodules smaller than 3 mm), which are critical in blood and lung pathology. To address this challenge, we propose CAF-YOLO, based on the YOLOv8 architecture, a nimble yet robust method for medical object detection that leverages the strengths of convolutional neural networks (CNNs) and transformers. To overcome the limitation of convolutional kernels, which have a constrained capacity to interact with distant information, we introduce an attention and convolution fusion module (ACFM). This module enhances the modeling of both global and local features, enabling the capture of long-term feature dependencies and spatial autocorrelation. Additionally, to improve the restricted single-scale feature aggregation inherent in feed-forward networks (FFN) within transformer architectures, we design a multi-scale neural network (MSNN). This network improves multi-scale information aggregation by extracting features across diverse scales. Experimental evaluations on widely used datasets, such as BCCD and LUNA16, validate the rationale and efficacy of CAF-YOLO. This methodology excels in detecting and precisely locating diverse and intricate micro-lesions within biomedical imagery. Our codes are available at https://github.com/xiaochen925/CAF-YOLO.