ELCT-YOLO: An Efficient One-Stage Model for Automatic Lung Tumor Detection Based on CT Images

Abstract

Research on lung cancer automatic detection using deep learning algorithms has achieved good results but, due to the complexity of tumor edge features and possible changes in tumor positions, it is still a great challenge to diagnose patients with lung tumors based on computed tomography (CT) images. In order to solve the problem of scales and meet the requirements of real-time detection, an efficient one-stage model for automatic lung tumor detection in CT Images, called ELCT-YOLO, is presented in this paper. Instead of deepening the backbone or relying on a complex feature fusion network, ELCT-YOLO uses a specially designed neck structure, which is suitable to enhance the multi-scale representation ability of the entire feature layer. At the same time, in order to solve the problem of lacking a receptive field after decoupling, the proposed model uses a novel Cascaded Refinement Scheme (CRS), composed of two different types of receptive field enhancement modules (RFEMs), which enables expanding the effective receptive field and aggregate multi-scale context information, thus improving the tumor detection performance of the model. The experimental results show that the proposed ELCT-YOLO model has strong ability in expressing multi-scale information and good robustness in detecting lung tumors of various sizes.

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans

“…Mammeri et al [24] utilized YOLO V7 for lung nodule detection and introduced a multiclass classification approach. Ji et al [25] proposed an efficient single-stage ELCT-YOLO model based on improvements to the YOLO V7-tiny model for lung tumor detection in CT images.…”

Nondestructive estimation method of live chicken leg weight based on deep learning

“…ELCT-YOLO is an improved and efficient network based on YOLO-v7 to solve the complexity of tumor edge features and the variability of tumor location. By redesigning the neck, the multiscale expression ability of the entire feature layer was appropriately enhanced ( Ji et al, 2023 ). A new cascaded refinement scheme was used to solve the lack of sensitivity field after decoupling, effectively aggregate multiscale context information, and improve the detection performance of the target region.…”

Special Issue “Statistical Data Modeling and Machine Learning with Applications II”

“…Paper [13] presents an efficient one-stage model for automatic lung tumor detection in computed tomography (CT) images, called ELCT-YOLO. It was designed to solve the problem of scales and meet the requirements of real-time tumor detection.…”