CPLOYO: A Pulmonary Nodule Detection Model with Multi-Scale Feature Fusion and Nonlinear Feature Learning

TL;DR

CPLOYO tackles the challenge of detecting small pulmonary nodules in CT images within IoT-enabled diagnostic pipelines. It introduces a cohesive set of modules—C2f_RepViTCAMF for backbone enhancement, MSCAF for multi-scale feature fusion, and a KAN-Bottleneck with CBAM-driven attention in the Neck—to achieve high precision, recall, and mAP while maintaining low latency. Leveraging transfer learning from MS COCO and image enhancement for low-contrast CTs, CPLOYO demonstrates state-of-the-art performance on LUNA16 and LIDC-IDRI with fast inference, underscoring its practical potential for real-time, resource-constrained medical applications. Ablation studies confirm the additive value of each component, highlighting improved detection without prohibitive complexity. The approach suggests meaningful impact for IoT-connected diagnostic workflows, enabling faster, more reliable lung cancer screening and triage.

Abstract

The integration of Internet of Things (IoT) technology in pulmonary nodule detection significantly enhances the intelligence and real-time capabilities of the detection system. Currently, lung nodule detection primarily focuses on the identification of solid nodules, but different types of lung nodules correspond to various forms of lung cancer. Multi-type detection contributes to improving the overall lung cancer detection rate and enhancing the cure rate. To achieve high sensitivity in nodule detection, targeted improvements were made to the YOLOv8 model. Firstly, the C2f\_RepViTCAMF module was introduced to augment the C2f module in the backbone, thereby enhancing detection accuracy for small lung nodules and achieving a lightweight model design. Secondly, the MSCAF module was incorporated to reconstruct the feature fusion section of the model, improving detection accuracy for lung nodules of varying scales. Furthermore, the KAN network was integrated into the model. By leveraging the KAN network's powerful nonlinear feature learning capability, detection accuracy for small lung nodules was further improved, and the model's generalization ability was enhanced. Tests conducted on the LUNA16 dataset demonstrate that the improved model outperforms the original model as well as other mainstream models such as YOLOv9 and RT-DETR across various evaluation metrics.

Figures (5)

• Figure 1: Overview structure of the lung nodule detection and classification system.
• Figure 2: Overall network architecture
• Figure 3: Structure Diagram of C2f_RepViTCAMF Modules
• Figure 4: Structure Diagram of KAN_BottleNeck Module
• Figure 5: Visual comparison of lung nodule detection results on the LUNA16