A Residual Multi-task Network for Joint Classification and Regression in Medical Imaging

2025-02-27

AI Summary

Pulmonary nodules exhibit heterogeneous morphologies and ill-defined boundaries, posing significant challenges for the detection of subtle or occluded nodules and their benign-malignant classification. To address these challenges, this paper proposes an end-to-end joint detection and classification framework featuring a novel residual multi-task collaborative architecture. The architecture employs a shared ResNet backbone and introduces cross-task residual connections to mitigate gradient vanishing and enhance semantic consistency between detection and classification tasks. It further integrates multi-task learning, joint loss optimization, and medical-image-specific data augmentation strategies. Evaluated on the LUNA16 and JSRT datasets, the framework achieves a nodule detection F1-score of 92.3% and a benign-malignant classification accuracy of 94.7%, substantially outperforming single-task baseline models. These results demonstrate the framework’s enhanced capability in modeling subtle pathological features.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Detection and classification of pulmonary nodules is a challenge in medical image analysis due to the variety of shapes and sizes of nodules and their high concealment. Despite the success of traditional deep learning methods in image classification, deep networks still struggle to perfectly capture subtle changes in lung nodule detection. Therefore, we propose a residual multi-task network (Res-MTNet) model, which combines multi-task learning and residual learning, and improves feature representation ability by sharing feature extraction layer and introducing residual connections. Multi-task learning enables the model to handle multiple tasks simultaneously, while the residual module solves the problem of disappearing gradients, ensuring stable training of deeper networks and facilitating information sharing between tasks. Res-MTNet enhances the robustness and accuracy of the model, providing a more reliable lung nodule analysis tool for clinical medicine and telemedicine.

Problem

• Detects and classifies pulmonary nodules accurately.
• Overcomes challenges in lung nodule feature extraction.
• Improves medical imaging analysis with Res-MTNet.

Innovation

• Residual Multi-task Network
• Combines multi-task learning
• Improves feature representation ability