Application of deep learning based on convolutional neural network model in multimodal ultrasound diagnosis of unexplained cervical lymph node enlargement

TL;DR

This study shows how deep learning, specifically CNNs, can accurately classify cervical lymph node pathologies using ultrasound images.

Contribution

The novel contribution is applying pre-trained CNNs to multimodal ultrasound data for cervical lymph node classification.

Findings

The pre-trained ResNet model achieved an elastography AUC of 0.925 in classifying lymph node pathologies.

Elastography was identified as the most reliable dataset for improving model accuracy.

Pre-training significantly improved model performance compared to non-pre-trained models.

Abstract

This study retrospectively analyzed the multimodal ultrasound features and clinical characteristics of 586 patients with unexplained cervical lymphadenopathy who were treated at three hospitals between October 2019 and December 2022. Statistically significant differences were found in the clinical and ultrasound features of all patients, including location, shape, margin, and color Doppler flow imaging (CDFI) (p<0.05). Deep learning models, particularly convolutional neural networks (CNNs), demonstrated great potential in classifying cervical lymph node pathologies using multimodal ultrasound images, including 2D imaging, color Doppler flow imaging (CDFI), and elastography. First, we pre-trained four convolutional neural networks using a public medical image dataset. Then, we fine-tuned the models for three-class classification of lymph nodes into metastatic, lymphoma, and benign using 2D, CDFI, and elastography images from the patients’ lymph nodes. The pre-trained ResNet model performed excellently, with an elastography AUC of 0.925, outperforming other models. Elastography became the most reliable feature extraction dataset, significantly enhancing the model’s accuracy in distinguishing between benign, lymphoma, and metastatic lymph nodes. Ablation experiments showed that pre-training significantly improved accuracy compared to non-pre-trained models. Grad-CAM visualization provided valuable interpretability, revealing how the model focuses on specific areas corresponding to each pathology. Based on this model, we developed a user-friendly server, CV4LymphNode (https://hwwlab.com/webserver/cv4lymphnode). This study highlights the potential of deep learning in accurately classifying cervical lymph node pathologies.

Figures