Variable-frame CNNLSTM for Breast Nodule Classification using Ultrasound Videos

2025-02-17

AI Summary

Conventional key-frame methods for breast nodule ultrasound video classification neglect temporal dynamics, while fixed-length 3D CNNs suffer from inefficient modeling due to rigid frame constraints. Method: This work pioneers the adaptation of natural language processing (NLP) strategies for variable-length sequence handling to medical video analysis, proposing a variable-length CNN-LSTM architecture. It incorporates frame-order preservation, zero-padding, and invalid-frame compression; integrates CNN-based feature dimensionality reduction (to 1×512), dynamic batching, and LSTM-based temporal modeling—ensuring temporal integrity while markedly improving computational efficiency. Contribution/Results: Experiments demonstrate that the proposed method achieves a 3–6% improvement in F1-score and a 1.5% gain in specificity over baselines, outperforming both fixed-length CNN-LSTM and key-frame approaches in accuracy and overall classification performance—effectively alleviating clinical diagnostic performance bottlenecks.

Technology Category

• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Multimodal Learning
• Natural Language Processing: Summarization

Application Category

• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The intersection of medical imaging and artificial intelligence has become an important research direction in intelligent medical treatment, particularly in the analysis of medical images using deep learning for clinical diagnosis. Despite the advances, existing keyframe classification methods lack extraction of time series features, while ultrasonic video classification based on three-dimensional convolution requires uniform frame numbers across patients, resulting in poor feature extraction efficiency and model classification performance. This study proposes a novel video classification method based on CNN and LSTM, introducing NLP's long and short sentence processing scheme into video classification for the first time. The method reduces CNN-extracted image features to 1x512 dimension, followed by sorting and compressing feature vectors for LSTM training. Specifically, feature vectors are sorted by patient video frame numbers and populated with padding value 0 to form variable batches, with invalid padding values compressed before LSTM training to conserve computing resources. Experimental results demonstrate that our variable-frame CNNLSTM method outperforms other approaches across all metrics, showing improvements of 3-6% in F1 score and 1.5% in specificity compared to keyframe methods. The variable-frame CNNLSTM also achieves better accuracy and precision than equal-frame CNNLSTM. These findings validate the effectiveness of our approach in classifying variable-frame ultrasound videos and suggest potential applications in other medical imaging modalities.

Problem

• Classifies breast nodules using ultrasound videos
• Improves time series feature extraction efficiency
• Enhances model performance with variable frame handling

Innovation

• CNN and LSTM for video classification
• Variable-frame processing with padding
• Feature compression before LSTM training