Using Few-Shot Learning to Classify Primary Lung Cancer and Other Malignancy with Lung Metastasis in Cytological Imaging via Endobronchial Ultrasound Procedures
This addresses the challenge of early detection of lung metastases in clinical settings with limited data, though it appears incremental as it builds on existing few-shot learning approaches.
The study tackled the problem of classifying primary lung cancer versus lung metastases in cytological imaging from endobronchial ultrasound procedures, achieving 49.59% accuracy with their few-shot learning model and improving to 55.48% accuracy with 20 image samples.
This study presents a computer-aided diagnosis (CAD) system to assist early detection of lung metastases during endobronchial ultrasound (EBUS) procedures, significantly reducing follow-up time and enabling timely treatment. Due to limited cytology images and morphological similarities among cells, classifying lung metastases is challenging, and existing research rarely targets this issue directly.To overcome data scarcity and improve classification, the authors propose a few-shot learning model using a hybrid pretrained backbone with fine-grained classification and contrastive learning. Parameter-efficient fine-tuning on augmented support sets enhances generalization and transferability. The model achieved 49.59% accuracy, outperforming existing methods. With 20 image samples, accuracy improved to 55.48%, showing strong potential for identifying rare or novel cancer types in low-data clinical environments.