Improving ultrasound image classification with local texture quantisation

Li, X., Liang, H., Nagala, S. and Chen, J. (2022) Improving ultrasound image classification with local texture quantisation. In: The International Conference on Acoustics, Speech, & Signal Processing (ICASSP). doi: 10.1109/ICASSP43922.2022.9747883

Abstract/Summary

Ultrasound image classification is important for disease diagnosis. It is more challenging than usual image classification tasks since ultrasound images are difficult to collect and usually contain lots of noise. This paper proposes a novel image classification framework for small-scaled and noisy ultrasound image datasets. The framework first transforms images into discrete \textit{index grids}. The index grids use discrete indices encoding the local texture patterns of the images. Then, it will conduct classification based on index grids. The proposed framework can significantly reduce the impact of noise as well as the amount of training data that needed. Comparing with existing models, the proposed framework is a lite model and has better explainability. We evaluated the proposed approach on two public ultrasound image datasets for thyroid nodule classification and breast nodule classification. The experiment results show that the proposed approach achieves the new state-of-the-art.

Item Type	Conference or Workshop Item (Paper)
URI	https://reading-clone.eprints-hosting.org/id/eprint/102485
Identification Number/DOI	10.1109/ICASSP43922.2022.9747883
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science Interdisciplinary centres and themes > Health Innovation Partnership (HIP)
Download/View statistics	View download statistics for this item