UltraMAE: Multi-modal Masked Autoencoder for Ultrasound Pre-training

Aimon Rahman, Vishal M. Patel
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1196-1206, 2024.

Abstract

Pre-training on a large dataset such as ImageNet followed by supervised fine-tuning has brought success in various deep learning-based tasks. However, the modalities of natural images and ultrasound images have considerable differences, making pre-training on natural images ineffective for ultrasound-related tasks. In this paper, we introduce a unified masking-based model for both ultrasound images and videos that learns better visual representation than the network with single-modality representations. This is the first large-scale generalized ultrasound pre-training network that simultaneously utilizes 100,000+ videos and images of different parts of the human anatomy such as the liver, bones, heart, thyroids, nerves, etc, making the network an effective benchmark pretrained model for any ultrasound-specific downstream tasks. We propose a novel method for ultrasound image analysis that utilizes an ultrasound-specific confidence map to guide low-level representation learning through masked feature acquisition. Our pre-trained network has demonstrated remarkable efficacy and versatility in tackling both classification and segmentation tasks across a range of ultrasound pathologies, highlighting its potential for widespread adoption and impact in the ultrasound field. In addition, we show that our pre-training model can be leveraged to learn efficiently with a small number of labeled ultrasound images.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-rahman24a, title = {UltraMAE: Multi-modal Masked Autoencoder for Ultrasound Pre-training}, author = {Rahman, Aimon and Patel, Vishal M.}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1196--1206}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/rahman24a/rahman24a.pdf}, url = {https://proceedings.mlr.press/v250/rahman24a.html}, abstract = {Pre-training on a large dataset such as ImageNet followed by supervised fine-tuning has brought success in various deep learning-based tasks. However, the modalities of natural images and ultrasound images have considerable differences, making pre-training on natural images ineffective for ultrasound-related tasks. In this paper, we introduce a unified masking-based model for both ultrasound images and videos that learns better visual representation than the network with single-modality representations. This is the first large-scale generalized ultrasound pre-training network that simultaneously utilizes 100,000+ videos and images of different parts of the human anatomy such as the liver, bones, heart, thyroids, nerves, etc, making the network an effective benchmark pretrained model for any ultrasound-specific downstream tasks. We propose a novel method for ultrasound image analysis that utilizes an ultrasound-specific confidence map to guide low-level representation learning through masked feature acquisition. Our pre-trained network has demonstrated remarkable efficacy and versatility in tackling both classification and segmentation tasks across a range of ultrasound pathologies, highlighting its potential for widespread adoption and impact in the ultrasound field. In addition, we show that our pre-training model can be leveraged to learn efficiently with a small number of labeled ultrasound images.} }
Endnote
%0 Conference Paper %T UltraMAE: Multi-modal Masked Autoencoder for Ultrasound Pre-training %A Aimon Rahman %A Vishal M. Patel %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-rahman24a %I PMLR %P 1196--1206 %U https://proceedings.mlr.press/v250/rahman24a.html %V 250 %X Pre-training on a large dataset such as ImageNet followed by supervised fine-tuning has brought success in various deep learning-based tasks. However, the modalities of natural images and ultrasound images have considerable differences, making pre-training on natural images ineffective for ultrasound-related tasks. In this paper, we introduce a unified masking-based model for both ultrasound images and videos that learns better visual representation than the network with single-modality representations. This is the first large-scale generalized ultrasound pre-training network that simultaneously utilizes 100,000+ videos and images of different parts of the human anatomy such as the liver, bones, heart, thyroids, nerves, etc, making the network an effective benchmark pretrained model for any ultrasound-specific downstream tasks. We propose a novel method for ultrasound image analysis that utilizes an ultrasound-specific confidence map to guide low-level representation learning through masked feature acquisition. Our pre-trained network has demonstrated remarkable efficacy and versatility in tackling both classification and segmentation tasks across a range of ultrasound pathologies, highlighting its potential for widespread adoption and impact in the ultrasound field. In addition, we show that our pre-training model can be leveraged to learn efficiently with a small number of labeled ultrasound images.
APA
Rahman, A. & Patel, V.M.. (2024). UltraMAE: Multi-modal Masked Autoencoder for Ultrasound Pre-training. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1196-1206 Available from https://proceedings.mlr.press/v250/rahman24a.html.

Related Material