Abstract

In recent years, automated Gallbladder Cancer (GBC) detection has gained the attention of researchers. Current state-of-the-art (SOTA) methodologies relying on ultrasound sonography (US) images exhibit limited generalization, emphasizing the need for transformative approaches. We observe that individual US frames may lack sufficient information to capture disease manifestation. This study advocates for a paradigm shift towards video-based GBC detection, leveraging the inherent advantages of spatiotemporal representations. Employing the Masked Autoencoder (MAE) for representation learning, we address shortcomings in conventional image-based methods. We propose a novel design called FocusMAE to systematically bias the selection of masking tokens from high-information regions, fostering a more refined representation of malignancy. Additionally, we contribute the most extensive US video dataset for GBC detection. We also note that, this is the first study on US video-based GBC detection. We validate the proposed methods on the curated dataset, and report a new SOTA accuracy of 96.4% for the GBC detection problem, against an accuracy of 84% by current Image-based SOTA - GBCNet and RadFormer, and 94.7% by Video-based SOTA - AdaMAE. We further demonstrate the generality of the proposed FocusMAE on a public CT-based Covid detection dataset, reporting an improvement in accuracy by 3.3% over current baselines.

Key Results

Download Dataset

The US video dataset is an extension of the GBUSV dataset, which contains 32 benign and 32 malignant videos. We have added 27 more malignant videos to the dataset, making it a total of 91 videos and the most comprehensive US video dataset for GBC detection. To obtain the dataset, please fill and sign this License Agreement, and send it to Dr. Pankaj Gupta and Dr. Chetan Arora.
After duly verifying the License Agreement, we will mail the dataset download link to you.
Note: Incomplete agreements (i.e. missing ink seal/ signature, institute email, or other necessary information) will be ignored. We will only accept requests from permanent employees/ faculty of the requesting institute, and will ignore requests from students. Student Researchers must ask their Supervisor/ Head of the Department to fill out and send the agreement to us.

BibTeX (Citation)

@article{basu2024focusmae,
    title={FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders},
    author={Basu, Soumen and Gupta, Mayuna and Madan, Chetan and Gupta, Pankaj and Arora, Chetan},
    journal={arXiv preprint arXiv:2403.08848},
    year={2024}
}