FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders

• URL: http://arxiv.org/abs/2403.08848v2
• Date: Fri, 29 Mar 2024 21:22:06 GMT
• Title: FocusMAE: Gallbladder Cancer Detection from Ultrasound Videos with Focused Masked Autoencoders
• Authors: Soumen Basu, Mayuna Gupta, Chetan Madan, Pankaj Gupta, Chetan Arora,
• Abstract summary: This study advocates for a paradigm shift towards video-based detection. We propose a novel design called FocusMAE to systematically bias the selection of masking tokens from high-information regions. We report a state-of-the-art (SOTA) accuracy of 96.4% for the GBC detection problem, against an accuracy of 84% by current Image-based SOTA - RadFormer, and 94.7% by Video-based SOTA - AdaMAE.
• Score: 7.76606060260265
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• 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 state-of-the-art (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. The source code and pretrained models are available at: https://gbc-iitd.github.io/focusmae

Related papers

• D-MASTER: Mask Annealed Transformer for Unsupervised Domain Adaptation in Breast Cancer Detection from Mammograms [5.00208619516796]
  We focus on the problem of Unsupervised Domain Adaptation (uda) for breast cancer detection from mammograms problem. Recent advancements have shown that masked image modeling serves as a robust pretext task for UDA. When applied to cross-domain BCDM, these techniques struggle with breast abnormalities such as masses, asymmetries, and micro-calcifications. This often results in more false positives per image (FPI) and significant noise in pseudo-labels typically used to bootstrap such techniques.
  arXiv  Detail & Related papers  (2024-07-09T06:35:17Z)
• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Gall Bladder Cancer Detection from US Images with Only Image Level Labels [7.89876701812201]
  We focus on Gallbladder Cancer (GBC) detection using only image-level labels. It is difficult to train a standard image classification model for GBC detection. Since no bounding box annotations is available for training, we pose the problem as weakly supervised object detection.
  arXiv  Detail & Related papers  (2023-09-11T06:37:12Z)
• Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection [122.4894940892536]
  We present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss.
  arXiv  Detail & Related papers  (2022-09-25T04:56:10Z)
• Preservation of High Frequency Content for Deep Learning-Based Medical Image Classification [74.84221280249876]
  An efficient analysis of large amounts of chest radiographs can aid physicians and radiologists. We propose a novel Discrete Wavelet Transform (DWT)-based method for the efficient identification and encoding of visual information.
  arXiv  Detail & Related papers  (2022-05-08T15:29:54Z)
• Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning [17.694219750908413]
  We explore the potential of CNN-based models for gallbladder cancer detection from ultrasound (USG) images. USG is the most common diagnostic modality for GB diseases due to its low cost and accessibility. We propose GBCNet to tackle the challenges in our problem.
  arXiv  Detail & Related papers  (2022-04-25T04:43:33Z)
• Explainable multiple abnormality classification of chest CT volumes with AxialNet and HiResCAM [89.2175350956813]
  We introduce the challenging new task of explainable multiple abnormality classification in volumetric medical images. We propose a multiple instance learning convolutional neural network, AxialNet, that allows identification of top slices for each abnormality. We then aim to improve the model's learning through a novel mask loss that leverages HiResCAM and 3D allowed regions.
  arXiv  Detail & Related papers  (2021-11-24T01:14:33Z)
• CNN Filter Learning from Drawn Markers for the Detection of Suggestive Signs of COVID-19 in CT Images [58.720142291102135]
  We propose a method that does not require either large annotated datasets or backpropagation to estimate the filters of a convolutional neural network (CNN) For a few CT images, the user draws markers at representative normal and abnormal regions. The method generates a feature extractor composed of a sequence of convolutional layers, whose kernels are specialized in enhancing regions similar to the marked ones.
  arXiv  Detail & Related papers  (2021-11-16T15:03:42Z)
• Ensemble of CNN classifiers using Sugeno Fuzzy Integral Technique for Cervical Cytology Image Classification [1.6986898305640261]
  We propose a fully automated computer-aided diagnosis tool for classifying single-cell and slide images of cervical cancer. We use the Sugeno Fuzzy Integral to ensemble the decision scores from three popular deep learning models, namely, Inception v3, DenseNet-161 and ResNet-34.
  arXiv  Detail & Related papers  (2021-08-21T08:41:41Z)
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization [59.719925639875036]
  We propose a framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects.
  arXiv  Detail & Related papers  (2021-04-08T19:04:55Z)
• Learning from Suspected Target: Bootstrapping Performance for Breast Cancer Detection in Mammography [6.323318523772466]
  We introduce a novel top likelihood loss together with a new sampling procedure to select and train the suspected target regions. We firstly test our proposed method on a private dense mammogram dataset. Results show that our proposed method greatly reduce the false positive rate and the specificity is increased by 0.25 on detecting mass type cancer.
  arXiv  Detail & Related papers  (2020-03-01T09:04:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.