Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification

• URL: http://arxiv.org/abs/2401.03912v1
• Date: Mon, 8 Jan 2024 14:16:54 GMT
• Title: Attention-Guided Erasing: A Novel Augmentation Method for Enhancing Downstream Breast Density Classification
• Authors: Adarsh Bhandary Panambur, Hui Yu, Sheethal Bhat, Prathmesh Madhu, Siming Bayer, Andreas Maier
• Abstract summary: This study introduces a novel data augmentation technique termed Attention-Guided Erasing (AGE) AGE is devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. We validate our methodology using the publicly available VinDr-Mammo dataset.
• Score: 5.351205777021679
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The assessment of breast density is crucial in the context of breast cancer screening, especially in populations with a higher percentage of dense breast tissues. This study introduces a novel data augmentation technique termed Attention-Guided Erasing (AGE), devised to enhance the downstream classification of four distinct breast density categories in mammography following the BI-RADS recommendation in the Vietnamese cohort. The proposed method integrates supplementary information during transfer learning, utilizing visual attention maps derived from a vision transformer backbone trained using the self-supervised DINO method. These maps are utilized to erase background regions in the mammogram images, unveiling only the potential areas of dense breast tissues to the network. Through the incorporation of AGE during transfer learning with varying random probabilities, we consistently surpass classification performance compared to scenarios without AGE and the traditional random erasing transformation. We validate our methodology using the publicly available VinDr-Mammo dataset. Specifically, we attain a mean F1-score of 0.5910, outperforming values of 0.5594 and 0.5691 corresponding to scenarios without AGE and with random erasing (RE), respectively. This superiority is further substantiated by t-tests, revealing a p-value of p<0.0001, underscoring the statistical significance of our approach.

Related papers

• DensiThAI, A Multi-View Deep Learning Framework for Breast Density Estimation using Infrared Images [0.8594140167290097]
  This study investigates the feasibility of estimating breast density using artificial intelligence over infrared thermal images.<n>We propose DensiThAI, a multi-view deep learning framework for breast density classification from thermal images.
  arXiv  Detail & Related papers  (2026-01-29T07:53:57Z)
• Attention-Enhanced Deep Learning Ensemble for Breast Density Classification in Mammography [0.0]
  This study proposes an automated deep learning system for robust binary classification of breast density.<n>We implemented and compared four advanced convolutional neural networks.<n>We developed a novel Combined Focal Label Smoothing Loss function that integrates focal loss, label smoothing, and class-balanced weighting.
  arXiv  Detail & Related papers  (2025-07-08T21:26:33Z)
• A Foundational Generative Model for Breast Ultrasound Image Analysis [42.618964727896156]
  Foundational models have emerged as powerful tools for addressing various tasks in clinical settings. We present BUSGen, the first foundational generative model specifically designed for breast ultrasound analysis. With few-shot adaptation, BUSGen can generate repositories of realistic and informative task-specific data.
  arXiv  Detail & Related papers  (2025-01-12T16:39:13Z)
• Beyond the Eye: A Relational Model for Early Dementia Detection Using Retinal OCTA Images [43.73298205923969]
  We present a novel PolarNet+ that uses retinal optical coherence tomography angiography ( OCTA) to discriminate early-onset Alzheimer's disease (AD) and mild cognitive impairment (MCI) subjects from controls.<n>Our method first maps OCTA images from Cartesian coordinates to polar coordinates, allowing approximate sub-region calculation.<n>We then introduce a multi-view module to serialize and analyze the images along three dimensions for comprehensive, clinically useful information extraction.
  arXiv  Detail & Related papers  (2024-08-09T15:10:34Z)
• Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning [1.4053129774629076]
  This study presents an unsupervised domain adaptation method aimed at autonomously generating image masks outlining regions of interest (ROIs) for differentiating breast lesions in breast ultrasound (US) imaging. Our semi-supervised learning approach utilizes a primitive model trained on a small public breast US dataset with true annotations. This model is then iteratively refined for the domain adaptation task, generating pseudo-masks for our private, unannotated breast US dataset.
  arXiv  Detail & Related papers  (2024-04-18T18:25:00Z)
• Supervised Contrastive Vision Transformer for Breast Histopathological Image Classification [0.0]
  Invasive ductal carcinoma (IDC) is the most prevalent form of breast cancer. We present a novel approach, Supervised Contrastive Vision Transformer (SupCon-ViT), for improving the classification of IDC.
  arXiv  Detail & Related papers  (2024-04-17T03:51:55Z)
• Breast Cancer Image Classification Method Based on Deep Transfer Learning [40.392772795903795]
  A breast cancer image classification model algorithm combining deep learning and transfer learning is proposed. Experimental results demonstrate that the algorithm achieves an efficiency of over 84.0% in the test set, with a significantly improved classification accuracy compared to previous models.
  arXiv  Detail & Related papers  (2024-04-14T12:09:47Z)
• Certification of Deep Learning Models for Medical Image Segmentation [44.177565298565966]
  We present for the first time a certified segmentation baseline for medical imaging based on randomized smoothing and diffusion models. Our results show that leveraging the power of denoising diffusion probabilistic models helps us overcome the limits of randomized smoothing.
  arXiv  Detail & Related papers  (2023-10-05T16:40:33Z)
• In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detection [0.4433315630787158]
  This paper investigates the impact of breast density distribution on the generalization performance of deep-learning models on mammography images. We propose a robust augmentation framework to bridge the domain gap between the source and target inside a dataset.
  arXiv  Detail & Related papers  (2023-06-12T06:46:42Z)
• Active Learning Enhances Classification of Histopathology Whole Slide Images with Attention-based Multiple Instance Learning [48.02011627390706]
  We train an attention-based MIL and calculate a confidence metric for every image in the dataset to select the most uncertain WSIs for expert annotation. With a novel attention guiding loss, this leads to an accuracy boost of the trained models with few regions annotated for each class. It may in the future serve as an important contribution to train MIL models in the clinically relevant context of cancer classification in histopathology.
  arXiv  Detail & Related papers  (2023-03-02T15:18:58Z)
• Stain-invariant self supervised learning for histopathology image analysis [74.98663573628743]
  We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin stained images of breast cancer. Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets.
  arXiv  Detail & Related papers  (2022-11-14T18:16:36Z)
• Corneal endothelium assessment in specular microscopy images with Fuchs' dystrophy via deep regression of signed distance maps [48.498376125522114]
  This paper proposes a UNet-based segmentation approach that requires minimal post-processing. It achieves reliable CE morphometric assessment and guttae identification across all degrees of Fuchs' dystrophy.
  arXiv  Detail & Related papers  (2022-10-13T15:34:20Z)
• High-resolution synthesis of high-density breast mammograms: Application to improved fairness in deep learning based mass detection [48.88813637974911]
  Computer-aided detection systems based on deep learning have shown good performance in breast cancer detection. High-density breasts show poorer detection performance since dense tissues can mask or even simulate masses. This study aims to improve the mass detection performance in high-density breasts using synthetic high-density full-field digital mammograms.
  arXiv  Detail & Related papers  (2022-09-20T15:57:12Z)
• PCA: Semi-supervised Segmentation with Patch Confidence Adversarial Training [52.895952593202054]
  We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation. PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state. Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
  arXiv  Detail & Related papers  (2022-07-24T07:45:47Z)
• A multi-reconstruction study of breast density estimation using Deep Learning [0.9449650062296825]
  Breast density estimation is one of the key tasks performed during a screening exam. Deep-learning studies for breast density estimation use only a single modality for training a neural network. In this paper, we show that a neural network trained on all the modalities at once performs better than a neural network trained on any single modality.
  arXiv  Detail & Related papers  (2022-02-16T18:34:08Z)
• Open-Set Recognition of Breast Cancer Treatments [91.3247063132127]
  Open-set recognition generalizes a classification task by classifying test samples as one of the known classes from training or "unknown" We apply a recent existing Gaussian mixture variational autoencoder model, which achieves state-of-the-art results for image datasets, to breast cancer patient data. Not only do we obtain more accurate and robust classification results, with a 24.5% average F1 increase compared to a recent method, but we also reexamine open-set recognition in terms of deployability to a clinical setting.
  arXiv  Detail & Related papers  (2022-01-09T04:35:55Z)
• 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)
• An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization [45.00998416720726]
  We propose a framework to address the unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a final prediction.
  arXiv  Detail & Related papers  (2020-02-13T15:28:42Z)

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.