M&M: Tackling False Positives in Mammography with a Multi-view and
Multi-instance Learning Sparse Detector
- URL: http://arxiv.org/abs/2308.06420v1
- Date: Fri, 11 Aug 2023 23:59:47 GMT
- Title: M&M: Tackling False Positives in Mammography with a Multi-view and
Multi-instance Learning Sparse Detector
- Authors: Yen Nhi Truong Vu, Dan Guo, Ahmed Taha, Jason Su, Thomas Paul Matthews
- Abstract summary: Deep-learning-based object detection methods show promise for improving screening mammography, but high rates of false positives can hinder their effectiveness in clinical practice.
We identify three challenges: unlike natural images, a malignant mammogram typically contains only one malignant finding; mammography exams contain two views of each breast, and both views ought to be considered to make a correct assessment.
We tackle the three aforementioned challenges by: (1) leveraging Sparse R-CNN and showing that sparse detectors are more appropriate than dense detectors for mammography; (2) including a multi-view cross-attention module to synthesize information from different views; and (3) incorporating multi-instance
- Score: 13.67324365495568
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Deep-learning-based object detection methods show promise for improving
screening mammography, but high rates of false positives can hinder their
effectiveness in clinical practice. To reduce false positives, we identify
three challenges: (1) unlike natural images, a malignant mammogram typically
contains only one malignant finding; (2) mammography exams contain two views of
each breast, and both views ought to be considered to make a correct
assessment; (3) most mammograms are negative and do not contain any findings.
In this work, we tackle the three aforementioned challenges by: (1) leveraging
Sparse R-CNN and showing that sparse detectors are more appropriate than dense
detectors for mammography; (2) including a multi-view cross-attention module to
synthesize information from different views; (3) incorporating multi-instance
learning (MIL) to train with unannotated images and perform breast-level
classification. The resulting model, M&M, is a Multi-view and Multi-instance
learning system that can both localize malignant findings and provide
breast-level predictions. We validate M&M's detection and classification
performance using five mammography datasets. In addition, we demonstrate the
effectiveness of each proposed component through comprehensive ablation
studies.
Related papers
- Features Fusion for Dual-View Mammography Mass Detection [1.5146068448101746]
We propose a new model called MAMM-Net, which allows the processing of both mammography views simultaneously.
Our experiments show superior performance on the publicM dataset compared to the previous state-of-the-art model.
arXiv Detail & Related papers (2024-04-25T16:30:30Z) - Towards Robust Natural-Looking Mammography Lesion Synthesis on
Ipsilateral Dual-Views Breast Cancer Analysis [1.1098503592431275]
Two major issues of mammogram classification tasks are leveraging multi-view mammographic information and class-imbalance handling.
We propose a simple but novel method for enhancing examined view (main view) by leveraging low-level feature information from the auxiliary view.
We also propose a simple but novel malignant mammogram synthesis framework for up synthesizing minor class samples.
arXiv Detail & Related papers (2023-09-07T06:33:30Z) - MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain
Multi-Center Breast Cancer Screening [4.587250201300601]
Mammography poses challenges due to the high variability and patterns in mammograms.
MammoDG is a novel deep-learning framework for generalisable and reliable analysis of cross-domain multi-center mammography data.
arXiv Detail & Related papers (2023-08-02T10:10:22Z) - LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical
Imaging via Second-order Graph Matching [59.01894976615714]
We introduce LVM-Med, the first family of deep networks trained on large-scale medical datasets.
We have collected approximately 1.3 million medical images from 55 publicly available datasets.
LVM-Med empirically outperforms a number of state-of-the-art supervised, self-supervised, and foundation models.
arXiv Detail & Related papers (2023-06-20T22:21:34Z) - BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations [17.133754045164444]
Methods to detect malignant lesions from screening mammograms are usually trained with fully annotated datasets.
However, real-world screening mammogram datasets commonly have a subset that is weakly annotated with just the global classification.
We propose a middle-ground solution for the dilemma, which is to formulate the training as a weakly- and semi-supervised learning problem.
arXiv Detail & Related papers (2023-01-31T05:14:49Z) - GraVIS: Grouping Augmented Views from Independent Sources for
Dermatology Analysis [52.04899592688968]
We propose GraVIS, which is specifically optimized for learning self-supervised features from dermatology images.
GraVIS significantly outperforms its transfer learning and self-supervised learning counterparts in both lesion segmentation and disease classification tasks.
arXiv Detail & Related papers (2023-01-11T11:38:37Z) - Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA)
First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features.
Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
arXiv Detail & Related papers (2022-09-27T15:50:31Z) - Act Like a Radiologist: Towards Reliable Multi-view Correspondence
Reasoning for Mammogram Mass Detection [49.14070210387509]
We propose an Anatomy-aware Graph convolutional Network (AGN) for mammogram mass detection.
AGN is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability.
Experiments on two standard benchmarks reveal that AGN significantly exceeds the state-of-the-art performance.
arXiv Detail & Related papers (2021-05-21T06:48:34Z) - Malignancy Prediction and Lesion Identification from Clinical
Dermatological Images [65.1629311281062]
We consider machine-learning-based malignancy prediction and lesion identification from clinical dermatological images.
We first identify all lesions present in the image regardless of sub-type or likelihood of malignancy, then it estimates their likelihood of malignancy, and through aggregation, it also generates an image-level likelihood of malignancy.
arXiv Detail & Related papers (2021-04-02T20:52:05Z) - M3Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia
Screening from CT Imaging [85.00066186644466]
We propose a Multi-task Multi-slice Deep Learning System (M3Lung-Sys) for multi-class lung pneumonia screening from CT imaging.
In addition to distinguish COVID-19 from Healthy, H1N1, and CAP cases, our M 3 Lung-Sys also be able to locate the areas of relevant lesions.
arXiv Detail & Related papers (2020-10-07T06:22:24Z) - Synthesizing lesions using contextual GANs improves breast cancer
classification on mammograms [0.4297070083645048]
We present a novel generative adversarial network (GAN) model for data augmentation that can realistically synthesize and remove lesions on mammograms.
With self-attention and semi-supervised learning components, the U-net-based architecture can generate high resolution (256x256px) outputs.
arXiv Detail & Related papers (2020-05-29T21:23:00Z)
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.