BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations

• URL: http://arxiv.org/abs/2301.13418v4
• Date: Tue, 2 Apr 2024 11:03:02 GMT
• Title: BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations
• Authors: Yuanhong Chen, Yuyuan Liu, Chong Wang, Michael Elliott, Chun Fung Kwok, Carlos Pena-Solorzano, Yu Tian, Fengbei Liu, Helen Frazer, Davis J. McCarthy, Gustavo Carneiro,
• Abstract summary: 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.
• Score: 17.133754045164444
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Methods to detect malignant lesions from screening mammograms are usually trained with fully annotated datasets, where images are labelled with the localisation and classification of cancerous lesions. However, real-world screening mammogram datasets commonly have a subset that is fully annotated and another subset that is weakly annotated with just the global classification (i.e., without lesion localisation). Given the large size of such datasets, researchers usually face a dilemma with the weakly annotated subset: to not use it or to fully annotate it. The first option will reduce detection accuracy because it does not use the whole dataset, and the second option is too expensive given that the annotation needs to be done by expert radiologists. In this paper, we propose a middle-ground solution for the dilemma, which is to formulate the training as a weakly- and semi-supervised learning problem that we refer to as malignant breast lesion detection with incomplete annotations. To address this problem, our new method comprises two stages, namely: 1) pre-training a multi-view mammogram classifier with weak supervision from the whole dataset, and 2) extending the trained classifier to become a multi-view detector that is trained with semi-supervised student-teacher learning, where the training set contains fully and weakly-annotated mammograms. We provide extensive detection results on two real-world screening mammogram datasets containing incomplete annotations, and show that our proposed approach achieves state-of-the-art results in the detection of malignant breast lesions with incomplete annotations.

Related papers

• Semi- and Weakly-Supervised Learning for Mammogram Mass Segmentation with Limited Annotations [49.33388736227072]
  We propose a semi- and weakly-supervised learning framework for mass segmentation. We use limited strongly-labeled samples and sufficient weakly-labeled samples to achieve satisfactory performance. Experiments on CBIS-DDSM and INbreast datasets demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-03-14T12:05:25Z)
• M&M: Tackling False Positives in Mammography with a Multi-view and Multi-instance Learning Sparse Detector [13.67324365495568]
  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
  arXiv  Detail & Related papers  (2023-08-11T23:59:47Z)
• An End-to-End Framework For Universal Lesion Detection With Missing Annotations [24.902835211573628]
  We present a novel end-to-end framework for mining unlabeled lesions while simultaneously training the detector. Our framework follows the teacher-student paradigm. High-confidence predictions are combined with partially-labeled ground truth for training the student model.
  arXiv  Detail & Related papers  (2023-03-27T09:16:10Z)
• Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images [83.7047542725469]
  Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development. We present a method, named Label Cleaning Multiple Instance Learning (LC-MIL), to refine coarse annotations on a single WSI without the need of external training data. Our experiments on a heterogeneous WSI set with breast cancer lymph node metastasis, liver cancer, and colorectal cancer samples show that LC-MIL significantly refines the coarse annotations, outperforming the state-of-the-art alternatives, even while learning from a single slide.
  arXiv  Detail & Related papers  (2021-09-22T15:06:06Z)
• Deep Semi-supervised Metric Learning with Dual Alignment for Cervical Cancer Cell Detection [49.78612417406883]
  We propose a novel semi-supervised deep metric learning method for cervical cancer cell detection. Our model learns an embedding metric space and conducts dual alignment of semantic features on both the proposal and prototype levels. We construct a large-scale dataset for semi-supervised cervical cancer cell detection for the first time, consisting of 240,860 cervical cell images.
  arXiv  Detail & Related papers  (2021-04-07T17:11:27Z)
• Semi-Automatic Data Annotation guided by Feature Space Projection [117.9296191012968]
  We present a semi-automatic data annotation approach based on suitable feature space projection and semi-supervised label estimation. We validate our method on the popular MNIST dataset and on images of human intestinal parasites with and without fecal impurities. Our results demonstrate the added-value of visual analytics tools that combine complementary abilities of humans and machines for more effective machine learning.
  arXiv  Detail & Related papers  (2020-07-27T17:03:50Z)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)
• Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images [51.893494939675314]
  We propose a novel weakly supervised segmentation framework based on partial points annotation. We show that our method can achieve competitive performance compared to the fully supervised counterpart and the state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-10T15:41:29Z)
• Semi-supervised lung nodule retrieval [2.055949720959582]
  A content based image retrieval (CBIR) system provides as its output a set of images, ranked by similarity to the query image. Ground truth on similarity between dataset elements (e.g. between nodules) is not readily available, thus greatly challenging machine learning methods. The current study suggests a semi-supervised approach that involves two steps: 1) Automatic annotation of a given partially labeled dataset; 2) Learning a semantic similarity metric space based on the predicated annotations. The proposed system is demonstrated in lung nodule retrieval using the LIDC dataset, and shows that it is feasible to learn embedding from predicted ratings.
  arXiv  Detail & Related papers  (2020-05-04T19:26:14Z)
• A Two-Stage Multiple Instance Learning Framework for the Detection of Breast Cancer in Mammograms [13.842620686759616]
  Mammograms are commonly employed in the large scale screening of breast cancer. We propose a two-stage Multiple Instance Learning framework for image-level detection of malignancy. A global image-level feature is computed as a weighted average of patch-level features learned using a CNN. Our method performed well on the task of localization of masses with an average Precision/Recall of 0.76/0.80 and acheived an average AUC of 0.91 on the imagelevel classification task.
  arXiv  Detail & Related papers  (2020-04-24T13:06:47Z)

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.