Cross-View Relation Networks for Mammogram Mass Detection

Ma, Jiechao; Li, Xiang; Li, Hongwei; Wang, Ruixuan; Menze, Bjoern; Zheng, Wei‐Shi

doi:10.1109/icpr48806.2021.9413132

Cited by 22 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He Li et al [32] augmented a conditional graph learner module to map between the ROIs. In addition, [38], [39], proposed a cross-view CNN model to construct the relationship between the features of two mammogram views, MLO and CC. These techniques improve the performance of the mass detection models by exploiting feature correlations.…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised Multi-graph-attention for Breast Cancer Detection

Ibrahim¹

2022

Preprint

View full text Add to dashboard Cite

<p>Mammography is the most widely used breast screening method for early detection and routine monitoring of breast cancer. Most mammogram classification or segmentation techniques are limited to simple binary classifications of the abnormalities in mammograms or classifying specific cropped regions. However, these methods encode merely the texture features of the X-ray-filmed lesions, despite the relationships and patterns. Thus, most of these models have inefficient learning capacities, hindered by supervised learning processes that require extensive annotated data, which is not feasible in the medical domain. To overcome these challenges, we model the deep texture and spatial features of every small segment of the mammogram in a complex multi-graph network.</p> <p>Moreover, we proposed a semi-supervised mammogram multi-graph attention network (MMGAT) to classify each element into all probabilistic categories. The attention and the dense relationships in the multi-graph network empower the proposed model with significant learning capacities, resulting in a competitive performance outperforming the recent state-of-the-art mammogram classification models. The proposed model can localise every abnormal segment of the mammogram and classify each as a malignant or benign region of a mass or calcification cancerous. The proposed MMGAT requires only 40\% of the data for training to achieve the highest AUC of 0.97 and an F1 score of 0.95 on the publically available DDSM.</p>

show abstract

Section: Related Workmentioning

confidence: 99%

Semi-supervised Multi-graph-attention for Breast Cancer Detection

Ibrahim¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Lesion detection from mammograms has been studied by Ribli et al (2018) and Dhungel et al (2015), who developed CAD sys- tems based on modern visual object detection methods. Ma et al (2021) implemented a relation network (Hu et al, 2018) to learn the inter-relationships between the region proposals from ipsi-lateral mammographic views. Yang et al (2020Yang et al ( , 2021 proposed a system that focused on the detection and classification of masses from mammograms by exploring complementary information from ipsilateral and bilateral mammographic views.…”

Section: Introductionmentioning

confidence: 99%

BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations

Chen¹,

Liu²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

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 weaklyand 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.

show abstract

“…Alternatively, Ma et al [13] implement a relation network [9] to learn the inter-relationships between the region proposals, which can be inaccurate and introduce noise that may lead to a poor learning process, and the lack of globallocal analysis may lead to sub-optimal performance. MommiNet-v2 [32] is a system focused on the detection and classification of masses from mammograms that explores cross-view information from ipsilateral and bilateral mammographic views, but its focus on the detection and classification of masses limits its performance on global classification that also considers other types of lesions, such as architectural distortions and calcification.…”

Section: Introductionmentioning

confidence: 99%

Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

Chen

Wang

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views. These multiple related images provide complementary diagnostic information and can improve the radiologist's classification accuracy. Unfortunately, most existing deep learning systems, trained with globallylabelled images, lack the ability to jointly analyse and integrate global and local information from these multiple views. By ignoring the potentially valuable information present in multiple images of a screening episode, one limits the potential accuracy of these systems.Here, we propose a new multi-view global-local analysis method that mimics the radiologist's reading procedure, based on a global consistency learning and local co-occurrence learning of ipsilateral views in mammograms. Extensive experiments show that our model outperforms competing methods, in terms of classification accuracy and generalisation, on a large-scale private dataset and two publicly available datasets, where models are exclusively trained and tested with global labels.

show abstract

Cross-View Relation Networks for Mammogram Mass Detection

Cited by 22 publications

References 17 publications

Semi-supervised Multi-graph-attention for Breast Cancer Detection

Semi-supervised Multi-graph-attention for Breast Cancer Detection

BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations

Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation

Contact Info

Product

Resources

About