Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection

Liu, Yuhang; Zhang, Fandong; Wang, Siwen; Wang, Yizhou; Yu, Yizhou

doi:10.1109/cvpr42600.2020.00387

Cited by 51 publications

(30 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper substantially extends our conference paper [21] from four major aspects. (1) Besides utilizing ipsilateral views [21], our AGN further considers the complementary effect of bilateral views to learn intact multi-view information of mammogram, which helps to make more comprehensive and precise clinical decisions. Specifically, we propose a novel inception graph convolutional network for modeling the structural similarities of bilateral views.…”

Section: Introductionsupporting

confidence: 56%

See 1 more Smart Citation

Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection

Liu¹,

Zhang

Chen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Mammogram mass detection is crucial for diagnosing and preventing the breast cancers in clinical practice. The complementary effect of multi-view mammogram images provides valuable information about the breast anatomical prior structure and is of great significance in digital mammography interpretation. However, unlike radiologists who can utilize the natural reasoning ability to identify masses based on multiple mammographic views, how to endow the existing object detection models with the capability of multi-view reasoning is vital for decision-making in clinical diagnosis but remains the boundary to explore. In this paper, we propose an Anatomy-aware Graph convolutional Network (AGN), which is tailored for mammogram mass detection and endows existing detection methods with multi-view reasoning ability. The proposed AGN consists of three steps. Firstly, we introduce a Bipartite Graph convolutional Network (BGN) to model the intrinsic geometric and semantic relations of ipsilateral views. Secondly, considering that the visual asymmetry of bilateral views is widely adopted in clinical practice to assist the diagnosis of breast lesions, we propose an Inception Graph convolutional Network (IGN) to model the structural similarities of bilateral views. Finally, based on the constructed graphs, the multi-view information is propagated through nodes methodically, which equips the features learned from the examined view with multi-view reasoning ability. Experiments on two standard benchmarks reveal that AGN significantly exceeds the state-of-the-art performance. Visualization results show that AGN provides interpretable visual cues for clinical diagnosis.

show abstract

Section: Introductionsupporting

confidence: 56%

“…Table 1 and Table 2 display the experimental results on DDSM dataset. Baseline results in Table 1 are cited from their original papers [5], [21], [74], [75], [76]. In Table 2, we re-implemented the baseline methods in our experiments.…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection

Liu¹,

Zhang

Chen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Both pre-training tasks are implemented using the openmmlab toolbox 1 . Stochastic Gradient Descent (SGD) with a momentum of 0.9 and weight decay of 0.0001 is adopted as the optimizer.…”

Section: Methodsmentioning

confidence: 99%

“…With the rapid advancement of deep learning techniques, fast and accurate medical image analysis systems have emerged as an instrumental tool for routine clinical practice. These systems have been deployed with the objectives of improving efficiency and accuracy in a variety of applications, including but not limited to assisting radiologists in image interpretation with automatic lesion detection [1], [2], improving the accuracy of prognostic evaluation or disease triage with image classification [3]- [5], and improving the efficiency and accuracy of target area delineation in radiotherapy with automatic target area segmentation [6], [7]. Deep learning algorithms show promising results in the medical field, similar to their success on natural images; nevertheless, large-scale annotated medical image datasets are still required to develop deep learning models further.…”

Section: Introductionmentioning

confidence: 99%

Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training

Zhang¹,

Li²,

Zhou³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications. As a result, constructing high-performance 3D convolutional neural networks from scratch remains a difficult task in the absence of a sufficient pre-training parameter. Previous efforts on 3D pre-training have frequently relied on selfsupervised approaches, which use either predictive or contrastive learning on unlabeled data to build invariant 3D representations. However, because of the unavailability of large-scale supervision information, obtaining semantically invariant and discriminative representations from these learning frameworks remains problematic. In this paper, we revisit an innovative yet simple fully-supervised 3D network pre-training framework to take advantage of semantic supervisions from large-scale 2D natural image datasets. With a redesigned 3D network architecture, reformulated natural images are used to address the problem of data scarcity and develop powerful 3D representations. Comprehensive experiments on four benchmark datasets demonstrate that the proposed pre-trained models can effectively accelerate convergence while also improving accuracy for a variety of 3D medical imaging tasks such as classification, segmentation and detection. In addition, as compared to training from scratch, it can save up to 60% of annotation efforts. On the NIH DeepLesion dataset, it likewise achieves state-ofthe-art detection performance, outperforming earlier selfsupervised and fully-supervised pre-training approaches, as well as methods that do training from scratch. To facilitate further development of 3D medical models, our code and pre-trained model weights are publicly available at https://github.com/urmagicsmine/CSPR.

show abstract

“…Compared with traditional breast mass classification methods, deep learning can automatically extract discriminative features from mammographic images and avoid the problem of poor discriminative ability of features using the manual design feature extraction method. We cited the experimental results in the works of literatures for Eltonsy [ 26 ], Sampat [ 37 ], Wu [ 38 ], Junior [ 39 ], Liu [ 40 ] and Cao [ 41 ] in Table 1 . RetinaNet [ 42 ], FSAF [ 43 ], Foveabox [ 44 ] and our method in Table 1 are evaluated on the subset used in this paper.…”

Section: Methodsmentioning

confidence: 99%

Breast Mass Detection in Mammography Based on Image Template Matching and CNN

Sun

Wang

et al. 2021

Sensors

View full text Add to dashboard Cite

In recent years, computer vision technology has been widely used in the field of medical image processing. However, there is still a big gap between the existing breast mass detection methods and the real-world application due to the limited detection accuracy. It is known that humans locate the regions of interest quickly and further identify whether these regions are the targets we found. In breast cancer diagnosis, we locate all the potential regions of breast mass by glancing at the mammographic image from top to bottom and from left to right, then further identify whether these regions are a breast mass. Inspired by the process of human detection of breast mass, we proposed a novel breast mass detection method to detect breast mass on a mammographic image by stimulating the process of human detection. The proposed method preprocesses the mammographic image via the mathematical morphology method and locates the suspected regions of breast mass by the image template matching method. Then, it obtains the regions of breast mass by classifying these suspected regions into breast mass and background categories using a convolutional neural network (CNN). The bounding box of breast mass obtained by the mathematical morphology method and image template matching method are roughly due to the mathematical morphology method, which transforms all of the brighter regions into approximate circular areas. For regression of a breast mass bounding box, the optimal solution should be searched in the feasible region and the Particle Swarm Optimization (PSO) is suitable for solving the problem of searching the optimal solution within a certain range. Therefore, we refine the bounding box of breast mass by the PSO algorithm. The proposed breast mass detection method and the compared detection methods were evaluated on the open database Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed method is superior to all of the compared detection methods in detection performance.

show abstract

Cross-View Correspondence Reasoning Based on Bipartite Graph Convolutional Network for Mammogram Mass Detection

Cited by 51 publications

References 48 publications

Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection

Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection

Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training

Breast Mass Detection in Mammography Based on Image Template Matching and CNN

Contact Info

Product

Resources

About