Latent feature representation with 3-D multi-view deep convolutional neural network for bilateral analysis in digital breast tomosynthesis

Kim, Dae Hoe; Kim, Seong-Tae; Ro, Yong Man

doi:10.1109/icassp.2016.7471811

Cited by 32 publications

(24 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the performance of various methods on automated DBT mass detection at aspects of the classifier used, DBT dataset size, Sen, Acc, and AUC in Table 5, our network achieve quite a competitive result than some of them. Among these models, we will discuss in detail the research works by Kim et al [31], Fotin et al [32], and Samala et al [33], which applied deep learning methods to DBT mass detection and segmentation. eir works evaluated the DBT mass automatic segmentation CAD frameworks, which are based on both hand-crafted feature and deep convolutional neural network (DCNN)-based models.…”

Section: Discussionmentioning

confidence: 99%

“…e results of the DCNN model have shown the AUC of over 80% and the 80% Sen. Fotin et al [32] have developed a CAD framework of the DBT mass detection using a DCNN that is trained on the generated candidate region of interest (ROIs), which contains 1864 breast lesions in the mammography and 339 breast lesions from the DBT images data. It is reported that their model achieved an Acc of 86.40% and 89% Sen. e latent bilateral feature representations of masses in reconstructed DBT volumes o are classified with the DCNN model proposed by Kim et al [31], in which low-level features are [18], and Schie et al [17]. Chan et al [15] introduce three methods based on 2D and 3D, and the hybrid that combines 2D and 3D.…”

Section: Discussionmentioning

confidence: 99%

“…ese predictions are then fused into the final image label using one of the following three voting schemes. e first three (Majority voting, Maximum probability, and Sum of probabilities) are also used and compared [31], whereas the other one (Connectivity) is proposed by us. Our motivation behind this voting schemes is to reinforce spatial consistency between votes of patches because in reality the true image label is likely to be assigned based on the structure of a particular connected region of the tissue rather than on many disconnected bits.…”

mentioning

confidence: 99%

See 2 more Smart Citations

DBT Masses Automatic Segmentation Using U-Net Neural Networks

Lai

Yang

2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

To improve the automatic segmentation accuracy of breast masses in digital breast tomosynthesis (DBT) images, we propose a DBT mass automatic segmentation algorithm by using a U-Net architecture. Firstly, to suppress the background tissue noise and enhance the contrast of the mass candidate regions, after the top-hat transform of DBT images, a constraint matrix is constructed and multiplied with the DBT image. Secondly, an efficient U-Net neural network is built and image patches are extracted before data augmentation to establish the training dataset to train the U-Net model. And then the presegmentation of the DBT tumors is implemented, which initially classifies per pixel into two different types of labels. Finally, all regions smaller than 50 voxels considered as false positives are removed, and the median filter smoothes the mass boundaries to obtain the final segmentation results. The proposed method can effectively improve the performance in the automatic segmentation of the masses in DBT images. Using the detection Accuracy (Acc), Sensitivity (Sen), Specificity (Spe), and area under the curve (AUC) as evaluation indexes, the Acc, Sen, Spe, and AUC for DBT mass segmentation in the entire experimental dataset is 0.871, 0.869, 0.882, and 0.859, respectively. Our proposed U-Net-based DBT mass automatic segmentation system obtains promising results, which is superior to some classical architectures, and may be expected to have clinical application prospects.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

DBT Masses Automatic Segmentation Using U-Net Neural Networks

Lai

Yang

2020

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Dhungel et al proposed another model using the cascade of random forest classifiers and deep learning for mass detection in another paper [138]. A 3D multi-view model for the learning of bilateral features from digital breast tomosynthesis (DBT) was proposed in [88]. From the source volume, they obtained the volume of interest (VOI), which was treated as a separate input than the VOI in the registered target.…”

Section: Models and Algorithmsmentioning

confidence: 99%

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

Munir

Elahi

Ayub

et al. 2019

Cancers

344

182

View full text Add to dashboard Cite

In this paper, we first describe the basics of the field of cancer diagnosis, which includes steps of cancer diagnosis followed by the typical classification methods used by doctors, providing a historical idea of cancer classification techniques to the readers. These methods include Asymmetry, Border, Color and Diameter (ABCD) method, seven-point detection method, Menzies method, and pattern analysis. They are used regularly by doctors for cancer diagnosis, although they are not considered very efficient for obtaining better performance. Moreover, considering all types of audience, the basic evaluation criteria are also discussed. The criteria include the receiver operating characteristic curve (ROC curve), Area under the ROC curve (AUC), F1 score, accuracy, specificity, sensitivity, precision, dice-coefficient, average accuracy, and Jaccard index. Previously used methods are considered inefficient, asking for better and smarter methods for cancer diagnosis. Artificial intelligence and cancer diagnosis are gaining attention as a way to define better diagnostic tools. In particular, deep neural networks can be successfully used for intelligent image analysis. The basic framework of how this machine learning works on medical imaging is provided in this study, i.e., pre-processing, image segmentation and post-processing. The second part of this manuscript describes the different deep learning techniques, such as convolutional neural networks (CNNs), generative adversarial models (GANs), deep autoencoders (DANs), restricted Boltzmann’s machine (RBM), stacked autoencoders (SAE), convolutional autoencoders (CAE), recurrent neural networks (RNNs), long short-term memory (LTSM), multi-scale convolutional neural network (M-CNN), multi-instance learning convolutional neural network (MIL-CNN). For each technique, we provide Python codes, to allow interested readers to experiment with the cited algorithms on their own diagnostic problems. The third part of this manuscript compiles the successfully applied deep learning models for different types of cancers. Considering the length of the manuscript, we restrict ourselves to the discussion of breast cancer, lung cancer, brain cancer, and skin cancer. The purpose of this bibliographic review is to provide researchers opting to work in implementing deep learning and artificial neural networks for cancer diagnosis a knowledge from scratch of the state-of-the-art achievements.

show abstract

“…Deep learning approaches have achieved impressive accuracies in computer-aided detection (CADe) and computer-aided diagnosis (CADx) on various modalities. 12,13,15 The use of the current deep learning approaches for CADx in real world is limited due to the lack of interpretability. So, the interpretability of the decisions made by the deep learning approach needs to be investigated for real world deployment.…”

Section: Introductionmentioning

confidence: 99%

ICADx: interpretable computer aided diagnosis of breast masses

Kim

Lee

Kim

et al. 2018

Medical Imaging 2018: Computer-Aided Diagnosis

Self Cite

View full text Add to dashboard Cite

In this study, a novel computer aided diagnosis (CADx) framework is devised to investigate interpretability for classifying breast masses. Recently, a deep learning technology has been successfully applied to medical image analysis including CADx. Existing deep learning based CADx approaches, however, have a limitation in explaining the diagnostic decision. In real clinical practice, clinical decisions could be made with reasonable explanation. So current deep learning approaches in CADx are limited in real world deployment. In this paper, we investigate interpretability in CADx with the proposed interpretable CADx (ICADx) framework. The proposed framework is devised with a generative adversarial network, which consists of interpretable diagnosis network and synthetic lesion generative network to learn the relationship between malignancy and a standardized description (BI-RADS). The lesion generative network and the interpretable diagnosis network compete in an adversarial learning so that the two networks are improved. The effectiveness of the proposed method was validated on public mammogram database. Experimental results showed that the proposed ICADx framework could provide the interpretability of mass as well as mass classification. It was mainly attributed to the fact that the proposed method was effectively trained to find the relationship between malignancy and interpretations via the adversarial learning. These results imply that the proposed ICADx framework could be a promising approach to develop the CADx system.

show abstract

Latent feature representation with 3-D multi-view deep convolutional neural network for bilateral analysis in digital breast tomosynthesis

Cited by 32 publications

References 16 publications

DBT Masses Automatic Segmentation Using U-Net Neural Networks

DBT Masses Automatic Segmentation Using U-Net Neural Networks

Cancer Diagnosis Using Deep Learning: A Bibliographic Review

ICADx: interpretable computer aided diagnosis of breast masses

Contact Info

Product

Resources

About