Injecting and removing suspicious features in breast imaging with CycleGAN: A pilot study of automated adversarial attacks using neural networks on small images

Becker, Anton S.; Jendele, Lukáš; Skopek, Ondrej; Berger, Nicole; Ghafoor, Soleen; Marcon, Magda; Konukoğlu, Ender

doi:10.1016/j.ejrad.2019.108649

Cited by 28 publications

(24 citation statements)

References 21 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, supervised learning, such as Inception V3, and unsupervised learning, such as deep belief networks and autoencoders, have repeatedly been utilised in the early diagnosis of Alzheimer's disease [17][18][19]. Additionally, tasks of segmentation and prognosis have increased in DL studies alongside classification tasks, and the use of generative adversarial networks (GANs) are now more frequently reported [20,21].…”

Section: Introductionmentioning

confidence: 99%

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Wang

Huang

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

To evaluate the general rules and future trajectories of deep learning (DL) networks in medical image analysis through bibliometric and hot spot analysis of original articles published between 2012 and 2020. Methods: Original articles related to DL and medical imaging were retrieved from the PubMed database. For the analysis, data regarding radiological subspecialties; imaging techniques; DL networks; sample size; study purposes, setting, origins and design; statistical analysis; funding sources; authors; and first authors' affiliation was manually extracted from each article. The Bibliographic Item Co-Occurrence Matrix Builder and VOSviewer were used to identify the research topics of the included articles and illustrate the future trajectories of studies.Results: The study included 2685 original articles. The number of publications on DL and medical imaging has increased substantially since 2017, accounting for 97.2% of all included articles. We evaluated the rules of the application of 47 DL networks to eight radiological tasks on 11 human organ sites. Neuroradiology, thorax, and abdomen were frequent research subjects, while thyroid was under-represented. Segmentation and classification tasks were the primary purposes. U-Net, ResNet, and VGG were the most frequently used Convolutional neural network-derived networks. GAN-derived networks were widely developed and applied in 2020, and transfer learning was highlighted in the COVID-19 studies. Brain, prostate, and diabetic retinopathy-related studies were mature research topics in the field. Breast-and lung-related studies were in a stage of rapid development.Conclusions: This study evaluates the general rules and future trajectories of DL network application in medical image analyses and provides guidance for future studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Wang

Huang

et al. 2022

European Journal of Radiology

View full text Add to dashboard Cite

show abstract

“…This technique learns two mappings by transforming images between two different domains using two GANS and maintains their reconstruction by a cycle-consistency loss and hence the name. In fact, CycleGAN was adopted by Becker et al 48 in order to artificially inject or remove suspicious features and thus increase the size of the BCDR and INbreast datasets. Moreover, a cross-modality synthesis approach was introduced by Cai et al 49 , it was inspired by CycleGAN between CT and magnetic resonance images (MRI) and it was applied on 2D/3D images for segmentation.…”

Section: Methodsmentioning

confidence: 99%

Connected-UNets: a deep learning architecture for breast mass segmentation

et al. 2021

View full text Add to dashboard Cite

Breast cancer analysis implies that radiologists inspect mammograms to detect suspicious breast lesions and identify mass tumors. Artificial intelligence techniques offer automatic systems for breast mass segmentation to assist radiologists in their diagnosis. With the rapid development of deep learning and its application to medical imaging challenges, UNet and its variations is one of the state-of-the-art models for medical image segmentation that showed promising performance on mammography. In this paper, we propose an architecture, called Connected-UNets, which connects two UNets using additional modified skip connections. We integrate Atrous Spatial Pyramid Pooling (ASPP) in the two standard UNets to emphasize the contextual information within the encoder–decoder network architecture. We also apply the proposed architecture on the Attention UNet (AUNet) and the Residual UNet (ResUNet). We evaluated the proposed architectures on two publically available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Experiments were also conducted using additional synthetic data using the cycle-consistent Generative Adversarial Network (CycleGAN) model between two unpaired datasets to augment and enhance the images. Qualitative and quantitative results show that the proposed architecture can achieve better automatic mass segmentation with a high Dice score of 89.52%, 95.28%, and 95.88% and Intersection over Union (IoU) score of 80.02%, 91.03%, and 92.27%, respectively, on CBIS-DDSM, INbreast, and the private dataset.

show abstract

“…Types of failures in the image generations are also reported in the paper. A system to insert and remove malignant features on mammograms was proposed by Becker et al [133]. In their work, Becker et al further determined whether human expert readers can easily understand whether the images were AI-generated.…”

Section: Generative Adversarial Network (Gan)mentioning

confidence: 99%

“…Korkinof et al [134] opted for GAN to generate mammogram images, but they did not provide benchmarks for comparisons to other state-of-the-art techniques. The same consideration goes for CycleGAN, adopted by Becker et al [133] for mammogram synthesis. Sparse autoencoders are used by Yang et al [136] to analyse breast asymmetries (sensitivity 97%) on a local dataset.…”

Section: Pros and Cons Of Deep Learning Approachesmentioning

confidence: 99%

See 1 more Smart Citation

A Bottom-Up Review of Image Analysis Methods for Suspicious Region Detection in Mammograms

et al. 2021

View full text Add to dashboard Cite

Breast cancer is one of the most common death causes amongst women all over the world. Early detection of breast cancer plays a critical role in increasing the survival rate. Various imaging modalities, such as mammography, breast MRI, ultrasound and thermography, are used to detect breast cancer. Though there is a considerable success with mammography in biomedical imaging, detecting suspicious areas remains a challenge because, due to the manual examination and variations in shape, size, other mass morphological features, mammography accuracy changes with the density of the breast. Furthermore, going through the analysis of many mammograms per day can be a tedious task for radiologists and practitioners. One of the main objectives of biomedical imaging is to provide radiologists and practitioners with tools to help them identify all suspicious regions in a given image. Computer-aided mass detection in mammograms can serve as a second opinion tool to help radiologists avoid running into oversight errors. The scientific community has made much progress in this topic, and several approaches have been proposed along the way. Following a bottom-up narrative, this paper surveys different scientific methodologies and techniques to detect suspicious regions in mammograms spanning from methods based on low-level image features to the most recent novelties in AI-based approaches. Both theoretical and practical grounds are provided across the paper sections to highlight the pros and cons of different methodologies. The paper’s main scope is to let readers embark on a journey through a fully comprehensive description of techniques, strategies and datasets on the topic.

show abstract

Injecting and removing suspicious features in breast imaging with CycleGAN: A pilot study of automated adversarial attacks using neural networks on small images

Cited by 28 publications

References 21 publications

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

Connected-UNets: a deep learning architecture for breast mass segmentation

A Bottom-Up Review of Image Analysis Methods for Suspicious Region Detection in Mammograms

Contact Info

Product

Resources

About