DCGANs for Realistic Breast Mass Augmentation in X-ray Mammography

Alyafi, Basel; Díaz, Oliver; Martí, Robert

doi:10.48550/arxiv.1909.02062

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we conducted an observers study and analysed the distribution of the real and the generated patches to strengthen our argument in our previous application-driven work. 5 fake lesions real lesions…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, few papers shed a light over visualising the feature space of the generated images and/or reviewing specialists opinion. 3 In a previous work, 5 we used Deep Convolutional GANs 6 and proved that the generated synthetic images were effective in enhancing the classification process even in unbalanced conditions (where the class under study (positive) was minor to the normal (negative) class). In order to conduct an integrated study and to satisfy the requirements of image synthesis definition (realism and anatomic plausibility conditions) in Ref.…”

Section: Introductionmentioning

confidence: 94%

See 1 more Smart Citation

Quality analysis of DCGAN-generated mammography lesions

Alyafi

Díaz

Elangovan

et al. 2020

15th International Workshop on Breast Imaging (IWBI2020)

Self Cite

View full text Add to dashboard Cite

Medical image synthesis has gained a great focus recently, especially after the introduction of Generative Adversarial Networks (GANs). GANs have been used widely to provide anatomically-plausible and diverse samples for augmentation and other applications, including segmentation and super resolution. In our previous work, Deep Convolutional GANs were used to generate synthetic mammogram lesions, masses mainly, that could enhance the classification performance in imbalanced datasets. In this new work, a deeper investigation was carried out to explore other aspects of the generated images evaluation, i.e., realism, feature space distribution, and observers studies. t-Stochastic Neighbor Embedding (t-SNE) was used to reduce the dimensionality of real and fake images to enable 2D visualisations. Additionally, two expert radiologists performed a realism-evaluation study. Visualisations showed that the generated images have a similar feature distribution of the real ones, avoiding outliers. Moreover, Receiver Operating Characteristic (ROC) curve showed that the radiologists could not, in many cases, distinguish between synthetic and real lesions, giving 48% and 61% accuracies in a balanced sample set.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%