Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification

Pang, Ting; Wong, Jeannie Hsiu Ding; Ng, Wei Lin; Chan, Chee Seng

doi:10.1016/j.cmpb.2021.106018

Cited by 96 publications

(56 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It has been recognised as both a productive and disruptive force in healthcare [1]. In particular, radiology, radiotherapy and pathology are the three medical specialities that saw the more prominent AI role [2][3][4][5]. Some clinicians may also view AI as a threat to the future of their medical practice [6].…”

Section: Introductionmentioning

confidence: 99%

The perceptions of medical physicists towards relevance and impact of artificial intelligence

et al. 2021

Self Cite

View full text Add to dashboard Cite

Arti cial intelligence (AI) is an innovative tool that is revolutionising healthcare and medical physics, possibly impacting clinical practices, research, and the profession. The relevance of AI and its impact on the clinical practice and routine of professionals in medical physics were evaluated by medical physicists and researchers in this eld. An online survey questionnaire was designed for distribution to professionals and students in medical physics around the world. In addition to demographics questions, we surveyed opinions on the role of AI in medical physicists' practice, the possibility of AI threatening/disrupting the medical physicists' practice and career, the need for medical physicists to acquire knowledge on AI, and the need for teaching AI in postgraduate medical physics programmes. The level of knowledge of medical physicists on AI was also consulted. A total of 1019 responders from 94 countries participated. More than 85% of the responders agree that AI will play an essential role in medical physicists' practice. AI should be taught in the postgraduate medical physics programmes, and that more applications such as quality control, treatment planning will be performed by AI. Half of them thought AI would not threaten/disrupt the medical physicists' practice. AI knowledge was mainly acquired through self-taught and work-related activities. Nonetheless, many (40%) admitted that they have no skill in AI. The general perception of medical physicists is that AI is here to stay, and it will in uence our practice. Medical physicists should be prepared with education and training for this new reality.

show abstract

Section: Introductionmentioning

confidence: 99%

The perceptions of medical physicists towards relevance and impact of artificial intelligence

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…The accuracy achieved was 95.48%. In [ 66 ], authors implemented a semi-supervised generative adversarial network (GAN) model and achieved an accuracy of 90.41%. The proposed method achieved an accuracy of 99.1% using a BUSi augmented dataset, where the computational time is 13.599 (s).…”

Section: Experimental Results and Analysismentioning

confidence: 99%

Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion

Jabeen

Khan

Alhaisoni

et al. 2022

Sensors

185

View full text Add to dashboard Cite

After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them.

show abstract

“…Another related work is [ 32 ] where they observed an increase in top-1 accuracy between 1% and 3% for a very few classes using ImageNet dataset and BigGAN architecture. Finally, in [ 36 ] they performed a comparison among several semi-supervised GAN-based data augmentation methods, but did not observe any improvement over classical data augmentation.…”

Section: Discussionmentioning

confidence: 99%

Generative Adversarial Networks to Improve Fetal Brain Fine-Grained Plane Classification

Montero

Bonet‐Carne

Burgos-Artizzu

2021

Sensors

View full text Add to dashboard Cite

Generative adversarial networks (GANs) have been recently applied to medical imaging on different modalities (MRI, CT, X-ray, etc). However there are not many applications on ultrasound modality as a data augmentation technique applied to downstream classification tasks. This study aims to explore and evaluate the generation of synthetic ultrasound fetal brain images via GANs and apply them to improve fetal brain ultrasound plane classification. State of the art GANs stylegan2-ada were applied to fetal brain image generation and GAN-based data augmentation classifiers were compared with baseline classifiers. Our experimental results show that using data generated by both GANs and classical augmentation strategies allows for increasing the accuracy and area under the curve score.

show abstract

Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification

Cited by 96 publications

References 24 publications

The perceptions of medical physicists towards relevance and impact of artificial intelligence

The perceptions of medical physicists towards relevance and impact of artificial intelligence

Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion

Generative Adversarial Networks to Improve Fetal Brain Fine-Grained Plane Classification

Contact Info

Product

Resources

About