scholarly journals A generative adversarial network-based abnormality detection using only normal images for model training with application to digital breast tomosynthesis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Albert Swiecicki ◽  
Nicholas Konz ◽  
Mateusz Buda ◽  
Maciej A. Mazurowski

AbstractDeep learning has shown tremendous potential in the task of object detection in images. However, a common challenge with this task is when only a limited number of images containing the object of interest are available. This is a particular issue in cancer screening, such as digital breast tomosynthesis (DBT), where less than 1% of cases contain cancer. In this study, we propose a method to train an inpainting generative adversarial network to be used for cancer detection using only images that do not contain cancer. During inference, we removed a part of the image and used the network to complete the removed part. A significant error in completing an image part was considered an indication that such location is unexpected and thus abnormal. A large dataset of DBT images used in this study was collected at Duke University. It consisted of 19,230 reconstructed volumes from 4348 patients. Cancerous masses and architectural distortions were marked with bounding boxes by radiologists. Our experiments showed that the locations containing cancer were associated with a notably higher completion error than the non-cancer locations (mean error ratio of 2.77). All data used in this study has been made publicly available by the authors.

Author(s):  
Suzanne L. van Winkel ◽  
Alejandro Rodríguez-Ruiz ◽  
Linda Appelman ◽  
Albert Gubern-Mérida ◽  
Nico Karssemeijer ◽  
...  

Abstract Objectives Digital breast tomosynthesis (DBT) increases sensitivity of mammography and is increasingly implemented in breast cancer screening. However, the large volume of images increases the risk of reading errors and reading time. This study aims to investigate whether the accuracy of breast radiologists reading wide-angle DBT increases with the aid of an artificial intelligence (AI) support system. Also, the impact on reading time was assessed and the stand-alone performance of the AI system in the detection of malignancies was compared to the average radiologist. Methods A multi-reader multi-case study was performed with 240 bilateral DBT exams (71 breasts with cancer lesions, 70 breasts with benign findings, 339 normal breasts). Exams were interpreted by 18 radiologists, with and without AI support, providing cancer suspicion scores per breast. Using AI support, radiologists were shown examination-based and region-based cancer likelihood scores. Area under the receiver operating characteristic curve (AUC) and reading time per exam were compared between reading conditions using mixed-models analysis of variance. Results On average, the AUC was higher using AI support (0.863 vs 0.833; p = 0.0025). Using AI support, reading time per DBT exam was reduced (p < 0.001) from 41 (95% CI = 39–42 s) to 36 s (95% CI = 35– 37 s). The AUC of the stand-alone AI system was non-inferior to the AUC of the average radiologist (+0.007, p = 0.8115). Conclusions Radiologists improved their cancer detection and reduced reading time when evaluating DBT examinations using an AI reading support system. Key Points • Radiologists improved their cancer detection accuracy in digital breast tomosynthesis (DBT) when using an AI system for support, while simultaneously reducing reading time. • The stand-alone breast cancer detection performance of an AI system is non-inferior to the average performance of radiologists for reading digital breast tomosynthesis exams. • The use of an AI support system could make advanced and more reliable imaging techniques more accessible and could allow for more cost-effective breast screening programs with DBT.


2020 ◽  
Vol 34 (05) ◽  
pp. 8830-8837
Author(s):  
Xin Sheng ◽  
Linli Xu ◽  
Junliang Guo ◽  
Jingchang Liu ◽  
Ruoyu Zhao ◽  
...  

We propose a novel introspective model for variational neural machine translation (IntroVNMT) in this paper, inspired by the recent successful application of introspective variational autoencoder (IntroVAE) in high quality image synthesis. Different from the vanilla variational NMT model, IntroVNMT is capable of improving itself introspectively by evaluating the quality of the generated target sentences according to the high-level latent variables of the real and generated target sentences. As a consequence of introspective training, the proposed model is able to discriminate between the generated and real sentences of the target language via the latent variables generated by the encoder of the model. In this way, IntroVNMT is able to generate more realistic target sentences in practice. In the meantime, IntroVNMT inherits the advantages of the variational autoencoders (VAEs), and the model training process is more stable than the generative adversarial network (GAN) based models. Experimental results on different translation tasks demonstrate that the proposed model can achieve significant improvements over the vanilla variational NMT model.


2019 ◽  
Vol 1 (2) ◽  
pp. 122-126
Author(s):  
Sarah M Friedewald ◽  
Sonya Bhole ◽  
Lilian Wang ◽  
Dipti Gupta

Abstract Digital breast tomosynthesis (DBT) is rapidly becoming the standard of care for breast cancer screening. Implementing DBT into practice is relatively straightforward. However, there are important elements of the transition that one must consider to facilitate this process. Understanding the Digital Imaging and Communications in Medicine (DICOM) standard for DBT, as well as how images are displayed, is critical to a successful transition. Standardization of these processes will allow easier transmission of images from facility to facility, and limit the potential for errors in interpretation. Additionally, recent changes in federal regulations will require compliance with mandated training for the radiologist, technologist, and physicist, as well as accreditation for each DBT unit. These regulations aim to ensure high-quality imaging across the country as has been previously seen with standard digital mammography. Synthesized imaging is the most recent improvement for DBT, potentially obviating the need for a simultaneous traditional digital mammogram exposure. Studies have demonstrated near equivalent performance when comparing the combination imaging of DBT and digital mammography versus DBT combined with synthetic imaging. As the quality of the synthetic images continues to improve, it is increasingly likely that it will replace the traditional mammogram. Adherence to DBT-specific parameters will enhance the physician experience and ultimately translate to increased cancer detection and fewer false positive examinations, benefiting all women who are screened for breast cancer.


Radiology ◽  
2016 ◽  
Vol 278 (3) ◽  
pp. 698-706 ◽  
Author(s):  
Richard E. Sharpe ◽  
Shambavi Venkataraman ◽  
Jordana Phillips ◽  
Vandana Dialani ◽  
Valerie J. Fein-Zachary ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document