scholarly journals A machine and human reader study on AI diagnosis model safety under attacks of adversarial images

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Qianwei Zhou ◽  
Margarita Zuley ◽  
Yuan Guo ◽  
Lu Yang ◽  
Bronwyn Nair ◽  
...  
Keyword(s):  
Breast Imaging ◽  
Model Development ◽  
Cad Model ◽  
Generative Adversarial Network ◽  
Safety Issues ◽  
Adversarial Network ◽  
Wrong Diagnosis ◽  
Diagnosis Model ◽  
Aided Diagnosis ◽  
Mammogram Images

AbstractWhile active efforts are advancing medical artificial intelligence (AI) model development and clinical translation, safety issues of the AI models emerge, but little research has been done. We perform a study to investigate the behaviors of an AI diagnosis model under adversarial images generated by Generative Adversarial Network (GAN) models and to evaluate the effects on human experts when visually identifying potential adversarial images. Our GAN model makes intentional modifications to the diagnosis-sensitive contents of mammogram images in deep learning-based computer-aided diagnosis (CAD) of breast cancer. In our experiments the adversarial samples fool the AI-CAD model to output a wrong diagnosis on 69.1% of the cases that are initially correctly classified by the AI-CAD model. Five breast imaging radiologists visually identify 29%-71% of the adversarial samples. Our study suggests an imperative need for continuing research on medical AI model’s safety issues and for developing potential defensive solutions against adversarial attacks.

scholarly journals MAGAN: Mask Attention Generative Adversarial Network for Liver Tumor CT Image Synthesis

2020 ◽  
Author(s):  
Yang Liu ◽  
Lu Meng ◽  
Jianping Zhong
Keyword(s):  
Liver Tumor ◽  
Medical Image ◽  
Ct Images ◽  
Computer Aided Diagnosis ◽  
Generative Adversarial Network ◽  
Liver Ct ◽  
Adversarial Network ◽  
Computer Aided ◽  
Image Dataset ◽  
Aided Diagnosis

Abstract Background: For deep learning, the size of the dataset greatly affects the final training effect. However, in the field of computer-aided diagnosis, medical image datasets are often limited and even scarce.Methods: We aim to synthesize medical images and enlarge the size of the medical image dataset. In the present study, we synthesized the liver CT images with a tumor based on the mask attention generative adversarial network (MAGAN). We masked the pixels of the liver tumor in the image as the attention map. And both the original image and attention map were loaded into the generator network to obtain the synthesized images. Then the original images, the attention map, and the synthesized images were all loaded into the discriminator network to determine if the synthesized images were real or fake. Finally, we can use the generator network to synthesize liver CT images with a tumor.Results: The experiments showed that our method outperformed the other state-of-the-art methods, and can achieve a mean peak signal-to-noise ratio (PSNR) as 64.72dB.Conclusions: All these results indicated that our method can synthesize liver CT images with tumor, and build large medical image dataset, which may facilitate the progress of medical image analysis and computer-aided diagnosis.

Effect of GLCM Texture Features on the Medio-Lateral Oblique (MLO) View of Digital Mammograms for Breast Cancer Detection

2020 ◽  
Vol 9 (2) ◽  
pp. 25-44
Author(s):  
Usha N. ◽  
Sriraam N. ◽  
Kavya N. ◽  
Bharathi Hiremath ◽  
Anupama K Pujar ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Classification Accuracy ◽  
Breast Imaging ◽  
Texture Features ◽  
Support Vector ◽  
Risk Of Death ◽  
Automated Method ◽  
Occurrence Matrix ◽  
Aided Diagnosis ◽  
Mammogram Images

Breast cancer is one among the most common cancers in women. The early detection of breast cancer reduces the risk of death. Mammograms are an efficient breast imaging technique for breast cancer screening. Computer aided diagnosis (CAD) systems reduce manual errors and helps radiologists to analyze the mammogram images. The mammogram images are typically in two views, cranial-caudal (CC) and medio lateral oblique (MLO) views. MLO contains pectoral muscles (chest muscles) at the upper right or left corner of the image. In this study, it was removed by using a semi-automated method. All the normal and abnormal images were filtered and enhanced to improve the quality. GLCM (Gray Level Co-occurrence Matrix) texture features were extracted and analyzed by changing the number of features in a feature set. Linear Support Vector Machine (LSVM) was used as classifier. The classification accuracy was improved as the number of features in GLCM feature set increases. Simulation results show an overall classification accuracy of 96.7% with 19 GLCM features using SVM classifiers.

scholarly journals The Establishment of Transformer-Based Computer-Aided Diagnosis Model to Improve the Classification Consistency of BI-RADS-US3–5 Nodules Among Radiologists: A Multi-Center Study

2021 ◽  
Author(s):  
Hongtao Ji ◽  
Qiang Zhu ◽  
Teng Ma ◽  
Yun Cheng ◽  
Shuai Zhou ◽  
...  
Keyword(s):  
Breast Imaging ◽  
Computer Aided Diagnosis ◽  
Image Features ◽  
Cad Model ◽  
Data Systems ◽  
Test Set ◽  
Classification Consistency ◽  
Computer Aided ◽  
Sensitivity Specificity ◽  
Aided Diagnosis

Abstract Background: Significant differences exist in classification outcomes for radiologists using ultrasonography-based breast imaging-reporting and data systems for diagnosing category 3–5 (BI-RADS-US 3–5) breast nodules, due to a lack of clear and distinguishing image features. As such, this study investigates the use of a transformer-based computer-aided diagnosis (CAD) model for improved BI-RADS-US 3–5 classification consistency.Methods: Five radiologists independently performed BI-RADS-US annotations on a breast ultrasonography image set collected from 20 hospitals in China. The data were divided into training, validation, testing, and sampling sets. The trained transformer-based CAD model was then used to classify test images, for which sensitivity, specificity, and accuracy were calculated. Variations in these metrics among the 5 radiologists were analyzed by referencing BI-RADS-US classification results for the sampling test set, provided by CAD, to determine whether classification consistency (the kappa value)，sensitivity, specificity, and accuracy had improved.Results: Classification accuracy for the CAD model applied to the test set was 95.7% for category 3 nodules, 97.6% for category 4A nodules, 95.60% for category 4B nodules, 94.2% for category 4C nodules, and 97.5% for category 5 nodules. Adjustments were made to 1,583 nodules, as 905 were classified to a higher category and 678 to a lower category in the sampling test set. As a result, the accuracy, sensitivity, and specificity of classification by each radiologist improved, with the consistency (kappa values) for all radiologists increasing to >0.60.Conclusions: The proposed transformer-based CAD model improved BI-RADS-US 3–5 nodule classification by individual radiologists and increased diagnostic consistency.

scholarly journals A Method of Offline Reinforcement Learning Virtual Reality Satellite Attitude Control Based on Generative Adversarial Network

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Jian Zhang ◽  
Fengge Wu
Keyword(s):  
Virtual Reality ◽  
Reinforcement Learning ◽  
Real World ◽  
Attitude Control ◽  
Control Method ◽  
Sensor Data ◽  
Generative Adversarial Network ◽  
Goal State ◽  
Safety Issues ◽  
Adversarial Network

Virtual reality satellites give people an immersive experience of exploring space. The intelligent attitude control method using reinforcement learning to achieve multiaxis synchronous control is one of the important tasks of virtual reality satellites. In real-world systems, methods based on reinforcement learning face safety issues during exploration, unknown actuator delays, and noise in the raw sensor data. To improve the sample efficiency and avoid safety issues during exploration, this paper proposes a new offline reinforcement learning method to make full use of samples. This method learns a policy set with imitation learning and a policy selector using a generative adversarial network (GAN). The performance of the proposed method was verified in a real-world system (reaction-wheel-based inverted pendulum). The results showed that the agent trained with our method reached and maintained a stable goal state in 10,000 steps, whereas the behavior cloning method only remained stable for 500 steps.

scholarly journals MAGAN: Mask Attention Generative Adversarial Network for Liver Tumor CT Image Synthesis

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Yang Liu ◽  
Lu Meng ◽  
Jianping Zhong
Keyword(s):  
Liver Tumor ◽  
Medical Image ◽  
Ct Images ◽  
Computer Aided Diagnosis ◽  
Generative Adversarial Network ◽  
Liver Ct ◽  
Adversarial Network ◽  
Computer Aided ◽  
Image Dataset ◽  
Aided Diagnosis

For deep learning, the size of the dataset greatly affects the final training effect. However, in the field of computer-aided diagnosis, medical image datasets are often limited and even scarce. We aim to synthesize medical images and enlarge the size of the medical image dataset. In the present study, we synthesized the liver CT images with a tumor based on the mask attention generative adversarial network (MAGAN). We masked the pixels of the liver tumor in the image as the attention map. And both the original image and attention map were loaded into the generator network to obtain the synthesized images. Then, the original images, the attention map, and the synthesized images were all loaded into the discriminator network to determine if the synthesized images were real or fake. Finally, we can use the generator network to synthesize liver CT images with a tumor. The experiments showed that our method outperformed the other state-of-the-art methods and can achieve a mean peak signal-to-noise ratio (PSNR) of 64.72 dB. All these results indicated that our method can synthesize liver CT images with a tumor and build a large medical image dataset, which may facilitate the progress of medical image analysis and computer-aided diagnosis. An earlier version of our study has been presented as a preprint in the following link: https://www.researchsquare.com/article/rs-41685/v1.

ORGANIC (1).pdf

2017 ◽  
Author(s):  
Benjamin Sanchez-Lengeling ◽  
Carlos Outeiral ◽  
Gabriel L. Guimaraes ◽  
Alan Aspuru-Guzik
Keyword(s):  
Machine Learning ◽  
Learning Community ◽  
Chemical Species ◽  
Material Design ◽  
Organic Photovoltaic ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Photovoltaic Material

Molecular discovery seeks to generate chemical species tailored to very specific needs. In this paper, we present ORGANIC, a framework based on Objective-Reinforced Generative Adversarial Networks (ORGAN), capable of producing a distribution over molecular space that matches with a certain set of desirable metrics. This methodology combines two successful techniques from the machine learning community: a Generative Adversarial Network (GAN), to create non-repetitive sensible molecular species, and Reinforcement Learning (RL), to bias this generative distribution towards certain attributes. We explore several applications, from optimization of random physicochemical properties to candidates for drug discovery and organic photovoltaic material design.

Sign in / Sign up

Export Citation Format

Share Document