2024
A general approach to improve adversarial robustness of DNNs for medical image segmentation and detection
Ma L, Chen J, Qian L, Liang L. A general approach to improve adversarial robustness of DNNs for medical image segmentation and detection. Progress In Biomedical Optics And Imaging 2024, 12926: 1292613-1292613-9. DOI: 10.1117/12.3006534.Peer-Reviewed Original ResearchAdversarial robustness of deep neural networksRobustness of deep neural networksAdversarial training methodDeep neural networksMedical image segmentationImage segmentationAdversarial robustnessAdversarial noiseLandmark detectionTraining methodsRobust deep neural networkMedical image analysis tasksDetection taskPerformance of DNN modelsImproving adversarial robustnessImage analysis tasksMedical imaging tasksCephalometric landmark detectionMedical imaging fieldAdversarial trainingObject detectionClassification taskDNN modelImage classificationAnalysis tasks
2023
Towards lifting the trade-off between accuracy and adversarial robustness of deep neural networks with application on COVID 19 CT image classification and medical image segmentation
Ma L, Liang L. Towards lifting the trade-off between accuracy and adversarial robustness of deep neural networks with application on COVID 19 CT image classification and medical image segmentation. Progress In Biomedical Optics And Imaging 2023, 12464: 124641u-124641u-8. DOI: 10.1117/12.2653392.Peer-Reviewed Original ResearchDeep neural networksAdversarial noiseImage classificationAdversarial robustness of deep neural networksNeural networkRobustness of deep neural networksDeep neural network modelImprove DNN robustnessAdversarial training methodMinimal accuracy degradationMedical image segmentationPublic medical datasetsCT image classificationDeep learning modelsAdversarial trainingAdversarial robustnessDefense methodsMedical datasetsSegmentation taskTraining samplesImage segmentationAccuracy degradationClean dataLearning modelsTrade-offs