Jiefei Wei

BackgroundThere is increasing evidence that artificial intelligence (AI) breast cancer risk evaluation tools using digital mammograms are highly informative for 1–6 years following a negative screening examination. We hypothesized that algorithms that have previously been shown to work well for cancer detection will also work well for risk assessment and that performance of algorithms for detection and risk assessment is correlated.MethodsTo evaluate our hypothesis, we designed a case-control study using paired mammograms at diagnosis and at the previous screening visit. The study included n = 3386 women from the OPTIMAM registry, that includes mammograms from women diagnosed with breast cancer in the English breast screening program 2010–2019. Cases were diagnosed with invasive breast cancer or ductal carcinoma in situ at screening and were selected if they had a mammogram available at …

With the widespread applications of Deep Neural Networks (DNNs), the safety of DNNs has become a significant issue. The vulnerability of the neural networks against adversarial examples deepens concerns about the safety of DNNs applications. This paper proposed a novel defence method to improve the adversarial robustness of DNN classifiers without using adversarial training. This method introduces two new loss functions. First, a zero-cross-entropy loss is used to punish overconfidence and find the appropriate confidence for different instances. Second, a logit balancing loss is proposed to protect DNNs from non-targeted attacks by regularising incorrect classes’ logits distribution. This method achieved competitive adversarial robustness compared to advanced adversarial training methods. Meanwhile, a novel robustness diagram is proposed to analyse, interpret and visualise the robustness of DNN …

Using manually selected cases for breast screener training is time-consuming and prohibitively costly. However, retrieving medical images of breasts via computer vision methods that reflect diagnostically relevant visual features is challenging because the overall appearance variability of whole breasts is high compared to often subtle lesions of interest. Our work aims to develop an automatic and low-costing tool for retrieving and recommending similar full-field digital mammograms (FFDMs) of breast cancer by providing a query image. This tool will help to identify poor reader performance in real-life screening that allows interventions to change practice according to error cases, such as reviewing practice or further training. The core element of this tool is automatic content-based image retrieval. In this paper, we propose an unsupervised method for training an artificial intelligence (AI) model to rank FFDMs …

With wide applications of machine learning algorithms, machine learning security has become a significant issue. The vulnerability to adversarial perturbations exists in most machine learning algorithms, including cutting-edge deep neural networks. The standard adversarial perturbation defence techniques with adversarial training need to generate adversarial examples during the training process, which require high computational costs. This paper proposed a novel defence method using self-adaptive logit balancing and Gaussian noise boost training. This method can improve the robustness of deep neural networks without high computational cost and achieve competitive results compared with the adversarial training methods. Meanwhile, this defence method enables deep learning systems to have proactive and reactive defence during the operation. A sub-classifier is trained to determine whether the system …

With the widespread applications of deep neural networks, the security of deep neural networks has become a significant issue, especially in safety-critical fields, such as biometric identification and authorisation, self-driving, robotics, aerospace and more. Testing and improving the robustness and trustworthiness of deep learning algorithms is an important and challenging topic of artificial intelligence. Without approval by reliable and rigorous checks, deep learning algorithms are not qualified to be used in real-world applications. However, traditional software verification methods can not be directly applied to deep neural networks because the number of system states and the possible inputs of deep neural networks is almost infinite. Furthermore, the finding of vulnerability to adversarial perturbations makes the situation of deep learning security even more challenging. This thesis studied the security issues of deep neural networks with the aims of testing, improving and visualising the robustness and trustworthiness of deep neural networks under adversarial attacks. First, a novel GAN-based verification framework is proposed to test the robustness and check deep learning systems’ safety boundaries. The proposed verification framework utilises the image-to-image translation technique to generate adversarial examples that can mislead the target deep neural network in a black-box way. This verification framework can guarantee the diversity of adversarial examples under the style or domain of interest and the realism of the synthetic adversarial examples. The novelty of this method is that it can test the deep learning model and the training data …

Verification and validation of deep learning algorithms is an important and challenging topic of artificial intelligence. Without approving by reliable and rigorous verification methods, deep learning algorithms, for instance, the convolutional neural networks, are not qualified to be used in real-world applications, especially in safety-critical areas. The gap between deep learning systems and the requirements in safety-critical application areas, such as autonomous robotics and self-driving vehicles, is the lack of Black-box V&V techniques that can test and evaluate the performance and the robustness of deep learning systems. To bridge this gap, we proposed a GAN based Black-box verification framework called AdversarialStyle for generating and searching adversarial examples in both targeted and non-targeted way from different styles or domains of interest. The AdversarialStyle can not only evaluate deep learning …