Adversarial training for prostate cancer classification using magnetic resonance imaging.

Twenty-five patients diagnosed with otogenic vertigo at the outpatient clinic of the Department of Otolaryngology-Head and Neck Surgery, Shanghai Jiao Tong University Affiliated Sixth People's Hospital from January to June 2020 were selected. Among them, 8 cases were male and 17 cases were female, aged (48±13) years. All the patients underwent internet combined with offline follow-up vestibular rehabilitation for 12 weeks, which included vestibulo-ocular reflex exercises, proprioceptive exercises and static/dynamic balance exercises. Computerized dynamic posturography (CDP) and dizziness handicap inventory (DHI) scores were compared before and after rehabilitation. The DHI score improved significantly after 12 weeks of vestibular rehabilitation (48.3±15.9 vs 26.7±17.9, t=5.319, P<0.001). Meanwhile, the sensory organization test (SOT) score was also improved (73.3±8.1 vs 76.1±6.6, t=2.066, P=0.050), while the difference of motor control test (MCT) latent stage score before and after rehabilitation was not statistically significant (140±13 vs 141±16, t=0.791, P=0.436). The current study demonstrates that vestibular rehabilitation based on mobile internet is convenient, economical and effective, and patients can benefit from it.

Evidence suggested that IL-17A was associated with renal function in type 2 diabetes. We used ultra-sensitive measurement to detect the concentration of IL-17A in human peripheral blood and explored the association of IL-17A with diabetic kidney disease (DKD). We recruited 138 participants from the Shanghai Diabetes Institute Inpatient Database of Shanghai Jiao Tong University Affiliated Sixth People's Hospital. Eighty-four individuals diagnosed as DKD were cases, and 54 type 2 diabetes individuals without DKD or diabetic retinopathy (DR) were controls. The concentration of serum IL-17A was detected by the High Sensitivity Immunoassay Quantitative Kit. Data was analysed by SAS. The concentration of serum IL-17A in our population ranged from 0.07 pg/mL to 2.96 pg/mL with the median of 0.502 pg/mL. Our results suggested that the level of serum IL-17A in DKD case group was higher than in the control (P unadjusted = 0.0496, P adjusted = 0.0298). And serum creatinine, eGFR, ACR were used as indicators of renal function. Serum creatinine and ACR were positive correlated with the level of serum IL-17A (P adjusted = 0.0148; P adjusted = 0.0369), while eGFR showed a negative correlation (P adjusted = 0.0167). Additionally, the level of serum IL-17A was also significantly higher in DR case group compared with the control group (p = 0.0224). Serum IL-17A level is associated with renal function decline and diabetic retinopathy in patients with type 2 diabetes in a Chinese Han population. Our results suggested that IL-17A may be a potential biomarker of DKD and DR.

Biomarkers of Distinguishing Neutrophil-Predominant Tuberculous Pleural Effusion from Parapneumonic Pleural Effusion

Engineered Nail Grafts Induce Nail Plate Regeneration Ectopically

State-of-the-art neural network models are actively used in various fields, but it is well-known that they are vulnerable to adversarial example attacks. Throughout the efforts to make the models robust against adversarial example attacks, it has been found to be a very difficult task. While many defense approaches were shown to be not effective, adversarial training remains as one of the promising methods. In adversarial training, the training data are augmented by “adversarial” samples generated using an attack algorithm. If the attacker uses a similar attack algorithm to generate adversarial examples, the adversarially trained network can be quite robust to the attack. However, there are numerous ways of creating adversarial examples, and the defender does not know what algorithm the attacker may use. A natural question is: Can we use adversarial training to train a model robust to multiple types of attack? Previous work have shown that, when a network is trained with adversarial examples generated from multiple attack methods, the network is still vulnerable to white-box attacks where the attacker has complete access to the model parameters. In this paper, we study this question in the context of black-box attacks, which can be a more realistic assumption for practical applications. Experiments with the MNIST dataset show that adversarially training a network with an attack method helps defending against that particular attack method, but has limited effect for other attack methods. In addition, even if the defender trains a network with multiple types of adversarial examples and the attacker attacks with one of the methods, the network could lose accuracy to the attack if the attacker uses a different data augmentation strategy on the target network. These results show that it is very difficult to make a robust network using adversarial training, even for black-box settings where the attacker has restricted information on the target network.

To evaluate the diagnostic performance of semi-supervised learning models for aggressive prostate cancer detection on MRI compared to fully supervised models trained with additional expert annotations. We used 1500 MRI scans from the PI-CAI challenge training subset. Positive scans had 220 human and 205 AI-generated annotations. The mtU-Net (proposed teacher-student semi-supervised approach) was compared to supervised (trained using only 220 human annotations) and semi-supervised (trained on human and AI-generated annotations) nnU-Net. The 205 AI-annotated scans were manually annotated, and a fully supervised model was trained. External validation was performed on a newly annotated dataset from the PROMIS study (n = 574,403 lesions) and the Prostate158 dataset (n = 158,126 lesions). Patient-level performance was evaluated using the area under the curve (AUC) and lesion-level detection (overlap > 0.10) using average precision (AP), along with 95% confidence Intervals (in brackets), and the DeLong test to compare AUCs against the supervised and fully supervised models. The fully supervised nnU-Net showed the highest performance on the internal PI-CAI test set (AUC = 0.89 [0.87-0.91], AP = 0.65 [0.60-0.70]) and external validation datasets PROMIS (AUC = 0.68 [0.64-0.72], AP = 0.24 [0.20-0.29]) and Prostate158 (AUC = 0.87 [0.82-0.92], AP = 0.64 [0.56-0.72]), significantly outperforming the supervised baseline (p < 0.05). The proposed semi-supervised mtU-Net demonstrated close external validation performance on PROMIS (AUC = 0.66 [0.62-0.71], AP = 0.20 [0.16-0.25]) and Prostate158 (AUC = 0.86 [0.81-0.92], AP = 0.58 [0.49-0.67]), significantly outperforming the supervised baseline on both datasets (p = 0.047 and p = 0.014, respectively), and showing no significant difference to the fully supervised model (p = 0.199 and p = 0.702, respectively). In prostate MRI tumor detection, fully supervised learning performed best. However, in external validation, the semi-supervised methods demonstrated performance that approached that of the fully supervised model, proving a valuable approach when expert annotations are limited. Question The need for extensive expert voxel-level annotations delays the development of AI-based prostate cancer diagnostic tools and their implementation in clinical practice. Findings The combination of pseudo-labeling with consistency regularization achieved performance comparable to that of fully supervised methods, demonstrating that data diversity matches the impact of expert annotation volume. Clinical relevance Semi-supervised learning reduces dependence on expert annotations while maintaining detection accuracy, enabling the development of scalable, automated diagnostic tools for prostate cancer amid growing clinical workflow demands.

Journal of Medical VirologyVolume 92, Issue 11 p. 2403-2405 LETTER TO THE EDITOR Clinical features and the treatment of children with COVID-19: A case series from Wenzhou, China Jing Cai, Jing Cai [email protected] orcid.org/0000-0003-3609-4291 Department of Comprehensive Medicine, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, ChinaSearch for more papers by this authorWenjie Sun, Wenjie Sun orcid.org/0000-0002-2608-9037 Institute of Clinical Medicine, The Second Affiliated Hospital of Fujian Traditional Chinese Medical University, Fuzhou, China Department of Health Promotion and Disease Prevention, Robert Stempel College of Public Health and Social Work, Florida International University, Miami, FloridaSearch for more papers by this authorJianping Huang, Jianping Huang orcid.org/0000-0003-2920-6363 Department of Neurology, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, ChinaSearch for more papers by this authorMichelle Gamber, Michelle Gamber orcid.org/0000-0001-9452-2210 Division of Public Health, School of Health Professions, Shenandoah University, Winchester, VirginiaSearch for more papers by this authorJing Wu, Jing Wu orcid.org/0000-0002-1224-0912 Department of Infectious Diseases, Huashan Hospital, Fudan University, Shanghai, ChinaSearch for more papers by this authorGuiqing He, Corresponding Author Guiqing He [email protected] orcid.org/0000-0002-6700-6920 Department of Infectious Diseases, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, China Infectious Diseases Laboratory, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, China Correspondence Jing Wu, Department of Infectious Diseases, Huashan Hospital, Fudan University, Shanghai 200040 China. Email: [email protected] Guiqing He, Department of Infectious Diseases, Wenzhou Central Hospital Medical Group, Wenzhou Sixth People's Hospital and the Wenzhou Central Hospital Medical Group, Infectious Diseases Laboratory, Wenzhou Sixth People's Hospital, Wenzhou, 325000 Zhejiang, China. Email: [email protected]Search for more papers by this author Jing Cai, Jing Cai [email protected] orcid.org/0000-0003-3609-4291 Department of Comprehensive Medicine, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, ChinaSearch for more papers by this authorWenjie Sun, Wenjie Sun orcid.org/0000-0002-2608-9037 Institute of Clinical Medicine, The Second Affiliated Hospital of Fujian Traditional Chinese Medical University, Fuzhou, China Department of Health Promotion and Disease Prevention, Robert Stempel College of Public Health and Social Work, Florida International University, Miami, FloridaSearch for more papers by this authorJianping Huang, Jianping Huang orcid.org/0000-0003-2920-6363 Department of Neurology, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, ChinaSearch for more papers by this authorMichelle Gamber, Michelle Gamber orcid.org/0000-0001-9452-2210 Division of Public Health, School of Health Professions, Shenandoah University, Winchester, VirginiaSearch for more papers by this authorJing Wu, Jing Wu orcid.org/0000-0002-1224-0912 Department of Infectious Diseases, Huashan Hospital, Fudan University, Shanghai, ChinaSearch for more papers by this authorGuiqing He, Corresponding Author Guiqing He [email protected] orcid.org/0000-0002-6700-6920 Department of Infectious Diseases, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, China Infectious Diseases Laboratory, Wenzhou Sixth People's Hospital, Wenzhou Central Hospital Medical Group, Wenzhou, China Correspondence Jing Wu, Department of Infectious Diseases, Huashan Hospital, Fudan University, Shanghai 200040 China. Email: [email protected] Guiqing He, Department of Infectious Diseases, Wenzhou Central Hospital Medical Group, Wenzhou Sixth People's Hospital and the Wenzhou Central Hospital Medical Group, Infectious Diseases Laboratory, Wenzhou Sixth People's Hospital, Wenzhou, 325000 Zhejiang, China. Email: [email protected]mSearch for more papers by this author First published: 30 May 2020 https://doi.org/10.1002/jmv.26092Citations: 4 Funding Information: Major Project of Wenzhou Municipal Science and Technology Bureau, Grant/Award Number: ZY202004; Zhejiang Basic Public Welfare Research Project, Grant/Award Number: LGF20H010003 Jing Cai and Wenjie Sun contributed equally to this study. Read the full textAboutPDF ToolsRequest permissionExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL No abstract is available for this article.Citing Literature Volume92, Issue11Special Issue on New coronavirus (2019‐nCoV or SARS‐CoV‐2) and the outbreak of the respiratory illness (COVID‐19): Part‐VIINovember 2020Pages 2403-2405 RelatedInformation

Development and Validation of Radiomics and Clinical Models for Predicting Gleason Grades in Prostate Cancer Across Tumor Subregions and Clinical Factors: A Dual-Center Study.

Adversarial training (AT) is widely considered as the most promising strategy to defend against adversarial attacks and has drawn increasing interest from researchers. However, the existing AT methods still suffer from two challenges. First, they are unable to handle unrestricted adversarial examples (UAEs), which are built from scratch, as opposed to restricted adversarial examples (RAEs), which are created by adding perturbations bound by an lp norm to observed examples. Second, the existing AT methods often achieve adversarial robustness at the expense of standard generalizability (i.e., the accuracy on natural examples) because they make a tradeoff between them. To overcome these challenges, we propose a unique viewpoint that understands UAEs as imperceptibly perturbed unobserved examples. Also, we find that the tradeoff results from the separation of the distributions of adversarial examples and natural examples. Based on these ideas, we propose a novel AT approach called Provable Unrestricted Adversarial Training (PUAT), which can provide a target classifier with comprehensive adversarial robustness against both UAE and RAE, and simultaneously improve its standard generalizability. Particularly, PUAT utilizes partially labeled data to achieve effective UAE generation by accurately capturing the natural data distribution through a novel augmented triple-GAN. At the same time, PUAT extends the traditional AT by introducing the supervised loss of the target classifier into the adversarial loss and achieves the alignment between the UAE distribution, the natural data distribution, and the distribution learned by the classifier, with the collaboration of the augmented triple-GAN. Finally, the solid theoretical analysis and extensive experiments conducted on widely-used benchmarks demonstrate the superiority of PUAT.

Neural language models show vulnerability to adversarial examples which are semantically similar to their original counterparts with a few words replaced by their synonyms. A common way to improve model robustness is adversarial training which follows two steps—collecting adversarial examples by attacking a target model, and fine-tuning the model on the augmented dataset with these adversarial examples. The objective of traditional adversarial training is to make a model produce the same correct predictions on an original/adversarial example pair. However, the consistency between model decision-makings on two similar texts is ignored. We argue that a robust model should behave consistently on original/adversarial example pairs, that is making the same predictions (what) based on the same reasons (how) which can be reflected by consistent interpretations. In this work, we propose a novel feature-level adversarial training method named FLAT. FLAT aims at improving model robustness in terms of both predictions and interpretations. FLAT incorporates variational word masks in neural networks to learn global word importance and play as a bottleneck teaching the model to make predictions based on important words. FLAT explicitly shoots at the vulnerability problem caused by the mismatch between model understandings on the replaced words and their synonyms in original/adversarial example pairs by regularizing the corresponding global word importance scores. Experiments show the effectiveness of FLAT in improving the robustness with respect to both predictions and interpretations of four neural network models (LSTM, CNN, BERT, and DeBERTa) to two adversarial attacks on four text classification tasks. The models trained via FLAT also show better robustness than baseline models on unforeseen adversarial examples across different attacks.

State-of-the-art Deep Neural Networks (DNNs) are promoting medical image processing. However, DNNs are susceptible to adversarial attacks, which could significantly deteriorate model performances and pose a threat to clinical diagnoses. One common method for prevention is through adversarial training, which is highly dependent on harnessing adversarial examples during the training stage. However, adversarial medical examples generated by many existing works are too perceptible to be adversarial examples. To improve the imperceptibility, we proposed a Regional Saliency Map Attack that generates an adversarial example by only perturbing a small number of pixels. Extensive experiments have shown that, on average, our method caused the same degradation in model performance by quantitatively less perceptible perturbations. Visualisations have also verified that the improvement in imperceptibility in an image is both global and regional.

Deep neural networks (DNNs) have gained widespread adoption in computer vision. Unfortunately, state-of-the-art DNNs are vulnerable to adversarial example (AE) attacks, where an adversary introduces imperceptible perturbations to a test example for defrauding DNNs. The obstacles have urged intensive research on improving the DNN robustness via adversarial training, that is, the clean data set is blended with adversarial examples to carry out training. However, the adversarial example attack technologies are open-ended, and the adversarial training is insufficient to focus on improving robustness performance. To circumvent this limitation, we mitigate adversarial example attacks from another perspective, which aims at detecting adversarial examples. Feature autoencoder detector (FADetector), a novel defense framework that exploits feature knowledge is proposed. One of the hallmarks of FADetector is to not involve adversarial examples to train the detector. Our extensive evaluation on MNIST and CIFAR-10 data sets demonstrates that our defense outperforms the conventional autoencoder detectors in terms of detection accuracy.

Despite deep neural networks (DNNs) have been widely applied in remote sensing (RS) scene classification and achieved satisfying performance, the vulnerability of DNNs towards adversarial examples significantly degrades their performance. Moreover, the relatively limited labeled samples of RS scene classification make DNNs more likely to overfit, leading to weak generalizability and noise sensitivity. This may result in DNNs being more vulnerable to adversarial examples. Consequently, the defense of adversarial examples is of crucial importance to improve both the generalizability and robustness of DNNs in the RS scene classification task. However, few studies have been conducted on defense for RS scene classification, especially ignoring the intrinsic characteristics of RS images. In this paper, an effective defense framework for RS scene classification, named reconstruction-assisted and distance-optimized adversarial training (RDAT), is proposed to defend adversarial examples. In order to solve the problems caused by high interclass similarity, a distance-optimized (DO) strategy is designed for adversarial training to strengthen the learning of underfitting content, increase the interclass distance, and improve the robustness of the networks. Furthermore, in order to generate high quality samples for adversarial training, a reconstruction-assisted (RA) block is proposed to eliminate adversarial perturbations in adversarial examples. Specifically, in this block, by swin transformer (SwinT) block and multi-scale convolution (MSC) block, SwinT-MSC-UNet (SMUNet) is constructed to fully extract global and multi-scale local features to adapt to the characteristics of RS images with large variance of ground object scales. Extensive experiments on the benchmark datasets, i.e., UC Merced (UCM) and Aerial Image Dataset (AID), have demonstrate that the proposed RDAT can effectively resist multiple adversarial attacks and yield superior results than other defense methods for RS scene classification.

A survey of robust adversarial training in pattern recognition: Fundamental, theory, and methodologies

Background - There is suggestive evidence of familial clustering of breast and prostate cancer in first-degree relatives; women with a family history of prostate cancer are at increased risk of breast cancer. Few studies have investigated joint family history of breast and prostate cancer and prostate cancer risk, and no study to date has examined lethal prostate cancer. Methods - We studied 42,672 from the Health Professionals Follow-up Study between 1996 to 2012. During follow-up, 4,258 prostate cancer cases were diagnosed, of whom 380 were lethal disease. Men self-reported family history of breast and prostate cancer, including in siblings or parents. Using cause-specific hazards regression, we estimated hazard ratios (HR) and 95% confidence intervals (CI) of the association between family history and prostate cancer risk and progression. Results - About 8% of men had a family history of prostate cancer, 8.7% had a family history of breast cancer, and 1.4% of men had a family history of both breast and prostate cancer. A family history of prostate cancer was significantly associated with an increased risk of prostate cancer (HR: 1.69; 95% CI: 1.54-1.85). Increased risk was higher for men with a father diagnosed with prostate cancer (HR: 1.64 95% CI: 1.49-1.80) than for men with a diagnosis in a brother(s) (HR: 1.51 95% CI: 1.27-1.80). A positive family history of breast cancer was associated with a small, but significant 22% increased risk (HR: 1.22; 95% CI: 1.11-1.35). Familial breast cancer in a sister (HR: 1.22 95% CI: 1.06-1.41) increased risk more than familial breast cancer in a mother (HR: 1.12; 95% CI: 0.99-1.25). Men with a family history of both prostate and breast cancer had a 52% (HR: 1.52; 95%CI: 1.23-1.88) increased risk of prostate cancer compared to men with no family history of either cancer. Risk of lethal prostate cancer was also significantly increased for men with a positive family history of prostate cancer (HR: 1.64; 95% CI: 1.20-2.24), as well as for men with a family history of breast cancer (HR: 1.47; 95% CI: 1.07-2.01). Conclusions - These results support the findings of familial aggregation of breast and prostate cancer, and for the first time suggest an association between familial breast cancer and lethal prostate cancer. Data from this prospective study have translational relevance for family counseling of cancer patients. Citation Format: Lauren E. Barber, Travis A. Gerke, Sarah C. Markt, Giovanni Parmigiani, Lorelei A. Mucci. A family affair: Prostate cancer risk and family history of breast or prostate cancer. [abstract]. In: Proceedings of the 107th Annual Meeting of the American Association for Cancer Research; 2016 Apr 16-20; New Orleans, LA. Philadelphia (PA): AACR; Cancer Res 2016;76(14 Suppl):Abstract nr 2543.