Protecting Prostate Cancer Classification From Rectal Artifacts via Targeted Adversarial Training.

Magnetic resonance imaging (MRI)-based deep neural networks (DNN) have been widely developed to perform prostate cancer (PCa) classification. However, in real-world clinical situations, prostate MRIs can be easily impacted by rectal artifacts, which have been found to lead to incorrect PCa classification. Existing DNN-based methods typically do not consider the interference of rectal artifacts on PCa classification, and do not design specific strategy to address this problem. In this study, we proposed a novel Targeted adversarial training with Proprietary Adversarial Samples (TPAS) strategy to defend the PCa classification model against the influence of rectal artifacts. Specifically, based on clinical prior knowledge, we generated proprietary adversarial samples with rectal artifact-pattern adversarial noise, which can severely mislead PCa classification models optimized by the ordinary training strategy. We then jointly exploited the generated proprietary adversarial samples and original samples to train the models. To demonstrate the effectiveness of our strategy, we conducted analytical experiments on multiple PCa classification models. Compared with ordinary training strategy, TPAS can effectively improve the single- and multi-parametric PCa classification at patient, slice and lesion level, and bring substantial gains to recent advanced models. In conclusion, TPAS strategy can be identified as a valuable way to mitigate the influence of rectal artifacts on deep learning models for PCa classification.

Traffic safety comprehensive evaluation of urban tunnel visual guiding system based on extension matter-element model: a case study in tunnel curves.

OBJECTIVE: The visual guiding system, as a tunnel traffic safety improvement method by using visual guiding facilities to actively guide driving safely, has been widely used in countries with many tunnels, in recent years. This paper aims to quantitatively study the comprehensive evaluation of traffic safety of the visual guiding system in tunnels, which has certain engineering application value and can provide support for the quantitative evaluation and optimal design of tunnel traffic safety. METHODS: Based on the analysis of the relevant factors of urban tunnel traffic safety, a multi-factor comprehensive evaluation system with 5 upper-level indicators and 12 basic-level indicators was proposed. Considering the independent and incompatible indicators, a comprehensive evaluation method of traffic safety of the visual guiding system in urban tunnels was constructed by using the extension matter-element model. Taking the scene of 4 types of tunnel curves, such as no facilities, horizontal stripe, chevron alignment sign, and LED arch, as examples, the comprehensive evaluation of various schemes were carried out by using simulation tests. RESULTS: The traffic safety comprehensive evaluation system of visual guiding system in urban tunnels can be analyzed from five aspects: perception reaction, guidance ability, driver factor, driving task, and facility appearance. The results demonstrated significant the comprehensive evaluation result of the target level of scene 1 was L4, scene 2 was L3, scene 3 was L2, and scene 4 was L1. That is, the final results of the comprehensive evaluation of the four scenes were poor, medium, good, and very good, respectively. CONCLUSIONS: In the scheme of visual guiding system for urban tunnel curves, the effectiveness of the three types of designs, from high to low, was the LED arch, chevron alignment sign, and horizontal stripe, and the safety of the scene without facilities was the lowest. Hence, setting the LED arch in the urban tunnel curve has a good effect in the aspects of guidance ability, sight distance, and sight zone, and is conducive to the driver's perception reaction and driving task.

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification.

Histopathological tissue classification is a fundamental task in computational pathology. Deep learning (DL)-based models have achieved superior performance but centralized training suffers from the privacy leakage problem. Federated learning (FL) can safeguard privacy by keeping training samples locally, while existing FL-based frameworks require a large number of well-annotated training samples and numerous rounds of communication which hinder their viability in real-world clinical scenarios. In this article, we propose a lightweight and universal FL framework, named federated deep-broad learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication. By simply integrating a pretrained DL feature extractor, a fast and lightweight broad learning inference system with a classical federated aggregation approach, FedDBL can dramatically reduce data dependency and improve communication efficiency. Five-fold cross-validation demonstrates that FedDBL greatly outperforms the competitors with only one-round communication and limited training samples, while it even achieves comparable performance with the ones under multiple-round communications. Furthermore, due to the lightweight design and one-round communication, FedDBL reduces the communication burden from 4.6 GB to only 138.4 KB per client using the ResNet-50 backbone at 50-round training. Extensive experiments also show the scalability of FedDBL on model generalization to the unseen dataset, various client numbers, model personalization and other image modalities. Since no data or deep model sharing across different clients, the privacy issue is well-solved and the model security is guaranteed with no model inversion attack risk. Code is available at https://github.com/tianpeng-deng/FedDBL.

Learning At a Glance: Towards Interpretable Data-Limited Continual Semantic Segmentation Via Semantic-Invariance Modelling.

Continual semantic segmentation (CSS) based on incremental learning (IL) is a great endeavour in developing human- like segmentation models. However, current CSS approaches encounter challenges in the trade-off between preserving old knowledge and learning new ones, where they still need large-scale annotated data for incremental training and lack interpretability. In this paper, we present Learning at a Glance (LAG), an efficient, robust, human- like and interpretable approach for CSS. Specifically, LAG is a simple and model-agnostic architecture, yet it achieves competitive CSS efficiency with limited incremental data. Inspired by human- like recognition patterns, we propose a semantic-invariance modelling approach via semantic features decoupling that simultaneously reconciles solid knowledge inheritance and new-term learning. Concretely, the proposed decoupling manner includes two ways, i.e., channel- wise decoupling and spatial-level neuron-relevant semantic consistency. Our approach preserves semantic-invariant knowledge as solid prototypes to alleviate catastrophic forgetting, while also constraining sample-specific contents through an asymmetric contrastive learning method to enhance model robustness during IL steps. Experimental results in multiple datasets validate the effectiveness of the proposed method. Furthermore, we introduce a novel CSS protocol that better reflects realistic data-limited CSS settings, and LAG achieves superior performance under multiple data-limited conditions.

Exploring the S Protein of SARS-CoV-2 to Design a Novel Multi-Epitope Vaccine against COVID-19 Based on Immunoinformatics Approaches.

BACKGROUND: Developing a novel COVID-19 multi-epitope vaccine (CoVMEV) is essential to containing the SARS-CoV-2 pandemic. METHODS: The virus's immunodominant B and T cell epitopes from the S protein were found and joined to create the CoVMEV. Bioinformatics techniques were used to investigate the secondary and tertiary structures, as well as the physical and chemical properties of CoVMEV. RESULTS: CoVMEV exhibited high antigenicity and immunogenicity scores, together with good water solubility and stability. Toll-like receptor 2 (TLR2) and toll-like receptor4 (TLR4), which are critical in triggering immunological responses, were also strongly favoured by CoVMEV. Molecular dynamics simulation and immune stimulation studies revealed that CoVMEV effectively activated T and B lymphocytes, and increased the number of active CD8+ T cells than similar vaccines. CONCLUSION: CoVMEV holds promise as a potential vaccine candidate for COVID-19, given its robust immunogenicity, stability, antigenicity, and capacity to stimulate a strong immune response. This study presents a significant design concept for the development of peptidyl vaccines targeting SARS-CoV-2. Further investigation and clinical trials will be crucial in assessing the efficacy and safety of CoVMEV as a potential vaccine for COVID-19.

FedDUS: Lung tumor segmentation on CT images through federated semi-supervised with dynamic update strategy.

BACKGROUND AND OBJECTIVE: Lung tumor annotation is a key upstream task for further diagnosis and prognosis. Although deep learning techniques have promoted automation of lung tumor segmentation, there remain challenges impeding its application in clinical practice, such as a lack of prior annotation for model training and data-sharing among centers. METHODS: In this paper, we use data from six centers to design a novel federated semi-supervised learning (FSSL) framework with dynamic model aggregation and improve segmentation performance for lung tumors. To be specific, we propose a dynamically updated algorithm to deal with model parameter aggregation in FSSL, which takes advantage of both the quality and quantity of client data. Moreover, to increase the accessibility of data in the federated learning (FL) network, we explore the FAIR data principle while the previous federated methods never involve. RESULT: The experimental results show that the segmentation performance of our model in six centers is 0.9348, 0.8436, 0.8328, 0.7776, 0.8870 and 0.8460 respectively, which is superior to traditional deep learning methods and recent federated semi-supervised learning methods. CONCLUSION: The experimental results demonstrate that our method is superior to the existing FSSL methods. In addition, our proposed dynamic update strategy effectively utilizes the quality and quantity information of client data and shows efficiency in lung tumor segmentation. The source code is released on (https://github.com/GDPHMediaLab/FedDUS).

Development and Validation of a Deep Learning Model to Reduce the Interference of Rectal Artifacts in MRI-based Prostate Cancer Diagnosis.

Purpose To develop an MRI-based model for clinically significant prostate cancer (csPCa) diagnosis that can resist rectal artifact interference. Materials and Methods This retrospective study included 2203 male patients with prostate lesions who underwent biparametric MRI and biopsy between January 2019 and June 2023. Targeted adversarial training with proprietary adversarial samples (TPAS) strategy was proposed to enhance model resistance against rectal artifacts. The automated csPCa diagnostic models trained with and without TPAS were compared using multicenter validation datasets. The impact of rectal artifacts on the diagnostic performance of each model at the patient and lesion levels was compared using the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUPRC). The AUC between models was compared using the DeLong test, and the AUPRC was compared using the bootstrap method. Results The TPAS model exhibited diagnostic performance improvements of 6% at the patient level (AUC: 0.87 vs 0.81, P < .001) and 7% at the lesion level (AUPRC: 0.84 vs 0.77, P = .007) compared with the control model. The TPAS model demonstrated less performance decline in the presence of rectal artifact-pattern adversarial noise than the control model (ΔAUC: -17% vs -19%, ΔAUPRC: -18% vs -21%). The TPAS model performed better than the control model in patients with moderate (AUC: 0.79 vs 0.73, AUPRC: 0.68 vs 0.61) and severe (AUC: 0.75 vs 0.57, AUPRC: 0.69 vs 0.59) artifacts. Conclusion This study demonstrates that the TPAS model can reduce rectal artifact interference in MRI-based csPCa diagnosis, thereby improving its performance in clinical applications. Keywords: MR-Diffusion-weighted Imaging, Urinary, Prostate, Comparative Studies, Diagnosis, Transfer Learning Clinical trial registration no. ChiCTR23000069832 Supplemental material is available for this article. Published under a CC BY 4.0 license.

A computed tomography-based multitask deep learning model for predicting tumour stroma ratio and treatment outcomes in patients with colorectal cancer: a multicentre cohort study.

BACKGROUND: Tumour-stroma interactions, as indicated by tumour-stroma ratio (TSR), offer valuable prognostic stratification information. Current histological assessment of TSR is limited by tissue accessibility and spatial heterogeneity. The authors aimed to develop a multitask deep learning (MDL) model to noninvasively predict TSR and prognosis in colorectal cancer (CRC). MATERIALS AND METHODS: In this retrospective study including 2268 patients with resected CRC recruited from four centres, the authors developed an MDL model using preoperative computed tomography (CT) images for the simultaneous prediction of TSR and overall survival. Patients in the training cohort ( n =956) and internal validation cohort (IVC, n =240) were randomly selected from centre I. Patients in the external validation cohort 1 (EVC1, n =509), EVC2 ( n =203), and EVC3 ( n =360) were recruited from other three centres. Model performance was evaluated with respect to discrimination and calibration. Furthermore, the authors evaluated whether the model could predict the benefit from adjuvant chemotherapy. RESULTS: The MDL model demonstrated strong TSR discrimination, yielding areas under the receiver operating curves (AUCs) of 0.855 (95% CI, 0.800-0.910), 0.838 (95% CI, 0.802-0.874), and 0.857 (95% CI, 0.804-0.909) in the three validation cohorts, respectively. The MDL model was also able to predict overall survival and disease-free survival across all cohorts. In multivariable Cox analysis, the MDL score (MDLS) remained an independent prognostic factor after adjusting for clinicopathological variables (all P <0.05). For stage II and stage III disease, patients with a high MDLS benefited from adjuvant chemotherapy [hazard ratio (HR) 0.391 (95% CI, 0.230-0.666), P =0.0003; HR=0.467 (95% CI, 0.331-0.659), P <0.0001, respectively], whereas those with a low MDLS did not. CONCLUSION: The multitask DL model based on preoperative CT images effectively predicted TSR status and survival in CRC patients, offering valuable guidance for personalized treatment. Prospective studies are needed to confirm its potential to select patients who might benefit from chemotherapy.

PA-Net: A phase attention network fusing venous and arterial phase features of CT images for liver tumor segmentation.

BACKGROUND AND OBJECTIVE: Liver cancer seriously threatens human health. In clinical diagnosis, contrast-enhanced computed tomography (CECT) images provide important supplementary information for accurate liver tumor segmentation. However, most of the existing methods of liver tumor automatic segmentation focus only on single-phase image features. And the existing multi-modal methods have limited segmentation effect due to the redundancy of fusion features. In addition, the spatial misalignment of multi-phase images causes feature interference. METHODS: In this paper, we propose a phase attention network (PA-Net) to adequately aggregate multi-phase information of CT images and improve segmentation performance for liver tumors. Specifically, we design a PA module to generate attention weight maps voxel by voxel to efficiently fuse multi-phase CT images features to avoid feature redundancy. In order to solve the problem of feature interference in the multi-phase image segmentation task, we design a new learning strategy and prove its effectiveness experimentally. RESULTS: We conduct comparative experiments on the in-house clinical dataset and achieve the SOTA segmentation performance on multi-phase methods. In addition, our method has improved the mean dice score by 3.3% compared with the single-phase method based on nnUNet, and our learning strategy has improved the mean dice score by 1.51% compared with the ML strategy. CONCLUSION: The experimental results show that our method is superior to the existing multi-phase liver tumor segmentation method, and provides a scheme for dealing with missing modalities in multi-modal tasks. In addition, our proposed learning strategy makes more effective use of arterial phase image information and is proven to be the most effective in liver tumor segmentation tasks using thick-layer CT images. The source code is released on (https://github.com/Houjunfeng203934/PA-Net).

SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation.

Accurate and automated segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a critical role in computer-aided diagnosis and treatment of breast cancer. However, this task is challenging, due to random variation in tumor sizes, shapes, appearances, and blurred boundaries of tumors caused by inherent heterogeneity of breast cancer. Moreover, the presence of ill-posed artifacts in DCE-MRI further complicate the process of tumor region annotation. To address the challenges above, we propose a scheme (named SwinHR) integrating prior DCE-MRI knowledge and temporal-spatial information of breast tumors. The prior DCE-MRI knowledge refers to hemodynamic information extracted from multiple DCE-MRI phases, which can provide pharmacokinetics information to describe metabolic changes of the tumor cells over the scanning time. The Swin Transformer with hierarchical re-parameterization large kernel architecture (H-RLK) can capture long-range dependencies within DCE-MRI while maintaining computational efficiency by a shifted window-based self-attention mechanism. The use of H-RLK can extract high-level features with a wider receptive field, which can make the model capture contextual information at different levels of abstraction. Extensive experiments are conducted in large-scale datasets to validate the effectiveness of our proposed SwinHR scheme, demonstrating its superiority over recent state-of-the-art segmentation methods. Also, a subgroup analysis split by MRI scanners, field strength, and tumor size is conducted to verify its generalization. The source code is released on (https://github.com/GDPHMediaLab/SwinHR).

Pathologic complete response prediction in breast cancer lesion segmentation and neoadjuvant therapy.

Objectives: Predicting whether axillary lymph nodes could achieve pathologic Complete Response (pCR) after breast cancer patients receive neoadjuvant chemotherapy helps make a quick follow-up treatment plan. This paper presents a novel method to achieve this prediction with the most effective medical imaging method, Dynamic Contrast-enhanced Magnetic Resonance Imaging (DCE-MRI). Methods: In order to get an accurate prediction, we first proposed a two-step lesion segmentation method to extract the breast cancer lesion region from DCE-MRI images. With the segmented breast cancer lesion region, we then used a multi-modal fusion model to predict the probability of axillary lymph nodes achieving pCR. Results: We collected 361 breast cancer samples from two hospitals to train and test the proposed segmentation model and the multi-modal fusion model. Both segmentation and prediction models obtained high accuracy. Conclusion: The results show that our method is effective in both the segmentation task and the pCR prediction task. It suggests that the presented methods, especially the multi-modal fusion model, can be used for the prediction of treatment response in breast cancer, given data from noninvasive methods only.

Inhibition of excessive autophagy alleviates renal injury and inflammation in a rat model of immunoglobulin A nephropathy.

The pathogenesis of immunoglobulin A nephropathy (IgAN) is closely related to immunity and inflammation. The clinical process of IgAN varies greatly, making the assessment of prognosis challenging and limiting progress on effective treatment measures. Autophagy is an important pathway for the development of IgAN. However, the role of autophagy in IgAN is complex, and the consequences of autophagy may change during disease progression. In the present study, we evaluated the dynamic changes in autophagy during IgAN. Specifically, we examined autophagy in the kidney of a rat model of IgAN at different time points. We found that autophagy was markedly and persistently induced in IgAN rats, and the expression level of inflammation was also persistently elevated. The autophagy enhancer rapamycin and autophagy inhibitor 3-methyladenine were used in this study, and the results showed that 3-methyladenine can alleviate renal injury and inflammation in IgAN rats. Our study provides further evidence for autophagy as a therapeutic target for IgAN.

A robust and efficient AI assistant for breast tumor segmentation from DCE-MRI via a spatial-temporal framework.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) allows screening, follow up, and diagnosis for breast tumor with high sensitivity. Accurate tumor segmentation from DCE-MRI can provide crucial information of tumor location and shape, which significantly influences the downstream clinical decisions. In this paper, we aim to develop an artificial intelligence (AI) assistant to automatically segment breast tumors by capturing dynamic changes in multi-phase DCE-MRI with a spatial-temporal framework. The main advantages of our AI assistant include (1) robustness, i.e., our model can handle MR data with different phase numbers and imaging intervals, as demonstrated on a large-scale dataset from seven medical centers, and (2) efficiency, i.e., our AI assistant significantly reduces the time required for manual annotation by a factor of 20, while maintaining accuracy comparable to that of physicians. More importantly, as the fundamental step to build an AI-assisted breast cancer diagnosis system, our AI assistant will promote the application of AI in more clinical diagnostic practices regarding breast cancer.

Unmixing Guided Unsupervised Network for RGB Spectral Super-Resolution.

Spectral super-resolution has attracted research attention recently, which aims to generate hyperspectral images from RGB images. However, most of the existing spectral super-resolution algorithms work in a supervised manner, requiring pairwise data for training, which is difficult to obtain. In this paper, we propose an Unmixing Guided Unsupervised Network (UnGUN), which does not require pairwise imagery to achieve unsupervised spectral super-resolution. In addition, UnGUN utilizes arbitrary other hyperspectral imagery as the guidance image to guide the reconstruction of spectral information. The UnGUN mainly includes three branches: two unmixing branches and a reconstruction branch. Hyperspectral unmixing branch and RGB unmixing branch decompose the guidance and RGB images into corresponding endmembers and abundances respectively, from which the spectral and spatial priors are extracted. Meanwhile, the reconstruction branch integrates the above spectral-spatial priors to generate a coarse hyperspectral image and then refined it. Besides, we design a discriminator to ensure that the distribution of generated image is close to the guidance hyperspectral imagery, so that the reconstructed image follows the characteristics of a real hyperspectral image. The major contribution is that we develop an unsupervised framework based on spectral unmixing, which realizes spectral super-resolution without paired hyperspectral-RGB images. Experiments demonstrate the superiority of UnGUN when compared with some SOTA methods.

MRI-based Quantification of Intratumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer.

Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting treatment response. Purpose To develop a quantitative measure of ITH on pretreatment MRI scans and test its performance for predicting pathologic complete response (pCR) after NAC in patients with breast cancer. Materials and Methods Pretreatment MRI scans were retrospectively acquired in patients with breast cancer who received NAC followed by surgery at multiple centers from January 2000 to September 2020. Conventional radiomics (hereafter, C-radiomics) and intratumoral ecological diversity features were extracted from the MRI scans, and output probabilities of imaging-based decision tree models were used to generate a C-radiomics score and ITH index. Multivariable logistic regression analysis was used to identify variables associated with pCR, and significant variables, including clinicopathologic variables, C-radiomics score, and ITH index, were combined into a predictive model for which performance was assessed using the area under the receiver operating characteristic curve (AUC). Results The training data set was comprised of 335 patients (median age, 48 years [IQR, 42-54 years]) from centers A and B, and 590, 280, and 384 patients (median age, 48 years [IQR, 41-55 years]) were included in the three external test data sets. Molecular subtype (odds ratio [OR] range, 4.76-8.39 [95% CI: 1.79, 24.21]; all P < .01), ITH index (OR, 30.05 [95% CI: 8.43, 122.64]; P < .001), and C-radiomics score (OR, 29.90 [95% CI: 12.04, 81.70]; P < .001) were independently associated with the odds of achieving pCR. The combined model showed good performance for predicting pCR to NAC in the training data set (AUC, 0.90) and external test data sets (AUC range, 0.83-0.87). Conclusion A model that combined an index created from pretreatment MRI-based imaging features quantitating ITH, C-radiomics score, and clinicopathologic variables showed good performance for predicting pCR to NAC in patients with breast cancer. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Rauch in this issue.

Artificial intelligence-quantified tumour-lymphocyte spatial interaction predicts disease-free survival in resected lung adenocarcinoma: A graph-based, multicentre study.

BACKGROUND AND OBJECTIVE: A high degree of lymphocyte infiltration is related to superior outcomes amongst patients with lung adenocarcinoma. Recent evidence indicates that the spatial interactions between tumours and lymphocytes also influence the anti-tumour immune responses, but the spatial analysis at the cellular level remains insufficient. METHODS: We proposed an artificial intelligence-quantified Tumour-Lymphocyte Spatial Interaction score (TLSI-score) by calculating the ratio between the number of spatial adjacent tumour-lymphocyte and the number of tumour cells based on topology cell graph constructed using H&E-stained whole-slide images. The association of TLSI-score with disease-free survival (DFS) was explored in 529 patients with lung adenocarcinoma across three independent cohorts (D1, 275; V1, 139; V2, 115). RESULTS: After adjusting for pTNM stage and other clinicopathologic risk factors, a higher TLSI-score was independently associated with longer DFS than a low TLSI-score in the three cohorts [D1, adjusted hazard ratio (HR), 0.674; 95% confidence interval (CI) 0.463-0.983; p = 0.040; V1, adjusted HR, 0.408; 95% CI 0.223-0.746; p = 0.004; V2, adjusted HR, 0.294; 95% CI 0.130-0.666; p = 0.003]. By integrating the TLSI-score with clinicopathologic risk factors, the integrated model (full model) improves the prediction of DFS in three independent cohorts (C-index, D1, 0.716 vs. 0.701; V1, 0.666 vs. 0.645; V2, 0.708 vs. 0.662) CONCLUSIONS: TLSI-score shows the second highest relative contribution to the prognostic prediction model, next to the pTNM stage. TLSI-score can assist in the characterising of tumour microenvironment and is expected to promote individualized treatment and follow-up decision-making in clinical practice.

Asymmetric rhodium-catalyzed click cycloaddition to access C-N axially chiral N-triazolyl indoles.

The copper-catalyzed azide-alkyne cycloaddition (CuAAC) reaction is regarded as a prime example of "click chemistry", but the asymmetric click cycloaddition of internal alkynes still remains challenging. A new asymmetric Rh-catalyzed click cycloaddition of N-alkynylindoles with azides was developed, providing atroposelective access to C-N axially chiral triazolyl indoles, a new type of heterobiaryl, with excellent yields and enantioselectivity. This asymmetric approach is efficient, mild, robust and atom-economic, and features very broad substrate scope with easily available Tol-BINAP ligands.

Inherit With Distillation and Evolve With Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory.

As a front-burner problem in incremental learning, class incremental semantic segmentation (CISS) is plagued by catastrophic forgetting and semantic drift. Although recent methods have utilized knowledge distillation to transfer knowledge from the old model, they are still unable to avoid pixel confusion, which results in severe misclassification after incremental steps due to the lack of annotations for past and future classes. Meanwhile data-replay-based approaches suffer from storage burdens and privacy concerns. In this paper, we propose to address CISS without exemplar memory and resolve catastrophic forgetting as well as semantic drift synchronously. We present Inherit with Distillation and Evolve with Contrast (IDEC), which consists of a Dense Knowledge Distillation on all Aspects (DADA) manner and an Asymmetric Region-wise Contrastive Learning (ARCL) module. Driven by the devised dynamic class-specific pseudo-labelling strategy, DADA distils intermediate-layer features and output-logits collaboratively with more emphasis on semantic-invariant knowledge inheritance. ARCL implements region-wise contrastive learning in the latent space to resolve semantic drift among known classes, current classes, and unknown classes. We demonstrate the effectiveness of our method on multiple CISS tasks by state-of-the-art performance, including Pascal VOC 2012, ADE20K and ISPRS datasets. Our method also shows superior anti-forgetting ability, particularly in multi-step CISS tasks.

Use of Pretreatment Multiparametric MRI to Predict Tumor Regression Pattern to Neoadjuvant Chemotherapy in Breast Cancer.

RATIONALE AND OBJECTIVES: To develop an easy-to-use model by combining pretreatment MRI and clinicopathologic features for early prediction of tumor regression pattern to neoadjuvant chemotherapy (NAC) in breast cancer. MATERIALS AND METHODS: We retrospectively analyzed 420 patients who received NAC and underwent definitive surgery in our hospital from February 2012 to August 2020. Pathologic findings of surgical specimens were used as the gold standard to classify tumor regression patterns into concentric and non-concentric shrinkage. Morphologic and kinetic MRI features were both analyzed. Univariable and multivariable analyses were performed to select the key clinicopathologic and MRI features for pretreatment prediction of regression pattern. Logistic regression and six machine learning methods were used to construct prediction models, and their performance were evaluated with receiver operating characteristic curve. RESULTS: Two clinicopathologic variables and three MRI features were selected as independent predictors to construct prediction models. The apparent area under the curve (AUC) of seven prediction models were in the range of 0.669-0.740. The logistic regression model yielded an AUC of 0.708 (95% confidence interval [CI]: 0.658-0.759), and the decision tree model achieved the highest AUC of 0.740 (95% CI: 0.691-0.787). For internal validation, the optimism-corrected AUCs of seven models were in the range of 0.592-0.684. There was no significant difference between the AUCs of the logistic regression model and that of each machine learning model. CONCLUSION: Prediction models combining pretreatment MRI and clinicopathologic features are useful for predicting tumor regression pattern in breast cancer, which can assist to select patients who can benefit from NAC for de-escalation of breast surgery and modify treatment strategy.