Nanoparticles targeting OPN loaded with BY1 inhibits vascular restenosis by inducing FTH1-dependent ferroptosis in vascular smooth muscle cells.

Vascular restenosis following angioplasty continues to pose a significant challenge. The heterocyclic trioxirane compound [1, 3, 5-tris((oxiran-2-yl)methyl)-1, 3, 5-triazinane-2, 4, 6-trione (TGIC)], known for its anticancer activity, was utilized as the parent ring to conjugate with a non-steroidal anti-inflammatory drug, resulting in the creation of the spliced conjugated compound BY1. We found that BY1 induced ferroptosis in VSMCs as well as in neointima hyperplasia. Furthermore, ferroptosis inducers amplified BY1-induced cell death, while inhibitors mitigated it, indicating the contribution of ferroptosis to BY1-induced cell death. Additionally, we established that ferritin heavy chain1 (FTH1) played a pivotal role in BY1-induced ferroptosis, as evidenced by the fact that FTH1 overexpression abrogated BY1-induced ferroptosis, while FTH1 knockdown exacerbated it. Further study found that BY1 induced ferroptosis by enhancing the NCOA4-FTH1 interaction and increasing the amount of intracellular ferrous. We compared the effectiveness of various administration routes for BY1, including BY1-coated balloons, hydrogel-based BY1 delivery, and nanoparticles targeting OPN loaded with BY1 (TOP@MPDA@BY1) for targeting proliferated VSMCs, for prevention and treatment of the restenosis. Our results indicated that TOP@MPDA@BY1 was the most effective among the three administration routes, positioning BY1 as a highly promising candidate for the development of drug-eluting stents or treatments for restenosis.

Construction and validation of a novel tumor morphology immune inflammatory nutritional score (TIIN score) for intrahepatic cholangiocarcinoma: a multicenter study.

BACKGROUND: Tumor morphology, immune function, inflammatory levels, and nutritional status play critical roles in the progression of intrahepatic cholangiocarcinoma (ICC). This multicenter study aimed to investigate the association between markers related to tumor morphology, immune function, inflammatory levels, and nutritional status with the prognosis of ICC patients. Additionally, a novel tumor morphology immune inflammatory nutritional score (TIIN score), integrating these factors was constructed. METHODS: A retrospective analysis was performed on 418 patients who underwent radical surgical resection and had postoperative pathological confirmation of ICC between January 2016 and January 2020 at three medical centers. The cohort was divided into a training set (n = 272) and a validation set (n = 146). The prognostic significance of 16 relevant markers was assessed, and the TIIN score was derived using LASSO regression. Subsequently, the TIIN-nomogram models for OS and RFS were developed based on the TIIN score and the results of multivariate analysis. The predictive performance of the TIIN-nomogram models was evaluated using ROC survival curves, calibration curves, and clinical decision curve analysis (DCA). RESULTS: The TIIN score, derived from albumin-to-alkaline phosphatase ratio (AAPR), albumin-globulin ratio (AGR), monocyte-to-lymphocyte ratio (MLR), and tumor burden score (TBS), effectively categorized patients into high-risk and low-risk groups using the optimal cutoff value. Compared to individual metrics, the TIIN score demonstrated superior predictive value for both OS and RFS. Furthermore, the TIIN score exhibited strong associations with clinical indicators including obstructive jaundice, CEA, CA19-9, Child-pugh grade, perineural invasion, and 8th edition AJCC N stage. Univariate and multivariate analysis confirmed the TIIN score as an independent risk factor for postoperative OS and RFS in ICC patients (p < 0.05). Notably, the TIIN-nomogram models for OS and RFS, constructed based on the multivariate analysis and incorporating the TIIN score, demonstrated excellent predictive ability for postoperative survival in ICC patients. CONCLUSION: The development and validation of the TIIN score, a comprehensive composite index incorporating tumor morphology, immune function, inflammatory level, and nutritional status, significantly contribute to the prognostic assessment of ICC patients. Furthermore, the successful application of the TIIN-nomogram prediction model underscores its potential as a valuable tool in guiding individualized treatment strategies for ICC patients. These findings emphasize the importance of personalized approaches in improving the clinical management and outcomes of ICC.

Circular RNA circIL21R promotes cervical cancer cells proliferation and migration by sponging the miR-1205/PTBP1 axis.

Increasing research has shown that the abnormal expression of circRNAs is closely related to tumorigenesis, apoptosis, and patient prognosis in cervical cancer. This study aimed to reveal the procancer role of circIL21R in cervical cancer and investigate its related molecular mechanisms. Bioinformatics analysis revealed that circIL21R promotes the progression of cervical cancer via the miR-1205/PTBP1 axis. CircIL21R expression was significantly greater in tumor tissue than in adjacent normal tissue, and higher circIL21R expression indicated shorter survival. We applied MTS assays, EdU assays, and Transwell assays to show that the overexpression of circIL21R promoted cervical cancer cell proliferation and invasion. Mechanistically, circIL21R promoted the expression of PTBP1 by sponging miR-1205. Moreover, rescue assays confirmed that regulating the expression of miR-1205 or PTBP1 could reverse the tumorigenic effect caused by circIL21R overexpression. In addition, circIL21R promoted the tumorigenesis of cervical cancer in vivo. In summary, our study demonstrated that circIL21R was highly expressed in cervical cancer and upregulated PTBP1 expression by acting as a ceRNA for miR-1205, making outstanding contributions to several malignant biological processes in cervical cancers, such as growth, proliferation, and invasion. CircIL21R is a potential biomarker for the diagnosis and treatment of cervical cancer.

The Correlation between Serum Vitamin D and Total IgE Levels and Chronic Spontaneous Urticaria among Chinese Population: A Retrospective Study.

Objective: This study aims to investigate the relationship between serum vitamin D, total IgE levels and chronic spontaneous urticaria (CSU). Methods: We collected data from 101 patients with chronic spontaneous urticaria (experimental group) and 115 healthy normal subjects (control group) in the same period of physical examination. Results: The results showed that the number of deficient and absolute deficient 25-hydroxyvitamin D in the experimental group was significantly lower than in the control group (P < 0.05). Pearson correlation analysis showed that the activity score of CSU patients was negatively correlated with serum vitamin D (r = -0.2278, P = 0.0220) and positively correlated with IgE (r = 0.2078, P = 0.0380). It was observed that serum vitamin D in CSU patients was negatively correlated with their activity (r = -0.2278, P = 0.0220) and positively correlated with age (r = 0.2675, P = 0.0069). The Point-biserial correlation analysis revealed that gender was positively correlated with serum vitamin D (Pearson correlation coefficient = 0.286, P = 0.004) and UAS score (Pearson correlation coefficient = 0.273, P = 0.006). Ordinal logistic regression analysis showed that only serum vitamin D was correlated to activity scores (P = 0.008). In addition to activity scores, age (P = 0.005) and gender (P = 0.04) were correlated to serum vitamin D. Conclusion: The activity score of CSU patients was negatively correlated with serum vitamin D and positively correlated with IgE. Serum vitamin D in CSU patients was negatively correlated with activity score and disease duration and positively correlated with age and gender.

An Integrated Clinical and Computerized Tomography-Based Radiomic Feature Model to Separate Benign from Malignant Pleural Effusion.

INTRODUCTION: Distinguishing between malignant pleural effusion (MPE) and benign pleural effusion (BPE) poses a challenge in clinical practice. We aimed to construct and validate a combined model integrating radiomic features and clinical factors using computerized tomography (CT) images to differentiate between MPE and BPE. METHODS: A retrospective inclusion of 315 patients with pleural effusion (PE) was conducted in this study (training cohort: n = 220; test cohort: n = 95). Radiomic features were extracted from CT images, and the dimensionality reduction and selection processes were carried out to obtain the optimal radiomic features. Logistic regression (LR), support vector machine (SVM), and random forest were employed to construct radiomic models. LR analyses were utilized to identify independent clinical risk factors to develop a clinical model. The combined model was created by integrating the optimal radiomic features with the independent clinical predictive factors. The discriminative ability of each model was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). RESULTS: Out of the total 1,834 radiomic features extracted, 15 optimal radiomic features explicitly related to MPE were picked to develop the radiomic model. Among the radiomic models, the SVM model demonstrated the highest predictive performance [area under the curve (AUC), training cohort: 0.876, test cohort: 0.774]. Six clinically independent predictive factors, including age, effusion laterality, procalcitonin, carcinoembryonic antigen, carbohydrate antigen 125 (CA125), and neuron-specific enolase (NSE), were selected for constructing the clinical model. The combined model (AUC: 0.932, 0.870) exhibited superior discriminative performance in the training and test cohorts compared to the clinical model (AUC: 0.850, 0.820) and the radiomic model (AUC: 0.876, 0.774). The calibration curves and DCA further confirmed the practicality of the combined model. CONCLUSION: This study presented the development and validation of a combined model for distinguishing MPE and BPE. The combined model was a powerful tool for assisting in the clinical diagnosis of PE patients.

Few-Shot Medical Image Segmentation via Generating Multiple Representative Descriptors.

Automatic medical image segmentation has witnessed significant development with the success of large models on massive datasets. However, acquiring and annotating vast medical image datasets often proves to be impractical due to the time consumption, specialized expertise requirements, and compliance with patient privacy standards, etc. As a result, Few-shot Medical Image Segmentation (FSMIS) has become an increasingly compelling research direction. Conventional FSMIS methods usually learn prototypes from support images and apply nearest-neighbor searching to segment the query images. However, only a single prototype cannot well represent the distribution of each class, thus leading to restricted performance. To address this problem, we propose to Generate Multiple Representative Descriptors (GMRD), which can comprehensively represent the commonality within the corresponding class distribution. In addition, we design a Multiple Affinity Maps based Prediction (MAMP) module to fuse the multiple affinity maps generated by the aforementioned descriptors. Furthermore, to address intra-class variation and enhance the representativeness of descriptors, we introduce two novel losses. Notably, our model is structured as a dual-path design to achieve a balance between foreground and background differences in medical images. Extensive experiments on four publicly available medical image datasets demonstrate that our method outperforms the state-of-the-art methods, and the detailed analysis also verifies the effectiveness of our designed module.

Predictive value of HTS grade in patients with intrahepatic cholangiocarcinoma undergoing radical resection: a multicenter study from China.

BACKGROUND: Intrahepatic cholangiocarcinoma (ICC) is a highly malignant tumor with a poor prognosis. This study aimed to investigate whether Hemoglobin, Albumin, Lymphocytes, and Platelets (HALP) score and Tumor Burden Score (TBS) serves as independent influencing factors following radical resection in patients with ICC. Furthermore, we sought to evaluate the predictive capacity of the combined HALP and TBS grade, referred to as HTS grade, and to develop a prognostic prediction model. METHODS: Clinical data for ICC patients who underwent radical resection were retrospectively analyzed. Univariate and multivariate Cox regression analyses were first used to find influencing factors of prognosis for ICC. Receiver operating characteristic (ROC) curves were then used to find the optimal cut-off values for HALP score and TBS and to compare the predictive ability of HALP, TBS, and HTS grade using the area under these curves (AUC). Nomogram prediction models were constructed and validated based on the results of the multivariate analysis. RESULTS: Among 423 patients, 234 (55.3%) were male and 202 (47.8) were aged ≥ 60 years. The cut-off value of HALP was found to be 37.1 and for TBS to be 6.3. Our univariate results showed that HALP, TBS, and HTS grade were prognostic factors of ICC patients (all P < 0.05), and ROC results showed that HTS had the best predictive value. The Kaplan-Meier curve showed that the prognosis of ICC patients was worse with increasing HTS grade. Additionally, multivariate regression analysis showed that HTS grade, carbohydrate antigen 19-9 (CA19-9), tumor differentiation, and vascular invasion were independent influencing factors for Overall survival (OS) and that HTS grade, CA19-9, CEA, vascular invasion and lymph node invasion were independent influencing factors for recurrence-free survival (RFS) (all P < 0.05). In the first, second, and third years of the training group, the AUCs for OS were 0.867, 0.902, and 0.881, and the AUCs for RFS were 0.849, 0.841, and 0.899, respectively. In the first, second, and third years of the validation group, the AUCs for OS were 0.727, 0.771, and 0.763, and the AUCs for RFS were 0.733, 0.746, and 0.801, respectively. Through the examination of calibration curves and using decision curve analysis (DCA), nomograms based on HTS grade showed excellent predictive performance. CONCLUSIONS: Our nomograms based on HTS grade had excellent predictive effects and may thus be able to help clinicians provide individualized clinical decision for ICC patients.

Discovery of novel tumor-targeted near-infrared probes with 6-substituted pyrrolo[2,3-d]pyrimidines as targeting ligands.

Since the overexpression of folate receptors (FRs) in certain types of cancers, a variety of FR-targeted fluorescent probes for tumor detection have been developed. However, the reported probes almost all have the same targeting ligand of folic acid with various fluorophores and/or linkers. In the present study, a series of novel tumor-targeted near-infrared (NIR) molecular fluorescent probes were designed and synthesized based on previously reported 6-substituted pyrrolo[2,3-d]pyrimidine antifolates. All newly synthesized probes showed specific FR binding in vitro, whereas GT-NIR-4 and GT-NIR-5 with a benzene and a thiophene ring, respectively, on the side chain of pyrrolo[2,3-d]pyrimidine exhibited better FR binding affinity than that of GT-NIR-6 with folic acid as targeting ligand. GT-NIR-4 also showed high tumor uptake in KB tumor-bearing mice with good pharmacokinetic properties and biological safety. This work demonstrates the first attempt to replace folic acid with antifolates as targeting ligands for tumor-targeted NIR probes.

Construction and validation of a novel prognostic model for intrahepatic cholangiocarcinoma based on a combined scoring system of systemic immune-inflammation index and albumin-bilirubin: a multicenter study.

Background: The degree of inflammation and immune status is widely recognized to be associated with intrahepatic cholangiocarcinoma (ICC) and is closely linked to poor postoperative survival. The purpose of this study was to evaluate whether the systemic immune-inflammatory index (SII) and the albumin bilirubin (ALBI) grade together exhibit better predictive strength compared to SII and ALBI separately in patients with ICC undergoing curative surgical resection. Methods: A retrospective analysis was performed on a cohort of 374 patients with histologically confirmed ICC who underwent curative surgical resection from January 2016 to January 2020 at three medical centers. The cohort was divided into a training set comprising 258 patients and a validation set consisting of 116 patients. Subsequently, the prognostic predictive abilities of three indicators, namely SII, ALBI, and SII+ALBI grade, were evaluated. Independent risk factors were identified through univariate and multivariate analyses. The identified independent risk factors were then utilized to construct a nomogram prediction model, and the predictive strength of the nomogram prediction model was assessed through Receiver Operating Characteristic (ROC) survival curves and calibration curves. Results: Univariate analysis of the training set, consisting of 258 eligible patients with ICC, revealed that SII, ALBI, and SII+ALBI grade were significant prognostic factors for overall survival (OS) and recurrence-free survival (RFS) (p < 0.05). Multivariate analysis revealed the independent significance of SII+ALBI grade as a risk factor for postoperative OS and RFS (p < 0.05). Furthermore, we conducted an analysis of the correlation between SII, ALBI, SII+ALBI grade, and clinical features, indicating that SII+ALBI grade exhibited stronger associations with clinical and pathological characteristics compared to SII and ALBI. We constructed a predictive model for postoperative survival in ICC based on SII+ALBI grade, as determined by the results of multivariate analysis. Evaluation of the model's predictive strength was performed through ROC survival curves and calibration curves in the training set and validation set, revealing favorable predictive performance. Conclusion: The SII+ALBI grade, a novel classification based on inflammatory and immune status, serves as a reliable prognostic indicator for postoperative OS and RFS in patients with ICC.

Personalized intrahepatic cholangiocarcinoma prognosis prediction using radiomics: Application and development trend.

Radiomics was proposed by Lambin et al. in 2012 and since then there has been an explosion of related research. There has been significant interest in developing high-throughput methods that can automatically extract a large number of quantitative image features from medical images for better diagnostic or predictive performance. There have also been numerous radiomics investigations on intrahepatic cholangiocarcinoma in recent years, but no pertinent review materials are readily available. This work discusses the modeling analysis of radiomics for the prediction of lymph node metastasis, microvascular invasion, and early recurrence of intrahepatic cholangiocarcinoma, as well as the use of deep learning. This paper briefly reviews the current status of radiomics research to provide a reference for future studies.

Dynamic Unary Convolution in Transformers.

It is uncertain whether the power of transformer architectures can complement existing convolutional neural networks. A few recent attempts have combined convolution with transformer design through a range of structures in series, where the main contribution of this paper is to explore a parallel design approach. While previous transformed-based approaches need to segment the image into patch-wise tokens, we observe that the multi-head self-attention conducted on convolutional features is mainly sensitive to global correlations and that the performance degrades when these correlations are not exhibited. We propose two parallel modules along with multi-head self-attention to enhance the transformer. For local information, a dynamic local enhancement module leverages convolution to dynamically and explicitly enhance positive local patches and suppress the response to less informative ones. For mid-level structure, a novel unary co-occurrence excitation module utilizes convolution to actively search the local co-occurrence between patches. The parallel-designed Dynamic Unary Convolution in Transformer (DUCT) blocks are aggregated into a deep architecture, which is comprehensively evaluated across essential computer vision tasks in image-based classification, segmentation, retrieval and density estimation. Both qualitative and quantitative results show our parallel convolutional-transformer approach with dynamic and unary convolution outperforms existing series-designed structures.

Cardiac Adipose Tissue Segmentation via Image-Level Annotations.

Automatically identifying the structural substrates underlying cardiac abnormalities can potentially provide real-time guidance for interventional procedures. With the knowledge of cardiac tissue substrates, the treatment of complex arrhythmias such as atrial fibrillation and ventricular tachycardia can be further optimized by detecting arrhythmia substrates to target for treatment (i.e., adipose) and identifying critical structures to avoid. Optical coherence tomography (OCT) is a real-time imaging modality that aids in addressing this need. Existing approaches for cardiac image analysis mainly rely on fully supervised learning techniques, which suffer from the drawback of workload on labor-intensive annotation process of pixel-wise labeling. To lessen the need for pixel-wise labeling, we develop a two-stage deep learning framework for cardiac adipose tissue segmentation using image-level annotations on OCT images of human cardiac substrates. In particular, we integrate class activation mapping with superpixel segmentation to solve the sparse tissue seed challenge raised in cardiac tissue segmentation. Our study bridges the gap between the demand on automatic tissue analysis and the lack of high-quality pixel-wise annotations. To the best of our knowledge, this is the first study that attempts to address cardiac tissue segmentation on OCT images via weakly supervised learning techniques. Within an in-vitro human cardiac OCT dataset, we demonstrate that our weakly supervised approach on image-level annotations achieves comparable performance as fully supervised methods trained on pixel-wise annotations.

The molecular structure effects of starches and starch phosphates in the reverse flotation of quartz from hematite.

Native starches and their phosphates with various molecular structures was introduced as the depressant to realize the flotation of quartz from hematite in this study. The present starch phosphates (WSP, NSP, GSP) were modified by the reaction between phosphate and three different corn starches (WS, NS, G50). The synthesis and characterization of starch phosphates found that starch with high amylopectin content was easily modified into starch phosphates. Microflotation tests showed that starch phosphates exhibited stronger depressing abilities of hematite flotation than native starches. Zeta potential measurement showed that both starches and starch phosphates could positively shift the zeta potential of hematite, while starch phosphates had more effects than starches. XPS and MDS indicated that the chemisorption occurred between Fe of hematite surface and CO groups of starch-based depressants. In addition, starch phosphates could adsorb onto the hematite surface through PO groups. MDS also presented that the adsorption strength of starch phosphate was mainly determined by the type and number of generating chelating rings, and the molecular structure of starch significantly affected the formation of chelate rings. The proposed adsorption model insights will significantly promote the development of starch-based depressants for iron ore flotation and other mineral processing applications.

Comparison of chromatin accessibility landscapes during early development of prefrontal cortex between rhesus macaque and human.

Epigenetic information regulates gene expression and development. However, our understanding of the evolution of epigenetic regulation on brain development in primates is limited. Here, we compared chromatin accessibility landscapes and transcriptomes during fetal prefrontal cortex (PFC) development between rhesus macaques and humans. A total of 304,761 divergent DNase I-hypersensitive sites (DHSs) are identified between rhesus macaques and humans, although many of these sites share conserved DNA sequences. Interestingly, most of the cis-elements linked to orthologous genes with dynamic expression are divergent DHSs. Orthologous genes expressed at earlier stages tend to have conserved cis-elements, whereas orthologous genes specifically expressed at later stages seldom have conserved cis-elements. These genes are enriched in synapse organization, learning and memory. Notably, DHSs in the PFC at early stages are linked to human educational attainment and cognitive performance. Collectively, the comparison of the chromatin epigenetic landscape between rhesus macaques and humans suggests a potential role for regulatory elements in the evolution of differences in cognitive ability between non-human primates and humans.

Nanotechnology-Based Weapons to Combat Human Papillomavirus Infection Associated Diseases.

Persistent human papillomavirus (HPV) infection will eventually lead to clinical problems, varying from verrucous lesions to malignancies like cervical cancer, oral cancer, anus cancer, and so on. To address the aforementioned problems, nanotechnology-based strategies have been applied to detect the virus, prevent the interaction between virus and mammalian cells, and treat the virus-infected cells, due mainly to the unique physicochemical properties of nanoparticles. In this regard, many nanotechnology-based chemotherapies, gene therapy, vaccination, or combination therapy have been developed. In this Minireview, we outline the pathogenesis of HPV infection and the recent advances in nanotechnology-based weapons that can be applied in combating HPV-associated diseases.

The prognostic value of arginase-1 and glypican-3 expression levels in patients after surgical intrahepatic cholangiocarcinoma resection.

BACKGROUND: The aim of this study was to investigate the prognostic value of arginase-1 (Arg-1) and glypican-3 (GPC-3) in patients with intrahepatic cholangiocarcinoma (ICC). METHODS: Two hundred and thirty-seven patients with ICC were included in this study. All patients had undergone radical surgery and had complete clinical information. Immunohistochemistry was used to assess the levels of Arg-1 and GPC-3 in ICC tissues. Univariate and multivariate analyses were conducted to identify independent risk factors in ICC. The relationship between Arg-1 and GPC-3 levels and patient survival was determined using the Kaplan-Meier method. RESULTS: High Arg-1 and GPC-3 expression levels were associated with poor prognosis in patients with ICC, and they could be as new prognostic biomarkers in ICC. CONCLUSION: Arg-1 and GPC-3 can serve as independent prognostic biomarkers in ICC.

Recent Developments on Using Nanomaterials to Combat Candida albicans.

Vaginal candidiasis (VC) is a common disease of women and the main pathogen is Candida albicans (C. albicans). C. albicans infection incidence especially its drug resistance have become a global health threat due to the existence of C. albicans biofilms and the low bioavailability of traditional antifungal drugs. In recent years, nanomaterials have made great progresses in the field of antifungal applications. Some researchers have treated fungal infections with inorganic nanoparticles, represented by silver nanoparticles (AgNPs) with antifungal properties. Liposomes, polymeric nanoparticles, metal-organic frameworks (MOFs), and covalent organic frameworks (COFs) were also used to improve the bioavailability of antifungal drugs. Herein, we briefly introduced the recent developments on using above nanomaterials to combat C. albicans in antifungal applications.

Modality independent adversarial network for generalized zero shot image classification.

Zero Shot Learning (ZSL) aims to classify images of unseen target classes by transferring knowledge from source classes through semantic embeddings. The core of ZSL research is to embed both visual representation of object instance and semantic description of object class into a joint latent space and learn cross-modal (visual and semantic) latent representations. However, the learned representations by existing efforts often fail to fully capture the underlying cross-modal semantic consistency, and some of the representations are very similar and less discriminative. To circumvent these issues, in this paper, we propose a novel deep framework, called Modality Independent Adversarial Network (MIANet) for Generalized Zero Shot Learning (GZSL), which is an end-to-end deep architecture with three submodules. First, both visual feature and semantic description are embedded into a latent hyper-spherical space, where two orthogonal constraints are employed to ensure the learned latent representations discriminative. Second, a modality adversarial submodule is employed to make the latent representations independent of modalities to make the shared representations grab more cross-modal high-level semantic information during training. Third, a cross reconstruction submodule is proposed to reconstruct latent representations into the counterparts instead of themselves to make them capture more modality irrelevant information. Comprehensive experiments on five widely used benchmark datasets are conducted on both GZSL and standard ZSL settings, and the results show the effectiveness of our proposed method.

Heterogeneity Measurement of Cardiac Tissues Leveraging Uncertainty Information from Image Segmentation.

Identifying arrhythmia substrates and quantifying their heterogeneity has great potential to provide critical guidance for radio frequency ablation. However, quantitative analysis of heterogeneity on cardiac optical coherence tomography (OCT) images is lacking. In this paper, we conduct the first study on quantifying cardiac tissue heterogeneity from human OCT images. Our proposed method applies a dropout-based Monte Carlo sampling technique to measure the model uncertainty. The heterogeneity information is extracted by decoupling the intra/inter-tissue heterogeneity and tissue boundary uncertainty from the uncertainty measurement. We empirically demonstrate that our model can highlight the subtle features from OCT images, and the heterogeneity information extracted is positively correlated with the tissue heterogeneity information from corresponding histology images.

A Probabilistic Zero-Shot Learning Method via Latent Nonnegative Prototype Synthesis of Unseen Classes.

Zero-shot learning (ZSL), a type of structured multioutput learning, has attracted much attention due to its requirement of no training data for target classes. Conventional ZSL methods usually project visual features into semantic space and assign labels by finding their nearest prototypes. However, this type of nearest neighbor search (NNS)-based method often suffers from great performance degradation because of the nonuniform variances between different categories. In this article, we propose a probabilistic framework by taking covariance into account to deal with the above-mentioned problem. In this framework, we define a new latent space, which has two characteristics. The first is that the features in this space should gather within the classes and scatter between the classes, which is implemented by triplet learning; the second is that the prototypes of unseen classes are synthesized with nonnegative coefficients, which are generated by nonnegative matrix factorization (NMF) of relations between the seen classes and the unseen classes in attribute space. During training, the learned parameters are the projection model for triplet network and the nonnegative coefficients between the unseen classes and the seen classes. In the testing phase, visual features are projected into latent space and assigned with the labels that have the maximum probability among unseen classes for classic ZSL or within all classes for generalized ZSL. Extensive experiments are conducted on four popular data sets, and the results show that the proposed method can outperform the state-of-the-art methods in most circumstances.