Identification of texture MRI brain abnormalities on Fibromyalgia syndrome using interpretable machine learning models.

To provide objective diagnostic markers for fibromyalgia symptoms (FMS) diagnosis, we have created interpretable extreme gradient boosting (XGBoost) models using radiomics to aid in the diagnosis of chronic pain (CP) and to develop nomogram models for diagnosing subgroups of FMS. A group of 54 patients with CP and 71 healthy controls was randomly separated into training and validation groups, using a 7:3 ratio. Radiomics features were extracted from grey-matter and white-matter in the filtered mwp0* image. The Mann-Whitney U test, Spearman's rank correlation test, and least absolute shrinkage and selection operator (LASSO) were utilized to select features. An XGBoost model was created based on these features, and Shapley Additive exPlanations (SHAP) was used for personalization and visual interpretation. A nomogram was developed for the diagnosis of FMS subgroups, utilizing radiomics scores and clinical predictors. The efficacy of the nomogram was evaluated using the area under the receiver operating characteristic curve, while decision curve analysis was employed to evaluate its clinical efficacy. The XGBoost model displays stability in the training validation group, indicating lower overfitting of CP model. The nomogram model combined with the rad-score has a greater ability to distinguish between typical and sub-clinical than the clinical factor model alone. We developed and validated a CP diagnosis model by XGBoost and realized model visualization through SHAP. The rad-score obtained by machine learning was used to build a nomogram model that combines clinical scales to distinguish patients with typical and sub-clinical fibromyalgia.

Asiaticoside ameliorates uterine injury induced by zearalenone in mice by reversing endometrial barrier disruption, oxidative stress and apoptosis.

Zearalenone (ZEA) is a mycotoxin produced by Fusarium fungi that has been shown to have adverse effects on human and animal health, particularly on the fertility of females. As a saponin derived from the medicinal plant Centella asiatica, asiaticoside (AS) has multiple bioactivities. This study aimed to investigate the protective effects of AS on ZEA-induced uterine injury and the underlying mechanism. In the present study, we demonstrated that AS could rescue ZEA-induced uterine histopathological damage and modulate the secretion of sex hormones, including progesterone (P4), luteinizing hormone (LH), and estradiol (E2), in ZEA-treated mice. Moreover, AS alleviated ZEA-induced damage to endometrial barrier function by upregulating the expression of tight junction proteins (ZO-1, occludin, and claudin-3). Further mechanistic investigations indicated that ZEA reduces the antioxidant capacity of uterine tissues, whereas AS improves the antioxidant capacity through activating the Nrf2 signaling pathway. Most notably, the protective effect of AS was blocked in Nrf2 gene knockout (Nrf2-/-) mice. Moreover, the p38/ERK MAPK pathway has been implicated in regulating ZEA toxicity and the beneficial effect of AS. Additionally, an Nrf2 inhibitor (ML385) weaken the suppressive effect of AS on the oxidative stress and MAPK pathway. AS also inhibits ZEA-induced apoptosis in uterine tissues via the PI3K/Akt signaling pathway. However, when the PI3K small molecule inhibitor LY294002 was co-administered, the ability of AS to suppress the expression of apoptosis-related proteins and inhibit ZEA-induced apoptosis decreased. Collectively, these findings reveal the involvement of multiple pathways and targets in the protective effect of AS against ZEA-induced uterine injury, providing a new perspective for the application of AS and the development of a ZEA antidote.

ResNeXt-CC: a novel network based on cross-layer deep-feature fusion for white blood cell classification.

Accurate diagnosis of white blood cells from cytopathological images is a crucial step in evaluating leukaemia. In recent years, image classification methods based on fully convolutional networks have drawn extensive attention and achieved competitive performance in medical image classification. In this paper, we propose a white blood cell classification network called ResNeXt-CC for cytopathological images. First, we transform cytopathological images from the RGB color space to the HSV color space so as to precisely extract the texture features, color changes and other details of white blood cells. Second, since cell classification primarily relies on distinguishing local characteristics, we design a cross-layer deep-feature fusion module to enhance our ability to extract discriminative information. Third, the efficient attention mechanism based on the ECANet module is used to promote the feature extraction capability of cell details. Finally, we combine the modified softmax loss function and the central loss function to train the network, thereby effectively addressing the problem of class imbalance and improving the network performance. The experimental results on the C-NMC 2019 dataset show that our proposed method manifests obvious advantages over the existing classification methods, including ResNet-50, Inception-V3, Densenet121, VGG16, Cross ViT, Token-to-Token ViT, Deep ViT, and simple ViT about 5.5-20.43% accuracy, 3.6-23.56% F1-score, 3.5-25.71% AUROC and 8.1-36.98% specificity, respectively.

Identifying the genetic association between the cerebral cortex and fibromyalgia.

Fibromyalgia (FM) is a central sensitization syndrome that is strongly associated with the cerebral cortex. This study used bidirectional two-sample Mendelian randomization (MR) analysis to investigate the bidirectional causality between FM and the cortical surface area and cortical thickness of 34 brain regions. Inverse variance weighted (IVW) was used as the primary method for this study, and sensitivity analyses further supported the results. The forward MR analysis revealed that genetically determined thinner cortical thickness in the parstriangularis (OR = 0.0567 mm, PIVW = 0.0463), caudal middle frontal (OR = 0.0346 mm, PIVW = 0.0433), and rostral middle frontal (OR = 0.0285 mm, PIVW = 0.0463) was associated with FM. Additionally, a reduced genetically determined cortical surface area in the pericalcarine (OR = 0.9988 mm2, PIVW = 0.0085) was associated with an increased risk of FM. Conversely, reverse MR indicated that FM was associated with cortical thickness in the caudal middle frontal region (ß = -0.0035 mm, PIVW = 0.0265), fusiform region (ß = 0.0024 mm, SE = 0.0012, PIVW = 0.0440), the cortical surface area in the supramarginal (ß = -9.3938 mm2, PIVW = 0.0132), and postcentral regions (ß = -6.3137 mm2, PIVW = 0.0360). Reduced cortical thickness in the caudal middle frontal gyrus is shown to have a significant relationship with FM prevalence in a bidirectional causal analysis.

SLIVER: Unveiling large scale gene regulatory networks of single-cell transcriptomic data through causal structure learning and modules aggregation.

Prevalent Gene Regulatory Network (GRN) construction methods rely on generalized correlation analysis. However, in biological systems, regulation is essentially a causal relationship that cannot be adequately captured solely through correlation. Therefore, it is more reasonable to infer GRNs from a causal perspective. Existing causal discovery algorithms typically rely on Directed Acyclic Graphs (DAGs) to model causal relationships, but it often requires traversing the entire network, which result in computational demands skyrocketing as the number of nodes grows and make causal discovery algorithms only suitable for small networks with one or two hundred nodes or fewer. In this study, we propose the SLIVER (cauSaL dIscovery Via dimEnsionality Reduction) algorithm which integrates causal structural equation model and graph decomposition. SLIVER introduces a set of factor nodes, serving as abstractions of different functional modules to integrate the regulatory relationships between genes based on their respective functions or pathways, thus reducing the GRN to the product of two low-dimensional matrices. Subsequently, we employ the structural causal model (SCM) to learn the GRN within the gene node space, enforce the DAG constraint in the low-dimensional space, and guide each factor to aggregate various functions through cosine similarity. We evaluate the performance of the SLIVER algorithm on 12 real single cell transcriptomic datasets, and demonstrate it outperforms other 12 widely used methods both in GRN inference performance and computational resource usage. The analysis of the gene information integrated by factor nodes also demonstrate the biological explanation of factor nodes in GRNs. We apply it to scRNA-seq of Type 2 diabetes mellitus to capture the transcriptional regulatory structural changes of ß cells under high insulin demand.

Cross-modal attention network for retinal disease classification based on multi-modal images.

Multi-modal eye disease screening improves diagnostic accuracy by providing lesion information from different sources. However, existing multi-modal automatic diagnosis methods tend to focus on the specificity of modalities and ignore the spatial correlation of images. This paper proposes a novel cross-modal retinal disease diagnosis network (CRD-Net) that digs out the relevant features from modal images aided for multiple retinal disease diagnosis. Specifically, our model introduces a cross-modal attention (CMA) module to query and adaptively pay attention to the relevant features of the lesion in the different modal images. In addition, we also propose multiple loss functions to fuse features with modality correlation and train a multi-modal retinal image classification network to achieve a more accurate diagnosis. Experimental evaluation on three publicly available datasets shows that our CRD-Net outperforms existing single-modal and multi-modal methods, demonstrating its superior performance.

UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-Scale Generation and Registration Enhancement.

Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies.

Suppressing label noise in medical image classification using mixup attention and self-supervised learning.

Deep neural networks (DNNs) have been widely applied in medical image classification and achieve remarkable classification performance. These achievements heavily depend on large-scale accurately annotated training data. However, label noise is inevitably introduced in the medical image annotation, as the labeling process heavily relies on the expertise and experience of annotators. Meanwhile, DNNs suffer from overfitting noisy labels, degrading the performance of models. Therefore, in this work, we innovatively devise a noise-robust training approach to mitigate the adverse effects of noisy labels in medical image classification. Specifically, we incorporate contrastive learning and intra-group mixup attention strategies into vanilla supervised learning. The contrastive learning for feature extractor helps to enhance visual representation of DNNs. The intra-group mixup attention module constructs groups and assigns self-attention weights for group-wise samples, and subsequently interpolates massive noisy-suppressed samples through weighted mixup operation. We conduct comparative experiments on both synthetic and real-world noisy medical datasets under various noise levels. Rigorous experiments validate that our noise-robust method with contrastive learning and mixup attention can effectively handle with label noise, and is superior to state-of-the-art methods. An ablation study also shows that both components contribute to boost model performance. The proposed method demonstrates its capability of curb label noise and has certain potential toward real-world clinic applications.

GlanceSeg: Real-time microaneurysm lesion segmentation with gaze-map-guided foundation model for early detection of diabetic retinopathy.

Early-stage diabetic retinopathy (DR) presents challenges in clinical diagnosis due to inconspicuous and minute microaneurysms (MAs), resulting in limited research in this area. Additionally, the potential of emerging foundation models, such as the segment anything model (SAM), in medical scenarios remains rarely explored. In this work, we propose a human-in-the-loop, label-free early DR diagnosis framework called GlanceSeg, based on SAM. GlanceSeg enables real-time segmentation of MA lesions as ophthalmologists review fundus images. Our human-in-the-loop framework integrates the ophthalmologist's gaze maps, allowing for rough localization of minute lesions in fundus images. Subsequently, a saliency map is generated based on the located region of interest, which provides prompt points to assist the foundation model in efficiently segmenting MAs. Finally, a domain knowledge filtering (DKF) module refines the segmentation of minute lesions. We conducted experiments on two newly-built public datasets, i.e., IDRiD and Retinal-Lesions, and validated the feasibility and superiority of GlanceSeg through visualized illustrations and quantitative measures. Additionally, we demonstrated that GlanceSeg improves annotation efficiency for clinicians and further enhances segmentation performance through fine-tuning using annotations. The clinician-friendly GlanceSeg is able to segment small lesions in real-time, showing potential for clinical applications.

Establishment and validation of a nomogram to predict postoperative anemia after total hip arthroplasty.

BACKGROUND: Anemia is a common complication of total hip arthroplasty (THA). In this study, we evaluated the preoperative risk factors for postoperative anemia after THA and developed a nomogram model based on related preoperative and intraoperative factors. METHODS: From January 2020 to May 2023, 927 THA patients at the same medical center were randomly assigned to either the training or validation cohort. The correlation between preoperative and intraoperative risk factors and postoperative anemia after THA was evaluated using univariate and multivariate logistic regression analysis. A nomogram was developed using these predictive variables. The effectiveness and validation for the clinical application of this nomogram were evaluated using the concordance index (C-index), receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA). RESULTS: Through univariate and multivariate logistic regression analysis, 7 independent predictive factors were identified in the training cohort: Lower body mass index (BMI), extended operation time, greater intraoperative bleeding, lower preoperative hemoglobin level, abnormally high preoperative serum amyloid A (SAA) level, history of cerebrovascular disease, and history of osteoporosis. The C-index of the model was 0.871, while the AUC indices for the training and validation cohorts were 84.4% and 87.1%, respectively. In addition, the calibration curves of both cohorts showed excellent consistency between the observed and predicted probabilities. The DCA curves of the training and validation cohorts were high, indicating the high clinical applicability of the model. CONCLUSIONS: Lower BMI, extended operation time, increased intraoperative bleeding, reduced preoperative hemoglobin level, elevated preoperative SAA level, history of cerebrovascular disease, and history of osteoporosis were seven independent preoperative risk factors associated with postoperative anemia after THA. The nomogram developed could aid in predicting postoperative anemia, facilitating advanced preparation, and enhancing blood management. Furthermore, the nomogram could assist clinicians in identifying patients most at risk for postoperative anemia.

Altered whole brain functional activity in patients with fibromyalgia.

OBJECTIVES: Fibromyalgia (FM) is a chronic pain disorder that takes a severe physical and psychological toll on patients and severely reduces their quality of life. In recent years, an increasing number of studies have used functional magnetic resonance imaging (fMRI) to investigate its pathogenesis. However, a recent summary analysis of functional connectivity in patients with FM is lacking. METHODS: We searched bibliographic databases, including PubMed, Web of Science (from inception until September 1st, 2022). Two separate researchers assessed the bias and quality of the studies. In order to further explain the core mechanism for FM, the abnormal brain function of FM was investigated by Activation Likelihood Estimation (ALE) analysis. RESULTS: Twenty-six FM publications (1,056 subjects) were eligible to be included in an ALE analysis. We found that the anterior cingulate (ACC) and insula (Ins) were abnormally active in patients with FM. In particular, the peak coordinates of (8,46,4) and (-46, -4,10) correspond to brain regions that were less active than healthy individuals. Furthermore, the Z-values were 4.46 and 4.97, while the p-values were 4.06 and 3.38. Surprisingly, we found that the degree of pain was negatively correlated with the activation of Ins (SDM-Z = -2.714). CONCLUSIONS: This study demonstrates abnormal brain activation which could lead to increased sensitivity of pain in patients with FM. The study sheds light on the central mechanisms of FM and provides the basis for further research.

Microplastics as potential barriers to ultraviolet light emitting diode inactivation of MS2 bacteriophage: Influence of water-quality parameters.

Microplastics have emerged as a concerning contaminant in drinking water sources, potentially interacting with pathogenic microorganisms and affecting the disinfection processes. In this study, MS2 was selected as an alternative for the human enteric virus. The influence of microplastics polyvinylchloride (MPs-PVC) on ultraviolet light emitting diode (UV-LED) inactivation of MS2 was investigated under various water chemistry conditions, such as MPs-PVC concentration, pH, salinity, and humic acid concentration. The results revealed that higher concentrations of MPs-PVC led to the reduced inactivation of MS2 by decreased UV transmittance, hindering the disinfection process. Additionally, the inactivation efficiency of MS2 in the presence of MPs-PVC was influenced by pH, and acidic solution (pH at 4, 5, and 6) exhibited higher efficiency compared to alkaline solution (pH at 8 and 9) and neutral solution (pH at 7). The low Na+ concentrations (0-50 mM) had a noticeable effect on MS2 inaction efficiency in the presence of MPs-PVC, while the addition of Ca2+ posed an insignificant effect due to the preferential interaction with MPs-PVC. Furthermore, the inactivation rate of MS2 initially increased and then decreased with increasing the concentration of humic acid, which was significantly different without MPs-PVC. These findings shed light on the complex interactions between MPs-PVC and MS2 in the UV-LED disinfection process under various water-quality parameters, contributing to drinking water safety and treatment.

Research trends and hotspots in prostate cancer associated exosome: a bibliometric analysis.

Background: Prostate cancer is viewed as the second most common cancer in men worldwide. In our study, we used bibliometric analysis to construct a visual map of the relationship between prostate cancer and exosomes with the intent of uncovering research trends and current hotspots in this field. Method: We searched the Web of Science Core Collection for all publications in the prostate cancer associated with exosome field came out since 2010. With the assistance of bibliometric analysis software such as VOSviewer and CiteSpace, we conducted data extraction and analysis for countries/regions, institutions, authors, journals, references and keywords. Results: A bibliometric analysis of 990 publications was performed. Since 2010, the published quantity and cited frequency of the prostate cancer-associated exosome field have revealed an increasing tendency. In this field, we visualized the research trends by the means of analyzing the references and keywords. We obtained the statistical data: the total citations of publications have increased to 55,462, the average citation per article has reached 55.3 times, and the H-index has amounted to 110. Our findings supported that USA, China and Italy rank the top countries with both the maximum publications and strongest cooperations. Harvard Medical School, Cedars Sinai Med Ctr, Johns Hopkins University, are top institutions in the center of research as they are held to be. Thery C, Skog J and Taylor DD are the leading and outstanding professors and researchers. And top journals like Prostate, Plos One and Journal of Extracellular Vesicle expressed keen interests in this field. Based on our analysis and research, we believe that this field is attracting more and more attention and will focus on tumor bone metastasis, drug delivery, and tumor suppressor. Conclusion: In the past 12 years, researchers have dedicated their efforts to prostate cancer associated exosome. On the basis of previous studies, scientists are showing increasingly solicitude for the role of exosome in prostate cancer progression and potential therapy such as drug delivery.

Global research trends of the application of artificial intelligence in bladder cancer since the 21st century: a bibliometric analysis.

Introduction: Since the significant breakthroughs in artificial intelligence (AI) algorithms, the application of AI in bladder cancer has rapidly expanded. AI can be used in all aspects of the bladder cancer field, including diagnosis, treatment and prognosis prediction. Nowadays, these technologies have an excellent medical auxiliary effect and are in explosive development, which has aroused the intense interest of researchers. This study will provide an in-depth analysis using bibliometric analysis to explore the trends in this field. Method: Documents regarding the application of AI in bladder cancer from 2000 to 2022 were searched and extracted from the Web of Science Core Collection. These publications were analyzed by bibliometric analysis software (CiteSpace, Vosviewer) to visualize the relationship between countries/regions, institutions, journals, authors, references, keywords. Results: We analyzed a total of 2368 publications. Since 2016, the number of publications in the field of AI in bladder cancer has increased rapidly and reached a breathtaking annual growth rate of 43.98% in 2019. The U.S. has the largest research scale, the highest study level and the most significant financial support. The University of North Carolina is the institution with the highest level of research. EUROPEAN UROLOGY is the most influential journal with an impact factor of 24.267 and a total citation of 11,848. Wiklund P. has the highest number of publications, and Menon M. has the highest number of total citations. We also find hot research topics within the area through references and keywords analysis, which include two main parts: AI models for the diagnosis and prediction of bladder cancer and novel robotic-assisted surgery for bladder cancer radicalization and urinary diversion. Conclusion: AI application in bladder cancer is widely studied worldwide and has shown an explosive growth trend since the 21st century. AI-based diagnostic and predictive models will be the next protagonists in this field. Meanwhile, the robot-assisted surgery is still a hot topic and it is worth exploring the application of AI in it. The advancement and application of algorithms will be a massive driving force in this field.

Early clinical efficacy analysis of enhanced recovery following surgery combined with interscalene brachial plexus block for arthroscopic rotator cuff repair.

To explore the early clinical value of enhanced recovery after surgery (ERAS) with interscalene brachial plexus block (ISB) for arthroscopic rotator cuff repair (ARCR). We enrolled 240 patients who underwent arthroscopic rotator cuff repair, randomly divided into 3 groups (n = 80 each). Groups A, B, and C underwent only surgery, surgery + ERAS, and ISB + surgery + ERAS, respectively. We analyzed the clinical data and postoperative indicators for the 3 patient groups. Group comparisons of clinical data and postoperative indicators revealed no significant differences in clinical characteristics (P > .05). Group C showed superior Visual Analog Scale scores at 0-6 and 6-24 hours postoperatively (P < .05), and the shortest length of hospital stay (LOS) (P < .05). At 6 weeks and 3 months postoperatively, Constant-Murley shoulder score and University of California-Los Angeles scores were better in Groups B and C than in Group A (P < .05). Joint swelling was more common in Group A than in Groups B and C (P < .05) but with no significant difference in the incidence of postoperative stiffness (P > .05). ERAS can relieve postoperative pain, shorten LOS, and help restore shoulder joint mobility, thereby reducing postoperative swelling. ISB + ERAS optimized pain control and allowed a shorter LOS, but had similar effects on early functional recovery and complications.

Retinal layers changes in patients with age-related macular degeneration treated with intravitreal anti-VEGF agents.

BACKGROUND: The purpose of this study was to investigate retinal layers changes in patients with age-related macular degeneration (AMD) treated with anti-vascular endothelial growth factor (anti-VEGF) agents and to evaluate if these changes may affect treatment response. METHODS: This study included 496 patients with AMD or PCV who were treated with anti-VEGF agents and followed up for at least 6 months. A comprehensive analysis of retinal layers affecting visual acuity was conducted. To eliminate the fact that the average thickness calculated may lead to differences tending to converge towards the mean, we proposed that the retinal layer was divided into different regions and the thickness of the retinal layer was analyzed at the same time. The labeled data will be publicly available for further research. RESULTS: Compared to baseline, significant improvement in visual acuity was observed in patients at the 6-month follow-up. Statistically significant reduction in central retinal thickness and separate retinal layer thickness was also observed (p < 0.05). Among all retinal layers, the thickness of the external limiting membrane to retinal pigment epithelium/Bruch's membrane (ELM to RPE/BrM) showed the greatest reduction. Furthermore, the subregional assessment revealed that the ELM to RPE/BrM decreased greater than that of other layers in each region. CONCLUSION: Treatment with anti-VEGF agents effectively reduced retinal thickness in all separate retinal layers as well as the retina as a whole and anti-VEGF treatment may be more targeted at the edema site. These findings could have implications for the development of more precise and targeted therapies for AMD treatment.

A lightweight network based on dual-stream feature fusion and dual-domain attention for white blood cells segmentation.

Introduction: Accurate white blood cells segmentation from cytopathological images is crucial for evaluating leukemia. However, segmentation is difficult in clinical practice. Given the very large numbers of cytopathological images to be processed, diagnosis becomes cumbersome and time consuming, and diagnostic accuracy is also closely related to experts' experience, fatigue and mood and so on. Besides, fully automatic white blood cells segmentation is challenging for several reasons. There exists cell deformation, blurred cell boundaries, and cell color differences, cells overlapping or adhesion. Methods: The proposed method improves the feature representation capability of the network while reducing parameters and computational redundancy by utilizing the feature reuse of Ghost module to reconstruct a lightweight backbone network. Additionally, a dual-stream feature fusion network (DFFN) based on the feature pyramid network is designed to enhance detailed information acquisition. Furthermore, a dual-domain attention module (DDAM) is developed to extract global features from both frequency and spatial domains simultaneously, resulting in better cell segmentation performance. Results: Experimental results on ALL-IDB and BCCD datasets demonstrate that our method outperforms existing instance segmentation networks such as Mask R-CNN, PointRend, MS R-CNN, SOLOv2, and YOLACT with an average precision (AP) of 87.41%, while significantly reducing parameters and computational cost. Discussion: Our method is significantly better than the current state-of-the-art single-stage methods in terms of both the number of parameters and FLOPs, and our method has the best performance among all compared methods. However, the performance of our method is still lower than the two-stage instance segmentation algorithms. in future work, how to design a more lightweight network model while ensuring a good accuracy will become an important problem.

Discriminative ensemble meta-learning with co-regularization for rare fundus diseases diagnosis.

Deep neural networks (DNNs) have been widely applied in the medical image community, contributing to automatic ophthalmic screening systems for some common diseases. However, the incidence of fundus diseases patterns exhibits a typical long-tailed distribution. In clinic, a small number of common fundus diseases have sufficient observed cases for large-scale analysis while most of the fundus diseases are infrequent. For these rare diseases with extremely low-data regimes, it is challenging to train DNNs to realize automatic diagnosis. In this work, we develop an automatic diagnosis system for rare fundus diseases, based on the meta-learning framework. The system incorporates a co-regularization loss and the ensemble-learning strategy into the meta-learning framework, fully leveraging the advantage of multi-scale hierarchical feature embedding. We initially conduct comparative experiments on our newly-constructed lightweight multi-disease fundus images dataset for the few-shot recognition task (namely, FundusData-FS). Moreover, we verify the cross-domain transferability from miniImageNet to FundusData-FS, and further confirm our method's good repeatability. Rigorous experiments demonstrate that our method can detect rare fundus diseases, and is superior to the state-of-the-art methods. These investigations demonstrate that the potential of our method for the real clinical practice is promising.

Computational approaches for the reconstruction of optic nerve fibers along the visual pathway from medical images: a comprehensive review.

Optic never fibers in the visual pathway play significant roles in vision formation. Damages of optic nerve fibers are biomarkers for the diagnosis of various ophthalmological and neurological diseases; also, there is a need to prevent the optic nerve fibers from getting damaged in neurosurgery and radiation therapy. Reconstruction of optic nerve fibers from medical images can facilitate all these clinical applications. Although many computational methods are developed for the reconstruction of optic nerve fibers, a comprehensive review of these methods is still lacking. This paper described both the two strategies for optic nerve fiber reconstruction applied in existing studies, i.e., image segmentation and fiber tracking. In comparison to image segmentation, fiber tracking can delineate more detailed structures of optic nerve fibers. For each strategy, both conventional and AI-based approaches were introduced, and the latter usually demonstrates better performance than the former. From the review, we concluded that AI-based methods are the trend for optic nerve fiber reconstruction and some new techniques like generative AI can help address the current challenges in optic nerve fiber reconstruction.