The Role of Artificial Intelligence in Epiretinal Membrane Care: A Scoping Review

Topic

In ophthalmology, artificial intelligence (AI) demonstrates potential in using ophthalmic imaging across diverse diseases, often matching ophthalmologists' performance. However, the range of machine learning models for epiretinal membrane (ERM) management, which differ in methodology, application, and performance, remains largely unsynthesized.

Clinical Relevance

Epiretinal membrane management relies on clinical evaluation and imaging, with surgical intervention considered in cases of significant impairment. AI analysis of ophthalmic images and clinical features could enhance ERM detection, characterization, and prognostication, potentially improving clinical decision-making. This scoping review aims to evaluate the methodologies, applications, and reported performance of AI models in ERM diagnosis, characterization, and prognostication.

Methods

A comprehensive literature search was conducted across 5 electronic databases including Ovid MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science Core Collection from inception to November 14, 2024. Studies pertaining to AI algorithms in the context of ERM were included. The primary outcomes measured will be the reported design, application in ERM management, and performance of each AI model.

Results

Three hundred ninety articles were retrieved, with 33 studies meeting inclusion criteria. There were 30 studies (91%) reporting their training and validation methods. Altogether, 61 distinct AI models were included. OCT scans and fundus photographs were used in 26 (79%) and 7 (21%) papers, respectively. Supervised learning and both supervised and unsupervised learning were used in 32 (97%) and 1 (3%) studies, respectively. Twenty-seven studies (82%) developed or adapted AI models using images, whereas 5 (15%) had models using both images and clinical features, and 1 (3%) used preoperative and postoperative clinical features without ophthalmic images. Study objectives were categorized into 3 stages of ERM care. Twenty-three studies (70%) implemented AI for diagnosis (stage 1), 1 (3%) identified ERM characteristics (stage 2), and 6 (18%) predicted vision impairment after diagnosis or postoperative vision outcomes (stage 3). No articles studied treatment planning. Three studies (9%) used AI in stages 1 and 2. Of the 16 studies comparing AI performance to human graders (i.e., retinal specialists, general ophthalmologists, and trainees), 10 (63%) reported equivalent or higher performance.

Conclusion

Artificial intelligence-driven assessments of ophthalmic images and clinical features demonstrated high performance in detecting ERM, identifying its morphological properties, and predicting visual outcomes following ERM surgery. Future research might consider the validation of algorithms for clinical applications in personal treatment plan development, ideally to identify patients who might benefit most from surgery.

Financial Disclosures

The author(s) have no proprietary or commercial interest in any materials discussed in this article.

A comprehensive primer and review of PROTACs and their In Silico design

The cutting-edge technique of Proteolysis Targeting Chimeras, or PROTACs, has gained significant attention as a viable approach for specific protein degradation. This innovative technology has vast potential in fields such as cancer therapy and drug development. The development of effective and specific therapies for a range of diseases is within reach with PROTACs, which can target previously "undruggable" proteins while circumventing the off-target effects of conventional small molecule inhibitors. This manuscript aims to discuss the application of in silico techniques to the design of these groundbreaking molecules and develop PROTAC complexes, in order to identify potential PROTAC candidates with favorable drug-like properties. Additionally, this manuscript reviews the strengths and weaknesses of these methods to demonstrate their utility and highlights the challenges and future prospects of in silico PROTAC design. The present review provides a valuable and beginner-friendly resource for researchers and drug developers interested in using in silico methods for PROTAC design, specifically ternary structure prediction.

Genome-Wide Identification, Phylogeny, and Abiotic Stress Response Analysis of OSCA Family Genes in the Alpine Medicinal Herb Notopterygium franchetii

Hyperosmolality-gated calcium-permeable cation channel protein denoted as OSCA, which are mechanosensitive pore-forming ion channels, play a pivotal role in plants' responses to abiotic stressors. Notopterygium franchetii, an endemic perennial plant species distributed in the Qinghai-Tibetan Plateau and its adjacent high-altitude regions, is likely to have undergone adaptive evolution in response to extreme abiotic stress conditions. The current study was conducted to characterize the genome-wide characteristics and phylogenetic evolution of the OSCA gene family in N. franchetii and identify its response patterns to drought and high-temperature stresses. We examined the gene family's structural features, phylogenetic relationships, and response to abiotic stresses. The N. franchetii genome had 29 OSCA gene family members on 11 chromosomes. Subcellular localization showed they were mainly in the cell membrane, and a promoter cis-acting element study found that the OSCA gene family contained methyl jasmonate, abscisic acid, and various adversity and hormone response components. Under drought stress, most of the NofOSCAs genes showed a tendency to increase over time in the roots of N. franchetii, while in the aboveground parts, most of the NofOSCAs genes showed a tendency to increase and then decrease. The expression of different NofOSCAs genes in N. franchetii also showed alternating changes under high-temperature stress. Nine members of NofOSCAs were found to be linked to the PPI network, and these members were involved in membrane structure, transmembrane transport, and ion channel function. Our analysis of differential expression revealed that the expression of OSCA genes differed among the different N. franchetii tissues, with the roots exhibiting the highest average expression level, and many genes displayed tissue-specific high expression patterns. These results provided novel insights into the phylogenetic evolution and abiotic stress response mechanisms in the high-altitude medicinal herb N. franchetii.

Relationships Between Breast Edema and Axillary Lymph Node Metastasis in Breast Cancer

Background/Objectives: To investigate the association between MRI features of primary breast cancers with axillary status, aiming to identify possible imaging biomarkers. Methods: Patients diagnosed with breast cancer between 2021 and 2023 in our clinic were retrospectively evaluated, and those that presented as mass lesions on preoperative MRI examinations (n: 123) were included in the study. Patients with and without metastatic axillary lymph nodes (mALN) were compared in terms of breast density, background parenchymal enhancement, tumor size, location in the breast, distance from the skin, patient age, presence of edema, multiple foci, histopathological type and molecular subtype of tumors. In multifocal/multicentric cases, the largest lesion was taken into consideration. Prepectoral and subcutaneous edema were considered diffuse edema, while perilesional edema was considered focal edema. MannWhitney U/Student-t test, Chi- square/Fischer Exact tests and logistic regression analysis were used for statistical analyses as appropriate. Results: Axilla was positive in 88 patients. There was a statistically significant difference in terms of edema, age, molecular subtype, Ki-67 index, number of lesions, tumor size, and laterality between the two groups (p < 0.05). Univariate logistic regression analysis showed that all included variables were statistically significant (p < 0.05). Multivariate logistic regression analysis revealed that presence of edema (OR: 2.46 CI; 1.11-5.48, p = 0.027) and multiple lesions (OR: 1.86 CI; 1.01-3.43, p = 0.046) were significantly associated with mALN. There was no significant difference between peritumoral edema and diffuse edema. Conclusions: Our study showed a statistically significant relationship between the axillary status and the presence of edema and multiple tumoral lesions on MRI. These findings have a potential to serve as prognostic imaging biomarkers for predicting the presence of mALN. Further studies with larger case series are needed to support our findings.

Optical Coherence Tomography Characteristics Between Idiopathic Epiretinal Membranes and Secondary Epiretinal Membranes due to Peripheral Retinal Hole

Purpose: In clinical practice, some eyes preoperatively diagnosed with "idiopathic epiretinal membranes (iERM)" will be amended to "secondary epiretinal membranes (sERM)" once peripheral retinal hole is detected. This study utilized optical coherence tomography (OCT) images to compare the characteristics between the iERM and sERM due to peripheral retinal hole (PRH). Methods: In this retrospective, cross-sectional study, 635 eyes that had undergone pars plana vitrectomy with membrane peeling were enrolled. A total of 115 eyes (18.1%) detected with peripheral retinal holes were allocated to the sERM-PRH group while the other 520 eyes were to the iERM group. The demographic data and OCT characteristics were compared between the two groups. Besides, all the eyes were evaluated by a double-grading scheme: severity grading of ERM progression into four stages plus anatomical classification into three kinds of part-thickness macular holes associated with ERMs. Results: No significant difference was found in age, gender, symptom duration, axial length, or best-corrected visual acuity between the two groups. There was also no difference concerning the features based on OCT, ranging from central macular thickness, the ratios of the photoreceptor inner/outer segment junction line defect, intraretinal fluid, cotton ball sign, to epiretinal proliferation. However, the native difference in parafoveal thickness between the temporal and nasal quadrants was observed in the iERM group, yet disappeared in the sERM-PRH group. Moreover, eyes between the two groups were distributionally similar in both grading scales. Conclusion: Our results demonstrated that even OCT images could hardly provide effective clues for early differentiating sERM from iERM, which highlighted the necessity of a thorough pre- and intro-operative fundus examination of the peripheral retina for clinicians.

Healthy competition? Market structure and the quality of clinical care given to standardised patients in Tanzania

The private health care sector in many low- and middle-income countries is rapidly expanding. Private sector advocates have long argued that market competition drives private providers to become more efficient and responsive to patients but empirical studies are limited to mostly high-income settings. We examine whether the number of competing health facilities in close proximity is associated with quality and prices, in a sample of 228 private for-profit and faith-based facilities in Tanzania. Primary data collection took place in the health facilities between February and June 2018. By exploiting data on the quality of clinical care given to unannounced standardised patients, we are able to compare quality across providers without confounding due to patient characteristics. We find that more local competition is associated with poorer clinical quality. The former is driven by an increase in unnecessary care rather than a reduction in appropriate care. Policymakers in such settings should be cautious in assuming that market competition will drive up quality of care.

Artificial intelligence-based assessment of imaging biomarkers in epiretinal membrane surgery

PurposeThis study investigated the applicability of a validated AI-algorithm for analyzing different retinal biomarkers in eyes affected by epiretinal membranes (ERMs) before and after surgery.MethodsA retrospective study included 40 patients surgically treated for ERMs removal between November 2022 and January 2024. Pars plana vitrectomy with ERM/ILM peeling was performed by a single experienced surgeon. A validated AI algorithm was used to analyze OCT scans, focusing on intraretinal fluid (IRF) and subretinal fluid (SRF) volumes, external limiting membrane (ELM) and ellipsoid zone (EZ) interruption percentages and hyper-reflective foci (HRF) counts.ResultsPostoperative best corrected visual acuity (BCVA) significantly improved (p < 0.01), and central macular thickness (CMT) decreased from 483.61 ± 96.32 to 386.82 ± 94.86 µm (p = 0.001). IRF volume reduced from 0.283 ± 0.39 mm3 to 0.142 ± 0.27 mm3 (p = 0.036) particularly in the central 1 mm-circle. SRF, HRF and EZ/ELM interruption percentages exhibited no significant differences (p > 0.05). Significant correlations (p < 0.05) were found between preoperative BCVA and postoperative BCVA (r = 0.45); CMT reduction and postoperative BCVA (r = 0.42), preoperative IRF and Visual Recovery (r = -0.48), ELM and EZ interruption and visual recovery (r = -0.43 and r = -0.47 respectively). Multivariate analysis demonstrated that fluid distribution, especially in the central subfield, correlated with BCVA recovery (R2 = 0.38; p < 0.05; Pillai's Trace = 0.79).ConclusionThe study highlights AI's potential in quantifying OCT biomarkers in ERMs surgery. The findings suggest that improved BCVA is associated with reduced CMT, IRF, and redistribution of IRF towards the periphery. EZ and ELM integrities remain crucial prognostic factors, emphasizing the importance of the preoperative analysis.

Yolo-pest: an optimized YoloV8x for detection of small insect pests using smart traps

Fruit flies and fall-armyworm are one of the major insect pest that adversely affect fruit and crops, whereas fall-armyworm is also a highly destructive pest in maize crop but also damage other economically important field crops and vegetables. Adults of both pests can fly, making it hard to monitor them in the field. This study focuses on fine-tuning the YoloV8x model for automated monitoring and identifying insect pests, like fruit flies and fall-armyworms, in open fields and closed environments using IoT-based Smart Traps. The conventional techniques for monitoring of these insect pests involve pheromone attractants and sticky traps that require regular farm visits. We developed an IoT-based device, called Smart Trap, that attracts insect pests with pheromones and captures real-time images using cameras and IoT sensors. Its main objective is automated pest monitoring in fields or indoor grain storage houses. Images captured by smart traps are transmitted to the server, where Yolo-pest, a fine-tuned YoloV8x model with customized hyperparameters performs in real time for object detection. The performance of the smart trap was evaluated in a mango orchard (Fruit Flies) and maize field (fall Armyworm) in an arid climate, achieving a 94% average detection accuracy. The validation process on grayscale and coloured images further confirmed the model's consistent accuracy in identifying insect pests in maze crop and mango orchards. The mobile application also enhances the practical utility as having a user-friendly interface for real time identification of insect pest. Farmers can easily acces the information and data remotely that empowering them for efficient pest maangment.

Artificial Intelligence Performance in Image-Based Cancer Identification: Umbrella Review of Systematic Reviews

BACKGROUND

Artificial intelligence (AI) has the potential to transform cancer diagnosis, ultimately leading to better patient outcomes.

OBJECTIVE

We performed an umbrella review to summarize and critically evaluate the evidence for the AI-based imaging diagnosis of cancers.

METHODS

PubMed, Embase, Web of Science, Cochrane, and IEEE databases were searched for relevant systematic reviews from inception to June 19, 2024. Two independent investigators abstracted data and assessed the quality of evidence, using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Systematic Reviews and Research Syntheses. We further assessed the quality of evidence in each meta-analysis by applying the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria. Diagnostic performance data were synthesized narratively.

RESULTS

In a comprehensive analysis of 158 included studies evaluating the performance of AI algorithms in noninvasive imaging diagnosis across 8 major human system cancers, the accuracy of the classifiers for central nervous system cancers varied widely (ranging from 48% to 100%). Similarities were observed in the diagnostic performance for cancers of the head and neck, respiratory system, digestive system, urinary system, female-related systems, skin, and other sites. Most meta-analyses demonstrated positive summary performance. For instance, 9 reviews meta-analyzed sensitivity and specificity for esophageal cancer, showing ranges of 90%-95% and 80%-93.8%, respectively. In the case of breast cancer detection, 8 reviews calculated the pooled sensitivity and specificity within the ranges of 75.4%-92% and 83%-90.6%, respectively. Four meta-analyses reported the ranges of sensitivity and specificity in ovarian cancer, and both were 75%-94%. Notably, in lung cancer, the pooled specificity was relatively low, primarily distributed between 65% and 80%. Furthermore, 80.4% (127/158) of the included studies were of high quality according to the JBI Critical Appraisal Checklist, with the remaining studies classified as medium quality. The GRADE assessment indicated that the overall quality of the evidence was moderate to low.

CONCLUSIONS

Although AI shows great potential for achieving accelerated, accurate, and more objective diagnoses of multiple cancers, there are still hurdles to overcome before its implementation in clinical settings. The present findings highlight that a concerted effort from the research community, clinicians, and policymakers is required to overcome existing hurdles and translate this potential into improved patient outcomes and health care delivery.

TRIAL REGISTRATION

PROSPERO CRD42022364278; https://www.crd.york.ac.uk/PROSPERO/view/CRD42022364278.

Deep learning-based breast MRI for predicting axillary lymph node metastasis: a systematic review and meta-analysis

BACKGROUND

To perform a systematic review and meta-analysis that assesses the diagnostic performance of deep learning algorithms applied to breast MRI for predicting axillary lymph nodes metastases in patients of breast cancer.

METHODS

A systematic literature search in PubMed, MEDLINE, and Embase databases for articles published from January 2004 to February 2025. Inclusion criteria were: patients with breast cancer; deep learning using MRI images was applied to predict axillary lymph nodes metastases; sufficient data were present; original research articles. Quality Assessment of Diagnostic Accuracy Studies-AI and Checklist for Artificial Intelligence in Medical Imaging was used to assess the quality. Statistical analysis included pooling of diagnostic accuracy and investigating between-study heterogeneity. A summary receiver operating characteristic curve (SROC) was performed. R statistical software (version 4.4.0) was used for statistical analyses.

RESULTS

A total of 10 studies were included. The pooled sensitivity and specificity were 0.76 (95% CI, 0.67-0.83) and 0.81 (95% CI, 0.74-0.87), respectively, with both measures having moderate between-study heterogeneity (I2 = 61% and 60%, respectively; p < 0.01). The SROC analysis yielded a weighted AUC of 0.788.

CONCLUSION

This meta-analysis demonstrates that deep learning algorithms applied to breast MRI offer promising diagnostic performance for predicting axillary lymph node metastases in breast cancer patients. Incorporating deep learning into clinical practice may enhance decision-making by providing a non-invasive method to more accurately predict lymph node involvement, potentially reducing unnecessary surgeries.

In Situ Monitoring and Estimation of α-Lactose Monohydrate Crystal Growth in the Microdroplets

In this study, a new microfluidic chip that generates microscale emulsion droplets to confine α-lactose monohydrate crystal (α-LM) solutions in the microdroplets was used to prepare uniform-sized crystals. In situ observations for α-LM growth were performed by using a dual-camera structured light system consisting of two cameras fixed at different angles, achieving a satisfactory three-dimensional (3D) shape reconstruction. After 3D shape reconstruction from image processing, the 3D axial size, crystal surface area, and volume of α-LM in the microdroplets were measured at different time intervals. By fitting these data, we could quantitatively estimate 3D axial growth rates, real-time concentration, and supersaturation (σ) of α-LM. The experimental results show that the growth rate of α-LM from aqueous solution is the fastest in the nucleated 100-150 min after nucleation, and the particle volume of α-LM is about 7.08 × 10-6 cm3 at σ = 1.5. The fitted polynomial coefficients show that the growth processes of α-LM in the microdroplets are mainly between second-order growth and fourth-order growth. The nucleation and growth mechanisms of α-LM in microdroplets are also clarified. In general, the real-time monitoring of α-LM growth in the microdroplets could avoid interference and damage to the crystals from various impurities and external forces, maintaining the characteristics of the natural growth of the crystals. The results demonstrate the applicability of the proposed method by correctly predicting the experimental morphologies of α-LM grown from the solutions.

LiteMamba-Bound: A lightweight Mamba-based model with boundary-aware and normalized active contour loss for skin lesion segmentation

In the field of medical science, skin segmentation has gained significant importance, particularly in dermatology and skin cancer research. This domain demands high precision in distinguishing critical regions (such as lesions or moles) from healthy skin in medical images. With growing technological advancements, deep learning models have emerged as indispensable tools in addressing these challenges. One of the state-of-the-art modules revealed in recent years, the 2D Selective Scan (SS2D), based on state-space models that have already seen great success in natural language processing, has been increasingly adopted and is gradually replacing Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Leveraging the strength of this module, this paper introduces LiteMamba-Bound, a lightweight model with approximately 957K parameters, designed for skin image segmentation tasks. Notably, the Channel Attention Dual Mamba (CAD-Mamba) block is proposed within both the encoder and decoder alongside the Mix Convolution with Simple Attention bottleneck block to emphasize key features. Additionally, we propose the Reverse Attention Boundary Module to highlight challenging boundary features. Also, the Normalized Active Contour loss function presented in this paper significantly improves the model's performance compared to other loss functions. To validate performance, we conducted tests on two skin image datasets, ISIC2018 and PH2, with results consistently showing superior performance compared to other models. Our code will be made publicly available at: https://github.com/kwanghwi242/A-new-segmentation-model.

A privacy-preserving dependable deep federated learning model for identifying new infections from genome sequences

The traditional molecular-based identification (TMID) technique of new infections from genome sequences (GSs) has made significant contributions so far. However, due to the sensitive nature of the medical data, the TMID technique of transferring the patient's data to the central machine or server may create severe privacy and security issues. In recent years, the progression of deep federated learning (DFL) and its remarkable success in many domains has guided as a potential solution in this field. Therefore, we proposed a dependable and privacy-preserving DFL-based identification model of new infections from GSs. The unique contributions include automatic effective feature selection, which is best suited for identifying new infections, designing a dependable and privacy-preserving DFL-based LeNet model, and evaluating real-world data. To this end, a comprehensive experimental performance evaluation has been conducted. Our proposed model has an overall accuracy of 99.12% after independently and identically distributing the dataset among six clients. Moreover, the proposed model has a precision of 98.23%, recall of 98.04%, f1-score of 96.24%, Cohen's kappa of 83.94%, and ROC AUC of 98.24% for the same configuration, which is a noticeable improvement when compared to the other benchmark models. The proposed dependable model, along with empirical results, is encouraging enough to recognize as an alternative for identifying new infections from other virus strains by ensuring proper privacy and security of patients' data.

Using deep convolutional networks combined with signal processing techniques for accurate prediction of surface quality

This paper uses deep learning techniques to present a framework for predicting and classifying surface roughness in milling parts. The acoustic emission (AE) signals captured during milling experiments were converted into 2D images using four encoding Signal processing: Segmented Stacked Permuted Channels (SSPC), Segmented sampled Stacked Channels (SSSC), Segmented sampled Stacked Channels with linear downsampling (SSSC*), and Recurrence Plots (RP). These images were fed into convolutional neural networks, including VGG16, ResNet18, ShuffleNet and CNN-LSTM for predicting the category of surface roughness values. This work used the average surface roughness (Ra) as the main roughness attribute. Among the Signal processing techniques, SSPC could achieve the highest accuracy, above 98%, across most models, owing to minimal preprocessing of signals. ShuffleNet demonstrated a strong combination of accuracy (96-98%) and low computational cost. The robustness of networks was evaluated by introducing Gaussian noise at two levels. SSPC and SSSC were the most noise-resistant approaches, maintaining testing accuracy above 90% at high noise. Augmenting acoustic data with machining parameters (cutting speed, depth, feed rate, tool type) as additional inputs could improve the model's accuracy and convergence rate, especially for noisy data. Finally, ShuffleNet was identified as an optimal architecture for real-time monitoring due to its accuracy, noise resilience, and low computational cost. In summary, this study demonstrates the capability of deep convolutional networks combined with innovative signal encoding techniques to accurately predict surface roughness values and categories under various cutting conditions. Based on process signatures, the framework provides a data-driven approach to monitoring and optimizing machining processes in real-time.

Axillary lymph node metastasis in breast cancer: from historical axillary surgery to updated advances in the preoperative diagnosis and axillary management

Axillary lymph node status, which was routinely assessed by axillary lymph node dissection (ALND) until the 1990s, is a crucial factor in determining the stage, prognosis, and therapeutic strategy used for breast cancer patients. Axillary surgery for breast cancer patients has evolved from ALND to minimally invasive approaches. Over the decades, the application of noninvasive imaging techniques, machine learning approaches and emerging clinical prediction models for the detection of axillary lymph node metastasis greatly improves clinical diagnostic efficacy and provides optimal surgical selection. In this work, we summarize the historical axillary surgery and updated perspectives of axillary management for breast cancer patients.

Hyperparameter Optimization for Tomato Leaf Disease Recognition Based on YOLOv11m

The automated recognition of disease in tomato leaves can greatly enhance yield and allow farmers to manage challenges more efficiently. This study investigates the performance of YOLOv11 for tomato leaf disease recognition. All accessible versions of YOLOv11 were first fine-tuned on an improved tomato leaf disease dataset consisting of a healthy class and 10 disease classes. YOLOv11m was selected for further hyperparameter optimization based on its evaluation metrics. It achieved a fitness score of 0.98885, with a precision of 0.99104, a recall of 0.98597, and a mAP@.5 of 0.99197. This model underwent rigorous hyperparameter optimization using the one-factor-at-a-time (OFAT) algorithm, with a focus on essential parameters such as batch size, learning rate, optimizer, weight decay, momentum, dropout, and epochs. Subsequently, random search (RS) with 100 configurations was performed based on the results of OFAT. Among them, the C47 model demonstrated a fitness score of 0.99268 (a 0.39% improvement), with a precision of 0.99190 (0.09%), a recall of 0.99348 (0.76%), and a mAP@.5 of 0.99262 (0.07%). The results suggest that the final model works efficiently and is capable of accurately detecting and identifying tomato leaf diseases, making it suitable for practical farming applications.

Attention-Guided Residual U-Net with SE Connection and ASPP for Watershed-Based Cell Segmentation in Microscopy Images

Time-lapse microscopy imaging is a crucial technique in biomedical studies for observing cellular behavior over time, providing essential data on cell numbers, sizes, shapes, and interactions. Manual analysis of hundreds or thousands of cells is impractical, necessitating the development of automated cell segmentation approaches. Traditional image processing methods have made significant progress in this area, but the advent of deep learning methods, particularly those using U-Net-based networks, has further enhanced performance in medical and microscopy image segmentation. However, challenges remain, particularly in accurately segmenting touching cells in images with low signal-to-noise ratios. Existing methods often struggle with effectively integrating features across different levels of abstraction. This can lead to model confusion, particularly when important contextual information is lost or the features are not adequately distinguished. The challenge lies in appropriately combining these features to preserve critical details while ensuring robust and accurate segmentation. To address these issues, we propose a novel framework called RA-SE-ASPP-Net, which incorporates Residual Blocks, Attention Mechanism, Squeeze-and-Excitation connection, and Atrous Spatial Pyramid Pooling to achieve precise and robust cell segmentation. We evaluate our proposed architecture using an induced pluripotent stem cell reprogramming dataset, a challenging dataset that has received limited attention in this field. Additionally, we compare our model with different ablation experiments to demonstrate its robustness. The proposed architecture outperforms the baseline models in all evaluated metrics, providing the most accurate semantic segmentation results. Finally, we applied the watershed method to the semantic segmentation results to obtain precise segmentations with specific information for each cell.

Exploration of alcohol dehydrogenase EutG from Bacillus tropicus as an eco-friendly approach for the degradation of polycyclic aromatic compounds

Polycyclic aromatic compounds (PACs) are pervasive environmental contaminants derived from diverse sources including pyrogenic (e.g., combustion processes), petrogenic (e.g., crude oil), and biological origins. They are commonly found in gasoline, coal, and crude oil, reflecting their prevalence and varied origins in natural and anthropogenic activities. The aim of this study is to use Bacillus tropicus which is a spore-forming, gram-positive and facultative anaerobic bacteria, containing a gene for PACs degradtion. In this study bacterial sample was collected from women's vaginal discharge through streaking and spreading techniques. The DNA was extracted from bacterial culture and then the bacterium was identified through 16S rRNA which appeared to be B.tropicus. Then the computational analysis was conducted where the sequence similarity and functional analysis of alcohol dehydrogenase EutG protein from B.tropicus was analyzed through PSI-BLAT and SMART tool, respectively. The PSI-BLAST showed 100% query coverage score and 9 domains of alcohol dehydrogenase EutG protein were predicted through SMART tool. The quality of the protein was also assessed through ProQ server with a predicted LQ score of 8.091, a Maxsub score of - 0.350 and a z score of - 10.76. Then the phylogentic analysis was conducted to know the evolutionary relationship and closely related taxa. The 3D structure of the protein was predicted through SWISS MODEL and its quality was predicted through ERRAT with overall qauality factor of 98.708. The Ramachandran plot also predicted its quality and showed that 93.8% residues were in the most favored region. After this, 3D stucture of PACs were obtained from PubChem and molecular docking of the protein was performed with each of the compound. The lowest energy of - 10.3 was obtained with Indeno[1,2,3-cd] pyrene and the best docked complex was visulaized through discover studio to analyze its binding residues. Lastly, in-silico site-directed mutagenesis studies were performed which showed that the EutG gene (codes for alcoholic dehydrogenase) obtained from B. tropicus, will not get altered or have any decreasing effect on the enzyme's stability if it goes through any mutations. This suggests that B. tropicus can act as an efficient, non-virulent, and reliable candidate for the eco-friendly and cost-effective bioremediation of PACs.

Predicting Axillary Lymph Node Metastasis in Young Onset Breast Cancer: A Clinical-Radiomics Nomogram Based on DCE-MRI

Background

Young onset breast cancer, diagnosed in women under 50, is known for its aggressive nature and challenging prognosis. Precisely forecasting axillary lymph node metastasis (ALNM) is essential for customizing treatment plans and enhancing patient results.

Objective

This research sought to create and verify a clinical-radiomics nomogram that combines radiomic features from Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) with standard clinical predictors to improve the accuracy of predicting ALNM in young breast cancer patients.

Methods

We performed a retrospective analysis at one facility, involving the creation and validation of a nomogram in two stages.At first, a medical model was developed utilizing conventional indicators like tumor dimensions, molecular classifications, multifocal presence, and MRI-determined ALN status.A more detailed clinical-radiomics model was subsequently developed by integrating radiomic characteristics derived from DCE-MRI images.These models were created using logistic regression analyses on a training dataset, and their effectiveness was assessed by measuring the area under the receiver operating characteristic curve (AUC) in a separate validation dataset.

Results

The clinical-radiomics nomogram surpassed the clinical-only model, recording an AUC of 0.892 in the training dataset and 0.877 in the validation dataset.Significant predictors included MRI-reported ALN status and select radiomic features, which markedly enhanced the model's predictive capacity.

Conclusion

Integrating radiomic features with clinical predictors in a nomogram significantly improves ALNM prediction in young onset breast cancer, providing a valuable tool for personalized treatment planning. This study underscores the potential of merging advanced imaging data with clinical insights to refine oncological predictive models. Future research should expand to multicentric studies and include genomic data to boost the nomogram's generalizability and precision.

Tool wear prediction based on XGBoost feature selection combined with PSO-BP network

To address the challenge of accurately capturing tool wear states in small sample scenarios, this paper proposes a tool wear prediction method that combines XGBoost feature selection with a PSO-BP network. In order to solve the problem of input feature selection and parameter selection in BP neural network, a double-layer programming model of input feature and parameter selection is established, which is solved by XGBoost and PSO. Initially, vibration and cutting force signals from CNC machining are preprocessed using time-domain segmentation, Hampel filtering, and wavelet denoising. Subsequently, time-domain, frequency-domain, and time-frequency domain features are extracted from the preprocessed data using FFT and wavelet packet decomposition, followed by feature screening for tool wear mapping via Pearson correlation and XGBoost feature importance analysis as model input. Finally, PSO is employed to optimize BPNN parameters. Experimental results show that PSO outperforms other algorithms in training the tool wear prediction model, with XGBoost feature selection reducing model construction time by 57.4% and increasing accuracy by 63.57%, demonstrating superior feature selection capabilities over Decision Tree, Random Fores, Adaboost and Extra Trees. These findings suggest that the proposed method can effectively predict tool wear in real-world CNC machining, contributing to improved production efficiency, reduced tool replacement frequency, and lower maintenance costs, thereby providing valuable insights for industrial applications.

Time Series Forecasting Model Based on the Adapted Transformer Neural Network and FFT-Based Features Extraction

In today's data-driven world, where information is one of the most valuable resources, forecasting the behavior of time series, collected by modern sensor networks and IoT systems, is crucial across various fields, including finance, climatology, and engineering. However, existing neural network models often struggle with time series forecasting collected by different sensors due to challenges such as large data volumes, long-term dependencies, noise, and anomalies, which can negatively impact predictive accuracy. This paper aims to enhance the accuracy of time series forecasting by proposing an adapted transformer architecture combined with an innovative data preprocessing method. The proposed preprocessing technique employs the fast Fourier transform (FFT) to transition from the time domain to the frequency domain, enriching the data with additional frequency-domain features. These features are represented as complex numbers, which improve the informational content of the data for subsequent analysis, thereby boosting forecasting performance. Furthermore, the paper introduces a modified transformer model specifically designed to address the identified challenges in time series prediction. The performance of the proposed model was evaluated using three diverse datasets collected by different sensors, each with varying measurement frequencies, data types, and application domains, providing a comprehensive comparison with state-of-the-art models such as LSTM, FFT-LSTM, DeepAR, Transformer, and FFT-Transformer. Extensive evaluation using five distinct performance metrics demonstrates that the proposed model consistently outperforms existing methods, achieving the highest accuracy across all datasets.

Prediction of the Stability of Protein Substructures Using AI/ML Techniques

This chapter explores the innovative application of machine learning techniques to understand and predict the stability of protein substructures. Accurately identifying stable substructures within proteins necessitates incorporating the local context, crucial for elucidating the roles of supersecondary structures. This approach emphasizes the importance of contextual information in understanding the stability and functionality of protein regions, thereby providing a more comprehensive view of protein mechanics and interactions. The chapter focuses on our findings regarding the DnaK Hsp70 chaperone protein, utilizing it as a case study. This research highlights how context-dependent physico-chemical features derived from protein sequences can accurately classify residues into stable and unstable substructures by leveraging logistic regression, random forest, and support vector machine methods. The findings represent a pivotal step towards the rational design of proteins with tailored properties, offering new insights into protein engineering and the fundamental principles underpinning protein supersecondary structures.

Association between Regional Market Competition and Early Femoropopliteal Interventions for Claudication

BACKGROUND

Regional market competition is known to impact practice patterns in surgical care. We aimed to investigate the association of regional market competition with the utilization of early peripheral vascular interventions (PVIs) for the treatment of claudication, and the subsequent impact on clinical outcomes.

METHODS

We conducted a retrospective analysis of 100% Medicare fee-for-service claims data from January 2019 to December 2021 to identify patients with a new diagnosis of claudication. We calculated the Herfindahl-Hirschman Index for all sites of service performing PVI according to Health Service Area. Multivariable logistic regression and Cox proportional hazards models were used to assess the association of regional market competition with early (<6 months) PVI for claudication, and progression to chronic limb-threatening ischemia, repeat PVI, and major amputation.

RESULTS

We identified 300,492 patients with a new diagnosis of claudication (mean age 73.8 years, 51.6% male, 11.1% Black), of which 6.1% underwent an early PVI for claudication. Most patients (72.4%) were treated in low-competition markets. After adjusting for patient characteristics, patients treated in moderate-competition markets had the highest odds of receiving an early PVI. Regional market competition was not associated with conversion to chronic limb-threatening ischemia or repeat PVI (P > 0.05), but patients treated in high- (adjusted hazard ratio [aHR] 0.70, 95% confidence interval [CI] 0.56-0.86) and moderate- (aHR 0.82, 95% CI 0.69-0.92) competition markets had lower hazards of major amputation compared to patients treated in low-competition markets. Early PVI was significantly associated with worse clinical outcomes after adjusting for all factors including market competition (all, P < 0.05).

CONCLUSIONS

There is a complex interplay between regional market competition, early PVI utilization, and subsequent clinical outcomes for patients with claudication. Early PVI continues to demonstrate a strong association with unfavorable clinical outcomes even when accounting for market competition.

PDE4D inhibitors: Opening a new era of PET diagnostics for Alzheimer's disease

As the incidence of Alzheimer's disease (AD) continues to rise, the need for an effective PET radiotracer to facilitate early diagnosis has become more pressing than ever before in modern medicine. Phosphodiesterase (PDE) is closely related to cognitive impairment and neuroinflammatory processes in AD. Current research progress shows that specific PDE4D inhibitors radioligands can bind specifically to the PDE4D enzyme in the brain, thereby showing pathology-related signal enhancement in AD animal models, indicating the potential of these ligands as effective radiotracers. At the same time, we need to pay attention to the important role computer aided drug design (CADD) plays in advancing AD drug design and PET imaging. Future research will verify the potential of these ligands in clinical applications through computer simulation techniques, providing patients with timely intervention and treatment, which is of great significance.

Effect of shear rate on early Shewanella oneidensis adhesion dynamics monitored by deep learning

Understanding pioneer bacterial adhesion is essential to appreciate bacterial colonization and consider appropriate control strategies. This bacterial entrapment at the wall is known to be controlled by many physical, chemical or biological factors, including hydrodynamic conditions. However, due to the nature of early bacterial adhesion, i.e. a short and dynamic process with low biomass involved, such investigations are challenging. In this context, our study aimed to evaluate the effect of wall shear rate on the early bacterial adhesion dynamics. Firstly, at the population scale by assessing bacterial colonization kinetics and the mechanisms responsible for wall transfer under shear rates using a time-lapse approach. Secondly, at the individual scale, by implementing an automated image processing method based on deep learning to track each individual pioneer bacterium on the wall. Bacterial adhesion experiments are performed on a model bacterium (Shewanella oneidensis MR-1) at different shear rates (0 to1250 s-1) in a microfluidic system mounted under a microscope equipped with a CCD camera. Image processing was performed using a trained neural network (YOLOv8), which allowed information extraction, i.e. bacterial wall residence time and orientation for each adhered bacterium during pioneer colonization (14 min). Collected from over 20,000 bacteria, our results showed that adhered bacteria had a very short residence time at the wall, with over 70 % remaining less than 1 min. Shear rates had a non-proportional effect on pioneer colonization with a bell-shape profile suggesting that intermediate shear rates improved both bacterial wall residence time as well as colonization rate and level. This lack of proportionality highlights the dual effect of wall shear rate on early bacterial colonization; initially increasing it improves bacterial colonization up to a threshold, beyond which it leads to higher bacterial wall detachment. The present study provides quantitative data on the individual dynamics of just adhered bacteria within a population when exposed to different rates of wall shear.

Exploring coronavirus sequence motifs through convolutional neural network for accurate identification of COVID-19

The SARS-CoV-2 virus reportedly originated in Wuhan in 2019, causing the coronavirus outbreak (COVID-19), which was technically designated as a global epidemic. Numerous studies have been carried out to diagnose and treat COVID-19 throughout the midst of the disease's spread. However, the genetic similarity between COVID-19 and other types of coronaviruses makes it challenging to differentiate between them. Therefore it's essential to swiftly identify if an epidemic is brought on by a brand-new virus or a well-known disease. In the present article, the DeepCoV deep-learning (DL) approach utilizes layered convolutional neural networks (CNNs) to classify viral serious acute respiratory syndrome coronavirus 2 (SARS-CoV-2) besides other viral diseases. Additionally, various motifs linked with SARS-CoV-2 can be located by examining the computational filter processes. In identifying these important motifs, DeepCoV reveals the transparency of CNNs. Experiments were conducted using the 2019nCoVR datasets, and the results indicate that DeepCoV performed more accurately than several benchmark ML models. Additionally, DeepCoV scored its maximum area under the precision-recall curve (AUCPR) and receiver operating characteristic curve (AUC-ROC) at 98.62% and 98.58%, respectively. Overall, these investigations provide strong knowledge of the employment of deep learning (DL) algorithms as a crucial alternative to identifying SARS-CoV-2 and identifying patterns of disease in the SARS-CoV-2 genes.

Identification of Diagnostic Biomarkers for Compensatory Liver Cirrhosis Based on Gut Microbiota and Urine Metabolomics Analyses

Liver cirrhosis is one of the most prevalent chronic liver disorders with high mortality. We aimed to explore changed gut microbiome and urine metabolome in compensatory liver cirrhosis (CLC) patients, thus providing novel diagnostic biomarkers for CLC. Forty fecal samples from healthy volunteers (control: 19) and CLC patients (patient: 21) were undertaken 16S rDNA sequencing. Chromatography-mass spectrometry was performed on 40 urine samples (20 controls and 20 patients). Microbiome and metabolome data were separately analyzed using corresponding bioinformatics approaches. The diagnostic model was constructed using the least absolute shrinkage and selection operator regression. The optimal diagnostic model was determined by five-fold cross-validation. Pearson correlation analysis was applied to clarify the relations among the diagnostic markers. 16S rDNA sequencing analyses showed changed overall alpha diversity and beta diversity in patient samples compared with those of controls. Similarly, we identified 841 changed metabolites. Pathway analysis revealed that the differential metabolites were mainly associated with pathways, such as tryptophan metabolism, purine metabolism, and steroid hormone biosynthesis. A 9-maker diagnostic model for CLC was determined, including 7 microorganisms and 2 metabolites. In this model, there were multiple correlations between microorganisms and metabolites. Subdoligranulum, Agathobacter, norank_f_Eubacterium_coprostanoligenes_group, Butyricicoccus, Lachnospiraceae_UCG_004, and L-2,3-Dihydrodipicolinate were elevated in CLC patients, whereas Blautia, Monoglobus, and 5-Acetamidovalerate were reduced. A novel diagnostic model for CLC was constructed and verified to be reliable, which provides new strategies for the diagnosis and treatment of CLC.

Current advances in the use of artificial intelligence in predicting and managing urological complications

BACKGROUND

Artificial intelligence (AI) has emerged as a promising avenue for improving patient care and surgical outcomes in urological surgery. However, the extent of AI's impact in predicting and managing complications is not fully elucidated.

OBJECTIVES

We review the application of AI to foresee and manage complications in urological surgery, assess its efficacy, and discuss challenges to its use.

METHODS AND MATERIALS

A targeted non-systematic literature search was conducted using the PubMed and Google Scholar databases to identify studies on AI in urological surgery and its complications. Evidence from the studies was synthesised.

RESULTS

Incorporating AI into various facets of urological surgery has shown promising advancements. From preoperative planning to intraoperative guidance, AI is revolutionising the field, demonstrating remarkable proficiency in tasks such as image analysis, decision-making support, and complication prediction. Studies show that AI programmes are highly accurate, increase surgical precision and efficiency, and reduce complications. However, implementation challenges exist in AI errors, human errors, and ethical issues.

CONCLUSION

AI has great potential in predicting and managing surgical complications of urological surgery. Advancements have been made, but challenges and ethical considerations must be addressed before widespread AI implementation.

Accurate Identification of Cancer Cells in Complex Pre-Clinical Models Using a Deep-Learning Neural Network: A Transfection-Free Approach

3D co-cultures are key tools for in vitro biomedical research as they recapitulate more closely the in vivo environment while allowing a tighter control on the culture's composition and experimental conditions. The limited technologies available for the analysis of these models, however, hamper their widespread application. The separation of the contribution of the different cell types, in particular, is a fundamental challenge. In this work, ORACLE (OvaRiAn Cancer ceLl rEcognition) is presented, a deep neural network trained to distinguish between ovarian cancer and healthy cells based on the shape of their nucleus. The extensive validation that are conducted includes multiple cell lines and patient-derived cultures to characterize the effect of all the major potential confounding factors. High accuracy and reliability are maintained throughout the analysis (F1score> 0.9 and Area under the ROC curve -ROC-AUC- score = 0.99) demonstrating ORACLE's effectiveness with this detection and classification task. ORACLE is freely available (https://github.com/MarilisaCortesi/ORACLE/tree/main) and can be used to recognize both ovarian cancer cell lines and primary patient-derived cells. This feature is unique to ORACLE and thus enables for the first time the analysis of in vitro co-cultures comprised solely of patient-derived cells.

An In Silico Approach to Discover Efficient Natural Inhibitors to Tie Up Epstein-Barr Virus Infection

Epstein-Barr virus (EBV), also known as human herpesvirus 4, is a member of the herpes virus family. EBV is a widespread virus and causes infectious mononucleosis, which manifests with symptoms such as fever, fatigue, lymphadenopathy, splenomegaly, and hepatomegaly. Additionally, EBV is associated with different lymphocyte-associated non-malignant, premalignant, and malignant diseases. So far, no effective treatment or therapeutic drug is known for EBV-induced infections and diseases. This study investigated natural compounds that inhibit EBV glycoprotein L (gL) and block EBV fusion in host cells. We utilised computational approaches, including molecular docking, in silico ADMET analysis, and molecular dynamics simulation. We docked 628 natural compounds against gL and identified the four best compounds based on binding scores and pharmacokinetic properties. These four compounds, with PubChem CIDs 4835509 (CHx-HHPD-Ac), 2870247 (Cyh-GlcNAc), 21206004 (Hep-HHPD-Ac), and 51066638 (Und-GlcNAc), showed several interactions with EBV gL. However, molecular dynamics simulations indicated that the protein-ligand complexes of CID: 4835509 (CHx-HHPD-Ac) and CID: 2870247 (Cyh-GlcNAc) are more stable than those of the other two compounds. Therefore, CIDs 4835509 and 2870247 (Cyh-GlcNAc) may be potent natural inhibitors of EBV infection. These findings can open a new way for effective drug design against EBV and its associated infections and diseases.

Evaluation of particle tracking codes for dispersing particles in porous media

Particle tracking (PT) is a popular technique in microscopy, microfluidics and colloidal transport studies, where image analysis is used to reconstruct trajectories from bright spots in a video. The performance of many PT algorithms has been rigorously tested for directed and Brownian motion in open media. However, PT is frequently used to track particles in porous media where complex geometries and viscous flows generate particles with high velocity variability over time. Here, we present an evaluation of four PT algorithms for a simulated dispersion of particles in porous media across a range of particle speeds and densities. Of special note, we introduce a new velocity-based PT linking algorithm (V-TrackMat) that achieves high accuracy relative to the other PT algorithms. Our findings underscore that traditional statistics, which revolve around detection and linking proficiency, fall short in providing a holistic comparison of PT codes because they tend to underpenalize aggressive linking techniques. We further elucidate that all codes analyzed show a decrease in performance due to high speeds, particle densities, and trajectory noise. However, linking algorithms designed to harness velocity data show superior performance, especially in the case of high-speed advective motion. Lastly, we emphasize how PT error can influence transport analysis.

Prediction of viral families and hosts of single-stranded RNA viruses based on K-Mer coding from phylogenetic gene sequences

There are billions of virus species worldwide, and viruses, the smallest parasitic entities, pose a serious threat. Therefore, fighting associated disorders requires an understanding of the genetic structure of viruses. Considering the wide diversity and rapid evolution of viruses, there is a critical need to quickly and accurately classify viral species and their potential hosts to better understand transmission dynamics, facilitating the development of targeted therapies. Recognizing this, this study has investigated the classes of RNA viruses based on their genomic sequences using Machine Learning (ML) and Deep Learning (DL) models. The PhyVirus dataset, consisting of pathogenic Single-stranded RNA viruses of Baltimore group four (+ssRNA) and five (-ssRNA) with different hosts and species, was analyzed. The dataset containing viral gene sequences was analyzed using the K-Mer coding technique, which is based on base words of various lengths. The study used classical ML algorithms (Random Forest, Gradient Boosting and Extra Trees) and the Fully Connected Deep Neural Network, a Deep Learning algorithm, to predict viral families and hosts. Detailed analyses were performed on the classifier performance in scenarios with different train-test ratios and different word lengths (k-values) for K-Mer. The observed results show that Fully Connected Deep Neural Network has a high success rate of 99.60 % in predicting virus families. In predicting virus hosts, the Extra Trees classifier achieved the highest success rate of 81.53 %. This study is considered to be the first classification study in the literature on this dataset, which has a very large family and host diversity consisting of gene sequences of Single-stranded RNA viruses. Our detailed investigations on how varying word lengths based on K-Mer coding in gene sequences affect the classification into viral families and hosts make this study particularly valuable. This study shows that ML and DL methods have the potential to produce valuable results in phylogenetic studies. In addition, the results and high-performance values show that these methods can be successfully used in regenerative applications of gene sequences or in studies such as the elimination of losses in gene sequences.

Omission of sentinel lymph node biopsy in patients with clinically axillary lymph node-negative early breast cancer (OMSLNB): protocol for a prospective, non-inferiority, single-arm, phase II clinical trial in China

INTRODUCTION

Sentinel lymph node biopsy (SLNB) is a standard procedure for patients with clinically assessed negative axillary lymph nodes (cN0) during early-stage breast cancer (EBC). However, the majority of EBC patients have a negative pathological confirmation of the sentinel lymph node (SLN), and axillary surgery is inevitably associated with postoperative complications. Considering that SLNB has no therapeutic benefit, this trial aims to determine the safety of omitting SLNB in patients with cN0 early invasive breast cancer.

METHODS AND ANALYSIS

The OMSLNB trial is a prospective, single-arm, non-inferiority, phase II, open-label study design involving female breast cancer patients with a tumor of ≤3 cm in diameter, who are considered axillary lymph-node-negative based on two or more radiological examinations, including axillary lymph node ultrasonography. Eligible patients will avoid axillary surgery but will undergo breast surgery, which is not limited to breast-conserving surgery. The trial begins in 2023 and is scheduled to end in 2027. The primary endpoint is 3 year invasive disease-free survival (iDFS). The secondary endpoints include the incidence of breast cancer-related lymphoedema, patient-reported outcomes, locoregional recurrence, local recurrence and regional recurrence. It is expected that the 3 year iDFS in patients undergoing SLNB is about 90%, combined with a non-inferiority cut-off of 5%, 80% power, 95% CIs, 0.05 test level, and 10% loss to follow-up rate, the planned enrollment is 311 patients. All enrolled patients will be included in the intention-to-treat analysis.

ETHICS AND DISSEMINATION

This trial was approved by the Ethics Committee of the First Affiliated Hospital of Nanjing Medical University (No.2023-SR-193). All participants must provide written informed consent to be eligible. The protocol will be described in a peer-reviewed manuscript, and the results will be published in scientific journals and/or at academic conferences.

TRIAL REGISTRATION NUMBER

NCT05935150.

Artificial intelligence in retinal screening using OCT images: A review of the last decade (2013-2023)

BACKGROUND AND OBJECTIVES

Optical coherence tomography (OCT) has ushered in a transformative era in the domain of ophthalmology, offering non-invasive imaging with high resolution for ocular disease detection. OCT, which is frequently used in diagnosing fundamental ocular pathologies, such as glaucoma and age-related macular degeneration (AMD), plays an important role in the widespread adoption of this technology. Apart from glaucoma and AMD, we will also investigate pertinent pathologies, such as epiretinal membrane (ERM), macular hole (MH), macular dystrophy (MD), vitreomacular traction (VMT), diabetic maculopathy (DMP), cystoid macular edema (CME), central serous chorioretinopathy (CSC), diabetic macular edema (DME), diabetic retinopathy (DR), drusen, glaucomatous optic neuropathy (GON), neovascular AMD (nAMD), myopia macular degeneration (MMD) and choroidal neovascularization (CNV) diseases. This comprehensive review examines the role that OCT-derived images play in detecting, characterizing, and monitoring eye diseases.

METHOD

The 2020 PRISMA guideline was used to structure a systematic review of research on various eye conditions using machine learning (ML) or deep learning (DL) techniques. A thorough search across IEEE, PubMed, Web of Science, and Scopus databases yielded 1787 publications, of which 1136 remained after removing duplicates. Subsequent exclusion of conference papers, review papers, and non-open-access articles reduced the selection to 511 articles. Further scrutiny led to the exclusion of 435 more articles due to lower-quality indexing or irrelevance, resulting in 76 journal articles for the review.

RESULTS

During our investigation, we found that a major challenge for ML-based decision support is the abundance of features and the determination of their significance. In contrast, DL-based decision support is characterized by a plug-and-play nature rather than relying on a trial-and-error approach. Furthermore, we observed that pre-trained networks are practical and especially useful when working on complex images such as OCT. Consequently, pre-trained deep networks were frequently utilized for classification tasks. Currently, medical decision support aims to reduce the workload of ophthalmologists and retina specialists during routine tasks. In the future, it might be possible to create continuous learning systems that can predict ocular pathologies by identifying subtle changes in OCT images.

BNP-Track: a framework for superresolved tracking

Superresolution tools, such as PALM and STORM, provide nanoscale localization accuracy by relying on rare photophysical events, limiting these methods to static samples. By contrast, here, we extend superresolution to dynamics without relying on photodynamics by simultaneously determining emitter numbers and their tracks (localization and linking) with the same localization accuracy per frame as widefield superresolution on immobilized emitters under similar imaging conditions (≈50 nm). We demonstrate our Bayesian nonparametric track (BNP-Track) framework on both in cellulo and synthetic data. BNP-Track develops a joint (posterior) distribution that learns and quantifies uncertainty over emitter numbers and their associated tracks propagated from shot noise, camera artifacts, pixelation, background and out-of-focus motion. In doing so, we integrate spatiotemporal information into our distribution, which is otherwise compromised by modularly determining emitter numbers and localizing and linking emitter positions across frames. For this reason, BNP-Track remains accurate in crowding regimens beyond those accessible to other single-particle tracking tools.

Surface roughness prediction in turning processes using CEEMD-based vibration signal denoising and LSTM networks

Surface roughness plays a pivotal role in assessing machining quality, and numerous research efforts have been devoted to predicting surface roughness in turning processes primarily based on cutting parameters. However, it's important to recognize that surface roughness isn’t solely governed by cutting parameters; it is also influenced by tool characteristics, workpiece properties, and the prevailing machining conditions. Therefore, the accurate prediction of surface roughness during turning operations is of utmost importance for facilitating timely corrective measures. However, the accuracy of prediction is affected by the intense background noise and usage of manual feature extraction. To address these issues, this article proposes a novel method combining the complete ensemble empirical mode decomposition (CEEMD) and sequence long short-term memory (LSTM) networks. The CEEMD decomposes the measured vibration signals, and noise-free intrinsic mode functions (IMFs) are chosen based on cross-correlation. The noise-free IMFs are then reconstructed to get the denoised signal. The denoised signals are fed straight into the Sequence LSTM network, a deep learning-based prediction algorithm for accurate prediction. The network parameters are optimized to minimize the error. An experimental study was conducted to assess the suggested method, and the results show that it effectively predicts surface roughness during turning using vibration signals. Further, the proposed approach has proven effective compared with other denoising methods. The proposed method has significant applications in the manufacturing industry, where it can contribute to better quality control and process optimization.

Deep learning approaches for non-coding genetic variant effect prediction: current progress and future prospects

Recent advancements in high-throughput sequencing technologies have significantly enhanced our ability to unravel the intricacies of gene regulatory processes. A critical challenge in this endeavor is the identification of variant effects, a key factor in comprehending the mechanisms underlying gene regulation. Non-coding variants, constituting over 90% of all variants, have garnered increasing attention in recent years. The exploration of gene variant impacts and regulatory mechanisms has spurred the development of various deep learning approaches, providing new insights into the global regulatory landscape through the analysis of extensive genetic data. Here, we provide a comprehensive overview of the development of the non-coding variants models based on bulk and single-cell sequencing data and their model-based interpretation and downstream tasks. This review delineates the popular sequencing technologies for epigenetic profiling and deep learning approaches for discerning the effects of non-coding variants. Additionally, we summarize the limitations of current approaches in variant effect prediction research and outline opportunities for improvement. We anticipate that our study will offer a practical and useful guide for the bioinformatic community to further advance the unraveling of genetic variant effects.

Precise soil coverage in potato planting through plastic film using real-time image recognition with YOLOv4-tiny

Planting potatoes through plastic film with incomplete or excessive soil coverage over seed holes significantly impairs yield. Existing covering methods rely solely on mechanical transmissions, leading to bulky and inconsistent soil coverage of the seed holes. This paper reports an innovative method using a precise soil covering device based on the YOLOv4-tiny real-time object detection system to accurately identify potato plastic film holes and cover them with soil. The system adopts a lightweight and high-precision detection scheme, balancing increased network depth with reduced computation. It can identify holes in the plastic film in real-time and with high accuracy. To verify the effectiveness of YOLOv4-tiny real-time object detection system, a precise soil covering device based on this detection system has been designed and applied to a double crank multi-rod hill-drop planter. Field tests revealed that the system's average accuracy rate for detecting holes is approximately 98%, with an average processing time of 15.15 ms per frame. This fast and accurate performance, combined with the device's robust real-time operation and anti-interference capabilities during soil covering, effectively reduce the problems of soil cover omission and repeated covering caused by existing mechanical transmission methods. The findings reported in this paper are valuable for the development of autonomous potato plastic film precise soil covering devices for commercial use.

Transforming the future of ophthalmology: artificial intelligence and robotics' breakthrough role in surgical and medical retina advances: a mini review

Over the past decade, artificial intelligence (AI) and its subfields, deep learning and machine learning, have become integral parts of ophthalmology, particularly in the field of ophthalmic imaging. A diverse array of algorithms has emerged to facilitate the automated diagnosis of numerous medical and surgical retinal conditions. The development of these algorithms necessitates extensive training using large datasets of retinal images. This approach has demonstrated a promising impact, especially in increasing accuracy of diagnosis for unspecialized clinicians for various diseases and in the area of telemedicine, where access to ophthalmological care is restricted. In parallel, robotic technology has made significant inroads into the medical field, including ophthalmology. The vast majority of research in the field of robotic surgery has been focused on anterior segment and vitreoretinal surgery. These systems offer potential improvements in accuracy and address issues such as hand tremors. However, widespread adoption faces hurdles, including the substantial costs associated with these systems and the steep learning curve for surgeons. These challenges currently constrain the broader implementation of robotic surgical systems in ophthalmology. This mini review discusses the current research and challenges, underscoring the limited yet growing implementation of AI and robotic systems in the field of retinal conditions.

Artificial Intelligence, Digital Imaging, and Robotics Technologies for Surgical Vitreoretinal Diseases

OBJECTIVE

To review recent technological advancement in imaging, surgical visualization, robotics technology, and the use of artificial intelligence in surgical vitreoretinal (VR) diseases.

BACKGROUND

Technological advancements in imaging enhance both preoperative and intraoperative management of surgical VR diseases. Widefield imaging in fundal photography and OCT can improve assessment of peripheral retinal disorders such as retinal detachments, degeneration, and tumors. OCT angiography provides a rapid and noninvasive imaging of the retinal and choroidal vasculature. Surgical visualization has also improved with intraoperative OCT providing a detailed real-time assessment of retinal layers to guide surgical decisions. Heads-up display and head-mounted display utilize 3-dimensional technology to provide surgeons with enhanced visual guidance and improved ergonomics during surgery. Intraocular robotics technology allows for greater surgical precision and is shown to be useful in retinal vein cannulation and subretinal drug delivery. In addition, deep learning techniques leverage on diverse data including widefield retinal photography and OCT for better predictive accuracy in classification, segmentation, and prognostication of many surgical VR diseases.

CONCLUSION

This review article summarized the latest updates in these areas and highlights the importance of continuous innovation and improvement in technology within the field. These advancements have the potential to reshape management of surgical VR diseases in the very near future and to ultimately improve patient care.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

In-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation

Rapid tool wear conditions during the manufacturing process are crucial for the enhancement of product quality. As an extension of our recent works, in this research, a generic in-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation is proposed. With the engagement of dynamic mode decomposition, the real-time response of the sensing physical quantity during the end milling process can be predicted. Besides, by constructing the graph structure of the time series and calculating the difference between the predicted signal and the real-time signal, the anomaly can be acquired. Meanwhile, the tool wear state during the end milling process can be successfully evaluated. The proposed method is validated in milling tool wear experiments and received positive results (the mean relative error is recorded as 0.0507). The research, therefore, paves a new way to realize the in-situ tool wear condition monitoring.

Core proteome mediated subtractive approach for the identification of potential therapeutic drug target against the honeybee pathogen Paenibacillus larvae

Background & Objectives

American foulbrood (AFB), caused by the highly virulent, spore-forming bacterium Paenibacillus larvae, poses a significant threat to honey bee brood. The widespread use of antibiotics not only fails to effectively combat the disease but also raises concerns regarding honey safety. The current computational study was attempted to identify a novel therapeutic drug target against P. larvae, a causative agent of American foulbrood disease in honey bee.

Methods

We investigated effective novel drug targets through a comprehensive in silico pan-proteome and hierarchal subtractive sequence analysis. In total, 14 strains of P. larvae genomes were used to identify core genes. Subsequently, the core proteome was systematically narrowed down to a single protein predicted as the potential drug target. Alphafold software was then employed to predict the 3D structure of the potential drug target. Structural docking was carried out between a library of phytochemicals derived from traditional Chinese flora (n > 36,000) and the potential receptor using Autodock tool 1.5.6. Finally, molecular dynamics (MD) simulation study was conducted using GROMACS to assess the stability of the best-docked ligand.

Results

Proteome mining led to the identification of Ketoacyl-ACP synthase III as a highly promising therapeutic target, making it a prime candidate for inhibitor screening. The subsequent virtual screening and MD simulation analyses further affirmed the selection of ZINC95910054 as a potent inhibitor, with the lowest binding energy. This finding presents significant promise in the battle against P. larvae.

Conclusions

Computer aided drug design provides a novel approach for managing American foulbrood in honey bee populations, potentially mitigating its detrimental effects on both bee colonies and the honey industry.

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug-target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

Innovative Encapsulation Strategies for Food, Industrial, and Pharmaceutical Applications

Bioactive metabolites obtained from fruits and vegetables as well as many drugs have various capacities to prevent or treat various ailments. Nevertheless, their efficiency, in vivo, encounter many challenges resulting in lower efficacy as well as different side effects when high doses are used resulting in many challenges for their application. Indeed, demand for effective treatments with no or less unfavorable side effects is rising. Delivering active molecules to a particular site of action within the human body is an example of targeted therapy which remains a challenging field. Developments of nanotechnology and polymer science have great promise for meeting the growing demands of efficient options. Encapsulation of active ingredients in nano-delivery systems has become as a vitally tool for protecting the integrity of critical biochemicals, improving their delivery, enabling their controlled release and maintaining their biological features. Here, we examine a wide range of nano-delivery techniques, such as niosomes, polymeric/solid lipid nanoparticles, nanostructured lipid carriers, and nano-emulsions. The advantages of encapsulation in targeted, synergistic, and supportive therapies are emphasized, along with current progress in its application. Additionally, a revised collection of studies was given, focusing on improving the effectiveness of anticancer medications and addressing the problem of antimicrobial resistance. To sum up, this paper conducted a thorough analysis to determine the efficacy of encapsulation technology in the field of drug discovery and development.

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients

BACKGROUND

At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive.

OBJECTIVE

This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients.

METHODS

A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method.

RESULTS

Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models.

CONCLUSIONS

This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

Interpretable detection of epiretinal membrane from optical coherence tomography with deep neural networks

This study aimed to automatically detect epiretinal membranes (ERM) in various OCT-scans of the central and paracentral macula region and classify them by size using deep-neural-networks (DNNs). To this end, 11,061 OCT-images were included and graded according to the presence of an ERM and its size (small 100-1000 µm, large > 1000 µm). The data set was divided into training, validation and test sets (75%, 10%, 15% of the data, respectively). An ensemble of DNNs was trained and saliency maps were generated using Guided-Backprob. OCT-scans were also transformed into a one-dimensional-value using t-SNE analysis. The DNNs' receiver-operating-characteristics on the test set showed a high performance for no-ERM, small-ERM and large-ERM cases (AUC: 0.99, 0.92, 0.99, respectively; 3-way accuracy: 89%), with small-ERMs being the most difficult ones to detect. t-SNE analysis sorted cases by size and, in particular, revealed increased classification uncertainty at the transitions between groups. Saliency maps reliably highlighted ERM, regardless of the presence of other OCT features (i.e. retinal-thickening, intraretinal pseudo-cysts, epiretinal-proliferation) and entities such as ERM-retinoschisis, macular-pseudohole and lamellar-macular-hole. This study showed therefore that DNNs can reliably detect and grade ERMs according to their size not only in the fovea but also in the paracentral region. This is also achieved in cases of hard-to-detect, small-ERMs. In addition, the generated saliency maps can be used to highlight small-ERMs that might otherwise be missed. The proposed model could be used for screening-programs or decision-support-systems in the future.

Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction

In the field of drug discovery, there is a substantial challenge in seeking out chemical structures that possess desirable pharmacological, toxicological, and pharmacokinetic properties. Complications arise when drugs interfere with the functioning of cardiac ion channels, leading to serious cardiovascular consequences. The discontinuation and removal of numerous approved drugs from the market or at late development stages in the pipeline due to such inhibitory effects further highlight the urgency of addressing this issue. Consequently, the early prediction of potential blockers targeting cardiac ion channels during the drug discovery process is of paramount importance. This study introduces a deep learning framework that computationally determines the cardiotoxicity associated with the voltage-gated potassium channel (hERG), the voltage-gated calcium channel (Cav1.2), and the voltage-gated sodium channel (Nav1.5) for drug candidates. The predictive capabilities of three feature representations─molecular fingerprints, descriptors, and graph-based numerical representations─are rigorously benchmarked. Additionally, a novel training and evaluation data set framework is presented, enabling predictive model training of drug off-target cardiotoxicity using a comprehensive and large curated data set covering these three cardiac ion channels. To facilitate these predictions, a robust and comprehensive small molecule cardiotoxicity prediction tool named CToxPred has been developed. It is made available as open source under the permissive MIT license at https://github.com/issararab/CToxPred.

Clinical evaluation of deep learning systems for assisting in the diagnosis of the epiretinal membrane grade in general ophthalmologists

BACKGROUND

Epiretinal membrane (ERM) is a common age-related retinal disease detected by optical coherence tomography (OCT), with a prevalence of 34.1% among people over 60 years old. This study aims to develop artificial intelligence (AI) systems to assist in the diagnosis of ERM grade using OCT images and to clinically evaluate the potential benefits and risks of our AI systems with a comparative experiment.

METHODS

A segmentation deep learning (DL) model that segments retinal features associated with ERM severity and a classification DL model that grades the severity of ERM were developed based on an OCT dataset obtained from three hospitals. A comparative experiment was conducted to compare the performance of four general ophthalmologists with and without assistance from the AI in diagnosing ERM severity.

RESULTS

The segmentation network had a pixel accuracy (PA) of 0.980 and a mean intersection over union (MIoU) of 0.873, while the six-classification network had a total accuracy of 81.3%. The diagnostic accuracy scores of the four ophthalmologists increased with AI assistance from 81.7%, 80.7%, 78.0%, and 80.7% to 87.7%, 86.7%, 89.0%, and 91.3%, respectively, while the corresponding time expenditures were reduced. The specific results of the study as well as the misinterpretations of the AI systems were analysed.

CONCLUSION

Through our comparative experiment, the AI systems proved to be valuable references for medical diagnosis and demonstrated the potential to accelerate clinical workflows. Systematic efforts are needed to ensure the safe and rapid integration of AI systems into ophthalmic practice.

GPU-Based Parallel Processing Techniques for Enhanced Brain Magnetic Resonance Imaging Analysis: A Review of Recent Advances

The approach of using more than one processor to compute in order to overcome the complexity of different medical imaging methods that make up an overall job is known as GPU (graphic processing unit)-based parallel processing. It is extremely important for several medical imaging techniques such as image classification, object detection, image segmentation, registration, and content-based image retrieval, since the GPU-based parallel processing approach allows for time-efficient computation by a software, allowing multiple computations to be completed at once. On the other hand, a non-invasive imaging technology that may depict the shape of an anatomy and the biological advancements of the human body is known as magnetic resonance imaging (MRI). Implementing GPU-based parallel processing approaches in brain MRI analysis with medical imaging techniques might be helpful in achieving immediate and timely image capture. Therefore, this extended review (the extension of the IWBBIO2023 conference paper) offers a thorough overview of the literature with an emphasis on the expanding use of GPU-based parallel processing methods for the medical analysis of brain MRIs with the imaging techniques mentioned above, given the need for quicker computation to acquire early and real-time feedback in medicine. Between 2019 and 2023, we examined the articles in the literature matrix that include the tasks, techniques, MRI sequences, and processing results. As a result, the methods discussed in this review demonstrate the advancements achieved until now in minimizing computing runtime as well as the obstacles and problems still to be solved in the future.

AI-Enabled Crop Management Framework for Pest Detection Using Visual Sensor Data

Our research focuses on addressing the challenge of crop diseases and pest infestations in agriculture by utilizing UAV technology for improved crop monitoring through unmanned aerial vehicles (UAVs) and enhancing the detection and classification of agricultural pests. Traditional approaches often require arduous manual feature extraction or computationally demanding deep learning (DL) techniques. To address this, we introduce an optimized model tailored specifically for UAV-based applications. Our alterations to the YOLOv5s model, which include advanced attention modules, expanded cross-stage partial network (CSP) modules, and refined multiscale feature extraction mechanisms, enable precise pest detection and classification. Inspired by the efficiency and versatility of UAVs, our study strives to revolutionize pest management in sustainable agriculture while also detecting and preventing crop diseases. We conducted rigorous testing on a medium-scale dataset, identifying five agricultural pests, namely ants, grasshoppers, palm weevils, shield bugs, and wasps. Our comprehensive experimental analysis showcases superior performance compared to various YOLOv5 model versions. The proposed model obtained higher performance, with an average precision of 96.0%, an average recall of 93.0%, and a mean average precision (mAP) of 95.0%. Furthermore, the inherent capabilities of UAVs, combined with the YOLOv5s model tested here, could offer a reliable solution for real-time pest detection, demonstrating significant potential to optimize and improve agricultural production within a drone-centric ecosystem.