Normal Cases Research Articles

Automatic Method of Macular Diseases Detection Using Deep CNN-GRU Network in OCT Images

Abstract The increasing development of Deep Learning mechanism allowed ones to create semi-fully or fully automated diagnosis software solutions for medical imaging diagnosis. The convolutional neural networks are widely applied for central retinal diseases classification based on OCT images. The main aim of this study is to propose a new network, Deep CNN-GRU for classification of early-stage and end-stages macular diseases as age-related macular degeneration and diabetic macular edema (DME). Three types of disorders have been taken into consideration: drusen, choroidal neovascularization (CNV), DME, alongside with normal cases. The created automatic tool was verified on the well-known Labelled Optical Coherence Tomography (OCT) dataset. For the classifier evaluation the following measures were calculated: accuracy, precision, recall, and F1 score. Based on these values, it can be stated that the use of a GRU layer directly connected to a convolutional network plays a pivotal role in improving previously achieved results. Additionally, the proposed tool was compared with the state-of-the-art of deep learning studies performed on the Labelled OCT dataset. The Deep CNN-GRU network achieved high performance, reaching up to 98.90% accuracy. The obtained results of classification performance place the tool as one of the top solutions for diagnosing retinal diseases, both early and late stage.

Enhancing Paediatric Pneumonia Detection and Classification Using Customized CNNs and Transfer Learning Based Ensemble Models

Pneumonia is one of the most prominent causes of mortality in children who are below the age of five years in most parts of the globe. Hence, adequate pneumonia diagnosis is of paramount importance and is what drove this research effort which has led to the development of two transfer learning-based ensemble models. One of the proposed models classifies the chest radiographs into normal and pneumonia cases with outputs being generated from VGG-16, Inception-v3, and two custom-made convolutional neural networks, PneumoNet-v1 and PneumoNet-v2. The second model distinguishes bacterial from viral pneumonia with the help of Xception, MobileNet-v2, and PneumoNet-v1. To accomplish the aim of the study, the Guangzhou Women and Children’s Medical Center dataset (Kermany Dataset) was used to benchmark model performance. PneumoNet-v1 and PneumoNet-v2 were designed with an emphasis for high classification accuracy and have individual accuracies of 96.2% and 96.8%, respectively for pneumonia detection. The first ensemble model used for classifying between healthy and infected images attained a classification accuracy of 98.03%. The second model used for differentiating between bacterial and viral demonstrated an accuracy of 91.93%. The effectiveness of transfer learning-based ensemble models as well as of the proposed custom CNN designs in enhancing the analysis of paediatric pneumonia and facilitating better diagnosis has been explored in this research.

Integrating Microarray Data and Single-Cell RNA-Seq Reveals Key Gene Involved in Spermatogonia Stem Cell Aging

The in vitro generation of spermatogonial stem cells (SSCs) from embryonic stem cells (ESCs) offers a viable approach for addressing male infertility. A multitude of molecules participate in this intricate process, which requires additional elucidation. Despite the decline in SSCs in aged testes, SSCs are deemed immortal since they can multiply for three years with repeated transplantation. Nonetheless, the examination of aging is challenging due to the limited quantity and absence of precise indicators. Using a microarray, we assessed genome-wide transcripts (about 55,000 transcripts) of fibroblasts and SSCs. The WGCNA approach was then used to look for SSC-specific transcription factors (TFs) and hub SSC-specific genes based on ATAC-seq, DNase-seq, RNA-seq, and microarray data from the GEO databases as well as gene expression data (RNA-seq and microarray data). The microarray analysis of three human cases with different SSCs revealed that 6 genes were upregulated, and the expression of 23 genes was downregulated compared to the normal case in relation to aging genes. To reach these results, online assessments of Enrich Shiny GO, STRING, and Cytoscape were used to forecast the molecular and functional connections of proteins before identifying the master routes. The biological process and molecular function keywords of cell–matrix adhesion, telomerase activity, and telomere cap complex were shown to be significantly altered in upregulated differentially expressed genes (DEGs) by the functional enrichment analysis. According to our preliminary research, cell-specific TFs and TF-mediated GRNs are involved in the creation of SSCs. In order to maximize the induction efficiency of ESC differentiation into SSCs in vitro, hub SSC-specific genes and important SSC-specific TFs were identified, and sophisticated network regulation was proposed. According to our research, these genes and the hub proteins that they interact with may be able to shine a light on the pathophysiologies of infertility and aberrant germ cells.

Usefulness of visual classification for cardiac pathophysiology using count-washout rate map in iodine-123-beta-methyl-P-iodophenyl-pentadecanoic acid scintigraphy

Abstract Background Myocardial washout rate (WR) analysis of radiopharmaceuticals is utilized in nuclear cardiology to evaluate the clinical pathophysiology of the heart. WR is defined as the ratio of the difference between the counts in the early image and time-decay-corrected delayed image divided by the former. The myocardial WR of iodine-123-β-methyl iodophenyl-pentadecanoic acid (BMIPP) is an indicator of myocardial lipolysis, and a decreased WR (<10%) of BMIPP is one of the diagnostic criteria for triglyceride deposit cardiomyovasculopathy (TGCV). However, decreased BMIPP uptake in the early images, as in old myocardial infarction (OMI), would also cause a markedly decreased WR. Since the distinction between these clinical conditions cannot be made based on WR alone, simultaneous evaluation of the counts in the early image and WR is needed to properly understand the cardiac pathophysiology. Purpose To differentiate between TGCV and non-TGCV with OMI, both of which show decreased BMIPP WR, a new Count-WR Map (CWRM) method was evaluated. The purpose is to visually and easily distinguish between the two conditions using CWRM. Methods We introduced a CWRM consisting of two axes: counting in the early image, and WR. The count window was set to a maximum of the mean plus two standard deviations and a minimum of 50 counts, and the WR window was set to a maximum of 30 % and a minimum of -20%. CWRM was visually evaluated as normal, TGCV, non-TGCV with OMI, or TGCV with OMI. Results In normal cases, sufficient counts were observed in the early images, and WR did not decrease; CWRM showed light blue. In TGCV, sufficient counts were observed in the early image, but WRs markedly decreased; CWRM showed even orange. In non-TGCV with OMI, regions with decreased and preserved counts coexisted; CWRM showed light blue in the normal and black in the OMI region. In TGCV with OMI, CWRM showed orange in the TGCV myocardium and black in the OMI region (figure). Conclusions CWRM is useful for visually and easily differentiating TGCV from non-TGCV with OMI. CWRM can be applied to other cardiovascular diseases with count and WR variations for visual classification.

Artificial intelligence derived electrocardiograms: a comparative study of network architectures predicting sex and left ventricular dysfunction

Abstract Background Within cardiovascular medicine, AI-driven electrocardiogram (ECG) analysis has emerged as a powerful tool, capable of predicting clinically significant abnormalities. The increasing growth of wearable technologies for ECG monitoring underscores the importance of advancing AI methodologies. While Convolutional Neural Networks (CNNs) have traditionally been the go-to choice for ECG analysis, the rise of Vision Transformers (ViTs), a novel computer vision paradigm, raises the question of their potential superiority. Purpose To compare the performance of CNNs and ViTs in ECG analysis, and to assess the efficiency of lean models using truncated ECG recordings. Methods We trained a model using 12-lead ECGs as input for the binary classification of two outputs: Sex (Male or Female) and Left ventricular dysfunction (LVD, defined as below 35%), determined by echocardiography within 2 weeks of the ECG. Models were developed using full standard ECGs, single lead and truncated recordings (1,2 and 4 10 seconds). We compared CNNs (PyTorch) and ViTs (HuggingFace) performance. We analyzed the explainability of our findings, representing the AI model's focus of interest on ECGs from normal cases versus those with reduced ejection fraction, thereby validating its diagnostic discernment (Fig 1) Results We identified 150,691 and 29,422 patients with valid ECG tests for the Sex and LVD prediction models, respectively. For the Sex outcome, the AUROCs were 0.911 (95% CI: 0.908-0.914) and 0.898 (95% CI: 0.894-0.901) for the CNN-based model and the ViT-based models, respectively, with the difference statistically significant (P-Value < 0.001). For the LVD outcome, the AUROCs were comparable at 0.878 (95% CI: 0.864-0.892) and 0.866 (95% CI: 0.853-0.879) for the CNN-based model and the ViT-based models, respectively, (P-Value = 0.056). Furthermore, we found that 98.8% for the maximal predictive power of the models was achieved within a 2 second time frame of a 12 lead ECG. Similarly, a single lead based model achieved a relatively high AUC for the prediction of LVD. Conclusions AI-ECG models developed with ViT architecture did not surpass CNN-based models in sex classification and LVD identification. Our study highlights the significance of lean models allowing for rapid prediction within 2-second tracings or using a single lead, demonstrates the potential for streamlined AI-ECG applications in clinical practice.

Fully automated detection of anomalous aortic origin of the coronary arteries in coronary CT images: a novel artificial intelligence-based screening tool

Abstract Background Anomalous Aortic Origin of the Coronary Artery (AAOCA) is a rare congenital disease that can be easily overlooked during contrast-enhanced Coronary Computed Tomography Angiography (CCTA) image analysis. Objective In this study, we aimed to develop a novel artificial intelligence-based screening tool to automate the detection of AAOCA in CCTA images. Method We enrolled 127 patients from the coronary artery anomaly registry from two centers with AAOCA diagnosis based on CCTA as well as 413 normal cases. A deep learning model was developed to automatically segment the aorta and the left ventricle (LV), after which the images were automatically cropped to the aortic root and LV intersection with a box size of 6 cm3. The images were then clipped to Hounsfield Units ranging from -400 to 750 and normalized to -1 to1. These cropped regions were fed into different residual convolutional neural networks (ResNet, with different depths 10, 18, 34 and 50) to detect AAOCA. Model development (parameter and hyperparameters optimization) was performed on the training and validation sets (70/10%), and finally, it was tested on the 20% untouched test set. Various classification metrics were reported for the detection of AAOCA. Results ResNet-10 achieved an AUC of 0.91 (sensitivity: 0.89, specificity: 0.86), while ResNet-18 showed improved performance with an AUC of 0.95 (sensitivity: 0.89, specificity: 0.95). ResNet-34 achieved an AUC of 0.94 (sensitivity: 0.83, specificity: 0.96), and ResNet-50 excelled with the highest AUC of 0.96 (sensitivity: 0.89, specificity: 0.95), indicating its superior capability in accurately identifying AAOCA. Conclusion We developed a high-performance AI tool for the fully automated detection of AAOCA using CCTA images. This tool can be used to evaluate large patient cohorts and detect AAOCA in extensive databases. Moreover, it can operate seamlessly alongside clinical assessments of CCTA scans, providing real-time alerts to medical personnel about potential AAOCA findings. This enhances diagnostic efficiency and supports early intervention in cardiovascular care.

Chest x-ray images: transfer learning model in COVID-19 detection.

This research aims to develop an effective algorithm for diagnosing COVID-19 in chest X-rays using the transfer learning method and support vector machines. In total, data was collected from 10 clinics, including both large city hospitals and smaller medical institutions. This ensured a diverse range of geographical and demographic information in the sample. An extensive data set was collected, including 10,000 chest X-ray images. 5000 images represent normal cases, 3993 images represent pneumonia cases, and 1007 images represent COVID-19 cases. Machine learning methods were applied to develop a classification model, and the results were compared with seven state-of-the-art models and a lightweight CNN architecture. The results showed that the proposed method achieves high accuracy values (Accuracy): 0.95 for COVID-19, 0.89 for pneumonia, and 0.92 for normal images (p < 0.05). Comparison with other models demonstrates statistically significant superiority of our method in accuracy across all three classes. The EfficientNet-B0 model surpasses our method only in accuracy for normal images with p < 0.01, confirming the advantages of our method. Our method demonstrates high sensitivity values (Sensitivity): 0.96 for COVID-19, 0.88 for pneumonia, and 0.93 for normal images (p < 0.05), outperforming most of the compared models. Correlation analysis showed Pearson coefficients of 0.92, 0.89, and 0.94 for COVID-19, pneumonia, and normal images, respectively, confirming a high degree of consistency between predicted and true class labels. In addition, the model was validated on external datasets to assess its generalizability. This validation confirmed its high level of effectiveness in a variety of clinical settings. This study confirms the importance of applying machine learning methods in medical applications and opens new perspectives for early diagnosis of infectious diseases. The practical application of the obtained results can enhance the efficiency of diagnosis and control the spread of COVID-19, as well as contribute to the development of innovative methods in medical practice.

A Framework for Detecting Pulmonary Diseases from Lung Sound Signals Using a Hybrid Multi-Task Autoencoder-SVM Model

Research focuses on the efficacy of Multi-Task Autoencoder (MTAE) models in signal classification due to their ability to handle many tasks while improving feature extraction. However, researchers have not thoroughly investigated the study of lung sounds (LSs) for pulmonary disease detection. This paper introduces a new framework that utilizes an MTAE model to detect lung diseases based on LS signals. The model integrates an autoencoder and a supervised classifier, simultaneously optimizing both classification accuracy and signal reconstruction. Furthermore, we propose a hybrid approach that combines an MTAE and a Support Vector Machine (MTAE-SVM) to enhance performance. We evaluated our model using LS signals from a publicly available database from King Abdullah University Hospital. The model attained an accuracy of 89.47% for four classes (normal, pneumonia, asthma, and chronic obstructive pulmonary disease) and 90.22% for three classes (normal, pneumonia, and asthma cases). Using the MTAE-SVM, the accuracy was further improved to 91.49% for four classes and 93.08% for three classes, respectively. The results indicate that the MTAE and MTAE-SVM have a considerable potential for detecting pulmonary diseases from lung sound signals. This could aid in the creation of more user-friendly and effective diagnostic tools.

The effect of adding pancreatin to standard otilinium bromide and simethicone treatment in type 2 diabetes mellitus patients with irritable bowel syndrome.

This study aimed to assess the impact of adding pancreatin (a pancreatic enzyme derivative) to standard treatment on patients diagnosed with Irritable Bowel Syndrome (IBS) and Type 2 Diabetes Mellitus (T2DM). IBS and T2DM frequently coexist, leading to significant gastrointestinal symptoms and a decrease in quality of life. Gastrointestinal symptoms arising in T2DM patients present challenges in management for both clinicians and patients. Standard treatments may not fully address these symptoms. Recent studies suggest that pancreatic enzyme replacement therapy may offer additional benefits. This study investigates whether adding pancreatin to standard treatment can improve gastrointestinal outcomes in this patient population. Conducted as a prospective observational study, the research involved patients diagnosed with IBS according to Rome IV criteria and having concomitant T2DM. The patients were divided into two groups: one receiving standard dual treatment (otilinium bromide + simethicone) and the other receiving a triple therapy including a pancreatin derivative in addition to the standard treatment. Various clinical scores and measurements, including Visual Analog Scale (VAS), Bristol Stool Chart (BSC), Irritable Bowel Syndrome-Severity Scoring System (IBS-SSS), and Irritable Bowel Syndrome Quality of Life Instrument (IBS-QOL), were assessed before and after treatment. The study comprised 121 patients, with a median age of 41 years (interquartile range [IQR] 38-48), of whom approximately 70.2% were female. Fifty-eight patients (47.9%) received dual therapy, while sixty-three patients (52.1%) received triple therapy. Before treatment, both groups exhibited similar pre-treatment Bristol stool scale results: normal (39.7% and 49.2%) and constipation (37.9% and 31.7%) in the dual and triple therapy subgroups, respectively (p > 0.05). Post-treatment, the triple therapy group showed a significantly higher proportion of normal cases on the Bristol stool scale (82.5%) compared to the dual therapy group (44.8%) (p < 0.001). After treatment, the triple therapy group demonstrated statistically significant improvements in VAS score (p < 0.001), IBS-SSS (p < 0.001), and IBS-QOL (p < 0.001) compared to the dual therapy group. There were no significant differences between groups in BMI, HbA1c levels, duration of diabetes, or diabetes treatment at baseline (p > 0.05 for all parameters). The findings suggest that adding pancreatin to standard therapies significantly enhanced the quality of life for patients with both IBS and T2DM, demonstrating improvements across various symptom measurements and indicating the potential benefits of this supplementary therapy in managing gastrointestinal symptoms in this population. Further studies are warranted to explore its broader clinical implications and mechanisms of action.

A Machine Learning Model Based on Global Mammographic Radiomic Features Can Predict Which Normal Mammographic Cases Radiology Trainees Find Most Difficult.

This study aims to investigate whether global mammographic radiomic features (GMRFs) can distinguish hardest- from easiest-to-interpret normal cases for radiology trainees (RTs). Data from 137 RTs were analysed, with each interpreting seven educational self-assessment test sets comprising 60 cases (40 normal and 20 cancer). The study only examined normal cases. Difficulty scores were computed based on the percentage of readers who incorrectly classified each case, leading to their classification as hardest- or easiest-to-interpret based on whether their difficulty scores fell within and above the 75th or within and below the 25th percentile, respectively (resulted in 140 cases in total used). Fifty-nine low-density and 81 high-density cases were identified. Thirty-four GMRFs were extracted for each case. A random forest machine learning model was trained to differentiate between hardest- and easiest-to-interpret normal cases and validated using leave-one-out-cross-validation approach. The model's performance was evaluated using the area under receiver operating characteristic curve (AUC). Significant features were identified through feature importance analysis. Difference between hardest- and easiest-to-interpret cases among 34 GMRFs and in difficulty level between low- and high-density cases was tested using Kruskal-Wallis. The model achieved AUC = 0.75 with cluster prominence and range emerging as the most useful features. Fifteen GMRFs differed significantly (p < 0.05) between hardest- and easiest-to-interpret cases. Difficulty level among low- vs high-density cases did not differ significantly (p = 0.12). GMRFs can predict hardest-to-interpret normal cases for RTs, underscoring the importance of GMRFs in identifying the most difficult normal cases for RTs and facilitating customised training programmes tailored to trainees' learning needs.

Early Cervical Cancer Diagnosis with SWIN-Transformer and Convolutional Neural Networks.

Introduction: Early diagnosis of cervical cancer at the precancerous stage is critical for effective treatment and improved patient outcomes. Objective: This study aims to explore the use of SWIN Transformer and Convolutional Neural Network (CNN) hybrid models combined with transfer learning to classify precancerous colposcopy images. Methods: Out of 913 images from 200 cases obtained from the Colposcopy Image Bank of the International Agency for Research on Cancer, 898 met quality standards and were classified as normal, precancerous, or cancerous based on colposcopy and histopathological findings. The cases corresponding to the 360 precancerous images, along with an equal number of normal cases, were divided into a 70/30 train-test split. The SWIN Transformer and CNN hybrid model combines the advantages of local feature extraction by CNNs with the global context modeling by SWIN Transformers, resulting in superior classification performance and a more automated process. The hybrid model approach involves enhancing image quality through preprocessing, extracting local features with CNNs, capturing the global context with the SWIN Transformer, integrating these features for classification, and refining the training process by tuning hyperparameters. Results: The trained model achieved the following classification performances on fivefold cross-validation data: a 94% Area Under the Curve (AUC), an 88% F1 score, and 87% accuracy. On two completely independent test sets, which were never seen by the model during training, the model achieved an 80% AUC, a 75% F1 score, and 75% accuracy on the first test set (precancerous vs. normal) and an 82% AUC, a 78% F1 score, and 75% accuracy on the second test set (cancer vs. normal). Conclusions: These high-performance metrics demonstrate the models' effectiveness in distinguishing precancerous from normal colposcopy images, even with modest datasets, limited data augmentation, and the smaller effect size of precancerous images compared to malignant lesions. The findings suggest that these techniques can significantly aid in the early detection of cervical cancer at the precancerous stage.

Deep learning on chest X-ray and computed tomography scans for detection of COVID-19 as a part of a network-centric digital health stack for future pandemics

Developing a reliable rapid screening protocol for highly infectious diseases like COVID-19 is of paramount interest since it facilitates the isolation of infected patients from the rest of the population. Reverse-transcription polymerase chain reaction (RT-PCR) test is presently the most widely accepted gold-standard test to detect COVID-19. In this method, the RNA of the virus is duplicated by a process called reverse transcription to form DNA for facilitating the copying process. Fluorescent dye is attached to the viral genetic material and copied billions of times through the process called polymerase chain reaction. Enhanced fluorescence is used to identify the presence of genetic material of the virus. These tests are time-consuming and have significant false negatives, i.e., a person with COVID-19 might be categorized as not having the virus. Large-scale RT-PCR testing has its own share of problems such as logistics, availability and affordability in underdeveloped nations, and reliability of the test results. Machine learning algorithms can act as a cheaper supplementary/alternative diagnostic tool for the testing process. In the current study, using publicly available chest X-ray image datasets, different convolutional neural network (CNN)-based models were developed for efficient identification of COVID-19 infected patients, and their efficacies were compared. Key innovations in training the CNNs are discussed. Our results indicate that EfficientNet, SeResNext, and ResNet are best at classifying normal, pneumonia and COVID-19 cases, respectively. The ResNet architecture with transfer learning performed best at detecting COVID-19 with an accuracy of 94%, a rate far superior to that in the RT-PCR test, which is typically in the range of 70 &amp;ndash; 80%. This is particularly attractive as an additional noninvasive protocol since such technology-augmented detection is likely to help in reducing the psychological refractory period due to COVID-19 infections. Toward the healthy lung initiative in the post-COVID-19 era, we propose close coupling of the present diagnostic protocols with digital approaches to ensure more reliable personal care within the ambit of large-scale pandemic control mechanisms. Such integration with emerging technological tools can create a benchmark for the first line of defense against future global pandemics.

The safety and efficacy of stapler method for transection of the pancreatic parenchyma during pancreatoduodenectomy (STRAP-PD trial): study protocol for a randomized control trial.

Pancreaticoduodenectomy is a highly difficult and invasive type of gastrointestinal surgery. Prevention of postoperative pancreatic fistula is important, and this may be possible by the stapler method. STRAP-PD is a single center randomized controlled trial. We compare a method of transecting the pancreatic parenchyma in pancreaticoduodenectomy using a surgical stapler device with a conventional transecting method using energy devices (e.g., scalpel, ultrasonic coagulator and incision devices). Patients with soft pancreas who are scheduled to undergo pancreaticoduodenectomy are randomized to arm A (conventional method) or arm B (stapler method). We aim to examine the safety and usefulness of dissection by the automatic suture device, with attention to the rate of pancreatic fistula ISGPF grade B or C and to postoperative complications. This is a single-center randomized study, which began in September 2023 at Wakayama Medical University Hospital. Pancreatic parenchymal transection is typically performed either by direct incision using a scalpel or by employing energy devices such as ultrasonic coagulating cutting devices during pancreaticoduodenectomy. In a prospective pilot study, we conducted pancreatic parenchymal transection in 20 consecutive normal pancreatic cases during pancreaticoduodenectomy, observing postoperative pancreatic fistula grade B in one case (5%). Traditional methods involving scalpel incision or the use of ultrasonic coagulating cutting devices have been historically favored but perceived as technically challenging, and they have been reliant upon the surgeon's skill. Notably, relatively high incidences of postoperative pancreatic fistula among patients with soft pancreas have also been observed. Our proposed stapler method may therefore be a useful method responsible for reducing the development of pancreatic fistula. This method would be as part of minimally-invasive surgery for pancreaticoduodenectomy. It uses an endoscopic linear stapler to cut the pancreatic parenchyma, so it is likely to be more convenient than conventional methods and can be used universally. TRIALREGISTRATION: University Hospital Medical Information Network Clinical Trials Registry,UMIN000052089. the Registration Date on 1st September 2023.

A Pragmatic Approach to Fetal Monitoring via Cardiotocography Using Feature Elimination and Hyperparameter Optimization.

Cardiotocography (CTG) is used to assess the health of the fetus during birth or antenatally in the third trimester. It concurrently detects the maternal uterine contractions (UC) and fetal heart rate (FHR). Fetal distress, which may require therapeutic intervention, can be diagnosed using baseline FHR and its reaction to uterine contractions. Using CTG, a pragmatic machine learning strategy based on feature reduction and hyperparameter optimization was suggested in this study to classify the various fetal states (Normal, Suspect, Pathological). An application of this strategy can be a decision support tool to manage pregnancies. On a public dataset of 2126 CTG recordings, the model was assessed using various standard CTG dataset specific and relevant classifiers. The classifiers' accuracy was improved by the proposed method. The model accuracy was increased to 97.20% while using Random Forest (best classifier). Practically speaking, the model was able to correctly predict 100% of all pathological cases and 98.8% of all normal cases in the dataset. The proposed model was also implemented on another public CTG dataset having 552 CTG signals, resulting in a 97.34% accuracy. If integrated with telemedicine, this proposed model could also be used for long-distance "stay at home" fetal monitoring in high-risk pregnancies.

Exploring the impact of work experience on the detection of specific cancers across different breast density levels on screening mammograms

PurposeThis study explores the attributes of true positive and false positive rates in screening mammogram test sets assessed by breast screening radiologists in order to identify the combined impact of prior images, breast density and lesion features with experience factors linked to diagnostic performance. Methods869 radiologists’ first-time readings across nine mammogram BREAST test sets with 361 normal and 179 cancer mammograms were collected between 2014 and 2023. Participants viewed digital mammograms on diagnostic monitors and localized abnormal lesions. The performances of readers in normal and cancer cases were compared with the ground truth and analyzed in four quartiles of breast density, lesion types and the availability of prior images using Man-Whitney U and Kruskal Wallis tests. The general linear model was applied to determine independent and significant covariates that affected the true positives and false positives. The correlation of the readers’ experience with the performances in different case and lesion features was explored using Spearman test. ResultsThe combination of lesion appearance and the availability of prior images had a significant impact on false positive results (P=0.033). The model that included lesion appearance, breast density, and no prior image status significantly influenced case true positives of readers (P=0.026). Meanwhile, the model considering only lesion appearance and breast density (P=0.002) had a significant effect on lesion true positives. There was a positive correlation observed between the number of cases read per week and readers’ performances, including TP rates and lesion sensitivity across various lesion types (P<0.05). Radiologists reading over 100 cases weekly achieved 80 % true positive rate for architectural distortion, asymmetric density, and masses, while this threshold increased to over 150 cases for calcifications. Detecting mixed lesion types required reading more than 60 cases weekly. Radiologists with over 5 years’ experience achieved 70–75 % accuracy in localizing cancer lesions. ConclusionFindings highlight the significant combined impact of breast density, prior image availability, lesion characteristics, and breast screening readers’ experience on breast cancer detection.

Experiment on Lung Disease Classification using YOLOv8

Lung diseases are a leading cause of illness and mortality worldwide. Accurate and timely diagnosis is crucial for improving patient outcomes, but manual interpretation of chest X-rays by radiologists may consume a significant amount of time and is susceptible to errors. This study leverages the state-of-the-art YOLOv8 deep learning model to develop an automated system for classifying lung diseases from chest X-ray images. The proposed approach utilizes a large, diverse dataset of 21,165 chest X-ray images categorized into four classes: COVID-19, viral pneumonia, lung opacity, and normal. The YOLOv8-cls model is fine-tuned using transfer learning and advanced data augmentation techniques. The system achieves a high accuracy of approximately 95% across all disease classes while maintaining real-time performance. Confusion matrix analysis demonstrates strong performance in correctly identifying each condition, with COVID-19, normal, viral pneumonia and lung opacity cases correctly identified 97%, 97%, 99% and 93% of the time respectively. The outcomes validate the adaptability and reliability of deep learning, specifically YOLOv8, for automated lung disease detection, offering the potential to improve clinical workflows and patient care by providing efficient screening tools for practitioners. The study addresses limitations of previous works by utilizing a large consolidated dataset, reporting comprehensive computational efficiency metrics, and extending classification complexity without substantially impacting accuracy or speed. Future research should focus on further optimizations and extending the curated image repositories to include under-represented patient groups to enhance the model's inclusiveness and robustness.

Investigation of essential parameters for the design of offshore wind turbine based on structural reliability

The probabilistic-based design method is gradually gaining attention in the wind industry because it provides more accurate modeling of uncertainty variables than that of traditional methods. Unfortunately, the numerous uncertainty variables involved in structural design are major obstacles to the successful application of this method. Therefore, this study presents a sensitivity analysis (SA) of a benchmark monopile offshore wind turbine (OWT) to screen the top-ranking variables from the viewpoint of reliability. Primarily, a comprehensive reliability SA framework of OWT is proposed, in which a novel measurement of soil uncertainties is conducted using quantitative analysis from the perspective of soil structure interaction (SSI). Subsequently, a reliability SA is conducted to explore the crucial variables influencing the structural safety from the uncertain clusters. The results indicate that Young's modulus, structural geometry, and SSI have significant effects on the structural reliability of excessive vibration failure. The hydrodynamic and aerodynamic load variables exhibit the most prominent influence on excessive deflection failure. Additionally, the SSI uncertainties exhibit a non-negligible effect in affecting the structural reliability, i.e., the lateral bending stiffness shows more sensitivity to the normal operation cases, whereas the impact of joint stiffness is more remarkable in parked scenarios.

Random subspace ensemble-based detection of false data injection attacks in automatic generation control systems

Automatic Generation Control (AGC) systems in smart grids are increasingly vulnerable to cyber-attacks, particularly False Data Injection (FDI) attacks, due to their reliance on information and communication technologies. These vulnerabilities pose significant threats to the reliable operation of power systems. To address this challenge, this research paper introduces the machine learning (ML) based cyberattack detection technique designed to identify FDI attacks with the highest accuracy proficiently. The study involves a comprehensive analysis of three features: the original discrete signal feature, the cycle-to-cycle-based feature, and the sample-to-sample-based feature. These features are utilized for detecting FDI attacks and distinguishing them from normal load variations. The research meticulously collects data by simulating diverse FDI attacks, including step attacks, pulse attacks, random attacks, and normal load variation cases on an AGC power system. Four ML classifiers are selected and compared for the classification task. The simulation results reveal that the sample-to-sample-based feature proves highly effective in distinguishing FDI attacks compared to the original signal and cycle-to-cycle-based features. Notably, the results indicate that the random subspace ensemble (RaSE) classifier, utilizing sample-to-sample-based features, effectively identifies and classifies all normal and FDI attacks. This research provides valuable insights into the potential of ML techniques for enhancing FDI attack detection in the AGC of power systems. It provides a potential pathway for overcoming the limitations associated with traditional model-based FDI detection methods.

Hybrid Approach of Multiclassification for Lung Cancer Types Identification

As a widespread health concern, lung cancer requires sophisticated detection techniques for a precise classification. This research proposes an integrated framework for improving how well lung cancer is detected by combining processing methods for images and machine learning. The dataset, which includes normal cases, large-cell carcinoma, squamous cell carcinoma, and adenocarcinoma, allows for a detailed investigation of various forms of lung cancer. K-means clustering is the initial stage of the approach of segmenting complex images. Utilizing the VGG16 model, features are extracted that are important for classification. Several classification models, such as SVM, Logistic Regression, and Feedforward Neural Network, are trained using the combined features from clustering and VGG16. This research goes beyond the dichotomy of benign and malignant cases, investigating in more detail the subtypes of large-cell carcinoma, squamous cell carcinoma, and adenocarcinoma. Including different classes of lung cancer increases the granularity of the classification process, improving diagnostic accuracy and clinical insights. The results highlight how well the suggested strategy works, which is a major advancement in the accurate identification of distinct kinds of lung cancer.

Bronchial asthma with normal forced expiratory volume in 1 second (FEV1) compared with low FEV1.

Cough variant asthma (CVA) is characterized by cough as a sole symptom and normal pulmonary function. However, it is unclear whether CVA really common among asthmatic patients with normal forced expiratory volume in 1 second (FEV1). The aim of this study was to evaluate the incidence of cough alone symptom among the subjects with normal FEV1 and to evaluate their differences from ordinary asthmatic subjects. We defined normal FEV1 as ≥90% predicted based on the article of Kotti GH. Of the patients with normal FEV1, we chose subjects without wheeze, and the duration of cough was not to ask, since the symptoms often occurred with acute exacerbation and timing of visiting a doctor depended on each patient's perception. Test for airway hyperresponsiveness was not performed in this study. Visual analogue scale (VAS) scores for cough and dyspnea, FEV1, and fractional exhaled nitric oxide (FeNO) responsiveness to inhaled corticosteroid (ICS)/long-acting beta2 agonist (LABA) treatment were compared in patients with normal FEV1 and with low FEV1 <90%. Correlations of changes in symptoms with changes of FEV1, FeNO, peripheral eosinophil count, and serum immunoglobulin E (IgE) at single time point were also examined in each group and in overall patients. The participants were 329 physician-diagnosed treatment-naive patients with asthma who were divided into 187 in normal FEV1 and 142 in low FEV1 groups. Cough without dyspnea was present in 16 patients (8.6%) in the normal FEV1 group, suggesting candidates for CVA in this analysis were quite few. Improvement in symptoms after treatment was similar between both groups. But VAS scores of dyspnea were still higher in the low FEV1 group. The degree of improvement in FEV1 after ICS/LABA treatment was less in the normal FEV1 group than in the low FEV1 group, but was still evident. Peripheral eosinophil count, serum IgE, and FeNO values before treatment were lower in the normal FEV1 group. In overall patients, improvements of symptoms after treatment were significantly correlated with FEV1 changes. Improvement of dyspnea was also significantly related to peripheral eosinophil count and change of FeNO, whereas improvement of cough was not related to these T helper 2 (Th2) response markers. Candidates for CVA among the patients with asthma with predicted FEV1 ≥90% were few. Participants with normal FEV1 respond well to ICS/LABA treatment for improvement of symptom. The change of FEV1 after treatment, and the pre-treatment blood eosinophil count, serum IgE, and FeNO were lower in normal FEV1 cases than in low FEV1 cases. These observations suggest asthmatic patients with normal FEV1, including candidates for CVA having just common mild asthma. In overall participants, symptoms of cough and dyspnea were similar, but were not identical in relation to the Th2 background.