Search

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

Simple Summary: The 2021 WHO classification of central nervous system (CNS) tumors is challenging for neuroradiologists due to the central role of the molecular profile of tumors. We performed a scoping review of recent literature to assess the existing data on the power of novel data analysis tools to predict new tumor classes by imaging. We found room for performance improvement for subgroups with lower incidence (e.g., 1p/19q codeleted or IDH1/2 mutated gliomas) and patients with rare diagnoses (e.g., pediatric gliomas, midline gliomas). More data regarding functional MRI techniques need to be collected. Studies explicitly designed to assess the generalizability of AI-aided tools for predicting molecular tumor subgroups are lacking. The 2021 WHO classification of CNS tumors is a challenge for neuroradiologists due to the central role of the molecular profile of tumors. The potential of novel data analysis tools in neuroimaging must be harnessed to maintain its role in predicting tumor subgroups. We performed a scoping review to determine current evidence and research gaps. A comprehensive literature search was conducted regarding glioma subgroups according to the 2021 WHO classification and the use of MRI, radiomics, machine learning, and deep learning algorithms. Sixty-two original articles were included and analyzed by extracting data on the study design and results. Only 8% of the studies included pediatric patients. Low-grade gliomas and diffuse midline gliomas were represented in one-third of the research papers. Public datasets were utilized in 22% of the studies. Conventional imaging sequences prevailed; data on functional MRI (DWI, PWI, CEST, etc.) are underrepresented. Multiparametric MRI yielded the best prediction results. IDH mutation and 1p/19q codeletion status prediction remain in focus with limited data on other molecular subgroups. Reported AUC values range from 0.6 to 0.98. Studies designed to assess generalizability are scarce. Performance is worse for smaller subgroups (e.g., 1p/19q codeleted or IDH1/2 mutated gliomas). More high-quality study designs with diversity in the analyzed population and techniques are needed. [ABSTRACT FROM AUTHOR]

Background: Dementia is a cognitive decline that leads to the progressive deterioration of an individual's ability to perform daily activities independently. As a result, a considerable amount of time and resources are spent on caretaking. Early detection of dementia can significantly reduce the effort and resources needed for caretaking. Aims: This research proposes an approach for assessing cognitive decline by analysing speech data, specifically focusing on speech relevance as a crucial indicator for memory recall. Methods & Procedures: This is a cross‐sectional, online, self‐administered. The proposed method used deep learning architecture based on transformers, with BERT (Bidirectional Encoder Representations from Transformers) and Sentence‐Transformer to derive encoded representations of speech transcripts. These representations provide contextually descriptive information that is used to analyse the relevance of sentences in their respective contexts. The encoded information is then compared using cosine similarity metrics to measure the relevance of uttered sequences of sentences. The study uses the Pitt Corpus Dementia dataset for experimentation, which consists of speech data from individuals with and without dementia. The accuracy of the proposed multi‐QA‐MPNet (Multi‐Query Maximum Inner Product Search Pretraining) model is compared with other pretrained transformer models of Sentence‐Transformer. Outcomes & Results: The results show that the proposed approach outperforms the other models in capturing context level information, particularly semantic memory. Additionally, the study explores the suitability of different similarity measures to evaluate the relevance of uttered sequences of sentences. The experimentation reveals that cosine similarity is the most appropriate measure for this task. Conclusions & Implications: This finding has significant implications for the early warning signs of dementia, as it suggests that cosine similarity metrics can effectively capture the semantic relevance of spoken language. The persistent cognitive decline over time acts as one of the indicators for prevalence of dementia. Additionally early dementia could be recognised by analysis on other modalities like speech and brain images. WHAT THIS PAPER ADDS: What is already known on this subject: It is already known that speech‐ and language‐based detection methods can be useful for dementia diagnosis, as language difficulties are often early signs of the disease. Additionally, deep learning algorithms have shown promise in detecting and diagnosing dementia through analysing large datasets, particularly in speech‐ and language‐based detection methods. However, further research is needed to validate the performance of these algorithms on larger and more diverse datasets and to address potential biases and limitations. What this paper adds to existing knowledge: This study presents a unique and effective approach for cognitive decline assessment through analysing speech data. The study provides valuable insights into the importance of context and semantic memory in accurately detecting the potential in dementia and demonstrates the applicability of deep learning models for this purpose. The findings of this study have important clinical implications and can inform future research and development in the field of dementia detection and care. What are the potential or actual clinical implications of this work?: The proposed approach for cognitive decline assessment using speech data and deep learning models has significant clinical implications. It has the potential to improve the accuracy and efficiency of dementia diagnosis, leading to earlier detection and more effective treatments, which can improve patient outcomes and quality of life. [ABSTRACT FROM AUTHOR]

In recent times, there has been considerable focus on harnessing artificial intelligence (AI) for medical image analysis and healthcare purposes. In this study, we introduce CADFU (Computer-Aided Diagnosis System for Foot Ulcers), a pioneering diabetic foot ulcer diagnosis system. The primary objective of CADFU is to detect and segment ulcers and similar chronic wounds in medical images. To achieve this, we employ two distinct algorithms. Firstly, DHuNeT, an innovative Dual-Phase Hyperactive UNet, is utilized for the segmentation task. Second, we used YOLOv8 for the task of detecting wounds. The DHuNeT autoencoder, employed for the wound segmentation task, is the paper's primary and most significant contribution. DHuNeT is the combination of sequentially stacking two UNet autoencoders. The hyperactive information transmission from the first UNet to the second UNet is the key idea of DHuNeT. The first UNet feeds the second UNet the features it has learned, and the two UNets combine their learned features to create new, more accurate, and effective features. We achieve good performance measures, especially in terms of the Dice co-efficient and precision, with segmentation scores of 85% and 92.6%, respectively. We obtain a mean average precision (mAP) of 86% in the detection task. Future hospitals could quickly monitor patients' health using the proposed CADFU system, which would be beneficial for both patients and doctors. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer worldwide. Early detection of melanoma is crucial for better outcomes, but this often can be challenging. This research explores the use of artificial intelligence (AI) techniques combined with non-invasive imaging methods to improve melanoma detection. The authors aim to evaluate the current state of AI-based techniques using tools including dermoscopy, optical coherence tomography (OCT), and reflectance confocal microscopy (RCM). The findings demonstrate that several AI algorithms perform as well as or better than dermatologists in detecting melanoma, particularly in the analysis of dermoscopy images. This research highlights the potential of AI to enhance diagnostic accuracy, leading to improved patient outcomes. Further studies are needed to address limitations and ensure the reliability and effectiveness of AI-based techniques. Background: Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. Objective: The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. Methods: A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. Results: We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Conclusions: Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability. [ABSTRACT FROM AUTHOR]

Introduction: Nowadays human immunodeficiency virus (HIV)/acquired immunodeficiency syndrome (AIDS) is very dangerous. HIV targets the resistant system and weakens people's denial against many contaminations and some kinds of cancer. As the virus breaks up and impairs the function of immunity, infected people gradually become immunodeficient. Both deep learning and machine learning models play a great role in the prediction of diseases. The function of immunity is CD4 cell count. In this study both the machine learning and deep learning algorithms were applied. Material and methods: In this paper the data were collected from data world. Support vector machine, random forest, naïve Bayes, gated recurrent unit, and long short-term memory were used to fit the incidence data. The performance of the model was evaluated by accuracy, precision, sensitivity, and F-score with respective errors. Results: Based on the evaluation, deep learning models achieve better results in the metrics of accuracy, precision, and F-score than machine learning models. But in sensitivity metrics machine learning models achieve better result than deep learning. Machine learning algorithms SVM, RF, and NB provide accuracy of 89.00%, 87.00%, and 86.94%; precision of 75.89%, 74.97%, and 75.78%; sensitivity of 87.96%, 84.00%, and 84.12%; F-score of 82.87%, 80.03%, and 79.05%, respectively. LSTM, GRU provides accuracy of 97.65%, 96.00%, precision of 77.35%, 84.00%, sensitivity of 87.93%, 82.98%, and F-score of 82.03%, 83.20%, respectively. Conclusions: The possibility survival of the illness is less than no illness. The existence of TB negative is higher than TB positive. In the machine learning model SVM provides better sensitivity with 87.96%, long short-term memory provides accuracy of 97.65%, precision of 77.35%, sensitivity of 87.93%, and F-score of 82.03%. [ABSTRACT FROM AUTHOR]

Approximately one-third of the veteran population suffers from post-traumatic stress disorder, a mental illness that is often co-morbid with social anxiety disorder. Student veterans are especially vulnerable as they struggle to adapt to a new, less structured lifestyle with few peers who understand their difficulties. To support mental health experts in the treatment of social anxiety disorder, this study utilized machine learning to detect anxiety in text transcribed from interviews with patients and applied topic modeling to highlight common stress factors for student veterans. We approach our anxiety detection task by exploring both deep learning and traditional machine learning strategies such as transformers, transfer learning, and support vector classifiers. Our models provide a tool to support psychologists and social workers in treating social anxiety. The results detailed in this paper could also have broader impacts in fields such as pedagogy and public health.1 [ABSTRACT FROM AUTHOR]

Glucose forecasting serves as a backbone for several healthcare applications, including real-time insulin dosing in people with diabetes and physical activity optimization. This paper presents a study on the use of machine learning (ML) and deep learning (DL) methods for predicting glucose variability (GV) in individuals with open-source automated insulin delivery systems (AID). A three-stage experimental framework is employed in this work to systematically implement and evaluate ML/DL methods on a large-scale diabetes dataset collected from individuals with open-source AID. The first stage involves data collection, the second stage involves data preparation and exploratory analysis, and the third stage involves developing, fine-tuning, and evaluating ML/DL models. The performance and resource costs of the models are evaluated alongside relative and proportional errors for 17 GV metrics. Evaluation of fine-tuned ML/DL models shows considerable accuracy in glucose forecasting and variability analysis up to 48 h in advance. The average MAE ranges from 2.50 mg/dL for long short-term memory models (LSTM) to 4.94 mg/dL for autoregressive integrated moving average (ARIMA) models, and the RMSE ranges from 3.7 mg/dL for LSTM to 7.67 mg/dL for ARIMA. Model execution time is proportional to the amount of data used for training, with long short-term memory models having the lowest execution time but the highest memory consumption compared to other models. This work successfully incorporates the use of appropriate programming frameworks, concurrency-enhancing tools, and resource and storage cost estimators to encourage the sustainable use of ML/DL in real-world AID systems. [ABSTRACT FROM AUTHOR]

Background: Auditory–perceptual assessment of voice is a subjective procedure. Artificial intelligence with deep learning (DL) may improve the consistency and accessibility of this task. It is unclear how a DL model performs on different acoustic features. Aims: To develop a generalizable DL framework for identifying dysphonia using a multidimensional acoustic feature. Methods & Procedures: Recordings of sustained phonations of /a/ and /i/ were retrospectively collected from a clinical database. Subjects contained 238 dysphonic and 223 vocally healthy speakers of Chinese Mandarin. All audio clips were split into multiple 1.5‐s segments and normalized to the same loudness level. Mel frequency cepstral coefficients and mel‐spectrogram were extracted from these standardized segments. Each set of features was used in a convolutional neural network (CNN) to perform a binary classification task. The best feature was obtained through a five‐fold cross‐validation on a random selection of 80% data. The resultant DL framework was tested on the remaining 20% data and a public German voice database. The performance of the DL framework was compared with those of two baseline machine‐learning models. Outcomes & Results: The mel‐spectrogram yielded the best model performance, with a mean area under the receiver operating characteristic curve of 0.972 and an accuracy of 92% in classifying audio segments. The resultant DL framework significantly outperformed both baseline models in detecting dysphonic subjects on both test sets. The best outcomes were achieved when classifications were made based on all segments of both vowels, with 95% accuracy, 92% recall, 98% precision and 98% specificity on the Chinese test set, and 92%, 95%, 90% and 89%, respectively, on the German set. Conclusions & Implications: This study demonstrates the feasibility of DL for automatic detection of dysphonia. The mel‐spectrogram is a preferred acoustic feature for the task. This framework may be used for vocal health screening and facilitate automatic perceptual evaluation of voice in the era of big data. WHAT THIS PAPER ADDS: What is already known on this subject: Auditory–perceptual assessment is the current gold standard in clinical evaluation of voice quality, but its value may be limited by the rater's reliability and accessibility. DL is a new method of artificial intelligence that can overcome these disadvantages and promote automatic voice assessment. This study explored the feasibility of a DL approach for automatic detection of dysphonia, along with a quantitative comparison of two common sets of acoustic features. What this study adds to existing knowledge: A CNN model is excellent at decoding multidimensional acoustic features, outperforming the baseline parameter‐based models in identifying dysphonic voices. The first 13 mel‐frequency cepstral coefficients (MFCCs) are sufficient for this task. The mel‐spectrogram results in greater performance, indicating the acoustic features are presented in a more favourable way than the MFCCs to the CNN model. What are the potential or actual clinical implications of this work?: DL is a feasible method for the detection of dysphonia. The current DL framework may be used for remote vocal health screening or documenting voice recovery after treatment. In future, DL models may potentially be used to perform auditory–perceptual tasks in an automatic, efficient, reliable and low‐cost manner. [ABSTRACT FROM AUTHOR]

BACKGROUND: The construction industry is an important productive sector worldwide. However, the industry is also responsible for high numbers of work-related accidents, which highlights the necessity for improving safety management on construction sites. In parallel, technological applications such as machine learning (ML) are used in many productive sectors, including construction, and have proved significant in process optimizations and decision-making. Thus, advanced studies are required to comprehend the best way of using this technology to enhance construction site safety. OBJECTIVE: This research developed a systematic literature review using ten scientific databases to retrieve relevant publications and fill the knowledge gaps regarding ML applications in construction accident prevention. METHODS: This study examined 73 scientific articles through bibliometric research and descriptive analysis. RESULTS: The results showed the publications timeline and the most recurrent journals, authors, institutions, and countries-regions. In addition, the review discovered information about the developed models, such as the research goals, the ML methods used, and the data features. The research findings revealed that USA and China are the leading countries regarding publications. Also, Support Vector Machine – SVM was the most used ML method. Furthermore, most models used textual data as a source, generally related to inspection reports and accident narratives. The data approach was usually related to facts before an accident (proactive data). CONCLUSION: The review highlighted improvement proposals for future works and provided insights into the application of ML in construction safety management. [ABSTRACT FROM AUTHOR]

Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part‐of‐speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic‐based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution‐based data augmentation methods, one of which is thesaurus‐based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST‐2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM‐AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well‐designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms. [ABSTRACT FROM AUTHOR]

To understand the current practices in stroke evaluation, the main clinical decision support system and artificial intelligence (AI) technologies need to be understood to assist the therapist in obtaining better insights about impairments and level of activity and participation in persons with stroke during rehabilitation. This scoping review maps the use of AI for the functional evaluation of persons with stroke; the context involves any setting of rehabilitation. Data were extracted from CENTRAL, MEDLINE, EMBASE, LILACS, CINAHL, PEDRO Web of Science, IEEE Xplore, AAAI Publications, ACM Digital Library, MathSciNet, and arXiv up to January 2021. The data obtained from the literature review were summarized in a single dataset in which each reference paper was considered as an instance, and the study characteristics were considered as attributes. The attributes used for the multiple correspondence analysis were publication year, study type, sample size, age, stroke phase, stroke type, functional status, AI type, and AI function. Forty-four studies were included. The analysis showed that spasticity analysis based on ML techniques was used for the cases of stroke with moderate functional status. The techniques of deep learning and pressure sensors were used for gait analysis. Machine learning techniques and algorithms were used for upper limb and reaching analyses. The inertial measurement unit technique was applied in studies where the functional status was between mild and severe. The fuzzy logic technique was used for activity classifiers. The prevailing research themes demonstrated the growing utility of AI algorithms for stroke evaluation. [ABSTRACT FROM AUTHOR]

Accurate physical activity monitoring is essential to understand the impact of physical activity on one's physical health and overall well-being. However, advances in human activity recognition algorithms have been constrained by the limited availability of large labelled datasets. This study aims to leverage recent advances in self-supervised learning to exploit the large-scale UK Biobank accelerometer dataset—a 700,000 person-days unlabelled dataset—in order to build models with vastly improved generalisability and accuracy. Our resulting models consistently outperform strong baselines across eight benchmark datasets, with an F1 relative improvement of 2.5–130.9% (median 24.4%). More importantly, in contrast to previous reports, our results generalise across external datasets, cohorts, living environments, and sensor devices. Our open-sourced pre-trained models will be valuable in domains with limited labelled data or where good sampling coverage (across devices, populations, and activities) is hard to achieve. [ABSTRACT FROM AUTHOR]

Cough is a common symptom of multiple respiratory diseases, such as asthma and chronic obstructive pulmonary disorder. Various research works targeted cough detection as a means for continuous monitoring of these respiratory health conditions. This has been mainly achieved using sophisticated machine learning or deep learning algorithms fed with audio recordings. In this work, we explore the use of an alternative detection method, since audio can generate privacy and security concerns related to the use of always-on microphones. This study proposes the use of a non-contact tri-axial accelerometer for motion detection to differentiate between cough and noncough events/movements. A total of 43 time-domain features were extracted from the acquired tri-axial accelerometry signals. These features were evaluated and ranked for their importance using six methods with adjustable conditions, resulting in a total of 11 feature rankings. The ranking methods included model-based feature importance algorithms, first principal component, leave-one-out, permutation, and recursive features elimination (RFE). The ranking results were further used in the feature selection of the top 10, 20, and 30 for use in cough detection. A total of 68 classification models using a simple logistic regression classifier are reported, using two approaches for data splitting: subject-record-split and leave-one-subject-out (LOSO). The best-performing model out of the 34 using subject-record-split obtained an accuracy of 92.20%, sensitivity of 90.87%, specificity of 93.52%, and F1 score of 92.09% using only 20 features selected by the RFE method. The bestperforming model out of the 34 using LOSO obtained an accuracy of 89.57%, sensitivity of 85.71%, specificity of 93.43%, and F1 score of 88.72% using only 10 features selected by the RFE method. These results demonstrate the ability for future implementation of a motion-based wearable cough detector. [ABSTRACT FROM AUTHOR]

Objectives: Dental radiographs, particularly bitewing radiographs, are widely used in dental diagnosis and treatment Dental image segmentation is difficult for various reasons, such as intricate structures, low contrast, noise, roughness, and unclear borders, resulting in poor image quality. Recent developments in deep learning models have improved performance in analyzing dental images. In this research, our primary objective is to determine the most effective segmentation technique for bitewing radiographs based on different metrics: accuracy, training time, and the number of training parameters as a reflection of architectural cost. Methods: In this research, we employ several deep learning models, namely Resnet-18, Resnet-50, Xception, Inception Resnet v2, and Mobilenetv2, to segment bitewing radiographs. The process begins by importing the radiographs into MATLAB®(MathWorks Inc), where the images are first improved, then segmented using the graph cut method based on regions to produce a binary mask that distinguishes the background from the original X-ray. Results: The deep learning models were trained on 298 and 99 radiograph training and validation sets and were evaluated using 99 images from the testing set. We also compare the segmentation model using several criteria, including accuracy, speed, and size, to determine which network is superior. Furthermore, we compare our findings with prior research to provide a comprehensive understanding of the advancements made in dental image segmentation. The accurate segmentation achieved was 93.67% and 94.42% by the Resnet-18 and Resnet-50 models, respectively. Conclusion: This research advances dental image analysis and facilitates more accurate diagnoses and treatment planning by determining the best segmentation technique. The outcomes of this study can guide researchers and practitioners in selecting appropriate segmentation methods for practical dental image analysis. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) has been integrated into dentistry for improvement of current dental practice. While many studies have explored the utilization of AI in various fields, the potential of AI in dentistry, particularly in low-middle income countries (LMICs) remains understudied. This scoping review aimed to study the existing literature on the applications of artificial intelligence in dentistry in low-middle income countries. A comprehensive search strategy was applied utilizing three major databases: PubMed, Scopus, and EBSCO Dentistry & Oral Sciences Source. The search strategy included keywords related to AI, Dentistry, and LMICs. The initial search yielded a total of 1587, out of which 25 articles were included in this review. Our findings demonstrated that limited studies have been carried out in LMICs in terms of AI and dentistry. Most of the studies were related to Orthodontics. In addition gaps in literature were noted such as cost utility and patient experience were not mentioned in the included studies. [ABSTRACT FROM AUTHOR]

Preterm birth (PTB) is the leading cause of infant mortality globally. Research has focused on developing predictive models for PTB without prioritizing cost-effective interventions. Physical activity and sleep present unique opportunities for interventions in low- and middle-income populations (LMICs). However, objective measurement of physical activity and sleep remains challenging and self-reported metrics suffer from low-resolution and accuracy. In this study, we use physical activity data collected using a wearable device comprising over 181,944 h of data across N = 1083 patients. Using a new state-of-the art deep learning time-series classification architecture, we develop a 'clock' of healthy dynamics during pregnancy by using gestational age (GA) as a surrogate for progression of pregnancy. We also develop novel interpretability algorithms that integrate unsupervised clustering, model error analysis, feature attribution, and automated actigraphy analysis, allowing for model interpretation with respect to sleep, activity, and clinical variables. Our model performs significantly better than 7 other machine learning and AI methods for modeling the progression of pregnancy. We found that deviations from a normal 'clock' of physical activity and sleep changes during pregnancy are strongly associated with pregnancy outcomes. When our model underestimates GA, there are 0.52 fewer preterm births than expected (P = 1.01e − 67, permutation test) and when our model overestimates GA, there are 1.44 times (P = 2.82e − 39, permutation test) more preterm births than expected. Model error is negatively correlated with interdaily stability (P = 0.043, Spearman's), indicating that our model assigns a more advanced GA when an individual's daily rhythms are less precise. Supporting this, our model attributes higher importance to sleep periods in predicting higher-than-actual GA, relative to lower-than-actual GA (P = 1.01e − 21, Mann-Whitney U). Combining prediction and interpretability allows us to signal when activity behaviors alter the likelihood of preterm birth and advocates for the development of clinical decision support through passive monitoring and exercise habit and sleep recommendations, which can be easily implemented in LMICs. [ABSTRACT FROM AUTHOR]

The purpose of this study is to explore how machine learning technologies can improve healthcare operations management. A machine learning-based model to solve a specific medical problem is developed to achieve this research purpose. Specifically, this study presents an AI solution for malaria infection diagnosis by applying the CNN (convolutional neural network) algorithm. Based on malaria microscopy image data from the NIH National Library of Medicine, a total of 24,958 images were used for deep learning training, and 2600 images were selected for final testing of the proposed diagnostic architecture. The empirical results indicate that the CNN diagnostic model correctly classified most malaria-infected and non-infected cases with minimal misclassification, with performance metrics of precision (0.97), recall (0.99), and f1-score (0.98) for uninfected cells, and precision (0.99), recall (0.97), and f1-score (0.98) for parasite cells. The CNN diagnostic solution rapidly processed a large number of cases with a high reliable accuracy of 97.81%. The performance of this CNN model was further validated through the k-fold cross-validation test. These results suggest the advantage of machine learning-based diagnostic methods over conventional manual diagnostic methods in improving healthcare operational capabilities in terms of diagnostic quality, processing costs, lead time, and productivity. In addition, a machine learning diagnosis system is more likely to enhance the financial profitability of healthcare operations by reducing the risk of unnecessary medical disputes related to diagnostic errors. As an extension for future research, propositions with a research framework are presented to examine the impacts of machine learning on healthcare operations management for safety and quality of life in global communities. [ABSTRACT FROM AUTHOR]

Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer affects millions of women worldwide. We aim to provide radiologists with automatic support for mammography review. We propose deploying deep learning models with Multiple Instance Learning algorithms for breast cancer diagnosis (cancer versus non-cancer classification) based on digital mammography images, taking advantage of data annotated at an image level without indicating where the lesion is. We employed algorithms to analyse original, high-resolution images with minimal reduction in size. We used graphical suggestions of attentional maps to verify the correctness of the algorithm and to indicate the areas of the images where cancer lesions are. Finally, we performed comparative and validation studies on external datasets differing in the number of images, pixel intensity levels, and subtypes of existing lesions, showing high accuracy and potential for generalisability of the algorithms. Breast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private dataset with 1174 non-cancer and 794 cancer images labelled at the image level with pathological ground truth confirmation. We used feature extractors (ResNet-18, ResNet-34, ResNet-50 and EfficientNet-B0) pre-trained on ImageNet. The best results were achieved with multimodal-view classification using both CC and MLO images simultaneously, resized by half, with a patch size of 224 px and an overlap of 0.25. It resulted in AUC-ROC = 0.896 ± 0.017, F1-score 81.8 ± 3.2, accuracy 81.6 ± 3.2, precision 82.4 ± 3.3, and recall 81.6 ± 3.2. Evaluation with the Chinese Mammography Database, with 5-fold cross-validation, patient-wise breakdowns, and transfer learning, resulted in AUC-ROC 0.848 ± 0.015, F1-score 78.6 ± 2.0, accuracy 78.4 ± 1.9, precision 78.8 ± 2.0, and recall 78.4 ± 1.9. The CLAM algorithm's attentional maps indicate the features most relevant to the algorithm in the images. Our approach was more effective than in many other studies, allowing for some explainability and identifying erroneous predictions based on the wrong premises. [ABSTRACT FROM AUTHOR]

Aim: We aim to predict metastasis in breast cancer patients with tree-based conventional machine learning algorithms and to observe which feature selection methods is more effective in machine learning methods related to microarray breast cancer data reducing the number of features. Material and Methods: Feature selection methods, least squares absolute shrinkage (LASSO), Boruta and maximum relevanceminimum redundancy (MRMR) and statistical preprocessing steps were first applied before the tree-based learning conventional machine learning methods like Decision-tree, Extremely randomized trees and Gradient Boosting Tree applied on the microarray breast cancer data. Results: Microarray data with 54675 features (202 (101/101 breast cancer patients with/without metastases)) was first reduced to 235 features, then the feature selection algorithms were applied and the most important features were found with tree-based machine learning algorithms. It was observed that the highest recall and F-measure values were obtained from the XGBoost method and the highest precision value was received from the Extra-tree method. The 10 arrays out of 54675 with the highest variable importance were listed. Conclusion: The most accurate results were obtained from the statistical preprocessed data for the XGBoost and Extra-trees machine learning algorithms. Statistical and microarray preprocessing steps would be enough in machine learning analysis of microarray data in breast cancer metastases predictions. [ABSTRACT FROM AUTHOR]

For the last 40 years, actigraphy or wearable accelerometry has provided an objective, low-burden and ecologically valid approach to assess real-world sleep and circadian patterns, contributing valuable data to epidemiological and clinical insights on sleep and sleep disorders. The proper use of wearable technology in sleep research requires validated algorithms that can derive sleep outcomes from the sensor data. Since the publication of the first automated scoring algorithm by Webster in 1982, a variety of sleep algorithms have been developed and contributed to sleep research, including many recent ones that leverage machine learning and / or deep learning approaches. However, it remains unclear how these algorithms compare to each other on the same data set and if these modern data science approaches improve the analytical validity of sleep outcomes based on wrist-worn acceleration data. This work provides a systematic evaluation across 8 state-of-the-art sleep algorithms on a common sleep data set with polysomnography (PSG) as ground truth. Despite the inclusion of recently published complex algorithms, simple regression-based and heuristic algorithms demonstrated slightly superior performance in sleep-wake classification and sleep outcome estimation. The performance of complex machine learning and deep learning models seem to suffer from poor generalization. This independent and systematic analytical validation of sleep algorithms provides key evidence on the use of wearable digital health technologies for sleep research and care. [ABSTRACT FROM AUTHOR]

Simple Summary: Tumor segmentation is a key step in oncologic imaging processing. We have recently developed a model to detect and segment neuroblastic tumors on MR images based on deep learning architecture nnU-Net. In this work, we performed an independent validation of the automatic segmentation tool with a large heterogeneous dataset. We reviewed the automatic segmentations and manually edited them when necessary. We were able to show that the automatic network was able to locate and segment the primary tumor on the T2 weighted images in the majority of cases, with an extremely high agreement between the automatic tool and the manually edited masks. The time needed for manual adjustment was very low. Objectives. To externally validate and assess the accuracy of a previously trained fully automatic nnU-Net CNN algorithm to identify and segment primary neuroblastoma tumors in MR images in a large children cohort. Methods. An international multicenter, multivendor imaging repository of patients with neuroblastic tumors was used to validate the performance of a trained Machine Learning (ML) tool to identify and delineate primary neuroblastoma tumors. The dataset was heterogeneous and completely independent from the one used to train and tune the model, consisting of 300 children with neuroblastic tumors having 535 MR T2-weighted sequences (486 sequences at diagnosis and 49 after finalization of the first phase of chemotherapy). The automatic segmentation algorithm was based on a nnU-Net architecture developed within the PRIMAGE project. For comparison, the segmentation masks were manually edited by an expert radiologist, and the time for the manual editing was recorded. Different overlaps and spatial metrics were calculated to compare both masks. Results. The median Dice Similarity Coefficient (DSC) was high 0.997; 0.944–1.000 (median; Q1–Q3). In 18 MR sequences (6%), the net was not able neither to identify nor segment the tumor. No differences were found regarding the MR magnetic field, type of T2 sequence, or tumor location. No significant differences in the performance of the net were found in patients with an MR performed after chemotherapy. The time for visual inspection of the generated masks was 7.9 ± 7.5 (mean ± Standard Deviation (SD)) seconds. Those cases where manual editing was needed (136 masks) required 124 ± 120 s. Conclusions. The automatic CNN was able to locate and segment the primary tumor on the T2-weighted images in 94% of cases. There was an extremely high agreement between the automatic tool and the manually edited masks. This is the first study to validate an automatic segmentation model for neuroblastic tumor identification and segmentation with body MR images. The semi-automatic approach with minor manual editing of the deep learning segmentation increases the radiologist's confidence in the solution with a minor workload for the radiologist. [ABSTRACT FROM AUTHOR]

Background: A critical part in preoperative planning for revision arthroplasty surgery involves the identification of the failed implant. Using a predictive artificial neural network (ANN) model, the objectives of this study were: (1) to develop a machine-learning algorithm using operative big data to identify an implant from a radiograph; and (2) to compare algorithms that optimise accuracy in a timely fashion. Methods: Using 2116 postoperative anteroposterior (AP) hip radiographs of total hip arthroplasties from 2002 to 2019, 10 artificial neural networks were modeled and trained to classify the radiograph according to the femoral stem implanted. Stem brand and model was confirmed with 1594 operative reports. Model performance was determined by classification accuracy toward a random 706 AP hip radiographs, and again on a consecutive series of 324 radiographs prospectively collected over 2019. Results: The Dense-Net 201 architecture outperformed all others with 100.00% accuracy in training data, 95.15% accuracy on validation data, and 91.16% accuracy in the unique prospective series of patients. This outperformed all other models on the validation (p < 0.0001) and novel series (p < 0.0001). The convolutional neural network also displayed the probability (confidence) of the femoral stem classification for any input radiograph. This neural network averaged a runtime of 0.96 (SD 0.02) seconds for an iPhone 6 to calculate from a given radiograph when converted to an application. Conclusions: Neural networks offer a useful adjunct to the surgeon in preoperative identification of the prior implant. [ABSTRACT FROM AUTHOR]

Computer tomography is an extensively used method for the detection of the disease in the subjects. Basically, computer-aided tomography depending on the artificial intelligence reveals its significance in smart health care monitoring system. Owing to its security and the private issue, analyzing the computed tomography dataset has become a tedious process. This study puts forward the convolutional autoencrypted deep learning neural network to assist unsupervised learning technique. By carrying out various experiments, our proposed method produces better results comparative to other traditional methods, which efficaciously solves the issues related to the artificial image description. Hence, the convolutional autoencoder is widely used in measuring the lumps in the bronchi. With the unsupervised machine learning, the extracted features are used for various applications. [ABSTRACT FROM AUTHOR]

A correct protocol assignment is critical to high-quality imaging examinations, and its automation can be amenable to natural language processing (NLP). Assigning protocols for abdominal imaging CT scans is particularly challenging given the multiple organ specific indications and parameters. We compared conventional machine learning, deep learning, and automated machine learning builder workflows for this multiclass text classification task. A total of 94,501 CT studies performed over 4 years and their assigned protocols were obtained. Text data associated with each study including the ordering provider generated free text study indication and ICD codes were used for NLP analysis and protocol class prediction. The data was classified into one of 11 abdominal CT protocol classes before and after augmentations used to account for imbalances in the class sample sizes. Four machine learning (ML) algorithms, one deep learning algorithm, and an automated machine learning (AutoML) builder were used for the multilabel classification task: Random Forest (RF), Tree Ensemble (TE), Gradient Boosted Tree (GBT), multi-layer perceptron (MLP), Universal Language Model Fine-tuning (ULMFiT), and Google's AutoML builder (Alphabet, Inc., Mountain View, CA), respectively. On the unbalanced dataset, the manually coded algorithms all performed similarly with F1 scores of 0.811 for RF, 0.813 for TE, 0.813 for GBT, 0.828 for MLP, and 0.847 for ULMFiT. The AutoML builder performed better with a F1 score of 0.854. On the balanced dataset, the tree ensemble machine learning algorithm performed the best with an F1 score of 0.803 and a Cohen's kappa of 0.612. AutoML methods took a longer time for completion of NLP model training and evaluation, 4 h and 45 min compared to an average of 51 min for manual methods. Machine learning and natural language processing can be used for the complex multiclass classification task of abdominal imaging CT scan protocol assignment. [ABSTRACT FROM AUTHOR]

Effective screening provides efficient and quick diagnoses of COVID-19 and could alleviate related problems in the health care system. A prediction model that combines multiple features to assess contamination risks was established in the hope of supporting healthcare workers worldwide in triaging patients, particularly in situations with limited health care resources. Furthermore, a lack of diagnosis kits and asymptomatic cases can lead to missed or delayed diagnoses, exposing visitors, medical staff, and patients to 2019-nCoV contamination. Non-clinical techniques including data mining, expert systems, machine learning, and other artificial intelligence technologies have a crucial role to play in containment and diagnosis in the COVID-19 outbreak. This study developed Enhanced Gravitational Search Optimization with a Hybrid Deep Learning Model (EGSO-HDLM) for COVID-19 diagnoses using epidemiology data. The major aim of designing the EGSO-HDLM model was the identification and classification of COVID-19 using epidemiology data. In order to examine the epidemiology data, the EGSO-HDLM model employed a hybrid convolutional neural network with a gated recurrent unit based fusion (HCNN-GRUF) model. In addition, the hyperparameter optimization of the HCNN-GRUF model was improved by the use of the EGSO algorithm, which was derived by including the concepts of cat map and the traditional GSO algorithm. The design of the EGSO algorithm helps in reducing the ergodic problem, avoiding premature convergence, and enhancing algorithm efficiency. To demonstrate the better performance of the EGSO-HDLM model, experimental validation on a benchmark dataset was performed. The simulation results ensured the enhanced performance of the EGSO-HDLM model over recent approaches. [ABSTRACT FROM AUTHOR]

Project success is critical in the crowdfunding domain. Rather than the existing project‐centric prediction methods, we propose a novel backer‐centric prediction method. We identify each backer's preferences based on their pledge history and calculate the cosine similarity between backer's preferences and the project as each backer's persuasibility. Finally, we aggregate all the backers' persuasibility to predict project success. To validate our method, we crawled data on 183,886 projects launched during or before December 2014 on Kickstarter, a crowdfunding website. We selected 4,922 backers with a total of 442,793 pledges to identify backers' preferences. The results show that a backer is more likely to be persuaded by a project that is more similar to the backer's preferences. Our findings not only demonstrate the efficacy of backers' pledge history for predicting crowdfunding project success but also verify that a backer‐centric method can supplement the existing project‐centric approaches. Our model and findings enable crowdfunding platform agencies, fund‐seeking entrepreneurs, and investors to predict the success of a crowdfunding project. [ABSTRACT FROM AUTHOR]

The objective of the study was to determine if the pathology depicted on a mammogram is either benign or malignant (ductal or non-ductal carcinoma) using deep learning and artificial intelligence techniques. A total of 559 patients underwent breast ultrasound, mammography, and ultrasound-guided breast biopsy. Based on the histopathological results, the patients were divided into three categories: benign, ductal carcinomas, and non-ductal carcinomas. The mammograms in the cranio-caudal view underwent pre-processing and segmentation. Given the large variability of the areola, an algorithm was used to remove it and the adjacent skin. Therefore, patients with breast lesions close to the skin were removed. The remaining breast image was resized on the Y axis to a square image and then resized to 512 × 512 pixels. A variable square of 322,622 pixels was searched inside every image to identify the lesion. Each image was rotated with no information loss. For data augmentation, each image was rotated 360 times and a crop of 227 × 227 pixels was saved, resulting in a total of 201,240 images. The reason why our images were cropped at this size is because the deep learning algorithm transfer learning used from AlexNet network has an input image size of 227 × 227. The mean accuracy was 95.8344% ± 6.3720% and mean AUC 0.9910% ± 0.0366%, computed on 100 runs of the algorithm. Based on the results, the proposed solution can be used as a non-invasive and highly accurate computer-aided system based on deep learning that can classify breast lesions based on changes identified on mammograms in the cranio-caudal view. [ABSTRACT FROM AUTHOR]

This study aimed to develop a method for detection of femoral neck fracture (FNF) including displaced and non-displaced fractures using convolutional neural network (CNN) with plain X-ray and to validate its use across hospitals through internal and external validation sets. This is a retrospective study using hip and pelvic anteroposterior films for training and detecting femoral neck fracture through residual neural network (ResNet) 18 with convolutional block attention module (CBAM) + +. The study was performed at two tertiary hospitals between February and May 2020 and used data from January 2005 to December 2018. Our primary outcome was favorable performance for diagnosis of femoral neck fracture from negative studies in our dataset. We described the outcomes as area under the receiver operating characteristic curve (AUC), accuracy, Youden index, sensitivity, and specificity. A total of 4,189 images that contained 1,109 positive images (332 non-displaced and 777 displaced) and 3,080 negative images were collected from two hospitals. The test values after training with one hospital dataset were 0.999 AUC, 0.986 accuracy, 0.960 Youden index, and 0.966 sensitivity, and 0.993 specificity. Values of external validation with the other hospital dataset were 0.977, 0.971, 0.920, 0.939, and 0.982, respectively. Values of merged hospital datasets were 0.987, 0.983, 0.960, 0.973, and 0.987, respectively. A CNN algorithm for FNF detection in both displaced and non-displaced fractures using plain X-rays could be used in other hospitals to screen for FNF after training with images from the hospital of interest. [ABSTRACT FROM AUTHOR]