Artificial Intelligence In Medical Imaging Research Articles

Evaluating artificial intelligence for medical imaging: a primer for clinicians.

Artificial intelligence has the potential to transform medical imaging. The effective integration of artificial intelligence into clinical practice requires a robust understanding of its capabilities and limitations. This paper begins with an overview of key clinical use cases such as detection, classification, segmentation and radiomics. It highlights foundational concepts in machine learning such as learning types and strategies, as well as the training and evaluation process. We provide a broad theoretical framework for assessing the clinical effectiveness of medical imaging artificial intelligence, including appraising internal validity and generalisability of studies, and discuss barriers to clinical translation. Finally, we highlight future directions of travel within the field including multi-modal data integration, federated learning and explainability. By having an awareness of these issues, clinicians can make informed decisions about adopting artificial intelligence for medical imaging, improving patient care and clinical outcomes.

Artificial intelligence/machine learning for neuroimaging to predict hemorrhagic transformation: Systematic review/meta-analysis.

Early and reliable prediction of hemorrhagic transformation (HT) in patients with acute ischemic stroke (AIS) is crucial for treatment decisions and early intervention. The purpose of this study was to conduct a systematic review and meta-analysis on the performance of artificial intelligence (AI) and machine learning (ML) models that utilize neuroimaging to predict HT. A systematic search of PubMed, EMBASE, and Web of Science was conducted until February 19, 2024. Inclusion criteria were as follows: patients with AIS who received reperfusion therapy; AI/ML algorithm using imaging to predict HT; or presence of sufficient data on the predictive performance. Exclusion criteria were as follows: articles with less than 20 patients; articles lacking algorithms that operate solely on images; or articles not detailing the algorithm used. The quality of eligible studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 and Checklist for Artificial Intelligence in Medical Imaging. Pooled sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated using a random-effects model, and a summary receiver operating characteristic curve was constructed using the Reitsma method. We identified six eligible studies, which included 1640 patients. Aside from an unclear risk of bias regarding flow and timing identified in two of the studies, all studies showed low risk of bias and applicability concerns in all categories. Pooled sensitivity, specificity, and DOR were.849,.878, and 45.598, respectively. AI/ML models can reliably predict the occurrence of HT in AIS patients. More prospective studies are needed for subgroup analyses and higher clinical certainty and usefulness.

Application of Medical Image Artificial Intelligence in Medical Diagnosis and Treatment

Application of Medical Image Artificial Intelligence in Medical Diagnosis and Treatment

Deep learning in pulmonary nodule detection and segmentation: a systematic review.

The accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature. This study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information. After screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient. This study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research. Deep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility. Deep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

Deep learning in pulmonary nodule detection and segmentation: a systematic review.

The accurate detection and precise segmentation of lung nodules on computed tomography are key prerequisites for early diagnosis and appropriate treatment of lung cancer. This study was designed to compare detection and segmentation methods for pulmonary nodules using deep-learning techniques to fill methodological gaps and biases in the existing literature. This study utilized a systematic review with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, searching PubMed, Embase, Web of Science Core Collection, and the Cochrane Library databases up to May 10, 2023. The Quality Assessment of Diagnostic Accuracy Studies 2 criteria was used to assess the risk of bias and was adjusted with the Checklist for Artificial Intelligence in Medical Imaging. The study analyzed and extracted model performance, data sources, and task-focus information. After screening, we included nine studies meeting our inclusion criteria. These studies were published between 2019 and 2023 and predominantly used public datasets, with the Lung Image Database Consortium Image Collection and Image Database Resource Initiative and Lung Nodule Analysis 2016 being the most common. The studies focused on detection, segmentation, and other tasks, primarily utilizing Convolutional Neural Networks for model development. Performance evaluation covered multiple metrics, including sensitivity and the Dice coefficient. This study highlights the potential power of deep learning in lung nodule detection and segmentation. It underscores the importance of standardized data processing, code and data sharing, the value of external test datasets, and the need to balance model complexity and efficiency in future research. Deep learning demonstrates significant promise in autonomously detecting and segmenting pulmonary nodules. Future research should address methodological shortcomings and variability to enhance its clinical utility. Deep learning shows potential in the detection and segmentation of pulmonary nodules. There are methodological gaps and biases present in the existing literature. Factors such as external validation and transparency affect the clinical application.

Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects.

Although artificial intelligence (AI) methods hold promise for medical imaging-based prediction tasks, their integration into medical practice may present a double-edged sword due to bias (i.e., systematic errors). AI algorithms have the potential to mitigate cognitive biases in human interpretation, but extensive research has highlighted the tendency of AI systems to internalize biases within their model. This fact, whether intentional or not, may ultimately lead to unintentional consequences in the clinical setting, potentially compromising patient outcomes. This concern is particularly important in medical imaging, where AI has been more progressively and widely embraced than any other medical field. A comprehensive understanding of bias at each stage of the AI pipeline is therefore essential to contribute to developing AI solutions that are not only less biased but also widely applicable. This international collaborative review effort aims to increase awareness within the medical imaging community about the importance of proactively identifying and addressing AI bias to prevent its negative consequences from being realized later. The authors began with the fundamentals of bias by explaining its different definitions and delineating various potential sources. Strategies for detecting and identifying bias were then outlined, followed by a review of techniques for its avoidance and mitigation. Moreover, ethical dimensions, challenges encountered, and prospects were discussed.

Artificial Intelligence in Medical Imaging: Applications of Deep Learning for Disease Detection and Diagnosis

The integration of artificial intelligence (AI) and deep learning techniques into medical imaging has revolutionized disease detection and diagnosis. This paper provides a comprehensive overview of the applications of deep learning in medical imaging and its impact on healthcare. The paper begins with an introduction to the fundamentals of deep learning, emphasizing convolutional neural networks (CNNs) and their relevance in analyzing medical images. It then explores various applications of deep learning in medical imaging, including automated disease detection and classification, image segmentation for precise anatomical localization, quantitative analysis for predictive modeling, personalized medicine, and workflow optimization. Case studies and examples from different medical specialties, such as oncology, cardiology, and neurology, are presented to illustrate the practical implementation and effectiveness of AI-driven approaches.

Reconciling privacy and accuracy in AI for medical imaging

Artificial intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example, in medical imaging. Privacy-enhancing technologies, such as differential privacy (DP), aim to circumvent these susceptibilities. DP is the strongest possible protection for training models while bounding the risks of inferring the inclusion of training samples or reconstructing the original data. DP achieves this by setting a quantifiable privacy budget. Although a lower budget decreases the risk of information leakage, it typically also reduces the performance of such models. This imposes a trade-off between robust performance and stringent privacy. Additionally, the interpretation of a privacy budget remains abstract and challenging to contextualize. Here we contrast the performance of artificial intelligence models at various privacy budgets against both theoretical risk bounds and empirical success of reconstruction attacks. We show that using very large privacy budgets can render reconstruction attacks impossible, while drops in performance are negligible. We thus conclude that not using DP at all is negligent when applying artificial intelligence models to sensitive data. We deem our results to lay a foundation for further debates on striking a balance between privacy risks and model performance.

What makes a good scientific presentation on artificial intelligence in medical imaging?

PurposeAdequate communication of scientific findings is crucial to enhance knowledge transfer. This study aimed to determine the key features of a good scientific oral presentation on artificial intelligence (AI) in medical imaging. MethodsA total of 26 oral presentations dealing with original research on AI studies in medical imaging at the 2023 RSNA annual meeting were included and systematically assessed by three observers. The presentation quality of the research question, inclusion criteria, reference standard, method, results, clinical impact, presentation clarity, presenter engagement, and the presentation's quality of knowledge transfer were assessed using five-point Likert scales. The number of slides, the average number of words per slide, the number of interactive slides, the number of figures, and the number of tables were also determined for each presentation. Mixed-effects ordinal regression was used to assess the association between the above-mentioned variables and the quality of knowledge transfer of the presentation. ResultsA significant positive association was found between the quality of the presentation of the research question and the presentation's quality of knowledge transfer (odds ratio [OR]: 2.5, P = 0.005). The average number of words per slide was significantly negatively associated with the presentation's quality of knowledge transfer (OR: 0.9, P < 0.001). No other significant associations were found. ConclusionResearchers who orally present their scientific findings in the field of AI and medical imaging should pay attention to clearly communicating their research question and minimizing the number of words per slide to maximize the value of their presentation.

An analysis of the market prospects for artificial intelligence in medical imaging: Envisioning a future where intelligent technology revolutionizes the field of medical imaging

An analysis of the market prospects for artificial intelligence in medical imaging: Envisioning a future where intelligent technology revolutionizes the field of medical imaging

Navigating the ethical landscape of artificial intelligence in radiography: a cross-sectional study of radiographers’ perspectives

BackgroundThe integration of artificial intelligence (AI) in radiography presents transformative opportunities for diagnostic imaging and introduces complex ethical considerations. The aim of this cross-sectional study was to explore radiographers’ perspectives on the ethical implications of AI in their field and identify key concerns and potential strategies for addressing them.MethodsA structured questionnaire was distributed to a diverse group of radiographers in Saudi Arabia. The questionnaire included items on ethical concerns related to AI, the perceived impact on clinical practice, and suggestions for ethical AI integration in radiography. The data were analyzed using quantitative and qualitative methods to capture a broad range of perspectives.ResultsThree hundred eighty-eight radiographers responded and had varying levels of experience and specializations. Most (44.8%) participants were unfamiliar with the integration of AI into radiography. Approximately 32.9% of radiographers expressed uncertainty regarding the importance of transparency and explanatory capabilities in the AI systems used in radiology. Many (36.9%) participants indicated that they believed that AI systems used in radiology should be transparent and provide justifications for their decision-making procedures. A significant preponderance (44%) of respondents agreed that implementing AI in radiology may increase ethical dilemmas. However, 27.8%expressed uncertainty in recognizing and understanding the potential ethical issues that could arise from integrating AI in radiology. Of the respondents, 41.5% stated that the use of AI in radiology required establishing specific ethical guidelines. However, a significant percentage (28.9%) expressed the opposite opinion, arguing that utilizing AI in radiology does not require adherence to ethical standards. In contrast to the 46.6% of respondents voicing concerns about patient privacy over AI implementation, 41.5% of respondents did not have any such apprehensions.ConclusionsThis study revealed a complex ethical landscape in the integration of AI in radiography, characterized by enthusiasm and apprehension among professionals. It underscores the necessity for ethical frameworks, education, and policy development to guide the implementation of AI in radiography. These findings contribute to the ongoing discourse on AI in medical imaging and provide insights that can inform policymakers, educators, and practitioners in navigating the ethical challenges of AI adoption in healthcare.

Improving Tuberculosis Diagnosis using Explainable Artificial Intelligence in Medical Imaging

The integration of artificial intelligence (AI) applications in the healthcare sector is ushering in a significant transformation, particularly in developing more effective strategies for early diagnosis and treatment of contagious diseases like tuberculosis. Tuberculosis, a global public health challenge, demands swift interventions to prevent its spread. While deep learning and image processing techniques show potential in extracting meaningful insights from complex radiological images, their accuracy is often scrutinized due to a lack of explainability. This research navigates the intersection of AI and tuberculosis diagnosis by focusing on explainable artificial intelligence (XAI). A meticulously designed deep learning model for tuberculosis detection is introduced alongside an exploration of XAI to unravel complex decisions. The core belief is that XAI, by elucidating diagnostic decision rationale, enhances the reliability of AI in clinical settings. Emphasizing the pivotal role of XAI in tuberculosis diagnosis, this study aims to impact future research and practical implementations, fostering the adoption of AI-driven disease diagnosis methodologies for global health improvement.

Invited Commentary: The Double-edged Sword of Bias in Medical Imaging Artificial Intelligence.

Invited Commentary: The Double-edged Sword of Bias in Medical Imaging Artificial Intelligence.

Can Artificial Intelligence Accurately Detect Urinary Stones? A Systematic Review.

Objectives: To perform a systematic review on artificial intelligence (AI) performances to detect urinary stones. Methods: A PROSPERO-registered (CRD473152) systematic search of Scopus, Web of Science, Embase, and PubMed databases was performed to identify original research articles pertaining to AI stone detection or measurement, using search terms ("automatic" OR "machine learning" OR "convolutional neural network" OR "artificial intelligence" OR "detection" AND "stone volume"). Risk-of-bias (RoB) assessment was performed according to the Cochrane RoB tool, the Joanna Briggs Institute Checklist for nonrandomized studies, and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Results: Twelve studies were selected for the final review, including three multicenter and nine single-center retrospective studies. Eleven studies completed at least 50% of the CLAIM checkpoints and only one presented a high RoB. All included studies aimed to detect kidney (5/12, 42%), ureter (2/12, 16%), or urinary (5/12, 42%) stones on noncontrast computed tomography (NCCT), but 42% intended to automate measurement. Stone distinction from vascular calcification interested two studies. All studies used AI machine learning network training and internal validation, but a single one provided an external validation. Trained networks achieved stone detection, with sensitivity, specificity, and accuracy rates ranging from 58.7% to 100%, 68.5% to 100%, and 63% to 99.95%, respectively. Detection Dice score ranged from 83% to 97%. A high correlation between manual and automated stone volume (r = 0.95) was noted. Differentiate distal ureteral stones and phleboliths seemed feasible. Conclusions: AI processes can achieve automated urinary stone detection from NCCT. Further studies should provide urinary stone detection coupled with phlebolith distinction and an external validation, and include anatomical abnormalities and urologic foreign bodies (ureteral stent and nephrostomy tubes) cases.

Advancements in Fundus Image Analysis: A Comprehensive Method of AI-Based Classification and Segmentation Technique

Medical imaging is a vital tool in the existing healthcare system for precise analysis and treatment of various medical conditions. The use of artificial intelligence particularly machine learning and deep learning approaches has changed the interpretation of medical images and resulted in substantial advances in the area. With the increasing occurrence of eye diseases and the imperative need for early diagnosis, artificial intelligence presents potential solutions for the automatic, precise, and early detection of various eye problems. New advances in machine learning and deep learning allow different ocular disorders to be automatically analyzed, classified, and segmented which leads to early and precise diagnosis. This study attempts to give a comprehensive overview of the rapidly evolving field by reviewing the most recent approaches, challenges, and possible uses of artificial intelligence in medical imaging for ocular illnesses with a focus on segmentation and classification. The research also presents advanced methodologies such as transfer learning with MobileNet and UNet for automating the diagnosis of various ocular problems using classification and segmentation. The study highlights the importance of early and accurate diagnoses for better patient outcomes.

Evaluating Biases and Quality Issues in Intermodality Image Translation Studies for Neuroradiology: A Systematic Review.

Intermodality image-to-image translation is an artificial intelligence technique for generating one technique from another. This review was designed to systematically identify and quantify biases and quality issues preventing validation and clinical application of artificial intelligence models for intermodality image-to-image translation of brain imaging. PubMed, Scopus, and IEEE Xplore were searched through August 2, 2023, for artificial intelligence-based image translation models of radiologic brain images. This review collected 102 works published between April 2017 and August 2023. Eligible studies were evaluated for quality using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and for bias using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). Medically-focused article adherence was compared with that of engineering-focused articles overall with the Mann-Whitney U test and for each criterion using the Fisher exact test. Median adherence to the relevant CLAIM criteria was 69% and 38% for PROBAST questions. CLAIM adherence was lower for engineering-focused articles compared with medically-focused articles (65% versus 73%, P < .001). Engineering-focused studies had higher adherence for model description criteria, and medically-focused studies had higher adherence for data set and evaluation descriptions. Our review is limited by the study design and model heterogeneity. Nearly all studies revealed critical issues preventing clinical application, with engineering-focused studies showing higher adherence for the technical model description but significantly lower overall adherence than medically-focused studies. The pursuit of clinical application requires collaboration from both fields to improve reporting.

Transparent medical image AI via an image-text foundation model grounded in medical literature.

Building trustworthy and transparent image-based medical artificial intelligence (AI) systems requires the ability to interrogate data and models at all stages of the development pipeline, from training models to post-deployment monitoring. Ideally, the data and associated AI systems could be described using terms already familiar to physicians, but this requires medical datasets densely annotated with semantically meaningful concepts. In the present study, we present a foundation model approach, named MONET (medical concept retriever), which learns how to connect medical images with text and densely scores images on concept presence to enable important tasks in medical AI development and deployment such as data auditing, model auditing and model interpretation. Dermatology provides a demanding use case for the versatility of MONET, due to the heterogeneity in diseases, skin tones and imaging modalities. We trained MONET based on 105,550 dermatological images paired with natural language descriptions from a large collection of medical literature. MONET can accurately annotate concepts across dermatology images as verified by board-certified dermatologists, competitively with supervised models built on previously concept-annotated dermatology datasets of clinical images. We demonstrate how MONET enables AI transparency across the entire AI system development pipeline, from building inherently interpretable models to dataset and model auditing, including a case study dissecting the results of an AI clinical trial.

Remote sensing image information extraction based on Compensated Fuzzy Neural Network and big data analytics

Medical imaging AI systems and big data analytics have attracted much attention from researchers of industry and academia. The application of medical imaging AI systems and big data analytics play an important role in the technology of content based remote sensing (CBRS) development. Environmental data, information, and analysis have been produced promptly using remote sensing (RS). The method for creating a useful digital map from an image data set is called image information extraction. Image information extraction depends on target recognition (shape and color). For low-level image attributes like texture, Classifier-based Retrieval(CR) techniques are ineffective since they categorize the input images and only return images from the determined classes of RS. The issues mentioned earlier cannot be handled by the existing expertise based on a keyword/metadata remote sensing data service model. To get over these restrictions, Fuzzy Class Membership-based Image Extraction (FCMIE), a technology developed for Content-Based Remote Sensing (CBRS), is suggested. The compensation fuzzy neural network (CFNN) is used to calculate the category label and fuzzy category membership of the query image. Use a basic and balanced weighted distance metric. Feature information extraction (FIE) enhances remote sensing image processing and autonomous information retrieval of visual content based on time-frequency meaning, such as color, texture and shape attributes of images. Hierarchical nested structure and cyclic similarity measure produce faster queries when searching. The experiment’s findings indicate that applying the proposed model can have favorable outcomes for assessment measures, including Ratio of Coverage, average means precision, recall, and efficiency retrieval that are attained more effectively than the existing CR model. In the areas of feature tracking, climate forecasting, background noise reduction, and simulating nonlinear functional behaviors, CFNN has a wide range of RS applications. The proposed method CFNN-FCMIE achieves a minimum range of 4–5% for all three feature vectors, sample mean and comparison precision-recall ratio, which gives better results than the existing classifier-based retrieval model. This work provides an important reference for medical imaging artificial intelligence system and big data analysis.

Diagnostic Accuracy of Artificial Intelligence-Based Algorithms in Automated Detection of Neck of Femur Fracture on a Plain Radiograph: A Systematic Review and Meta-analysis.

To evaluate the diagnostic accuracy of artificial intelligence-based algorithms in identifying neck of femur fracture on a plain radiograph. Systematic review and meta-analysis. PubMed, Web of science, Scopus, IEEE, and the Science direct databases were searched from inception to 30 July 2023. Eligible article types were descriptive, analytical, or trial studies published in the English language providing data on the utility of artificial intelligence (AI) based algorithms in the detection of the neck of the femur (NOF) fracture on plain X-ray. The prespecified primary outcome was to calculate the sensitivity, specificity, accuracy, Youden index, and positive and negative likelihood ratios. Two teams of reviewers (each consisting of two members) extracted the data from available information in each study. The risk of bias was assessed using a mix of the CLAIM (the Checklist for AI in Medical Imaging) and QUADAS-2 (A Revised Tool for the Quality Assessment of Diagnostic Accuracy Studies) criteria. Of the 437 articles retrieved, five were eligible for inclusion, and the pooled sensitivity of AIs in diagnosing the fracture NOF was 85%, with a specificity of 87%. For all studies, the pooled Youden index (YI) was 0.73. The average positive likelihood ratio (PLR) was 19.88, whereas the negative likelihood ratio (NLR) was 0.17. The random effects model showed an overall odds of 1.16 (0.84-1.61) in the forest plot, comparing the AI system with those of human diagnosis. The overall heterogeneity of the studies was marginal (I2 = 51%). The CLAIM criteria for risk of bias assessment had an overall >70% score. Artificial intelligence (AI)-based algorithms can be used as a diagnostic adjunct, benefiting clinicians by taking less time and effort in neck of the femur (NOF) fracture diagnosis. PROSPERO CRD42022375449. The online version contains supplementary material available at 10.1007/s43465-024-01130-6.

CHD-CXR: a de-identified publicly available dataset of chest x-ray for congenital heart disease.

Congenital heart disease is a prevalent birth defect, accounting for approximately one-third of major birth defects. The challenge lies in early detection, especially in underdeveloped medical regions where a shortage of specialized physicians often leads to oversight. While standardized chest x-rays can assist in diagnosis and treatment, their effectiveness is limited by subtle cardiac manifestations. However, the emergence of deep learning in computer vision has paved the way for detecting subtle changes in chest x-rays, such as lung vessel density, enabling the detection of congenital heart disease in children. This highlights the need for further investigation. The lack of expert-annotated, high-quality medical image datasets hinders the progress of medical image artificial intelligence. In response, we have released a dataset containing 828 DICOM chest x-ray files from children with diagnosed congenital heart disease, alongside corresponding cardiac ultrasound reports. This dataset emphasizes complex structural characteristics, facilitating the transition from machine learning to machine teaching in deep learning. To ascertain the dataset's applicability, we trained a preliminary model and achieved an area under the receiver operating characteristic curve (ROC 0.85). We provide detailed introductions and publicly available datasets at: https://www.kaggle.com/competitions/congenital-heart-disease.