Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine

The Evolving Role of Artificial Intelligence in Radiotherapy Treatment Planning-A Literature Review

This paper examines the integration of artificial intelligence (AI) in radiotherapy for cancer treatment. The importance of radiotherapy in cancer management and its time-intensive planning process make AI adoption appealing especially with the escalating demand for radiotherapy. This review highlights the efficacy of AI across medical domains, where it surpasses human capabilities in areas such as cardiology and dermatology. Focusing on radiotherapy, the paper details AI's applications in target segmentation, dose optimization, and outcome prediction. It discusses adaptive radiotherapy's benefits and AI's potential to enhance patient outcomes with much improved treatment accuracy. The paper explores ethical concerns, including data privacy and bias, stressing the need for robust guidelines. Educating healthcare professionals and patients about AI's role is crucial as it acknowledges potential job-role changes and concerns about patients' trust in the use of AI. Overall, the integration of AI in radiotherapy holds transformative potential in streamlining processes, improving outcomes, and reducing costs. AI's potential to reduce healthcare costs underscores its significance with impactful change globally. However, successful implementation hinges on addressing ethical and logistical challenges and fostering collaboration among healthcare professionals and patient population data sets for its optimal utilization. Rigorous education, collaborative efforts, and global data sharing will be the compass guiding its' success in radiotherapy and healthcare.

The knowledge and perception of patients in Malta towards artificial intelligence in medical imaging

INTRODUCTION

Artificial intelligence (AI) is becoming increasingly implemented in radiology, especially in image reporting. Patients' perceptions about AI integration in medical imaging is a relatively unexplored area that has received limited investigation in the literature. This study aimed to determine current knowledge and perceptions of patients in Malta towards AI application in medical imaging.

METHODS

A cross-sectional study using a self-designed paper-based questionnaire, partly adapted with permission from two previous studies, was distributed in English or Maltese language amongst eligible outpatients attending medical imaging examinations across public hospitals in Malta and Gozo in March 2023.

RESULTS

280 questionnaires were analysed, resulting in a 5.83 % confidence interval. 42.1 % of patients indicated basic AI knowledge, while 36.4 % reported minimal to no knowledge. Responses indicated favourable opinions towards the collaborative integration of humans and AI to improve healthcare. However, participants expressed preference for doctors to retain final-decision making when AI is used. For some statements, a statistically significant association was observed between patients' perception of AI-based technology and their gender, age, and educational background. Essentially, 92.1 % expressed the importance of being informed whenever AI is to be utilised in their care.

DISCUSSION

As key stakeholders, patients should be actively involved when AI technology is used. Informing patients about the use of AI in medical imaging is important to cultivate trust, address ethical concerns, and help ensure that AI integration in healthcare systems aligns with patients' values and needs.

CONCLUSION

This study highlights the need to enhance AI literacy amongst patients, possibly though awareness campaigns or educational programmes. Additionally, clear policies relating to the use of AI in medical imaging and how such AI use is communicated to patients are necessary.

Assessing the Emergence and Evolution of Artificial Intelligence and Machine Learning Research in Neuroradiology

BACKGROUND AND PURPOSE

Interest in artificial intelligence (AI) and machine learning (ML) has been growing in neuroradiology, but there is limited knowledge on how this interest has manifested into research and specifically, its qualities and characteristics. This study aims to characterize the emergence and evolution of AI/ML articles within neuroradiology and provide a comprehensive overview of the trends, challenges, and future directions of the field.

MATERIALS AND METHODS

We performed a bibliometric analysis of the American Journal of Neuroradiology; the journal was queried for original research articles published since inception (January 1, 1980) to December 3, 2022 that contained any of the following key terms: "machine learning," "artificial intelligence," "radiomics," "deep learning," "neural network," "generative adversarial network," "object detection," or "natural language processing." Articles were screened by 2 independent reviewers, and categorized into statistical modeling (type 1), AI/ML development (type 2), both representing developmental research work but without a direct clinical integration, or end-user application (type 3), which is the closest surrogate of potential AI/ML integration into day-to-day practice. To better understand the limiting factors to type 3 articles being published, we analyzed type 2 articles as they should represent the precursor work leading to type 3.

RESULTS

A total of 182 articles were identified with 79% being nonintegration focused (type 1 n = 53, type 2 n = 90) and 21% (n = 39) being type 3. The total number of articles published grew roughly 5-fold in the last 5 years, with the nonintegration focused articles mainly driving this growth. Additionally, a minority of type 2 articles addressed bias (22%) and explainability (16%). These articles were primarily led by radiologists (63%), with most (60%) having additional postgraduate degrees.

CONCLUSIONS

AI/ML publications have been rapidly increasing in neuroradiology with only a minority of this growth being attributable to end-user application. Areas identified for improvement include enhancing the quality of type 2 articles, namely external validation, and addressing both bias and explainability. These results ultimately provide authors, editors, clinicians, and policymakers important insights to promote a shift toward integrating practical AI/ML solutions in neuroradiology.

Trustworthy and ethical AI-enabled cardiovascular care: a rapid review

BACKGROUND

Artificial intelligence (AI) is increasingly used for prevention, diagnosis, monitoring, and treatment of cardiovascular diseases. Despite the potential for AI to improve care, ethical concerns and mistrust in AI-enabled healthcare exist among the public and medical community. Given the rapid and transformative recent growth of AI in cardiovascular care, to inform practice guidelines and regulatory policies that facilitate ethical and trustworthy use of AI in medicine, we conducted a literature review to identify key ethical and trust barriers and facilitators from patients' and healthcare providers' perspectives when using AI in cardiovascular care.

METHODS

In this rapid literature review, we searched six bibliographic databases to identify publications discussing transparency, trust, or ethical concerns (outcomes of interest) associated with AI-based medical devices (interventions of interest) in the context of cardiovascular care from patients', caregivers', or healthcare providers' perspectives. The search was completed on May 24, 2022 and was not limited by date or study design.

RESULTS

After reviewing 7,925 papers from six databases and 3,603 papers identified through citation chasing, 145 articles were included. Key ethical concerns included privacy, security, or confidentiality issues (n = 59, 40.7%); risk of healthcare inequity or disparity (n = 36, 24.8%); risk of patient harm (n = 24, 16.6%); accountability and responsibility concerns (n = 19, 13.1%); problematic informed consent and potential loss of patient autonomy (n = 17, 11.7%); and issues related to data ownership (n = 11, 7.6%). Major trust barriers included data privacy and security concerns, potential risk of patient harm, perceived lack of transparency about AI-enabled medical devices, concerns about AI replacing human aspects of care, concerns about prioritizing profits over patients' interests, and lack of robust evidence related to the accuracy and limitations of AI-based medical devices. Ethical and trust facilitators included ensuring data privacy and data validation, conducting clinical trials in diverse cohorts, providing appropriate training and resources to patients and healthcare providers and improving their engagement in different phases of AI implementation, and establishing further regulatory oversights.

CONCLUSION

This review revealed key ethical concerns and barriers and facilitators of trust in AI-enabled medical devices from patients' and healthcare providers' perspectives. Successful integration of AI into cardiovascular care necessitates implementation of mitigation strategies. These strategies should focus on enhanced regulatory oversight on the use of patient data and promoting transparency around the use of AI in patient care.

Artificial intelligence for ultrasonographic detection and diagnosis of hepatocellular carcinoma and cholangiocarcinoma

The effectiveness of ultrasonography (USG) in liver cancer screening is partly constrained by the operator's expertise. We aimed to develop and evaluate an AI-assisted system for detecting and classifying focal liver lesions (FLLs) from USG images. This retrospective study incorporated 26,288 USG images from 5444 patients to train YOLOv5 model for FLLs detection and classification of seven different types of FLLs, including hepatocellular carcinoma (HCC), cholangiocarcinoma (CCA), focal fatty infiltration, focal fatty sparing (FFS), cyst, hemangioma, and regenerative nodules. AI model performance was assessed for detection and diagnosis of the FLLs on a per-image and per-lesion basis. The AI achieved an overall FLLs detection rate of 84.8% (95%CI:83.3-86.4), with consistent performance for FLLs ≤ 1 cm and > 1 cm. It also exhibited sensitivity and specificity for distinguishing malignant FLLs from other benign FLLs at 97.0% (95%CI:95. 9-98.2) and 97.0% (95%CI:95.9-98.1), respectively. Among specific FLL types, CCA detection rate was at 92.2% (95%CI:88.0-96.4), followed by FFS at 89.7% (95%CI:87.1-92.3), and HCC at 82.3% (95%CI:77.1-87.5). The specificities and NPVs for regenerative nodules were 100% and 99.9% (95%CI:99.8-100.0), respectively. Our AI model can potentially assist physicians in FLLs detection and diagnosis during USG examinations. Further external validation is needed for clinical application.

Advancements in AI based healthcare techniques with FOCUS ON diagnostic techniques

Since the past decade, the interest towards more precise and efficient healthcare techniques with special emphasis on diagnostic techniques has increased. Artificial Intelligence has proved to be instrumental in development of various such techniques. The various types of AI like ML, NLP, RPA etc. are being used, which have streamlined and organised the Electronic Health Records (EHR) along with aiding the healthcare provider with decision making and sample and data analysis. This article also deals with the 3 major categories of diagnostic techniques - Imaging based, Pathology based and Preventive diagnostic techniques and what all changes and modifications were brought upon them, due to use of AI. Due to such a high demand, the investment in AI based healthcare techniques has increased substantially, with predicted market size of almost 188 billon USD by 2030. In India itself, AI in healthcare is expected to raise the GDP by 25 billion USD by 2028. But there are also several challenges associated with this like unavailability of quality data, black box issue etc. One of the major challenges is the ethical considerations and issues during use of medical records as it is a very sensitive document. Due to this, there is several trust issues associated with adoption of AI by many organizations. These challenges have also been discussed in this article. Need for further development in the AI based diagnostic techniques is also done in the article. Alongside, the production of such techniques and devices which are easy to use and simple to incorporate into the daily workflows have immense scope in the upcoming times. The increasing scope of Clinical Decision Support System, Telemedicine etc. make AI a promising field in the healthcare and diagnostics arena. Concluding the article, it can be said that despite the presence of various challenges to the implementation and usage, the future prospects for AI in healthcare is immense and work needs to be done in order to ensure the availability of resources for same so that high level of accuracy can be achieved and better health outcomes can be provided to patients. Ethical concerns need to be addressed for smooth implementation and to reduce the burden of the developers, which has been discussed in this narrative review article.

Artificial Intelligence-Enhanced Neurocritical Care for Traumatic Brain Injury : Past, Present and Future

In neurointensive care units (NICUs), particularly in cases involving traumatic brain injury (TBI), swift and accurate decision-making is critical because of rapidly changing patient conditions and the risk of secondary brain injury. The use of artificial intelligence (AI) in NICU can enhance clinical decision support and provide valuable assistance in these complex scenarios. This article aims to provide a comprehensive review of the current status and future prospects of AI utilization in the NICU, along with the challenges that must be overcome to realize this. Presently, the primary application of AI in NICU is outcome prediction through the analysis of preadmission and high-resolution data during admission. Recent applications include augmented neuromonitoring via signal quality control and real-time event prediction. In addition, AI can integrate data gathered from various measures and support minimally invasive neuromonitoring to increase patient safety. However, despite the recent surge in AI adoption within the NICU, the majority of AI applications have been limited to simple classification tasks, thus leaving the true potential of AI largely untapped. Emerging AI technologies, such as generalist medical AI and digital twins, harbor immense potential for enhancing advanced neurocritical care through broader AI applications. If challenges such as acquiring high-quality data and ethical issues are overcome, these new AI technologies can be clinically utilized in the actual NICU environment. Emphasizing the need for continuous research and development to maximize the potential of AI in the NICU, we anticipate that this will further enhance the efficiency and accuracy of TBI treatment within the NICU.

Patients' Attitudes Toward the Use of Artificial Intelligence as a Diagnostic Tool in Radiology in Saudi Arabia: Cross-Sectional Study

BACKGROUND

Artificial intelligence (AI) is widely used in various medical fields, including diagnostic radiology as a tool for greater efficiency, precision, and accuracy. The integration of AI as a radiological diagnostic tool has the potential to mitigate delays in diagnosis, which could, in turn, impact patients' prognosis and treatment outcomes. The literature shows conflicting results regarding patients' attitudes to AI as a diagnostic tool. To the best of our knowledge, no similar study has been conducted in Saudi Arabia.

OBJECTIVE

The objectives of this study are to examine patients' attitudes toward the use of AI as a tool in diagnostic radiology at King Khalid University Hospital, Saudi Arabia. Additionally, we sought to explore potential associations between patients' attitudes and various sociodemographic factors.

METHODS

This descriptive-analytical cross-sectional study was conducted in a tertiary care hospital. Data were collected from patients scheduled for radiological imaging through a validated self-administered questionnaire. The main outcome was to measure patients' attitudes to the use of AI in radiology by calculating mean scores of 5 factors, distrust and accountability (factor 1), procedural knowledge (factor 2), personal interaction and communication (factor 3), efficiency (factor 4), and methods of providing information to patients (factor 5). Data were analyzed using the student t test, one-way analysis of variance followed by post hoc and multivariable analysis.

RESULTS

A total of 382 participants (n=273, 71.5% women and n=109, 28.5% men) completed the surveys and were included in the analysis. The mean age of the respondents was 39.51 (SD 13.26) years. Participants favored physicians over AI for procedural knowledge, personal interaction, and being informed. However, the participants demonstrated a neutral attitude for distrust and accountability and for efficiency. Marital status was found to be associated with distrust and accountability, procedural knowledge, and personal interaction. Associations were also found between self-reported health status and being informed and between the field of specialization and distrust and accountability.

CONCLUSIONS

Patients were keen to understand the work of AI in radiology but favored personal interaction with a radiologist. Patients were impartial toward AI replacing radiologists and the efficiency of AI, which should be a consideration in future policy development and integration. Future research involving multicenter studies in different regions of Saudi Arabia is required.

Radiologists' perceptions on AI integration: An in-depth survey study

PURPOSE

To assess the perceptions and attitudes of radiologists toward the adoption of artificial intelligence (AI) in clinical practice.

METHODS

A survey was conducted among members of the SIRM Lombardy. Radiologists' attitudes were assessed comprehensively, covering satisfaction with AI-based tools, propensity for innovation, and optimism for the future. The questionnaire consisted of two sections: the first gathered demographic and professional information using categorical responses, while the second evaluated radiologists' attitudes toward AI through Likert-type responses ranging from 1 to 5 (with 1 representing extremely negative attitudes, 3 indicating a neutral stance, and 5 reflecting extremely positive attitudes). Questionnaire refinement involved an iterative process with expert panels and a pilot phase to enhance consistency and eliminate redundancy. Exploratory data analysis employed descriptive statistics and visual assessment of Likert plots, supported by non-parametric tests for subgroup comparisons for a thorough analysis of specific emerging patterns.

RESULTS

The survey yielded 232 valid responses. The findings reveal a generally optimistic outlook on AI adoption, especially among young radiologist (<30) and seasoned professionals (>60, p<0.01). However, while 36.2 % (84 out 232) of subjects reported daily use of AI-based tools, only a third considered their contribution decisive (30 %, 25 out of 84). AI literacy varied, with a notable proportion feeling inadequately informed (36 %, 84 out of 232), particularly among younger radiologists (46 %, p < 0.01). Positive attitudes towards the potential of AI to improve detection, characterization of anomalies and reduce workload (positive answers > 80 %) and were consistent across subgroups. Radiologists' opinions were more skeptical about the role of AI in enhancing decision-making processes, including the choice of further investigation, and in personalized medicine in general. Overall, respondents recognized AI's significant impact on the radiology profession, viewing it as an opportunity (61 %, 141 out of 232) rather than a threat (18 %, 42 out of 232), with a majority expressing belief in AI's relevance to future radiologists' career choices (60 %, 139 out of 232). However, there were some concerns, particularly among breast radiologists (20 of 232 responders), regarding the potential impact of AI on the profession. Eighty-four percent of the respondents consider the final assessment by the radiologist still to be essential.

CONCLUSION

Our results indicate an overall positive attitude towards the adoption of AI in radiology, though this is moderated by concerns regarding training and practical efficacy. Addressing AI literacy gaps, especially among younger radiologists, is essential. Furthermore, proactively adapting to technological advancements is crucial to fully leverage AI's potential benefits. Despite the generally positive outlook among radiologists, there remains significant work to be done to enhance the integration and widespread use of AI tools in clinical practice.

An Introductory Guide to Artificial Intelligence in Interventional Radiology: Part 2: Implementation Considerations and Harms

The introduction of artificial intelligence (AI) in interventional radiology (IR) will bring about new challenges and opportunities for patients and clinicians. AI may comprise software as a medical device or AI-integrated hardware and will require a rigorous evaluation that should be guided based on the level of risk of the implementation. A hierarchy of risk of harm and possible harms are described herein. A checklist to guide deployment of an AI in a clinical IR environment is provided. As AI continues to evolve, regulation and evaluation of the AI medical devices will need to continue to evolve to keep pace and ensure patient safety.

The Picasso's skepticism on computer science and the dawn of generative AI: questions after the answers to keep "machines-in-the-loop"

Starting from Picasso's quote ("Computers are useless. They can only give you answers"), we discuss the introduction of generative artificial intelligence (AI), including generative adversarial networks (GANs) and transformer-based architectures such as large language models (LLMs) in radiology, where their potential in reporting, image synthesis, and analysis is notable. However, the need for improvements, evaluations, and regulations prior to clinical use is also clear. Integration of LLMs into clinical workflow needs cautiousness, to avoid or at least mitigate risks associated with false diagnostic suggestions. We highlight challenges in synthetic image generation, inherent biases in AI models, and privacy concerns, stressing the importance of diverse training datasets and robust data privacy measures. We examine the regulatory landscape, including the 2023 Executive Order on AI in the United States and the 2024 AI Act in the European Union, which set standards for AI applications in healthcare. This manuscript contributes to the field by emphasizing the necessity of maintaining the human element in medical procedures while leveraging generative AI, advocating for a "machines-in-the-loop" approach.

Errors in Radiology: A Standard Review

Radiological interpretations, while essential, are not infallible and are best understood as expert opinions formed through the evaluation of available evidence. Acknowledging the inherent possibility of error is crucial, as it frames the discussion on improving diagnostic accuracy and patient care. A comprehensive review of error classifications highlights the complexity of diagnostic errors, drawing on recent frameworks to categorize them into perceptual and cognitive errors, among others. This classification underpins an analysis of specific error types, their prevalence, and implications for clinical practice. Additionally, we address the psychological impact of radiological practice, including the effects of mental health and burnout on diagnostic accuracy. The potential of artificial intelligence (AI) in mitigating errors is discussed, alongside ethical and regulatory considerations in its application. This research contributes to the body of knowledge on radiological errors, offering insights into preventive strategies and the integration of AI to enhance diagnostic practices. It underscores the importance of a nuanced understanding of errors in radiology, aiming to foster improvements in patient care and radiological accuracy.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis

BACKGROUND

Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality.

OBJECTIVE

This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data.

METHODS

In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips.

RESULTS

Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance.

CONCLUSIONS

Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

Technological Advances in SPECT and SPECT/CT Imaging

Single photon emission tomography/computed tomography (SPECT/CT) is a mature imaging technology with a dynamic role in the diagnosis and monitoring of a wide array of diseases. This paper reviews the technological advances, clinical impact, and future directions of SPECT and SPECT/CT imaging. The focus of this review is on signal amplifier devices, detector materials, camera head and collimator designs, image reconstruction techniques, and quantitative methods. Bulky photomultiplier tubes (PMTs) are being replaced by position-sensitive PMTs (PSPMTs), avalanche photodiodes (APDs), and silicon PMs to achieve higher detection efficiency and improved energy resolution and spatial resolution. Most recently, new SPECT cameras have been designed for cardiac imaging. The new design involves using specialised collimators in conjunction with conventional sodium iodide detectors (NaI(Tl)) or an L-shaped camera head, which utilises semiconductor detector materials such as CdZnTe (CZT: cadmium-zinc-telluride). The clinical benefits of the new design include shorter scanning times, improved image quality, enhanced patient comfort, reduced claustrophobic effects, and decreased overall size, particularly in specialised clinical centres. These noticeable improvements are also attributed to the implementation of resolution-recovery iterative reconstructions. Immense efforts have been made to establish SPECT and SPECT/CT imaging as quantitative tools by incorporating camera-specific modelling. Moreover, this review includes clinical examples in oncology, neurology, cardiology, musculoskeletal, and infection, demonstrating the impact of these advancements on clinical practice in radiology and molecular imaging departments.

Assessing Laterality Errors in Radiology: Comparing Generative Artificial Intelligence and Natural Language Processing

PURPOSE

We compared the performance of generative artificial intelligence (AI) (Augmented Transformer Assisted Radiology Intelligence [ATARI, Microsoft Nuance, Microsoft Corporation, Redmond, Washington]) and natural language processing (NLP) tools for identifying laterality errors in radiology reports and images.

METHODS

We used an NLP-based (mPower, Microsoft Nuance) tool to identify radiology reports flagged for laterality errors in its Quality Assurance Dashboard. The NLP model detects and highlights laterality mismatches in radiology reports. From an initial pool of 1,124 radiology reports flagged by the NLP for laterality errors, we selected and evaluated 898 reports that encompassed radiography, CT, MRI, and ultrasound modalities to ensure comprehensive coverage. A radiologist reviewed each radiology report to assess if the flagged laterality errors were present (reporting error-true-positive) or absent (NLP error-false-positive). Next, we applied ATARI to 237 radiology reports and images with consecutive NLP true-positive (118 reports) and false-positive (119 reports) laterality errors. We estimated accuracy of NLP and generative AI tools to identify overall and modality-wise laterality errors.

RESULTS

Among the 898 NLP-flagged laterality errors, 64% (574 of 898) had NLP errors and 36% (324 of 898) were reporting errors. The text query ATARI feature correctly identified the absence of laterality mismatch (NLP false-positives) with a 97.4% accuracy (115 of 118 reports; 95% confidence interval [CI] = 96.5%-98.3%). Combined vision and text query resulted in 98.3% accuracy (116 of 118 reports or images; 95% CI = 97.6%-99.0%), and query alone had a 98.3% accuracy (116 of 118 images; 95% CI = 97.6%-99.0%).

CONCLUSION

The generative AI-empowered ATARI prototype outperformed the assessed NLP tool for determining true and false laterality errors in radiology reports while enabling an image-based laterality determination. Underlying errors in ATARI text query in complex radiology reports emphasize the need for further improvement in the technology.

AATCT-IDS: A benchmark Abdominal Adipose Tissue CT Image Dataset for image denoising, semantic segmentation, and radiomics evaluation

BACKGROUND AND OBJECTIVE

The metabolic syndrome induced by obesity is closely associated with cardiovascular disease, and the prevalence is increasing globally, year by year. Obesity is a risk marker for detecting this disease. However, current research on computer-aided detection of adipose distribution is hampered by the lack of open-source large abdominal adipose datasets.

METHODS

In this study, a benchmark Abdominal Adipose Tissue CT Image Dataset (AATCT-IDS) containing 300 subjects is prepared and published. AATCT-IDS publics 13,732 raw CT slices, and the researchers individually annotate the subcutaneous and visceral adipose tissue regions of 3213 of those slices that have the same slice distance to validate denoising methods, train semantic segmentation models, and study radiomics. For different tasks, this paper compares and analyzes the performance of various methods on AATCT-IDS by combining the visualization results and evaluation data. Thus, verify the research potential of this data set in the above three types of tasks.

RESULTS

In the comparative study of image denoising, algorithms using a smoothing strategy suppress mixed noise at the expense of image details and obtain better evaluation data. Methods such as BM3D preserve the original image structure better, although the evaluation data are slightly lower. The results show significant differences among them. In the comparative study of semantic segmentation of abdominal adipose tissue, the segmentation results of adipose tissue by each model show different structural characteristics. Among them, BiSeNet obtains segmentation results only slightly inferior to U-Net with the shortest training time and effectively separates small and isolated adipose tissue. In addition, the radiomics study based on AATCT-IDS reveals three adipose distributions in the subject population.

CONCLUSION

AATCT-IDS contains the ground truth of adipose tissue regions in abdominal CT slices. This open-source dataset can attract researchers to explore the multi-dimensional characteristics of abdominal adipose tissue and thus help physicians and patients in clinical practice. AATCT-IDS is freely published for non-commercial purpose at: https://figshare.com/articles/dataset/AATTCT-IDS/23807256.

Academic radiology department subspeciality organization & fellowship offerings: A hodgepodge

INTRODUCTION

As opportunities for radiologists to subspecialize have increased, many avenues to organize Radiology department subspecialties exist. This study seeks to determine how academic U.S. Radiology departments structure themselves with respect to subspecialty divisions/sections, as there are no current standards for how Radiology departments are subdivided. Additionally, the extent of Radiology fellowships offered are assessed. The websites of academic U.S. Radiology departments, a highly influential source of information, were analyzed to perform this study.

MATERIALS & METHODS

Radiology department websites of all allopathic U.S. medical schools (n = 148) were assessed for the following: presence/absence of Radiology department subdivisions, division/section labels, number of divisions/sections, division/section titles, presence/absence of Radiology fellowships, number of fellowships, and fellowships titles.

RESULTS

114/148 (77 %) medical schools had Radiology department websites. According to their respective websites, 66/114 (58 %) academic Radiology departments had subspecialty divisions/sections, whereas 48/114 (42 %) had no divisions/sections listed. Of the departments that had divisions/sections, the median number of divisions/sections per department was nine, and ranged from two to 14. Fellowships were offered at 82/114 (72 %) academic Radiology departments that had websites, and the median number was six, ranging from one to 13.

CONCLUSION

There is marked heterogeneity of departmental organization across Radiology departments nationwide, likely due to the lack of current standards for how Radiology departments are subdivided into divisions/sections. Of the 77 % of medical schools that have Radiology department websites, only 58 % of departments listed divisions/sections, and 72 % posted fellowship offerings.

[Diagnosis of Rib Fracture Using Artificial Intelligence on Chest CT Images of Patients with Chest Trauma]

Purpose

To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma.

Materials and Methods

A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures.

Results

Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%).

Conclusion

The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

Knowledge, attitude, and perception of Arab medical students towards artificial intelligence in medicine and radiology: A multi-national cross-sectional study

OBJECTIVES

We aimed to assess undergraduate medical students' knowledge, attitude, and perception regarding artificial intelligence (AI) in medicine.

METHODS

A multi-national, multi-center cross-sectional study was conducted from March to April 2022, targeting undergraduate medical students in nine Arab countries. The study utilized a web-based questionnaire, with data collection carried out with the help of national leaders and local collaborators. Logistic regression analysis was performed to identify predictors of knowledge, attitude, and perception among the participants. Additionally, cluster analysis was employed to identify shared patterns within their responses.

RESULTS

Of the 4492 students surveyed, 92.4% had not received formal AI training. Regarding AI and deep learning (DL), 87.1% exhibited a low level of knowledge. Most students (84.9%) believed AI would revolutionize medicine and radiology, with 48.9% agreeing that it could reduce the need for radiologists. Students with high/moderate AI knowledge and training had higher odds of agreeing to endorse AI replacing radiologists, reducing their numbers, and being less likely to consider radiology as a career compared to those with low knowledge/no AI training. Additionally, the majority agreed that AI would aid in the automated detection and diagnosis of pathologies.

CONCLUSIONS

Arab medical students exhibit a notable deficit in their knowledge and training pertaining to AI. Despite this, they hold a positive perception of AI implementation in medicine and radiology, demonstrating a clear understanding of its significance for the healthcare system and medical curriculum.

CLINICAL RELEVANCE STATEMENT

This study highlights the need for widespread education and training in artificial intelligence for Arab medical students, indicating its significance for healthcare systems and medical curricula.

KEY POINTS

• Arab medical students demonstrate a significant knowledge and training gap when it comes to using AI in the fields of medicine and radiology. • Arab medical students recognize the importance of integrating AI into the medical curriculum. Students with a deeper understanding of AI were more likely to agree that all medical students should receive AI education. However, those with previous AI training were less supportive of this idea. • Students with moderate/high AI knowledge and training displayed increased odds of agreeing that AI has the potential to replace radiologists, reduce the demand for their services, and were less inclined to pursue a career in radiology, when compared to students with low knowledge/no AI training.

Oral Health Status and Treatment Needs Based on Artificial Intelligence (AI) Dental Panoramic Radiograph (DPR) Analysis: A Cross-Sectional Study

Background: The application of artificial intelligence (AI) is gaining popularity in modern dentistry. AI has been successfully used to interpret dental panoramic radiographs (DPRs) and quickly screen large groups of patients. This cross-sectional study aimed to perform a population-based assessment of the oral health status and treatment needs of the residents of Kielce, Poland, and the surrounding area based on DPR analysis performed by a high-accuracy AI algorithm trained with over 250,000 radiographs. Methods: This study included adults who had a panoramic radiograph performed, regardless of indications. The following diagnoses were used for analysis: (1) dental caries, (2) missing tooth, (3) dental filling, (4) root canal filling, (5) endodontic lesion, (6) implant, (7) implant abutment crown, (8) pontic crown, (9) dental abutment crown, and (10) sound tooth. The study sample included 980 subjects. Results: The patients had an average of 15 sound teeth, with the domination of the lower dental arch over the upper one. The most commonly identified pathology was dental caries, which affected 99% of participants. A total of 67% of patients underwent root canal treatment. Every fifth endodontically treated tooth presented a periapical lesion. Of study group members, 82% lost at least one tooth. Pontics were identified more often (9%) than implants (2%) in replacing missing teeth. Conclusions: DPR assessment by AI has proven to be an efficient method for population analysis. Despite recent improvements in the oral health status of Polish residents, its level is still unsatisfactory and suggests the need to improve oral health. However, due to some limitations of this study, the results should be interpreted with caution.

Familiarity, confidence and preference of artificial intelligence feedback and prompts by Australian breast cancer screening readers

Objectives This study explored the familiarity, perceptions and confidence of Australian radiology clinicians involved in reading screening mammograms, regarding artificial intelligence (AI) applications in breast cancer detection. Methods Sixty-five radiologists, breast physicians and radiology trainees participated in an online survey that consisted of 23 multiple choice questions asking about their experience and familiarity with AI products. Furthermore, the survey asked about their confidence in using AI outputs and their preference for AI modes applied in a breast screening context. Participants' responses to questions were compared using Pearson's χ 2 test. Bonferroni-adjusted significance tests were used for pairwise comparisons. Results Fifty-five percent of respondents had experience with AI in their workplaces, with automatic density measurement powered by machine learning being the most familiar AI product (69.4%). The top AI outputs with the highest ranks of perceived confidence were 'Displaying suspicious areas on mammograms with the percentage of cancer possibility' (67.8%) and 'Automatic mammogram classification (normal, benign, cancer, uncertain)' (64.6%). Radiology and breast physicians preferred using AI as second-reader mode (75.4% saying 'somewhat happy' to 'extremely happy') over triage (47.7%), pre-screening and first-reader modes (both with 26.2%) (P  < 0.001). Conclusion The majority of screen readers expressed increased confidence in utilising AI for highlighting suspicious areas on mammograms and for automatically classifying mammograms. They considered AI as an optimal second-reader mode being the most ideal use in a screening program. The findings provide valuable insights into the familiarities and expectations of radiologists and breast clinicians for the AI products that can enhance the effectiveness of the breast cancer screening programs, benefitting both healthcare professionals and patients alike.

Black box no more: A cross-sectional multi-disciplinary survey for exploring governance and guiding adoption of AI in medical imaging and radiotherapy in the UK

BACKGROUND

Medical Imaging and radiotherapy (MIRT) are at the forefront of artificial intelligence applications. The exponential increase of these applications has made governance frameworks necessary to uphold safe and effective clinical adoption. There is little information about how healthcare practitioners in MIRT in the UK use AI tools, their governance and associated challenges, opportunities and priorities for the future.

METHODS

This cross-sectional survey was open from November to December 2022 to MIRT professionals who had knowledge or made use of AI tools, as an attempt to map out current policy and practice and to identify future needs. The survey was electronically distributed to the participants. Statistical analysis included descriptive statistics and inferential statistics on the SPSS statistical software. Content analysis was employed for the open-ended questions.

RESULTS

Among the 245 responses, the following were emphasised as central to AI adoption: governance frameworks, practitioner training, leadership, and teamwork within the AI ecosystem. Prior training was strongly correlated with increased knowledge about AI tools and frameworks. However, knowledge of related frameworks remained low, with different professionals showing different affinity to certain frameworks related to their respective roles. Common challenges and opportunities of AI adoption were also highlighted, with recommendations for future practice.

Testing protocols and measurement techniques when using pressure sensors for sport and health applications: A comparative review

Plantar pressure measurement systems are routinely used in sports and health applications to assess locomotion. The purpose of this review is to describe and critically discuss: (a) applications of the pressure measurement systems in sport and healthcare, (b) testing protocols and considerations for clinical gait analysis, (c) clinical recommendations for interpreting plantar pressure data, (d) calibration procedures and their accuracy, and (e) the future of pressure sensor data analysis. Rigid pressure platforms are typically used to measure plantar pressures for the assessment of foot function during standing and walking, particularly when barefoot, and are the most accurate for measuring plantar pressures. For reliable data, two step protocol prior to contacting the pressure plate is recommended. In-shoe systems are most suitable for measuring plantar pressures in the field during daily living or dynamic sporting movements as they are often wireless and can measure multiple steps. They are the most suitable equipment to assess the effects of footwear and orthotics on plantar pressures. However, they typically have lower spatial resolution and sampling frequency than platform systems. Users of pressure measurement systems need to consider the suitability of the calibration procedures for their chosen application when selecting and using a pressure measurement system. For some applications, a bespoke calibration procedure is required to improve validity and reliability of the pressure measurement system. The testing machines that are commonly used for dynamic calibration of pressure measurement systems frequently have loading rates of less than even those found in walking, so the development of testing protocols that truly measure the loading rates found in many sporting movements are required. There is clear potential for AI techniques to assist in the analysis and interpretation of plantar pressure data to enable the more complete use of pressure system data in clinical diagnoses and monitoring.

Evaluation of deep learning-based reconstruction late gadolinium enhancement images for identifying patients with clinically unrecognized myocardial infarction

BACKGROUND

The presence of infarction in patients with unrecognized myocardial infarction (UMI) is a critical feature in predicting adverse cardiac events. This study aimed to compare the detection rate of UMI using conventional and deep learning reconstruction (DLR)-based late gadolinium enhancement (LGEO and LGEDL, respectively) and evaluate optimal quantification parameters to enhance diagnosis and management of suspected patients with UMI.

METHODS

This prospective study included 98 patients (68 men; mean age: 55.8 ± 8.1 years) with suspected UMI treated at our hospital from April 2022 to August 2023. LGEO and LGEDL images were obtained using conventional and commercially available inline DLR algorithms. The myocardial signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and percentage of enhanced area (Parea) employing the signal threshold versus reference mean (STRM) approach, which correlates the signal intensity (SI) within areas of interest with the average SI of normal regions, were analyzed. Analysis was performed using the standard deviation (SD) threshold approach (2SD-5SD) and full width at half maximum (FWHM) method. The diagnostic efficacies based on LGEDL and LGEO images were calculated.

RESULTS

The SNRDL and CNRDL were two times better than the SNRO and CNRO, respectively (P < 0.05). Parea-DL was elevated compared to Parea-O using the threshold methods (P < 0.05); however, no intergroup difference was found based on the FWHM method (P > 0.05). The Parea-DL and Parea-O also differed except between the 2SD and 3SD and the 4SD/5SD and FWHM methods (P < 0.05). The receiver operating characteristic curve analysis revealed that each SD method exhibited good diagnostic efficacy for detecting UMI, with the Parea-DL having the best diagnostic efficacy based on the 5SD method (P < 0.05). Overall, the LGEDL images had better image quality. Strong diagnostic efficacy for UMI identification was achieved when the STRM was ≥ 4SD and ≥ 3SD for the LGEDL and LGEO, respectively.

CONCLUSIONS

STRM selection for LGEDL magnetic resonance images helps improve clinical decision-making in patients with UMI. This study underscored the importance of STRM selection for analyzing LGEDL images to enhance diagnostic accuracy and clinical decision-making for patients with UMI, further providing better cardiovascular care.

A Theoretical Exploration of Artificial Intelligence's Impact on Feto-Maternal Health from Conception to Delivery

The implementation of Artificial Intelligence (AI) in healthcare is enhancing diagnostic accuracy in clinical setups. The use of AI in healthcare is steadily increasing with advancing technology, extending beyond disease diagnosis to encompass roles in feto-maternal health. AI harnesses Machine Learning (ML), Natural Language Processing (NLP), Artificial Neural Networks (ANN), and computer vision to analyze data and draw conclusions. Considering maternal health, ML analyzes vast datasets to predict maternal and fetal health outcomes, while NLP interprets medical texts and patient records to assist in diagnosis and treatment decisions. ANN models identify patterns in complex feto-maternal medical data, aiding in risk assessment and intervention planning whereas, computer vision enables the analysis of medical images for early detection of feto-maternal complications. AI facilitates early pregnancy detection, genetic screening, and continuous monitoring of maternal health parameters, providing real-time alerts for deviations, while also playing a crucial role in the early detection of fetal abnormalities through enhanced ultrasound imaging, contributing to informed decision-making. This review investigates into the application of AI, particularly through predictive models, in addressing the monitoring of feto-maternal health. Additionally, it examines potential future directions and challenges associated with these applications.

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

Objectives

To evaluate the diagnostic accuracy of artificial intelligence-based algorithms in identifying neck of femur fracture on a plain radiograph.

Design

Systematic review and meta-analysis.

Data sources

PubMed, Web of science, Scopus, IEEE, and the Science direct databases were searched from inception to 30 July 2023.

Eligibility criteria for study selection

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.

Main outcome measures

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.

Results

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.

Conclusion

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.

Study registration

PROSPERO CRD42022375449.

Supplementary Information

The online version contains supplementary material available at 10.1007/s43465-024-01130-6.

The diagnostic, therapeutic, and ethical impact of artificial intelligence in modern medicine

In the evolution of modern medicine, artificial intelligence (AI) has been proven to provide an integral aspect of revolutionizing clinical diagnosis, drug discovery, and patient care. With the potential to scrutinize colossal amounts of medical data, radiological and histological images, and genomic data in healthcare institutions, AI-powered systems can recognize, determine, and associate patterns and provide impactful insights that would be strenuous and challenging for clinicians to detect during their daily clinical practice. The outcome of AI-mediated search offers more accurate, personalized patient diagnoses, guides in research for new drug therapies, and provides a more effective multidisciplinary treatment plan that can be implemented for patients with chronic diseases. Among the many promising applications of AI in modern medicine, medical imaging stands out distinctly as an area with tremendous potential. AI-powered algorithms can now accurately and sensitively identify cancer cells and other lesions in medical images with greater accuracy and sensitivity. This allows for earlier diagnosis and treatment, which can significantly impact patient outcomes. This review provides a comprehensive insight into diagnostic, therapeutic, and ethical issues with the advent of AI in modern medicine.

From explanation to intervention: Interactive knowledge extraction from Convolutional Neural Networks used in radiology

Deep Learning models such as Convolutional Neural Networks (CNNs) are very effective at extracting complex image features from medical X-rays. However, the limited interpretability of CNNs has hampered their deployment in medical settings as they failed to gain trust among clinicians. In this work, we propose an interactive framework to allow clinicians to ask what-if questions and intervene in the decisions of a CNN, with the aim of increasing trust in the system. The framework translates a layer of a trained CNN into a measurable and compact set of symbolic rules. Expert interactions with visualizations of the rules promote the use of clinically-relevant CNN kernels and attach meaning to the rules. The definition and relevance of the kernels are supported by radiomics analyses and permutation evaluations, respectively. CNN kernels that do not have a clinically-meaningful interpretation are removed without affecting model performance. By allowing clinicians to evaluate the impact of adding or removing kernels from the rule set, our approach produces an interpretable refinement of the data-driven CNN in alignment with medical best practice.

Capturing artificial intelligence applications' value proposition in healthcare - a qualitative research study

Artificial intelligence (AI) applications pave the way for innovations in the healthcare (HC) industry. However, their adoption in HC organizations is still nascent as organizations often face a fragmented and incomplete picture of how they can capture the value of AI applications on a managerial level. To overcome adoption hurdles, HC organizations would benefit from understanding how they can capture AI applications' potential.We conduct a comprehensive systematic literature review and 11 semi-structured expert interviews to identify, systematize, and describe 15 business objectives that translate into six value propositions of AI applications in HC.Our results demonstrate that AI applications can have several business objectives converging into risk-reduced patient care, advanced patient care, self-management, process acceleration, resource optimization, and knowledge discovery.We contribute to the literature by extending research on value creation mechanisms of AI to the HC context and guiding HC organizations in evaluating their AI applications or those of the competition on a managerial level, to assess AI investment decisions, and to align their AI application portfolio towards an overarching strategy.

A machine learning approach to predicting vascular calcification risk of type 2 diabetes: A retrospective study

BACKGROUND

Recently, patients with type 2 diabetes mellitus (T2DM) have experienced a higher incidence and severer degree of vascular calcification (VC), which leads to an increase in the incidence and mortality of vascular complications in patients with T2DM.

HYPOTHESIS

To construct and validate prediction models for the risk of VC in patients with T2DM.

METHODS

Twenty-three baseline demographic and clinical characteristics were extracted from the electronic medical record system. Ten clinical features were screened with least absolute shrinkage and selection operator method and were used to develop prediction models based on eight machine learning (ML) algorithms (k-nearest neighbor [k-NN], light gradient boosting machine, logistic regression [LR], multilayer perception [(MLP], Naive Bayes [NB], random forest [RF], support vector machine [SVM], XGBoost [XGB]). Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, and precision.

RESULTS

A total of 1407 and 352 patients were retrospectively collected in the training and test sets, respectively. Among the eight models, the AUC value in the NB model was higher than the other models (NB: 0.753, LGB: 0.719, LR: 0.749, MLP: 0.715, RF: 0.722, SVM: 0.689, XGB:0.707, p < .05 for all). The k-NN model achieved the highest sensitivity of 0.75 (95% confidence interval [CI]: 0.633-0.857), the MLP model achieved the highest accuracy of 0.81 (95% CI: 0.767-0.852) and specificity of 0.875 (95% CI: 0.836-0.912).

CONCLUSIONS

This study developed a predictive model of VC based on ML and clinical features in type 2 diabetic patients. The NB model is a tool with potential to facilitate clinicians in identifying VC in high-risk patients.

Robot-assisted surgery and artificial intelligence-based tumour diagnostics: social preferences with a representative cross-sectional survey

BACKGROUND

The aim of this study was to assess social preferences for two different advanced digital health technologies and investigate the contextual dependency of the preferences.

METHODS

A cross-sectional online survey was performed among the general population of Hungary aged 40 years and over. Participants were asked to imagine that they needed a total hip replacement surgery and to indicate whether they would prefer a traditional or a robot-assisted (RA) hip surgery. To better understand preferences for the chosen method, the willingness to pay (WTP) method was used. The same assessment was conducted for preferences between a radiologist's and AI-based image analysis in establishing the radiological diagnosis of a suspected tumour. Respondents' electronic health literacy was assessed with the eHEALS questionnaire. Descriptive methods were used to assess sample characteristics and differences between subgroups. Associations were investigated with correlation analysis and multiple linear regressions.

RESULTS

Altogether, 1400 individuals (53.7% female) with a mean age of 58.3 (SD = 11.1) years filled in the survey. RA hip surgery was chosen by 762 (54.4%) respondents, but only 470 (33.6%) chose AI-based medical image evaluation. Those who opted for the digital technology had significantly higher educational levels and electronic health literacy (eHEALS). The majority of respondents were willing to pay to secure their preferred surgical (surgeon 67.2%, robot-assisted: 68.8%) and image assessment (radiologist: 70.9%; AI: 77.4%) methods, reporting similar average amounts in the first (p = 0.677), and a significantly higher average amount for radiologist vs. AI in the second task (p = 0.001). The regression showed a significant association between WTP and income, and in the hip surgery task, it also revealed an association with the type of intervention chosen.

CONCLUSIONS

Individuals with higher education levels seem to accept the advanced digital medical technologies more. However, the greater openness for RA surgery than for AI image assessment highlights that social preferences may depend considerably on the medical situation and the type of advanced digital technology. WTP results suggest rather firm preferences in the great majority of the cases. Determinants of preferences and real-world choices of affected patients should be further investigated in future studies.

From microscope to micropixels: A rapid review of artificial intelligence for the peripheral blood film

Artificial intelligence (AI) and its application in classification of blood cells in the peripheral blood film is an evolving field in haematology. We performed a rapid review of the literature on AI and peripheral blood films, evaluating the condition studied, image datasets, machine learning models, training set size, testing set size and accuracy. A total of 283 studies were identified, encompassing 6 broad domains: malaria (n = 95), leukemia (n = 81), leukocytes (n = 72), mixed (n = 25), erythrocytes (n = 15) or Myelodysplastic syndrome (MDS) (n = 1). These publications have demonstrated high self-reported mean accuracy rates across various studies (95.5% for malaria, 96.0% for leukemia, 94.4% for leukocytes, 95.2% for mixed studies and 91.2% for erythrocytes), with an overall mean accuracy of 95.1%. Despite the high accuracy, the challenges toward real world translational usage of these AI trained models include the need for well-validated multicentre data, data standardisation, and studies on less common cell types and non-malarial blood-borne parasites.

Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears

OBJECTIVE

The purpose of this systematic review was to summarize the results of original research studies evaluating the characteristics and performance of deep learning models for detection of knee ligament and meniscus tears on MRI.

MATERIALS AND METHODS

We searched PubMed for studies published as of February 2, 2022 for original studies evaluating development and evaluation of deep learning models for MRI diagnosis of knee ligament or meniscus tears. We summarized study details according to multiple criteria including baseline article details, model creation, deep learning details, and model evaluation.

RESULTS

19 studies were included with radiology departments leading the publications in deep learning development and implementation for detecting knee injuries via MRI. Among the studies, there was a lack of standard reporting and inconsistently described development details. However, all included studies reported consistently high model performance that significantly supplemented human reader performance.

CONCLUSION

From our review, we found radiology departments have been leading deep learning development for injury detection on knee MRIs. Although studies inconsistently described DL model development details, all reported high model performance, indicating great promise for DL in knee MRI analysis.

AI implementation in the UK landscape: Knowledge of AI governance, perceived challenges and opportunities, and ways forward for radiographers

INTRODUCTION

Despite the rapid increase of AI-enabled applications deployed in clinical practice, many challenges exist around AI implementation, including the clarity of governance frameworks, usability of validation of AI models, and customisation of training for radiographers. This study aimed to explore the perceptions of diagnostic and therapeutic radiographers, with existing theoretical and/or practical knowledge of AI, on issues of relevance to the field, such as AI implementation, including knowledge of AI governance and procurement, perceptions about enablers and challenges and future priorities for AI adoption.

METHODS

An online survey was designed and distributed to UK-based qualified radiographers who work in medical imaging and/or radiotherapy and have some previous theoretical and/or practical knowledge of working with AI. Participants were recruited through the researchers' professional networks on social media with support from the AI advisory group of the Society and College of Radiographers. Survey questions related to AI training/education, knowledge of AI governance frameworks, data privacy procedures, AI implementation considerations, and priorities for AI adoption. Descriptive statistics were employed to analyse the data, and chi-square tests were used to explore significant relationships between variables.

RESULTS

In total, 88 valid responses were received. Most radiographers (56.6 %) had not received any AI-related training. Also, although approximately 63 % of them used an evaluation framework to assess AI models' performance before implementation, many (36.9 %) were still unsure about suitable evaluation methods. Radiographers requested clearer guidance on AI governance, ample time to implement AI in their practice safely, adequate funding, effective leadership, and targeted support from AI champions. AI training, robust governance frameworks, and patient and public involvement were seen as priorities for the successful implementation of AI by radiographers.

CONCLUSION

AI implementation is progressing within radiography, but without customised training, clearer governance, key stakeholder engagement and suitable new roles created, it will be hard to harness its benefits and minimise related risks.

IMPLICATIONS FOR PRACTICE

The results of this study highlight some of the priorities and challenges for radiographers in relation to AI adoption, namely the need for developing robust AI governance frameworks and providing optimal AI training.

Evolving paradigms in breast cancer screening: Balancing efficacy, personalization, and equity

Breast cancer remains a significant global health challenge, with projections indicating a troubling increase in incidence. Breast cancer screening programs have long been hailed as life-saving initiatives, yet their true impact on mortality rates is a subject of ongoing debate. Screening poses the risk of false positives and the detection of indolent tumors, potentially leading to overtreatment. Bias factors, including lead time, length time, and selection biases, further complicate the assessment of screening efficacy. Recent studies suggest that AI-driven image analysis may revolutionize breast cancer screening, maintaining diagnostic accuracy while reducing radiologists' workload. However, the generalizability of these findings to diverse populations is a critical consideration. Personalized screening approaches and equitable access to advanced technologies are essential to mitigate disparities. In conclusion, the breast cancer screening landscape is evolving, emphasizing the need for risk stratification, appropriate imaging modalities, and a personalized approach to reduce overdiagnosis and focus on cancers with the potential to impact lives while prioritizing patient-centered care.

Rogue AI: Cautionary Cases in Neuroradiology and What We Can Learn From Them

Introduction In recent years, artificial intelligence (AI) in medical imaging has undergone unprecedented innovation and advancement, sparking a revolutionary transformation in healthcare. The field of radiology is particularly implicated, as clinical radiologists are expected to interpret an ever-increasing number of complex cases in record time. Machine learning software purchased by our institution is expected to help our radiologists come to a more prompt diagnosis by delivering point-of-care quantitative analysis of suspicious findings and streamlining clinical workflow. This paper explores AI's impact on neuroradiology, an area accounting for a substantial portion of recent radiology studies. We present a case series evaluating an AI software's performance in detecting neurovascular findings, highlighting five cases where AI interpretations differed from radiologists' assessments. Our study underscores common pitfalls of AI in the context of CT head angiograms, aiming to guide future AI algorithms.  Methods We conducted a retrospective case series study at Stony Brook University Hospital, a large medical center in Stony Brook, New York, spanning from October 1, 2021 to December 31, 2021, analyzing 140 randomly sampled CT angiograms using AI software. This software assessed various neurovascular parameters, and AI findings were compared with neuroradiologists' interpretations. Five cases with divergent interpretations were selected for detailed analysis. Results Five representative cases in which AI findings were discordant with radiologists' interpretations are presented with diagnoses including diffuse anoxic ischemic injury, cortical laminar necrosis, colloid cyst, right superficial temporal artery-to-middle cerebral artery (STA-MCA) bypass, and subacute bilateral subdural hematomas. Discussion The errors identified in our case series expose AI's limitations in radiology. Our case series reveals that AI's incorrect interpretations can stem from complexities in pathology, challenges in distinguishing densities, inability to identify artifacts, identifying post-surgical changes in normal anatomy, sensitivity limitations, and insufficient pattern recognition. AI's potential for improvement lies in refining its algorithms to effectively recognize and differentiate pathologies. Incorporating more diverse training datasets, multimodal data, deep-reinforcement learning, clinical context, and real-time learning capabilities are some ways to improve AI's performance in the field of radiology. Conclusion Overall, it is apparent that AI applications in radiology have much room for improvement before becoming more widely integrated into clinical workflows. While AI demonstrates remarkable potential to aid in diagnosis and streamline workflows, our case series highlights common pitfalls that underscore the need for continuous improvement. By refining algorithms, incorporating diverse datasets, embracing multimodal information, and leveraging innovative machine learning strategies, AI's diagnostic accuracy can be significantly improved.

Why Medical Students Pursue Radiology: A Current Longitudinal Survey on Motivations and Controversial Issues in Radiology

RATIONALE AND OBJECTIVES

Radiology is an increasingly competitive specialty. Various current factors influence medical students' decision to pursue a radiology career, including artificial intelligence (AI), remote reading, and COVID-19. This study seeks to determine the decision-making factors of all alumni from our medical school who matched into a radiology residency, and to gather opinions on emerging radiology topics.

MATERIALS AND METHODS

A survey querying decision-making factors and opinions on current radiology topics was distributed to all alumni from our medical school (first graduating class in 2011) who previously matched into a diagnostic or interventional radiology residency program (n = 57). Wilcoxon Rank-Sum and Fisher's Exact tests were used to determine statistical significance.

RESULTS

Forty-three of fifty-seven responses were received (75% response rate). The most influential factor that sparked respondents' interest in radiology was a radiology elective (25/43, 58%). Students who will finish radiology training in 2023 or later were more likely to be influenced by a mentor (15/23, 65%) than those who finished radiology training before 2023 (5/20, 25%) (p = 0.04). Respondents reported a 1.6/5 concern about AI negatively impacting their future career in radiology. There was 1.7/5 concern about performing radiology procedures on patients during the COVID-19 pandemic. Respondents predicted that remote reading would have a 3.2/5 positive impact on helping them achieve their preferred lifestyle. Job satisfaction among attending radiologists is rated at 4.3/5.

CONCLUSION

Radiology electives had the greatest influence in piquing students' interest in radiology, while mentorship is assuming increasing influence. AI is perceived as a relatively minimal threat to negatively impact radiologists' jobs. Respondents had little concern about performing radiology procedures during the COVID-19 pandemic. Remote reading is viewed as having a moderately positive impact on lifestyle. Responding radiologists enjoy notably high job satisfaction.

Assessment of inspiration and technical quality in anteroposterior thoracic radiographs using machine learning

INTRODUCTION

Chest radiographs are the most performed radiographic procedure, but suboptimal technical factors can impact clinical interpretation. A deep learning model was developed to assess technical and inspiratory adequacy of anteroposterior chest radiographs.

METHODS

Adult anteroposterior chest radiographs (n = 2375) were assessed for technical adequacy, and if otherwise technically adequate, for adequacy of inspiration. Images were labelled by an experienced radiologist with one of three ground truth labels: inadequate technique (n = 605, 25.5 %), adequate inspiration (n = 900, 37.9 %), and inadequate inspiration (n = 870, 36.6 %). A convolutional neural network was then iteratively trained to predict these labels and evaluated using recall, precision, F1 and micro-F1, and Gradient-weighted Class Activation Mapping analysis on a hold-out test set. Impact of kyphosis on model accuracy was assessed.

RESULTS

The model performed best for radiographs with adequate technique, and worst for images with inadequate technique. Recall was highest (89 %) for radiographs with both adequate technique and inspiration, with recall of 81 % for images with adequate technique and inadequate inspiration, and 60 % for images with inadequate technique, although precision was highest (85 %) for this category. Per-class F1 was 80 %, 81 % and 70 % for adequate inspiration, inadequate inspiration, and inadequate technique respectively. Weighted F1 and Micro F1 scores were 78 %. Presence or absence of kyphosis had no significant impact on model accuracy in images with adequate technique.

CONCLUSION

This study explores the promising performance of a machine learning algorithm for assessment of inspiratory adequacy and overall technical adequacy for anteroposterior chest radiograph acquisition.

IMPLICATIONS FOR PRACTICE

With further refinement, machine learning can contribute to education and quality improvement in radiology departments.

Understanding the factors influencing acceptability of AI in medical imaging domains among healthcare professionals: A scoping review

BACKGROUND

Artificial intelligence (AI) technology has the potential to transform medical practice within the medical imaging industry and materially improve productivity and patient outcomes. However, low acceptability of AI as a digital healthcare intervention among medical professionals threatens to undermine user uptake levels, hinder meaningful and optimal value-added engagement, and ultimately prevent these promising benefits from being realised. Understanding the factors underpinning AI acceptability will be vital for medical institutions to pinpoint areas of deficiency and improvement within their AI implementation strategies. This scoping review aims to survey the literature to provide a comprehensive summary of the key factors influencing AI acceptability among healthcare professionals in medical imaging domains and the different approaches which have been taken to investigate them.

METHODS

A systematic literature search was performed across five academic databases including Medline, Cochrane Library, Web of Science, Compendex, and Scopus from January 2013 to September 2023. This was done in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. Overall, 31 articles were deemed appropriate for inclusion in the scoping review.

RESULTS

The literature has converged towards three overarching categories of factors underpinning AI acceptability including: user factors involving trust, system understanding, AI literacy, and technology receptiveness; system usage factors entailing value proposition, self-efficacy, burden, and workflow integration; and socio-organisational-cultural factors encompassing social influence, organisational readiness, ethicality, and perceived threat to professional identity. Yet, numerous studies have overlooked a meaningful subset of these factors that are integral to the use of medical AI systems such as the impact on clinical workflow practices, trust based on perceived risk and safety, and compatibility with the norms of medical professions. This is attributable to reliance on theoretical frameworks or ad-hoc approaches which do not explicitly account for healthcare-specific factors, the novelties of AI as software as a medical device (SaMD), and the nuances of human-AI interaction from the perspective of medical professionals rather than lay consumer or business end users.

CONCLUSION

This is the first scoping review to survey the health informatics literature around the key factors influencing the acceptability of AI as a digital healthcare intervention in medical imaging contexts. The factors identified in this review suggest that existing theoretical frameworks used to study AI acceptability need to be modified to better capture the nuances of AI deployment in healthcare contexts where the user is a healthcare professional influenced by expert knowledge and disciplinary norms. Increasing AI acceptability among medical professionals will critically require designing human-centred AI systems which go beyond high algorithmic performance to consider accessibility to users with varying degrees of AI literacy, clinical workflow practices, the institutional and deployment context, and the cultural, ethical, and safety norms of healthcare professions. As investment into AI for healthcare increases, it would be valuable to conduct a systematic review and meta-analysis of the causal contribution of these factors to achieving high levels of AI acceptability among medical professionals.

Prospective effects of an artificial intelligence-based computer-aided detection system for prostate imaging on routine workflow and radiologists' outcomes

OBJECTIVES

Artificial intelligence (AI) is expected to alleviate the negative consequences of rising case numbers for radiologists. Currently, systematic evaluations of the impact of AI solutions in real-world radiological practice are missing. Our study addresses this gap by investigating the impact of the clinical implementation of an AI-based computer-aided detection system (CAD) for prostate MRI reading on clinicians' workflow, workflow throughput times, workload, and stress.

MATERIALS AND METHODS

CAD was newly implemented into radiology workflow and accompanied by a prospective pre-post study design. We assessed prostate MRI case readings using standardized work observations and questionnaires. The observation period was three months each in a single department. Workflow throughput times, PI-RADS score, CAD usage and radiologists' self-reported workload and stress were recorded. Linear mixed models were employed for effect identification.

RESULTS

In data analyses, 91 observed case readings (pre: 50, post: 41) were included. Variation of routine workflow was observed following CAD implementation. A non-significant increase in overall workflow throughput time was associated with CAD implementation (mean 16.99 ± 6.21 vs 18.77 ± 9.69 min, p = .51), along with an increase in diagnostic reading time for high suspicion cases (mean 15.73 ± 4.99 vs 23.07 ± 8.75 min, p = .02). Changes in radiologists' self-reported workload or stress were not found.

CONCLUSION

Implementation of an AI-based detection aid was associated with lower standardization and no effects over time on radiologists' workload or stress. Expectations of AI decreasing the workload of radiologists were not confirmed by our real-world study.

PRE-REGISTRATION

German register for clinical trials https://drks.de/; DRKS00027391.

Exploring the Potential of Artificial Intelligence in Breast Ultrasound

Breast ultrasound has emerged as a valuable imaging modality in the detection and characterization of breast lesions, particularly in women with dense breast tissue or contraindications for mammography. Within this framework, artificial intelligence (AI) has garnered significant attention for its potential to improve diagnostic accuracy in breast ultrasound and revolutionize the workflow. This review article aims to comprehensively explore the current state of research and development in harnessing AI's capabilities for breast ultrasound. We delve into various AI techniques, including machine learning, deep learning, as well as their applications in automating lesion detection, segmentation, and classification tasks. Furthermore, the review addresses the challenges and hurdles faced in implementing AI systems in breast ultrasound diagnostics, such as data privacy, interpretability, and regulatory approval. Ethical considerations pertaining to the integration of AI into clinical practice are also discussed, emphasizing the importance of maintaining a patient-centered approach. The integration of AI into breast ultrasound holds great promise for improving diagnostic accuracy, enhancing efficiency, and ultimately advancing patient's care. By examining the current state of research and identifying future opportunities, this review aims to contribute to the understanding and utilization of AI in breast ultrasound and encourage further interdisciplinary collaboration to maximize its potential in clinical practice.

Disparities in Breast Cancer Diagnostics: How Radiologists Can Level the Inequalities

Access to medical imaging is pivotal in healthcare, playing a crucial role in the prevention, diagnosis, and management of diseases. However, disparities persist in this scenario, disproportionately affecting marginalized communities, racial and ethnic minorities, and individuals facing linguistic or cultural barriers. This paper critically assesses methods to mitigate these disparities, with a focus on breast cancer screening. We underscore scientific mobility as a vital tool for radiologists to advocate for healthcare policy changes: it not only enhances diversity and cultural competence within the radiology community but also fosters international cooperation and knowledge exchange among healthcare institutions. Efforts to ensure cultural competency among radiologists are discussed, including ongoing cultural education, sensitivity training, and workforce diversification. These initiatives are key to improving patient communication and reducing healthcare disparities. This paper also highlights the crucial role of policy changes and legislation in promoting equal access to essential screening services like mammography. We explore the challenges and potential of teleradiology in improving access to medical imaging in remote and underserved areas. In the era of artificial intelligence, this paper emphasizes the necessity of validating its models across a spectrum of populations to prevent bias and achieve equitable healthcare outcomes. Finally, the importance of international collaboration is illustrated, showcasing its role in sharing insights and strategies to overcome global access barriers in medical imaging. Overall, this paper offers a comprehensive overview of the challenges related to disparities in medical imaging access and proposes actionable strategies to address these challenges, aiming for equitable healthcare delivery.

Nuclear medicine radiomics in digestive system tumors: Concept, applications, challenges, and future perspectives

Radiomics aims to develop novel biomarkers and provide relevant deeper subvisual information about pathology, immunophenotype, and tumor microenvironment. It uses automated or semiautomated quantitative analysis of high-dimensional images to improve characterization, diagnosis, and prognosis. Recent years have seen a rapid increase in radiomics applications in nuclear medicine, leading to some promising research results in digestive system oncology, which have been driven by big data analysis and the development of artificial intelligence. Although radiomics advances one step further toward the non-invasive precision medical analysis, it is still a step away from clinical application and faces many challenges. This review article summarizes the available literature on digestive system tumors regarding radiomics in nuclear medicine. First, we describe the workflow and steps involved in radiomics analysis. Subsequently, we discuss the progress in clinical application regarding the utilization of radiomics for distinguishing between various diseases and evaluating their prognosis, and demonstrate how radiomics advances this field. Finally, we offer our viewpoint on how the field can progress by addressing the challenges facing clinical implementation.

Deep learning diagnostic performance and visual insights in differentiating benign and malignant thyroid nodules on ultrasound images

This study aims to construct and evaluate a deep learning model, utilizing ultrasound images, to accurately differentiate benign and malignant thyroid nodules. The objective includes visualizing the model's process for interpretability and comparing its diagnostic precision with a cohort of 80 radiologists. We employed ResNet as the classification backbone for thyroid nodule prediction. The model was trained using 2096 ultrasound images of 655 distinct thyroid nodules. For performance evaluation, an independent test set comprising 100 cases of thyroid nodules was curated. In addition, to demonstrate the superiority of the artificial intelligence (AI) model over radiologists, a Turing test was conducted with 80 radiologists of varying clinical experience. This was meant to assess which group of radiologists' conclusions were in closer alignment with AI predictions. Furthermore, to highlight the interpretability of the AI model, gradient-weighted class activation mapping (Grad-CAM) was employed to visualize the model's areas of focus during its prediction process. In this cohort, AI diagnostics demonstrated a sensitivity of 81.67%, a specificity of 60%, and an overall diagnostic accuracy of 73%. In comparison, the panel of radiologists on average exhibited a diagnostic accuracy of 62.9%. The AI's diagnostic process was significantly faster than that of the radiologists. The generated heat-maps highlighted the model's focus on areas characterized by calcification, solid echo and higher echo intensity, suggesting these areas might be indicative of malignant thyroid nodules. Our study supports the notion that deep learning can be a valuable diagnostic tool with comparable accuracy to experienced senior radiologists in the diagnosis of malignant thyroid nodules. The interpretability of the AI model's process suggests that it could be clinically meaningful. Further studies are necessary to improve diagnostic accuracy and support auxiliary diagnoses in primary care settings.

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

Current risk scores using clinical risk factors for predicting ischemic heart disease (IHD) events-the leading cause of global mortality-have known limitations and may be improved by imaging biomarkers. While body composition (BC) imaging biomarkers derived from abdominopelvic computed tomography (CT) correlate with IHD risk, they are impractical to measure manually. Here, in a retrospective cohort of 8139 contrast-enhanced abdominopelvic CT examinations undergoing up to 5 years of follow-up, we developed multimodal opportunistic risk assessment models for IHD by automatically extracting BC features from abdominal CT images and integrating these with features from each patient's electronic medical record (EMR). Our predictive methods match and, in some cases, outperform clinical risk scores currently used in IHD risk assessment. We provide clinical interpretability of our model using a new method of determining tissue-level contributions from CT along with weightings of EMR features contributing to IHD risk. We conclude that such a multimodal approach, which automatically integrates BC biomarkers and EMR data, can enhance IHD risk assessment and aid primary prevention efforts for IHD. To further promote research, we release the Opportunistic L3 Ischemic heart disease (OL3I) dataset, the first public multimodal dataset for opportunistic CT prediction of IHD.

Artificial intelligence in breast imaging: potentials and challenges

Breast cancer, which is the most common type of malignant tumor among humans, is a leading cause of death in females. Standard treatment strategies, including neoadjuvant chemotherapy, surgery, postoperative chemotherapy, targeted therapy, endocrine therapy, and radiotherapy, are tailored for individual patients. Such personalized therapies have tremendously reduced the threat of breast cancer in females. Furthermore, early imaging screening plays an important role in reducing the treatment cycle and improving breast cancer prognosis. The recent innovative revolution in artificial intelligence (AI) has aided radiologists in the early and accurate diagnosis of breast cancer. In this review, we introduce the necessity of incorporating AI into breast imaging and the applications of AI in mammography, ultrasonography, magnetic resonance imaging, and positron emission tomography/computed tomography based on published articles since 1994. Moreover, the challenges of AI in breast imaging are discussed.

Role of robotics and artificial intelligence in oral health education. Knowledge, perception and attitude of dentists in India

BACKGROUND

Artificial intelligence or AI may be identified as the use of Personal Computers and/or machines in performing certain specific types of tasks that usually have the requirement of humanized knowledge. These specific tasks include acknowledgment of the problem, understanding disease dynamics, and determining the clinical diagnosis.

MATERIALS AND METHODS

This cross-sectional and prospective study was conducted on Dental professionals who were practicing all across India after obtaining approval from the Institutional Ethical Board. A previously validated as well as pre-analyzed questionnaire form was distributed using electronic mail and through the use of social media with a briefly explained description of the study purpose and an informed consent form. The study questionnaire comprised "close-ended" queries that were then divided into foursections. All the study participants were then instructed to select any one option among all the provided answers. The entire study was completed within one month. Collected observations were entered within a Microsoft Excel 2007® master chart. Statistical analytical software tool SPSS version 20.0, IBM Corporation was employed. "Chi-square" test was performed for evaluating statistical association. A P value lesser than 0.05 was fixed with statistical significance.

RESULTS

On analyzing the level of knowledge, 82.5% of subjects had knowledge of artificial intelligence while 11.4% had no knowledge and 6.1% had some knowledge of this tool. 69.1% were knowledgeable regarding the use of AI in lesional diagnosis, 12.8% had no knowledge regarding artificial intelligence for the diagnosis and 18.1% had no knowledge regarding AI in the diagnosis. 71% had knowledge concerning the use of AI for Imaging. Knowledge of AI in Oral Hygiene was seen in 54.3%. 91.2% of participants had knowledge of robotics use in Oral Surgery. 77% of dentists had knowledge regarding the use of AI for the enhancement of clinical practice. 95.5% had a higher 'positive' attitude toward the use of AI in academics. 69.1% of dentists had a positive attitude regarding AI incorporation in practice. 5% of dentists considered artificial intelligence better than human intelligence for diagnosis. 10% believed that disparities can exist between AI-based and human diagnosis.

CONCLUSION

Positive correlations were noted between knowledge, attitude, and practice of AI among studied dentists.

Image-encoded biological and non-biological variables may be used as shortcuts in deep learning models trained on multisite neuroimaging data

OBJECTIVE

This work investigates if deep learning (DL) models can classify originating site locations directly from magnetic resonance imaging (MRI) scans with and without correction for intensity differences.

MATERIAL AND METHODS

A large database of 1880 T1-weighted MRI scans collected across 41 sites originally for Parkinson's disease (PD) classification was used to classify sites in this study. Forty-six percent of the datasets are from PD patients, while 54% are from healthy participants. After preprocessing the T1-weighted scans, 2 additional data types were generated: intensity-harmonized T1-weighted scans and log-Jacobian deformation maps resulting from nonlinear atlas registration. Corresponding DL models were trained to classify sites for each data type. Additionally, logistic regression models were used to investigate the contribution of biological (age, sex, disease status) and non-biological (scanner type) variables to the models' decision.

RESULTS

A comparison of the 3 different types of data revealed that DL models trained using T1-weighted and intensity-harmonized T1-weighted scans can classify sites with an accuracy of 85%, while the model using log-Jacobian deformation maps achieved a site classification accuracy of 54%. Disease status and scanner type were found to be significant confounders.

DISCUSSION

Our results demonstrate that MRI scans encode relevant site-specific information that models could use as shortcuts that cannot be removed using simple intensity harmonization methods.

CONCLUSION

The ability of DL models to exploit site-specific biases as shortcuts raises concerns about their reliability, generalization, and deployability in clinical settings.