Impact of artificial intelligence on radiology: a EuroAIM survey among members of the European Society of Radiology

The Artificial Intelligence in Digital Radiology: Part 2: Towards an Investigation of acceptance and consensus on the Insiders

Background. The study deals with the introduction of the artificial intelligence in digital radiology. There is a growing interest in this area of scientific research in acceptance and consensus studies involving both insiders and the public, based on surveys focused mainly on single professionals. Purpose. The goal of the study is to perform a contemporary investigation on the acceptance and the consensus of the three key professional figures approaching in this field of application: (1) Medical specialists in image diagnostics: the medical specialists (MS)s; (2) experts in physical imaging processes: the medical physicists (MP)s; (3) AI designers: specialists of applied sciences (SAS)s. Methods. Participants (MSs = 92: 48 males/44 females, averaged age 37.9; MPs = 91: 43 males/48 females, averaged age 36.1; SAS = 90: 47 males/43 females, averaged age 37.3) were properly recruited based on specific training. An electronic survey was designed and submitted to the participants with a wide range questions starting from the training and background up to the different applications of the AI and the environment of application. Results. The results show that generally, the three professionals show (a) a high degree of encouraging agreement on the introduction of AI both in imaging and in non-imaging applications using both standalone applications and/or mHealth/eHealth, and (b) a different consent on AI use depending on the training background. Conclusions. The study highlights the usefulness of focusing on both the three key professionals and the usefulness of the investigation schemes facing a wide range of issues. The study also suggests the importance of different methods of administration to improve the adhesion and the need to continue these investigations both with federated and specific initiatives.

Information Security in Medical Robotics: A Survey on the Level of Training, Awareness and Use of the Physiotherapist

Cybersecurity is becoming an increasingly important aspect to investigate for the adoption and use of care robots, in term of both patients' safety, and the availability, integrity and privacy of their data. This study focuses on opinions about cybersecurity relevance and related skills for physiotherapists involved in rehabilitation and assistance thanks to the aid of robotics. The goal was to investigate the awareness among insiders about some facets of cybersecurity concerning human-robot interactions. We designed an electronic questionnaire and submitted it to a relevant sample of physiotherapists. The questionnaire allowed us to collect data related to: (i) use of robots and its relationship with cybersecurity in the context of physiotherapy; (ii) training in cybersecurity and robotics for the insiders; (iii) insiders' self-assessment on cybersecurity and robotics in some usage scenarios, and (iv) their experiences of cyber-attacks in this area and proposals for improvement. Besides contributing some specific statistics, the study highlights the importance of both acculturation processes in this field and monitoring initiatives based on surveys. The study exposes direct suggestions for continuation of these types of investigations in the context of scientific societies operating in the rehabilitation and assistance robotics. The study also shows the need to stimulate similar initiatives in other sectors of medical robotics (robotic surgery, care and socially assistive robots, rehabilitation systems, training for health and care workers) involving insiders.

Artificial intelligence in paediatric radiology: international survey of health care professionals' opinions

BACKGROUND

The nature of paediatric radiology work poses several challenges for developing and implementing artificial intelligence (AI) tools, but opinions of those working in the field are currently unknown.

OBJECTIVE

To evaluate the attitudes and perceptions toward AI amongst health care professionals working within children's imaging services.

MATERIALS AND METHODS

A web-based questionnaire was distributed to the membership of several paediatric and general radiological societies over a 4-month period (1 Feb - 31 May 2020). Survey questions covered attitudes toward AI in general, future impacts and suggested areas for development specifically within paediatric imaging.

RESULTS

Two hundred and forty responses were collected with the majority being from radiologists (159/240, 66.3%; 95% confidence interval [CI] 59.8-72.2%) or allied health care professionals (72/240, 31.3%; 95% CI 25.4-37.5%). Respondents agreed that AI could potentially alert radiologists to imaging abnormalities (148/240, 61.7%; 95% CI 55.2-67.9%) but preferred that results were checked by a human (200/240, 83.3%; 95% CI 78.0-87.8%). The majority did not believe jobs in paediatric radiology would be replaced by AI (205/240, 85.4%; 95% CI 80.3-89.6%) and that the development of AI tools should focus on improved diagnostic accuracy (77/240, 32.1%; 95% CI 26.2-38.4%), workflow efficiencies (60/240, 25.0%; 95% CI 19.7-30.9%) and patient safety (54/240, 22.5%; 95% CI 17.4-28.3%). The majority of European Society of Paediatric Radiology (ESPR) members (67/81, 82.7%; 95% CI 72.7-90.2%) welcomed the idea of a dedicated paediatric radiology AI task force with emphasis on educational events and anonymised dataset curation.

CONCLUSION

Imaging health care professionals working with children had a positive outlook regarding the use of AI in paediatric radiology, and did not feel their jobs were threatened. Future AI tools would be most beneficial for easily automated tasks and most practitioners welcomed the opportunity for further AI educational activities.

Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective

Background

Many artificial intelligence (AI) studies have focused on development of AI models, novel techniques, and reporting guidelines. However, little is understood about clinicians' perspectives of AI applications in medical fields including ophthalmology, particularly in light of recent regulatory guidelines. The aim for this study was to evaluate the perspectives of ophthalmologists regarding AI in 4 major eye conditions: diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD) and cataract.

Methods

This was a multi-national survey of ophthalmologists between March 1st, 2020 to February 29th, 2021 disseminated via the major global ophthalmology societies. The survey was designed based on microsystem, mesosystem and macrosystem questions, and the software as a medical device (SaMD) regulatory framework chaired by the Food and Drug Administration (FDA). Factors associated with AI adoption for ophthalmology analyzed with multivariable logistic regression random forest machine learning.

Results

One thousand one hundred seventy-six ophthalmologists from 70 countries participated with a response rate ranging from 78.8 to 85.8% per question. Ophthalmologists were more willing to use AI as clinical assistive tools (88.1%, n = 890/1,010) especially those with over 20 years' experience (OR 3.70, 95% CI: 1.10-12.5, p = 0.035), as compared to clinical decision support tools (78.8%, n = 796/1,010) or diagnostic tools (64.5%, n = 651). A majority of Ophthalmologists felt that AI is most relevant to DR (78.2%), followed by glaucoma (70.7%), AMD (66.8%), and cataract (51.4%) detection. Many participants were confident their roles will not be replaced (68.2%, n = 632/927), and felt COVID-19 catalyzed willingness to adopt AI (80.9%, n = 750/927). Common barriers to implementation include medical liability from errors (72.5%, n = 672/927) whereas enablers include improving access (94.5%, n = 876/927). Machine learning modeling predicted acceptance from participant demographics with moderate to high accuracy, and area under the receiver operating curves of 0.63-0.83.

Conclusion

Ophthalmologists are receptive to adopting AI as assistive tools for DR, glaucoma, and AMD. Furthermore, ML is a useful method that can be applied to evaluate predictive factors on clinical qualitative questionnaires. This study outlines actionable insights for future research and facilitation interventions to drive adoption and operationalization of AI tools for Ophthalmology.

Patients' Perceptions Toward Human-Artificial Intelligence Interaction in Health Care: Experimental Study

Background

It is believed that artificial intelligence (AI) will be an integral part of health care services in the near future and will be incorporated into several aspects of clinical care such as prognosis, diagnostics, and care planning. Thus, many technology companies have invested in producing AI clinical applications. Patients are one of the most important beneficiaries who potentially interact with these technologies and applications; thus, patients’ perceptions may affect the widespread use of clinical AI. Patients should be ensured that AI clinical applications will not harm them, and that they will instead benefit from using AI technology for health care purposes. Although human-AI interaction can enhance health care outcomes, possible dimensions of concerns and risks should be addressed before its integration with routine clinical care.

Objective

The main objective of this study was to examine how potential users (patients) perceive the benefits, risks, and use of AI clinical applications for their health care purposes and how their perceptions may be different if faced with three health care service encounter scenarios.

Methods

We designed a 2×3 experiment that crossed a type of health condition (ie, acute or chronic) with three different types of clinical encounters between patients and physicians (ie, AI clinical applications as substituting technology, AI clinical applications as augmenting technology, and no AI as a traditional in-person visit). We used an online survey to collect data from 634 individuals in the United States.

Results

The interactions between the types of health care service encounters and health conditions significantly influenced individuals’ perceptions of privacy concerns, trust issues, communication barriers, concerns about transparency in regulatory standards, liability risks, benefits, and intention to use across the six scenarios. We found no significant differences among scenarios regarding perceptions of performance risk and social biases.

Conclusions

The results imply that incompatibility with instrumental, technical, ethical, or regulatory values can be a reason for rejecting AI applications in health care. Thus, there are still various risks associated with implementing AI applications in diagnostics and treatment recommendations for patients with both acute and chronic illnesses. The concerns are also evident if the AI applications are used as a recommendation system under physician experience, wisdom, and control. Prior to the widespread rollout of AI, more studies are needed to identify the challenges that may raise concerns for implementing and using AI applications. This study could provide researchers and managers with critical insights into the determinants of individuals’ intention to use AI clinical applications. Regulatory agencies should establish normative standards and evaluation guidelines for implementing AI in health care in cooperation with health care institutions. Regular audits and ongoing monitoring and reporting systems can be used to continuously evaluate the safety, quality, transparency, and ethical factors of AI clinical applications.

Human, All Too Human? An All-Around Appraisal of the "Artificial Intelligence Revolution" in Medical Imaging

Artificial intelligence (AI) has seen dramatic growth over the past decade, evolving from a niche super specialty computer application into a powerful tool which has revolutionized many areas of our professional and daily lives, and the potential of which seems to be still largely untapped. The field of medicine and medical imaging, as one of its various specialties, has gained considerable benefit from AI, including improved diagnostic accuracy and the possibility of predicting individual patient outcomes and options of more personalized treatment. It should be noted that this process can actively support the ongoing development of advanced, highly specific treatment strategies (e.g., target therapies for cancer patients) while enabling faster workflow and more efficient use of healthcare resources. The potential advantages of AI over conventional methods have made it attractive for physicians and other healthcare stakeholders, raising much interest in both the research and the industry communities. However, the fast development of AI has unveiled its potential for disrupting the work of healthcare professionals, spawning concerns among radiologists that, in the future, AI may outperform them, thus damaging their reputations or putting their jobs at risk. Furthermore, this development has raised relevant psychological, ethical, and medico-legal issues which need to be addressed for AI to be considered fully capable of patient management. The aim of this review is to provide a brief, hopefully exhaustive, overview of the state of the art of AI systems regarding medical imaging, with a special focus on how AI and the entire healthcare environment should be prepared to accomplish the goal of a more advanced human-centered world.

Radiomics, machine learning, and artificial intelligence-what the neuroradiologist needs to know

PURPOSE

Artificial intelligence (AI) is playing an ever-increasing role in Neuroradiology.

METHODS

When designing AI-based research in neuroradiology and appreciating the literature, it is important to understand the fundamental principles of AI. Training, validation, and test datasets must be defined and set apart as priorities. External validation and testing datasets are preferable, when feasible. The specific type of learning process (supervised vs. unsupervised) and the machine learning model also require definition. Deep learning (DL) is an AI-based approach that is modelled on the structure of neurons of the brain; convolutional neural networks (CNN) are a commonly used example in neuroradiology.

RESULTS

Radiomics is a frequently used approach in which a multitude of imaging features are extracted from a region of interest and subsequently reduced and selected to convey diagnostic or prognostic information. Deep radiomics uses CNNs to directly extract features and obviate the need for predefined features.

CONCLUSION

Common limitations and pitfalls in AI-based research in neuroradiology are limited sample sizes ("small-n-large-p problem"), selection bias, as well as overfitting and underfitting.

Knowledge and attitudes towards artificial intelligence in imaging: a look at the quantitative survey literature

RATIONALE AND OBJECTIVES

There exists many single sample perspectives on artificial intelligence (AI). The aim of this review was to collate the current data on attitudes/knowledge towards AI in three unique populations: medical students, clinicians and patients.

MATERIALS AND METHODS

A literature search was performed on PubMed, Scopus and Web of Science pertaining to survey data on AI in radiology. Quality assessment was performed by an adapted version of the assessment tool from the National Heart, Lung and Blood Institute for Observational Studies.

RESULTS

Fourteen studies were found on attitudes/knowledge towards AI in radiology. Four studies examined medical students, seven on clinicians and three on patient populations. Deficiencies in the literature mainly related to sampling bias. Students had anxiety relating to future job prospects. Clinicians were optimistic and viewed AI as an aid to the diagnosis and wanted to further their knowledge. Patients were concerned about the lack of human interaction and accountability during error.

CONCLUSION

Attitudes and knowledge regarding AI in radiology remains a topic that needs to be researched further and education given pertaining to its use in a clinical setting.

Impact of COVID-19 on Radiology Faculty - An Exacerbation of Gender Differences in Unpaid Home Duties and Professional Productivity

RATIONALE AND OBJECTIVES

The COVID-19 pandemic stresses the tenuous balance between domestic obligations and academic output for women across professions. Our investigation aims to evaluate the impact of the pandemic on the home duties and workplace productivity of academic radiologists with respect to gender.

MATERIALS AND METHODS

A 49-question survey was distributed to 926 members of Association of University Radiologists in October 2020. Several categories were addressed: demographics; workplace changes; stress levels and personal experiences with illness; time spent on domestic obligations; and perception of productivity during COVID-19. Statistical analyses were performed using SAS version 9.4 software (SAS Institute, Cary, NC).

RESULTS

A total of 96 responses across 30 states, 53.1% male and 46.9% female were received. Women report spending more time on unpaid domestic duties than men prior to COVID-19, with men spending a median of 5-10 h/wk and women spending a median of 10-15 h/wk (p = 0.043). With pandemic onset, both genders reported that women did more of the homecare, when not split equally. Women with young children reported a significant decrease in work-from-home productivity compared to men with young children (p = 0.007). Men reported they had more time to be productive compared to women (p = 0.012).

CONCLUSION

The COVID-19 pandemic threatens to disrupt the advancement of women in radiology leadership roles by creating disparate effects on productivity due to increased workloads at home for women. This could potentially lead to decreases in promotions and research productivity in years to come that far outlast the acute phases of the pandemic.

Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors

This study aims to investigate the influence of interobserver manual segmentation variability on the reproducibility of 2D and 3D unenhanced computed tomography (CT)- and magnetic resonance imaging (MRI)-based texture analysis. Thirty patients with cartilaginous bone tumors (10 enchondromas, 10 atypical cartilaginous tumors, 10 chondrosarcomas) were retrospectively included. Three radiologists independently performed manual contour-focused segmentation on unenhanced CT and T1-weighted and T2-weighted MRI by drawing both a 2D region of interest (ROI) on the slice showing the largest tumor area and a 3D ROI including the whole tumor volume. Additionally, a marginal erosion was applied to both 2D and 3D segmentations to evaluate the influence of segmentation margins. A total of 783 and 1132 features were extracted from original and filtered 2D and 3D images, respectively. Intraclass correlation coefficient ≥ 0.75 defined feature stability. In 2D vs. 3D contour-focused segmentation, the rates of stable features were 74.71% vs. 86.57% (p < 0.001), 77.14% vs. 80.04% (p = 0.142), and 95.66% vs. 94.97% (p = 0.554) for CT and T1-weighted and T2-weighted images, respectively. Margin shrinkage did not improve 2D (p = 0.343) and performed worse than 3D (p < 0.001) contour-focused segmentation in terms of feature stability. In 2D vs. 3D contour-focused segmentation, matching stable features derived from CT and MRI were 65.8% vs. 68.7% (p = 0.191), and those derived from T1-weighted and T2-weighted images were 76.0% vs. 78.2% (p = 0.285). 2D and 3D radiomic features of cartilaginous bone tumors extracted from unenhanced CT and MRI are reproducible, although some degree of interobserver segmentation variability highlights the need for reliability analysis in future studies.

Artificial intelligence and the medical physics profession - A Swedish perspective

BACKGROUND

There is a continuous and dynamic discussion on artificial intelligence (AI) in present-day society. AI is expected to impact on healthcare processes and could contribute to a more sustainable use of resources allocated to healthcare in the future. The aim for this work was to establish a foundation for a Swedish perspective on the potential effect of AI on the medical physics profession.

MATERIALS AND METHODS

We designed a survey to gauge viewpoints regarding AI in the Swedish medical physics community. Based on the survey results and present-day situation in Sweden, a SWOT analysis was performed on the implications of AI for the medical physics profession.

RESULTS

Out of 411 survey recipients, 163 responded (40%). The Swedish medical physicists with a professional license believed (90%) that AI would change the practice of medical physics but did not foresee (81%) that AI would pose a risk to their practice and career. The respondents were largely positive to the inclusion of AI in educational programmes. According to self-assessment, the respondents' knowledge of and workplace preparedness for AI was generally low.

CONCLUSIONS

From the survey and SWOT analysis we conclude that AI will change the medical physics profession and that there are opportunities for the profession associated with the adoption of AI in healthcare. To overcome the weakness of limited AI knowledge, potentially threatening the role of medical physicists, and build upon the strong position in Swedish healthcare, medical physics education and training should include learning objectives on AI.

Radiology Community Attitude in Saudi Arabia about the Applications of Artificial Intelligence in Radiology

Artificial intelligence (AI) is a broad, umbrella term that encompasses the theory and development of computer systems able to perform tasks normally requiring human intelligence. The aim of this study is to assess the radiology community’s attitude in Saudi Arabia toward the applications of AI. Methods: Data for this study were collected using electronic questionnaires in 2019 and 2020. The study included a total of 714 participants. Data analysis was performed using SPSS Statistics (version 25). Results: The majority of the participants (61.2%) had read or heard about the role of AI in radiology. We also found that radiologists had statistically different responses and tended to read more about AI compared to all other specialists. In addition, 82% of the participants thought that AI must be included in the curriculum of medical and allied health colleges, and 86% of the participants agreed that AI would be essential in the future. Even though human–machine interaction was considered to be one of the most important skills in the future, 89% of the participants thought that it would never replace radiologists. Conclusion: Because AI plays a vital role in radiology, it is important to ensure that radiologists and radiographers have at least a minimum understanding of the technology. Our finding shows an acceptable level of knowledge regarding AI technology and that AI applications should be included in the curriculum of the medical and health sciences colleges.

Workload of diagnostic radiologists in the foreseeable future based on recent scientific advances: growth expectations and role of artificial intelligence

Objective

To determine the anticipated contribution of recently published medical imaging literature, including artificial intelligence (AI), on the workload of diagnostic radiologists.

Methods

This study included a random sample of 440 medical imaging studies published in 2019. The direct contribution of each study to patient care and its effect on the workload of diagnostic radiologists (i.e., number of examinations performed per time unit) was assessed. Separate analyses were done for an academic tertiary care center and a non-academic general teaching hospital.

Results

In the academic tertiary care center setting, 65.0% (286/440) of studies could directly contribute to patient care, of which 48.3% (138/286) would increase workload, 46.2% (132/286) would not change workload, 4.5% (13/286) would decrease workload, and 1.0% (3/286) had an unclear effect on workload. In the non-academic general teaching hospital setting, 63.0% (277/240) of studies could directly contribute to patient care, of which 48.7% (135/277) would increase workload, 46.2% (128/277) would not change workload, 4.3% (12/277) would decrease workload, and 0.7% (2/277) had an unclear effect on workload. Studies with AI as primary research area were significantly associated with an increased workload (p < 0.001), with an odds ratio (OR) of 10.64 (95% confidence interval (CI) 3.25–34.80) in the academic tertiary care center setting and an OR of 10.45 (95% CI 3.19–34.21) in the non-academic general teaching hospital setting.

Conclusions

Recently published medical imaging studies often add value to radiological patient care. However, they likely increase the overall workload of diagnostic radiologists, and this particularly applies to AI studies.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13244-021-01031-4.

Attitudes Toward Artificial Intelligence Among Radiologists, IT Specialists, and Industry

OBJECTIVES

We investigated the attitudes of radiologists, information technology (IT) specialists, and industry representatives on artificial intelligence (AI) and its future impact on radiological work.

MATERIALS AND METHODS

During a national meeting for AI, eHealth, and IT infrastructure in 2019, we conducted a survey to obtain participants' attitudes. A total of 123 participants completed 28 items exploring AI usage in medicine. The Kruskal-Wallis test was used to identify differences between radiologists, IT specialists, and industry representatives.

RESULTS

The strongest agreement between all respondents occurred with the following: plausibility checks are important to understand the decisions of the AI (93% agreement), validation of AI algorithms is mandatory (91%), and medicine becomes more efficient in the age of AI (86%). In contrast, only 25% of the respondents had confidence in the AI results, and only 17% believed that medicine will become more human through the use of AI. The answers were significantly different between the three professions for four items: relevance for protocol selection in cross-sectional imaging (p = 0.034), medical societies should be involved in validation (p = 0.028), patients should be informed about the use of AI (p = 0.047), and AI should be part of medical education (p = 0.026).

CONCLUSION

Currently, a discrepancy exists between high expectations for the future role of AI and low confidence in the results. This attitude was similar across all three groups. The demand for plausibility checks and the need to prove the usefulness in randomized controlled studies indicate what is needed in future research.

An international survey on AI in radiology in 1041 radiologists and radiology residents part 2: expectations, hurdles to implementation, and education

OBJECTIVES

Currently, hurdles to implementation of artificial intelligence (AI) in radiology are a much-debated topic but have not been investigated in the community at large. Also, controversy exists if and to what extent AI should be incorporated into radiology residency programs.

METHODS

Between April and July 2019, an international survey took place on AI regarding its impact on the profession and training. The survey was accessible for radiologists and residents and distributed through several radiological societies. Relationships of independent variables with opinions, hurdles, and education were assessed using multivariable logistic regression.

RESULTS

The survey was completed by 1041 respondents from 54 countries. A majority (n = 855, 82%) expects that AI will cause a change to the radiology field within 10 years. Most frequently, expected roles of AI in clinical practice were second reader (n = 829, 78%) and work-flow optimization (n = 802, 77%). Ethical and legal issues (n = 630, 62%) and lack of knowledge (n = 584, 57%) were mentioned most often as hurdles to implementation. Expert respondents added lack of labelled images and generalizability issues. A majority (n = 819, 79%) indicated that AI should be incorporated in residency programs, while less support for imaging informatics and AI as a subspecialty was found (n = 241, 23%).

CONCLUSIONS

Broad community demand exists for incorporation of AI into residency programs. Based on the results of the current study, integration of AI education seems advisable for radiology residents, including issues related to data management, ethics, and legislation.

KEY POINTS

• There is broad demand from the radiological community to incorporate AI into residency programs, but there is less support to recognize imaging informatics as a radiological subspecialty. • Ethical and legal issues and lack of knowledge are recognized as major bottlenecks for AI implementation by the radiological community, while the shortage in labeled data and IT-infrastructure issues are less often recognized as hurdles. • Integrating AI education in radiology curricula including technical aspects of data management, risk of bias, and ethical and legal issues may aid successful integration of AI into diagnostic radiology.

Challenges of Radiology education in the era of artificial intelligence

Artificial intelligence is a branch of computer science that is generating great expectations in medicine and particularly in radiology. Artificial intelligence will change not only the way we practice our profession, but also the way we teach it and learn it. Although the advent of artificial intelligence has led some to question whether it is necessary to continue training radiologists, there seems to be a consensus in the recent scientific literature that we should continue to train radiologists and that we should teach future radiologists about artificial intelligence and how to exploit it. The acquisition of competency in artificial intelligence should start in medical school, be consolidated in residency programs, and be maintained and updated during continuing medical education. This article aims to describe some of the challenges that artificial intelligencve can pose in the different stages of training in radiology, from medical school through continuing medical education.

Medical students' perceptions of the impact of artificial intelligence in radiology

OBJECTIVES

To analyze medical students' perceptions of the impact of artificial intelligence in radiology.

MATERIAL AND METHODS

A structured questionnaire comprising 28 items organized into six sections was distributed to students of medicine in Spain in December 2019.

RESULTS

A total of 341 students responded. Of these, 27 (7.9%) included radiology among their three main choices for specialization, and 51.9% considered that they clearly understood what artificial intelligence is. The overall rate of correct answers to the objective true-or-false questions about artificial intelligence was 70.7%. Whereas 75.9% expressed their disagreement with the hypothesis that artificial intelligence would replace radiologists, only 41.9% disagreed with the hypothesis that the demand for radiologists would decrease in the future. Only 36.7% expressed concerns about the role of artificial intelligence related to choosing radiology as a specialty. A greater proportion of students in the early years of medical school agreed with statements that radiologists accept artificial-intelligence-related technological changes and work with the industry to apply them as well as with statements about the need to include basic training about artificial intelligence in the medical school curriculum.

CONCLUSIONS

The students surveyed are aware of the impact of artificial intelligence in daily life, but not of the current debate about its potential applications in radiology. In general, they think that artificial intelligence will revolutionize radiology without having an alarming effect on the employability of radiologists. The students surveyed think that it is necessary to provide basic training about artificial intelligence in undergraduate medical school programs.

Artificial intelligence in gastrointestinal radiology: A review with special focus on recent development of magnetic resonance and computed tomography

Artificial intelligence (AI), particularly the deep learning technology, have been proven influential to radiology in the recent decade. Its ability in image classification, segmentation, detection and reconstruction tasks have substantially assisted diagnostic radiology, and has even been viewed as having the potential to perform better than radiologists in some tasks. Gastrointestinal radiology, an important subspecialty dealing with complex anatomy and various modalities including endoscopy, have especially attracted the attention of AI researchers and engineers worldwide. Consequently, recently many tools have been developed for lesion detection and image construction in gastrointestinal radiology, particularly in the fields for which public databases are available, such as diagnostic abdominal magnetic resonance imaging (MRI) and computed tomography (CT). This review will provide a framework for understanding recent advancements of AI in gastrointestinal radiology, with a special focus on hepatic and pancreatobiliary diagnostic radiology with MRI and CT. For fields where AI is less developed, this review will also explain the difficulty in AI model training and possible strategies to overcome the technical issues. The authors’ insights of possible future development will be addressed in the last section.

2020 ACR Data Science Institute Artificial Intelligence Survey

PURPOSE

The ACR Data Science Institute conducted its first annual survey of ACR members to understand how radiologists are using artificial intelligence (AI) in clinical practice and to provide a baseline for monitoring trends in AI use over time.

METHODS

The ACR Data Science Institute sent a brief electronic survey to all ACR members via email. Invitees were asked for demographic information about their practice and if and how they were currently using AI as part of their clinical work. They were also asked to evaluate the performance of AI models in their practices and to assess future needs.

RESULTS

Approximately 30% of radiologists are currently using AI as part of their practice. Large practices were more likely to use AI than smaller ones, and of those using AI in clinical practice, most were using AI to enhance interpretation, most commonly detection of intracranial hemorrhage, pulmonary emboli, and mammographic abnormalities. Of practices not currently using AI, 20% plan to purchase AI tools in the next 1 to 5 years.

CONCLUSION

The survey results indicate a modest penetrance of AI in clinical practice. Information from the survey will help researchers and industry develop AI tools that will enhance radiological practice and improve quality and efficiency in patient care.

Barriers and Enablers for Artificial Intelligence in Dental Diagnostics: A Qualitative Study

The present study aimed to identify barriers and enablers for the implementation of artificial intelligence (AI) in dental, specifically radiographic, diagnostics. Semi-structured phone interviews with dentists and patients were conducted between the end of May and the end of June 2020 (convenience/snowball sampling). A questionnaire developed along the Theoretical Domains Framework (TDF) and the Capabilities, Opportunities and Motivations influencing Behaviors model (COM-B) was used to guide interviews. Mayring's content analysis was employed to point out barriers and enablers. We identified 36 barriers, conflicting themes or enablers, covering nine of the fourteen domains of the TDF and all three determinants of behavior (COM). Both stakeholders emphasized chances and hopes for AI. A range of enablers for implementing AI in dental diagnostics were identified (e.g., the chance for higher diagnostic accuracy, a reduced workload, more comprehensive reporting and better patient-provider communication). Barriers related to reliance on AI and responsibility for medical decisions, as well as the explainability of AI and the related option to de-bug AI applications, emerged. Decision-makers and industry may want to consider these aspects to foster implementation of AI in dentistry.

Expanding the medical physicist curricular and professional programme to include Artificial Intelligence

PURPOSE

To provide a guideline curriculum related to Artificial Intelligence (AI), for the education and training of European Medical Physicists (MPs).

MATERIALS AND METHODS

The proposed curriculum consists of two levels: Basic (introducing MPs to the pillars of knowledge, development and applications of AI, in the context of medical imaging and radiation therapy) and Advanced. Both are common to the subspecialties (diagnostic and interventional radiology, nuclear medicine, and radiation oncology). The learning outcomes of the training are presented as knowledge, skills and competences (KSC approach).

RESULTS

For the Basic section, KSCs were stratified in four subsections: (1) Medical imaging analysis and AI Basics; (2) Implementation of AI applications in clinical practice; (3) Big data and enterprise imaging, and (4) Quality, Regulatory and Ethical Issues of AI processes. For the Advanced section instead, a common block was proposed to be further elaborated by each subspecialty core curriculum. The learning outcomes were also translated into a syllabus of a more traditional format, including practical applications.

CONCLUSIONS

This AI curriculum is the first attempt to create a guideline expanding the current educational framework for Medical Physicists in Europe. It should be considered as a document to top the sub-specialties' curriculums and adapted by national training and regulatory bodies. The proposed educational program can be implemented via the European School of Medical Physics Expert (ESMPE) course modules and - to some extent - also by the national competent EFOMP organizations, to reach widely the medical physicist community in Europe.

An international survey on AI in radiology in 1,041 radiologists and radiology residents part 1: fear of replacement, knowledge, and attitude

Objectives

Radiologists’ perception is likely to influence the adoption of artificial intelligence (AI) into clinical practice. We investigated knowledge and attitude towards AI by radiologists and residents in Europe and beyond.

Methods

Between April and July 2019, a survey on fear of replacement, knowledge, and attitude towards AI was accessible to radiologists and residents. The survey was distributed through several radiological societies, author networks, and social media. Independent predictors of fear of replacement and a positive attitude towards AI were assessed using multivariable logistic regression.

Results

The survey was completed by 1,041 respondents from 54 mostly European countries. Most respondents were male (n = 670, 65%), median age was 38 (24–74) years, n = 142 (35%) residents, and n = 471 (45%) worked in an academic center. Basic AI-specific knowledge was associated with fear (adjusted OR 1.56, 95% CI 1.10–2.21, p = 0.01), while intermediate AI-specific knowledge (adjusted OR 0.40, 95% CI 0.20–0.80, p = 0.01) or advanced AI-specific knowledge (adjusted OR 0.43, 95% CI 0.21–0.90, p = 0.03) was inversely associated with fear. A positive attitude towards AI was observed in 48% (n = 501) and was associated with only having heard of AI, intermediate (adjusted OR 11.65, 95% CI 4.25–31.92, p < 0.001), or advanced AI-specific knowledge (adjusted OR 17.65, 95% CI 6.16–50.54, p < 0.001).

Conclusions

Limited AI-specific knowledge levels among radiology residents and radiologists are associated with fear, while intermediate to advanced AI-specific knowledge levels are associated with a positive attitude towards AI. Additional training may therefore improve clinical adoption.

Key Points

• Forty-eight percent of radiologists and residents have an open and proactive attitude towards artificial intelligence (AI), while 38% fear of replacement by AI.

• Intermediate and advanced AI-specific knowledge levels may enhance adoption of AI in clinical practice, while rudimentary knowledge levels appear to be inhibitive.

• AI should be incorporated in radiology training curricula to help facilitate its clinical adoption.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-021-07781-5.

Handcrafted MRI radiomics and machine learning: Classification of indeterminate solid adrenal lesions

PURPOSE

To assess a radiomic machine learning (ML) model in classifying solid adrenal lesions (ALs) without fat signal drop on chemical shift (CS) as benign or malignant.

METHOD

55 indeterminate ALs (21 lipid poor adenomas, 15 benign pheocromocytomas, 1 oncocytoma, 12 metastases, 6 primary tumors) showing no fat signal drop on CS were retrospectively included. Manual 3D segmentation on T2-weighted and CS images was performed for subsequent radiomic feature extraction. After feature stability testing and an 80-20% train-test split, the train set was balanced via oversampling. Following a multi-step feature selection, an Extra Trees model was tuned with 5-fold stratified cross-validation in the train set and then tested on the hold-out test set.

RESULTS

A total of 3396 features were extracted from each AL, of which 133 resulted unstable while none had low variance (< 0.01). Highly correlated (r > 0.8) features were also excluded, leaving 440 parameters. Among these, Support Vector Machine 5-fold stratified cross-validated recursive feature elimination selected a subset of 6 features. ML obtained a cross-validation accuracy of 0.94 on the train and 0.91 on the test sets. Precision, recall and F1 score were respectively 0.92, 0.91 and 0.91.

CONCLUSIONS

Our MRI handcrafted radiomics and ML pipeline proved useful to characterize benign and malignant solid indeterminate adrenal lesions.

A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology

Artificial intelligence technology has advanced rapidly in recent years and has the potential to improve healthcare outcomes. However, technology uptake will be largely driven by clinicians, and there is a paucity of data regarding the attitude that clinicians have to this new technology. In June-August 2019 we conducted an online survey of fellows and trainees of three specialty colleges (ophthalmology, radiology/radiation oncology, dermatology) in Australia and New Zealand on artificial intelligence. There were 632 complete responses (n = 305, 230, and 97, respectively), equating to a response rate of 20.4%, 5.1%, and 13.2% for the above colleges, respectively. The majority (n = 449, 71.0%) believed artificial intelligence would improve their field of medicine, and that medical workforce needs would be impacted by the technology within the next decade (n = 542, 85.8%). Improved disease screening and streamlining of monotonous tasks were identified as key benefits of artificial intelligence. The divestment of healthcare to technology companies and medical liability implications were the greatest concerns. Education was identified as a priority to prepare clinicians for the implementation of artificial intelligence in healthcare. This survey highlights parallels between the perceptions of different clinician groups in Australia and New Zealand about artificial intelligence in medicine. Artificial intelligence was recognized as valuable technology that will have wide-ranging impacts on healthcare.

[Artificial intelligence in oncological radiology : A (p)review]

BACKGROUND

Artificial intelligence (AI) has the potential to fundamentally change medicine within the coming decades. Radiological imaging is one of the primary fields of its clinical application.

OBJECTIVES

In this article, we summarize previous AI developments with a focus on oncological radiology. Based on selected examples, we derive scenarios for developments in the next 10 years.

MATERIALS AND METHODS

This work is based on a review of various literature and product databases, publications by regulatory authorities, reports, and press releases.

CONCLUSIONS

The clinical use of AI applications is still in an early stage of development. The large number of research publications shows the potential of the field. Several certified products have already become available to users. However, for a widespread adoption of AI applications in clinical routine, several fundamental prerequisites are still awaited. These include the generation of evidence justifying the use of algorithms through representative clinical studies, adjustments to the framework for approval processes and dedicated education and teaching resources for its users. It is expected that use of AI methods will increase, thus, creating new opportunities for improved diagnostics, therapy, and more efficient workflows.

Practice Patterns and Challenges of Performing and Interpreting Prostate MRI: A Survey by the Society of Abdominal Radiology Prostate Disease-Focused Panel

OBJECTIVE. The purpose of this study was to report on the practice patterns and challenges of performing and interpreting prostate MRI. SUBJECTS AND METHODS. An electronic survey regarding prostate MRI practice patterns and challenges was sent to members of the Society of Abdominal Radiology. RESULTS. The response rate was 15% (212/1446). Most (65%) of the respondents were academic abdominal radiologists with 1-5 (52%), 6-10 (20%), 11-20 (15%), and more than 20 (5%) years of experience in reporting prostate MRI. The numbers of prostate MRI examinations reported per week were 0-5 (43%), 6-10 (38%), 11-20 (12%), 21-30 (5%), and more than 30 (2%). Imaging was performed at 3 T (58%), 1.5 T (20%), or either (21%), and most examinations (83%) were performed without an endorectal coil. Highest b values ranged from 800 to 5000 s/mm²; 1400 s/mm² (26%) and 1500 s/mm² (30%) were the most common. Most respondents (79%) acquired dynamic contrast-enhanced images with temporal resolution of less than 10 seconds. Most (71%) of the prostate MRI studies were used for fusion biopsy. PI-RADS version 2 was used by 92% of the respondents and template reporting by 80%. Challenges to performing and interpreting prostate MRI were scored on a 1-5 Likert scale (1, easy; 2, somewhat easy; 3, neutral; 4, somewhat difficult; 5, very difficult). The median scores were 2 or 3 for patient preparatory factors. Image acquisition and reporting factors were scored 1-2, except for performing spectroscopy or using an endorectal coil, both of which scored 4. Acquiring patient history scored 2 and quality factors scored 3. CONCLUSION. Most radiologists perform prostate MRI at 3 T without an endorectal coil and interpret the images using PI-RADS version 2. Challenges include obtaining quality images, acquiring feedback, and variability in the interpretation of PI-RADS scores.

Radiomic Machine Learning Classifiers in Spine Bone Tumors: A Multi-Software, Multi-Scanner Study

PURPOSE

Spinal lesion differential diagnosis remains challenging even in MRI. Radiomics and machine learning (ML) have proven useful even in absence of a standardized data mining pipeline. We aimed to assess ML diagnostic performance in spinal lesion differential diagnosis, employing radiomic data extracted by different software.

METHODS

Patients undergoing MRI for a vertebral lesion were retrospectively analyzed (n = 146, 67 males, 79 females; mean age 63 ± 16 years, range 8-89 years) and constituted the train (n = 100) and internal test cohorts (n = 46). Part of the latter had additional prior exams which constituted a multi-scanner, external test cohort (n = 35). Lesions were labeled as benign or malignant (2-label classification), and benign, primary malignant or metastases (3-label classification) for classification analyses. Features extracted via 3D Slicer heterogeneityCAD module (hCAD) and PyRadiomics were independently used to compare different combinations of feature selection methods and ML classifiers (n = 19).

RESULTS

In total, 90 and 1548 features were extracted by hCAD and PyRadiomics, respectively. The best feature selection method-ML algorithm combination was selected by 10 iterations of 10-fold cross-validation in the training data. For the 2-label classification ML obtained 94% accuracy in the internal test cohort, using hCAD data, and 86% in the external one. For the 3-label classification, PyRadiomics data allowed for 80% and 69% accuracy in the internal and external test sets, respectively.

CONCLUSIONS

MRI radiomics combined with ML may be useful in spinal lesion assessment. More robust pre-processing led to better consistency despite scanner and protocol heterogeneity.

Not all biases are bad: equitable and inequitable biases in machine learning and radiology

The application of machine learning (ML) technologies in medicine generally but also in radiology more specifically is hoped to improve clinical processes and the provision of healthcare. A central motivation in this regard is to advance patient treatment by reducing human error and increasing the accuracy of prognosis, diagnosis and therapy decisions. There is, however, also increasing awareness about bias in ML technologies and its potentially harmful consequences. Biases refer to systematic distortions of datasets, algorithms, or human decision making. These systematic distortions are understood to have negative effects on the quality of an outcome in terms of accuracy, fairness, or transparency. But biases are not only a technical problem that requires a technical solution. Because they often also have a social dimension, the 'distorted' outcomes they yield often have implications for equity. This paper assesses different types of biases that can emerge within applications of ML in radiology, and discusses in what cases such biases are problematic. Drawing upon theories of equity in healthcare, we argue that while some biases are harmful and should be acted upon, others might be unproblematic and even desirable-exactly because they can contribute to overcome inequities.

Artificial intelligence in radiology: relevance of collaborative work between radiologists and engineers for building a multidisciplinary team

The use of artificial intelligence (AI) algorithms in the field of radiology is becoming more common. Several studies have demonstrated the potential utility of machine learning (ML) and deep learning (DL) techniques as aids for radiologists to solve specific radiological challenges. The decision-making process, the establishment of specific clinical or radiological targets, the profile of the different professionals involved in the development of AI solutions, and the relation with partnerships and stakeholders are only some of the main issues that have to be faced and solved prior to starting the development of radiological AI solutions. Among all the players in this multidisciplinary team, the communication between radiologists and data scientists is essential for a successful collaborative work. There are specific skills that are inherent to radiological and medical training that are critical for identifying anatomical or clinical targets as well as for segmenting or labelling lesions. These skills would then have to be transferred, explained, and taught to the data science experts to facilitate their comprehension and integration into ML or DL algorithms. On the other hand, there is a wide range of complex software packages, deep neural-network architectures, and data transfer processes for which radiologists need the expertise of software engineers and data scientists in order to select the optimal manner to analyse and post-process this amount of data. This paper offers a summary of the top five challenges faced by radiologists and data scientists including tips and tricks to build a successful AI team.

Cautiously optimistic: A survey of radiation oncology professionals' perceptions of automation in radiotherapy planning

INTRODUCTION

While there is evidence to show the positive effects of automation, the impact on radiation oncology professionals has been poorly considered. This study examined radiation oncology professionals' perceptions of automation in radiotherapy planning.

METHOD

An online survey link was sent to the chief radiation therapists (RT) of all Australian radiotherapy centres to be forwarded to RTs, medical physicists (MP) and radiation oncologists (RO) within their institution. The survey was open from May-July 2019.

RESULTS

Participants were 204 RTs, 84 MPs and 37 ROs (response rates ∼10% of the overall radiation oncology workforce). Respondents felt automation resulted in improvement in consistency in planning (90%), productivity (88%), quality of planning (57%), and staff focus on patient care (49%). When asked about perceived impact of automation, the responses were; will change the primary tasks of certain jobs (66%), will allow staff to do the remaining components of their job more effectively (51%), will eliminate jobs (20%), and will not have an impact on jobs (6%). 27% of respondents believe automation will reduce job satisfaction. 71% of respondents strongly agree/agree that automation will cause a loss of skills, while only 25% strongly agree/agree that the training and education tools in their department are sufficient.

CONCLUSION

Although the effect of automation is perceived positively, there are some concerns on loss of skillsets and the lack of training to maintain this. These results highlight the need for continued education to ensure that skills and knowledge are not lost with automation.

Noninvasive Determination of IDH and 1p19q Status of Lower-grade Gliomas Using MRI Radiomics: A Systematic Review

BACKGROUND

Determination of isocitrate dehydrogenase (IDH) status and, if IDH-mutant, assessing 1p19q codeletion are an important component of diagnosis of World Health Organization grades II/III or lower-grade gliomas. This has led to research into noninvasively correlating imaging features ("radiomics") with genetic status.

PURPOSE

Our aim was to perform a diagnostic test accuracy systematic review for classifying IDH and 1p19q status using MR imaging radiomics, to provide future directions for integration into clinical radiology.

DATA SOURCES

Ovid (MEDLINE), Scopus, and the Web of Science were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Diagnostic Test Accuracy guidelines.

STUDY SELECTION

Fourteen journal articles were selected that included 1655 lower-grade gliomas classified by their IDH and/or 1p19q status from MR imaging radiomic features.

DATA ANALYSIS

For each article, the classification of IDH and/or 1p19q status using MR imaging radiomics was evaluated using the area under curve or descriptive statistics. Quality assessment was performed with the Quality Assessment of Diagnostic Accuracy Studies 2 tool and the radiomics quality score.

DATA SYNTHESIS

The best classifier of IDH status was with conventional radiomics in combination with convolutional neural network-derived features (area under the curve  = 0.95, 94.4% sensitivity, 86.7% specificity). Optimal classification of 1p19q status occurred with texture-based radiomics (area under the curve  = 0.96, 90% sensitivity, 89% specificity).

LIMITATIONS

A meta-analysis showed high heterogeneity due to the uniqueness of radiomic pipelines.

CONCLUSIONS

Radiogenomics is a potential alternative to standard invasive biopsy techniques for determination of IDH and 1p19q status in lower-grade gliomas but requires translational research for clinical uptake.

Workload for radiologists during on-call hours: dramatic increase in the past 15 years

Background

The objective of this study is to investigate the workload for radiologists during on-call hours and to quantify the 15-year trend in a large general hospital in Western Europe.

Methods

Data regarding the number of X-ray, ultrasound and computed tomography (CT) studies during on-call hours (weekdays between 6.00 p.m. and 7.00 a.m., weekends, and national holidays) between 2006 and 2020 were extracted from the picture archiving and communication system. All studies were converted into relative value units (RVUs) to estimate the on-call workload. The Mann–Kendall test was performed to assess the temporal trend.

Results

The total RVUs during on-call hours showed a significant increase between 2006 and 2020 (Kendall's tau-b = 0.657, p = 0.001). The overall workload in terms of RVUs during on-call hours has quadrupled. The number of X-ray studies significantly decreased (Kendall's tau-b = − 0.433, p = 0.026), whereas the number of CT studies significantly increased (Kendall's tau-b = 0.875, p < 0.001) between 2006 and 2020. CT studies which increased by more than 500% between 2006 and 2020 are CT for head trauma, brain CTA, brain CTV, chest CT (for suspected pulmonary embolism), spinal CT, neck CT, pelvic CT, and CT for suspected aortic dissection. The number of ultrasound studies did not change significantly (Kendall's tau-b = 0.202, p = 0.298).

Conclusions

The workload for radiologists during on-call hours increased dramatically in the past 15 years. The growing amount of CT studies is responsible for this increase. Radiologist and technician workforce should be matched to this ongoing increasing trend to avoid potential burn-out and to maintain quality and safety of radiological care.

Perceptions of Artificial Intelligence Among Healthcare Staff: A Qualitative Survey Study

Objectives: The medical community is in agreement that artificial intelligence (AI) will have a radical impact on patient care in the near future. The purpose of this study is to assess the awareness of AI technologies among health professionals and to investigate their perceptions toward AI applications in medicine. Design: A web-based Google Forms survey was distributed via the Royal Free London NHS Foundation Trust e-newsletter. Setting: Only staff working at the NHS Foundation Trust received an invitation to complete the online questionnaire. Participants: 98 healthcare professionals out of 7,538 (response rate 1.3%; CI 95%; margin of error 9.64%) completed the survey, including medical doctors, nurses, therapists, managers, and others. Primary outcome: To investigate the prior knowledge of health professionals on the subject of AI as well as their attitudes and worries about its current and future applications. Results: 64% of respondents reported never coming across applications of AI in their work and 87% did not know the difference between machine learning and deep learning, although 50% knew at least one of the two terms. Furthermore, only 5% stated using speech recognition or transcription applications on a daily basis, while 63% never utilize them. 80% of participants believed there may be serious privacy issues associated with the use of AI and 40% considered AI to be potentially even more dangerous than nuclear weapons. However, 79% also believed AI could be useful or extremely useful in their field of work and only 10% were worried AI will replace them at their job. Conclusions: Despite agreeing on the usefulness of AI in the medical field, most health professionals lack a full understanding of the principles of AI and are worried about potential consequences of its widespread use in clinical practice. The cooperation of healthcare workers is crucial for the integration of AI into clinical practice and without it the NHS may miss out on an exceptionally rewarding opportunity. This highlights the need for better education and clear regulatory frameworks.

Do we still need breast cancer screening in the era of targeted therapies and precision medicine?

Breast cancer (BC) is the most common female cancer and the second cause of death among women worldwide. The 5-year relative survival rate recently improved up to 90% due to increased population coverage and women's attendance to organised mammography screening as well as to advances in therapies, especially systemic treatments. Screening attendance is associated with a mortality reduction of at least 30% and a 40% lower risk of advanced disease. The stage at diagnosis remains the strongest predictor of recurrences. Systemic treatments evolved dramatically over the last 20 years: aromatase inhibitors improved the treatment of early-stage luminal BC; targeted monoclonal antibodies changed the natural history of anti-human epidermal growth factor receptor 2-positive (HER2) disease; immunotherapy is currently investigated in patients with triple-negative BC; gene expression profiling is now used with the aim of personalising systemic treatments. In the era of precision medicine, it is a challenging task to define the relative contribution of early diagnosis by screening mammography and systemic treatments in determining BC survival. Estimated contributions before 2000 were 46% for screening and 54% for treatment advances and after 2000, 37% and 63%, respectively. A model showed that the 10-year recurrence rate would be 30% and 25% using respectively chemotherapy or novel treatments in the absence of screening, but would drop to 19% and 15% respectively if associated with mammography screening. Early detection per se has not a curative intent and systemic treatment has limited benefit on advanced stages. Both screening mammography and systemic therapies continue to positively contribute to BC prognosis.

Web-based study on Chinese dermatologists' attitudes towards artificial intelligence

Background

Artificial intelligence (AI) has become a powerful tool and is attracting more attention in the field of medicine. There are a number of AI studies focusing on skin diseases, and there are many AI products that have been applied in dermatology. However, the attitudes of dermatologists, specifically those from China, towards AI, is not clear as few, if any studies have focused on this issue.

Methods

A web-based questionnaire was designed by experts from the Chinese Skin Image Database (CSID) and published on the UMER Doctor platform (an online learning platform for dermatologists developed by the Shanghai Wheat Color Intelligent Technology Company, China). A total of 1,228 Chinese dermatologists were recruited and provided answers to the questionnaire online. The differences of dermatologists' attitudes towards AI among the different groups (stratified by age, gender, hospital level, education degree, professional title, and hospital ownership) were compared by using the Mann-Whitney U test and the Kruskal-Wallis H test. The correlations between stratified factors and dermatologists’ attitudes towards AI were calculated by using the Spearman’s rank correlation test. SPSS (version 22.0) was utilized for all analyses. A two-sided P value <0.05 was considered statistically significant in all analyses.

Results

A total of 1,228 Chinese dermatologists from 30 provinces, autonomous regions, municipalities, and other regions (including Hong Kong, Macau, and Taiwan) participated in this survey. The dermatologists who participated acquired AI-related information mainly through the Internet, meetings or forums, and 70.51% of participated dermatologists acquired AI-related information by two or more approaches. In total, 99.51% of participated dermatologists pay attention (general, passive-active, and active attention) to information pertaining to AI. Stratified analyses revealed statistically significant differences in their attention levels (unconcerned, general, passive-active, and active attention) to AI-related information by gender, hospital level, education degree, and professional title (P values ≤1.79E−02). In total, 95.36% of the participated dermatologists thought the role of AI to be in “assisting the daily diagnosis and treatment activities for dermatologists”. Stratified analyses about the thought of AI roles (unconcerned, useless, assist, and replace) showed that there was no statistically significant difference except for the hospital level (P value =4.09E−03). The correlations between stratified factors with attention levels and the opinions of AI roles showed extremely weak correlations. Furthermore, 64.17% of participated dermatologists thought secondary hospitals in China are in most need of the application AI, and 91.78% of participated dermatologists thought the priority implementation of AI should be in skin tumors.

Conclusions

The majority of Chinese dermatologists are interested in AI information and acquired information about AI through a variety of approaches. Nearly all dermatologists are attentive to information on AI and think the role of AI is in “assisting the daily diagnosis and treatment activities for dermatologists”. Future AI implementation should be primarily focused on skin tumors and utilized in in secondary hospitals.

Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors

Objective

The objective was to identify barriers and facilitators to the implementation of artificial intelligence (AI) applications in clinical radiology in The Netherlands.

Materials and methods

Using an embedded multiple case study, an exploratory, qualitative research design was followed. Data collection consisted of 24 semi-structured interviews from seven Dutch hospitals. The analysis of barriers and facilitators was guided by the recently published Non-adoption, Abandonment, Scale-up, Spread, and Sustainability (NASSS) framework for new medical technologies in healthcare organizations.

Results

Among the most important facilitating factors for implementation were the following: (i) pressure for cost containment in the Dutch healthcare system, (ii) high expectations of AI’s potential added value, (iii) presence of hospital-wide innovation strategies, and (iv) presence of a “local champion.” Among the most prominent hindering factors were the following: (i) inconsistent technical performance of AI applications, (ii) unstructured implementation processes, (iii) uncertain added value for clinical practice of AI applications, and (iv) large variance in acceptance and trust of direct (the radiologists) and indirect (the referring clinicians) adopters.

Conclusion

In order for AI applications to contribute to the improvement of the quality and efficiency of clinical radiology, implementation processes need to be carried out in a structured manner, thereby providing evidence on the clinical added value of AI applications.

Key Points

• Successful implementation of AI in radiology requires collaboration between radiologists and referring clinicians.

• Implementation of AI in radiology is facilitated by the presence of a local champion.

• Evidence on the clinical added value of AI in radiology is needed for successful implementation.

Electronic supplementary material

The online version of this article (10.1007/s00330-020-06946-y) contains supplementary material, which is available to authorized users.

MRI radiomics-based machine-learning classification of bone chondrosarcoma

PURPOSE

To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI).

METHODS

We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group.

RESULTS

After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453).

CONCLUSIONS

Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.

Artificial intelligence: radiologists' expectations and opinions gleaned from a nationwide online survey

PURPOSE

To report the results of a nationwide online survey on artificial intelligence (AI) among radiologist members of the Italian Society of Medical and Interventional Radiology (SIRM).

METHODS AND MATERIALS

All members were invited to the survey as an initiative by the Imaging Informatics Chapter of SIRM. The survey consisted of 13 questions about the participants' demographic information, perceived advantages and issues related to AI implementation in radiological practice, and their overall opinion about AI.

RESULTS

In total, 1032 radiologists (equaling 9.5% of active SIRM members for the year 2019) joined the survey. Perceived AI advantages included a lower diagnostic error rate (750/1027, 73.0%) and optimization of radiologists' work (697/1027, 67.9%). The risk of a poorer professional reputation of radiologists compared with non-radiologists (617/1024, 60.3%), and increased costs and workload due to AI system maintenance and data analysis (399/1024, 39.0%) were seen as potential issues. Most radiologists stated that specific policies should regulate the use of AI (933/1032, 90.4%) and were not afraid of losing their job due to it (917/1032, 88.9%). Overall, 77.0% of respondents (794/1032) were favorable to the adoption of AI, whereas 18.0% (186/1032) were uncertain and 5.0% (52/1032) were unfavorable.

CONCLUSIONS

Radiologists had a mostly positive attitude toward the implementation of AI in their working practice. They were not concerned that AI will replace them, but rather that it might diminish their professional reputation.

Exploring the Role of Artificial Intelligence in an Emergency and Trauma Radiology Department

Emergency and trauma radiologists, emergency department’s physicians and nurses, researchers, departmental leaders, and health policymakers have attempted to discover efficient approaches to enhance the provision of quality patient care. There are increasing expectations for radiology practices to deliver a dedicated emergency radiology service providing 24/7/365 on-site attending radiologist coverage. Emergency radiologists (ERs) are pressed to meet the demand of increased imaging volume, provide accurate reports, maintain a lower proportion of discrepancy rate, and with a rapid report turnaround time of finalized reports. Thus, rendering the radiologists overburdened. The demand for an increased efficiency in providing quality care to acute patients has led to the emergence of artificial intelligence (AI) in the field. AI can be used to assist emergency and trauma radiologists deal with the ever-increasing imaging volume and workload, as AI methods have typically demonstrated a variety of applications in medical image analysis and interpretation, albeit most programs are in a training or validation phase. This article aims to offer an evidence-based discourse about the evolving role of artificial intelligence in assisting the imaging pathway in an emergency and trauma radiology department. We hope to generate a multidisciplinary discourse that addresses the technical processes, the challenges in the labour-intensive process of training, validation and testing of an algorithm, the need for emphasis on ethics, and how an emergency radiologist’s role is pivotal in the execution of AI-guided systems within the context of an emergency and trauma radiology department. This exploratory narrative serves the present-day health leadership’s information needs by proposing an AI supported and radiologist centered framework depicting the work flow within a department. It is suspected that the use of such a framework, if efficacious, could provide considerable benefits for patient safety and quality of care provided. Additionally, alleviating radiologist burnout and decreasing healthcare costs over time.