51
|
Biddle G, Assadsangabi R, Broadhead K, Hacein-Bey L, Ivanovic V. Diagnostic Errors in Cerebrovascular Pathology: Retrospective Analysis of a Neuroradiology Database at a Large Tertiary Academic Medical Center. AJNR Am J Neuroradiol 2022; 43:1271-1278. [PMID: 35926887 PMCID: PMC9451623 DOI: 10.3174/ajnr.a7596] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2021] [Accepted: 06/16/2022] [Indexed: 01/26/2023]
Abstract
BACKGROUND AND PURPOSE Diagnostic errors affect 2%-8% of neuroradiology studies, resulting in significant potential morbidity and mortality. This retrospective analysis of a large database at a single tertiary academic institution focuses on diagnostic misses in cerebrovascular pathology and suggests error-reduction strategies. MATERIALS AND METHODS CT and MR imaging reports from a consecutive database spanning 2015-2020 were searched for errors of attending physicians in cerebrovascular pathology. Data were collected on missed findings, study types, and interpretation settings. Errors were categorized as ischemic, arterial, venous, hemorrhagic, and "other." RESULTS A total of 245,762 CT and MR imaging neuroradiology examinations were interpreted during the study period. Vascular diagnostic errors were present in 165 reports, with a mean of 49.6 (SD, 23.3) studies on the shifts when an error was made, compared with 34.9 (SD, 19.2) on shifts without detected errors (P < .0001). Seventy percent of examinations occurred in the hospital setting; 93.3% of errors were perceptual; 6.7% were interpretive; and 93.9% (n = 155) were clinically significant (RADPEER 2B or 3B). The distribution of errors was arterial and ischemic each with 33.3%, hemorrhagic with 21.8%, and venous with 7.5%. Most errors involved brain MR imaging (30.3%) followed by head CTA (27.9%) and noncontrast head CT (26.1%). The most common misses were acute/subacute infarcts (25.1%), followed by aneurysms (13.7%) and subdural hematomas (9.7%). CONCLUSIONS Most cerebrovascular diagnostic errors were perceptual and clinically significant, occurred in the emergency/inpatient setting, and were associated with higher-volume shifts. Diagnostic errors could be minimized by adjusting search patterns to ensure vigilance on the sites of the frequently missed pathologies.
Collapse
Affiliation(s)
- G Biddle
- From the Neuroradiology Division (G.B., L.H.-B.), Department of Radiology, University of California Davis School of Medicine, Sacramento, California
| | - R Assadsangabi
- Neuroradiology Division (R.A.), Department of Radiology, University of Southern California, Los Angeles, California
| | - K Broadhead
- Department of Statistics (K.B.), University of California Davis, Davis, California
| | - L Hacein-Bey
- From the Neuroradiology Division (G.B., L.H.-B.), Department of Radiology, University of California Davis School of Medicine, Sacramento, California
| | - V Ivanovic
- Neuroradiology division (V.I.), Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin
| |
Collapse
|
52
|
Kerr KF, Longton GM, Reisch LM, Radick AC, Eguchi MM, Shucard HL, Pepe MS, Piepkorn MW, Elder DE, Barnhill RL, Elmore JG. Histopathological diagnosis of cutaneous melanocytic lesions: blinded and nonblinded second opinions offer similar improvement in diagnostic accuracy. Clin Exp Dermatol 2022; 47:1658-1665. [PMID: 35426450 PMCID: PMC9391266 DOI: 10.1111/ced.15219] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 04/12/2022] [Indexed: 11/30/2022]
Abstract
BACKGROUND Previous studies of second opinions in the diagnosis of melanocytic skin lesions have examined blinded second opinions, which do not reflect usual clinical practice. The current study, conducted in the USA, investigated both blinded and nonblinded second opinions for their impact on diagnostic accuracy. METHODS In total, 100 melanocytic skin biopsy cases, ranging from benign to invasive melanoma, were interpreted by 74 dermatopathologists. Subsequently, 151 dermatopathologists performed nonblinded second and third reviews. We compared the accuracy of single reviewers, second opinions obtained from independent, blinded reviewers and second opinions obtained from sequential, nonblinded reviewers. Accuracy was defined with respect to a consensus reference diagnosis. RESULTS The mean case-level diagnostic accuracy of single reviewers was 65.3% (95% CI 63.4-67.2%). Second opinions arising from sequential, nonblinded reviewers significantly improved accuracy to 69.9% (95% CI 68.0-71.7%; P < 0.001). Similarly, second opinions arising from blinded reviewers improved upon the accuracy of single reviewers (69.2%; 95% CI 68.0-71.7%). Nonblinded reviewers were more likely than blinded reviewers to give diagnoses in the same diagnostic classes as the first diagnosis. Nonblinded reviewers tended to be more confident when they agreed with previous reviewers, even with inaccurate diagnoses. CONCLUSION We found that both blinded and nonblinded second reviewers offered a similar modest improvement in diagnostic accuracy compared with single reviewers. Obtaining second opinions with knowledge of previous reviews tends to generate agreement among reviews, and may generate unwarranted confidence in an inaccurate diagnosis. Combining aspects of both blinded and nonblinded review in practice may leverage the advantages while mitigating the disadvantages of each approach. Specifically, a second pathologist could give an initial diagnosis blinded to the results of the first pathologist, with subsequent nonblinded discussion between the two pathologists if their diagnoses differ.
Collapse
Affiliation(s)
- Kathleen F Kerr
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Gary M Longton
- Program in Biostatistics, Division of Public Health Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Lisa M Reisch
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Andrea C Radick
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Megan M Eguchi
- Department of Medicine, University of California, Los Angeles, David Geffen School of Medicine, Los Angeles, CA, USA
| | - Hannah L Shucard
- Department of Biostatistics, University of Washington, Seattle, WA, USA
| | - Margaret S Pepe
- Program in Biostatistics, Division of Public Health Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA
| | - Michael W Piepkorn
- Division of Dermatology, Department of Medicine, University of Washington School of Medicine, Seattle, WA, USA
- Dermatopathology Northwest, Bellevue, WA, USA
| | - David E Elder
- Department of Pathology and Laboratory Medicine, Hospital of the University of Pennsylvania, Philadelphia, PA, USA
| | - Raymond L Barnhill
- Department of Translational Research, Institut Curie, Paris, France
- UFR of Medicine, University of Paris, Paris, France
| | - Joann G Elmore
- Department of Medicine, University of California, Los Angeles, David Geffen School of Medicine, Los Angeles, CA, USA
| |
Collapse
|
53
|
Possible Bias in Supervised Deep Learning Algorithms for CT Lung Nodule Detection and Classification. Cancers (Basel) 2022; 14:cancers14163867. [PMID: 36010861 PMCID: PMC9405732 DOI: 10.3390/cancers14163867] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2022] [Revised: 07/22/2022] [Accepted: 07/22/2022] [Indexed: 11/25/2022] Open
Abstract
Simple Summary Artificial Intelligence (AI) algorithms can assist clinicians in their daily tasks by automatically detecting and/or classifying nodules in chest CT scans. Bias of such algorithms is one of the reasons why implementation of them in clinical practice is still not widely adopted. There is no published review on the bias that these algorithms may contain. This review aims to present different types of bias in such algorithms and present possible ways to mitigate them. Only then it would be possible to ensure that these algorithms work as intended under many different clinical settings. Abstract Artificial Intelligence (AI) algorithms for automatic lung nodule detection and classification can assist radiologists in their daily routine of chest CT evaluation. Even though many AI algorithms for these tasks have already been developed, their implementation in the clinical workflow is still largely lacking. Apart from the significant number of false-positive findings, one of the reasons for that is the bias that these algorithms may contain. In this review, different types of biases that may exist in chest CT AI nodule detection and classification algorithms are listed and discussed. Examples from the literature in which each type of bias occurs are presented, along with ways to mitigate these biases. Different types of biases can occur in chest CT AI algorithms for lung nodule detection and classification. Mitigation of them can be very difficult, if not impossible to achieve completely.
Collapse
|
54
|
Influence of Prior Imaging Information on Diagnostic Accuracy for Focal Skeletal Processes—A Retrospective Analysis of the Consistency between Biopsy-Verified Imaging Diagnoses. Diagnostics (Basel) 2022; 12:diagnostics12071735. [PMID: 35885639 PMCID: PMC9319824 DOI: 10.3390/diagnostics12071735] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2022] [Revised: 07/14/2022] [Accepted: 07/15/2022] [Indexed: 12/03/2022] Open
Abstract
Introduction: Comparing imaging examinations with those previously obtained is considered mandatory in imaging guidelines. To our knowledge, no studies are available on neither the influence, nor the sequence, of prior imaging and reports on diagnostic accuracy using biopsy as the reference standard. Such data are important to minimize diagnostic errors and to improve the preparation of diagnostic imaging guidelines. The aim of our study was to provide such data. Materials and methods: A retrospective cohort of 216 consecutive skeletal biopsies from patients with at least 2 different imaging modalities (X-ray, CT and MRI) performed within 6 months of biopsy was identified. The diagnostic accuracy of the individual imaging modality was assessed. Finally, the possible influence of the sequence of imaging modalities was investigated. Results: No significant difference in the accuracy of the imaging modalities was shown, being preceded by another imaging modality or not. However, the sequence analyses indicate sequential biases, particularly if MRI was the first imaging modality. Conclusion: The sequence of the imaging modalities seems to influence the diagnostic accuracy against a pathology reference standard. Further studies are needed to establish evidence-based guidelines for the strategy of using previous imaging and reports to improve diagnostic accuracy.
Collapse
|
55
|
Dempsey PJ, Murphy MC, Marnane M, Murphy S, Kavanagh EC. MRA-detected intracranial atherosclerotic disease in patients with TIA and minor stroke. Ir J Med Sci 2022:10.1007/s11845-022-03094-8. [PMID: 35840826 DOI: 10.1007/s11845-022-03094-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2021] [Accepted: 07/06/2022] [Indexed: 10/17/2022]
Abstract
OBJECTIVES Patients with TIA and minor stroke commonly undergo CT and CTA in the emergency department with subsequent MRI with MRA for further workup. The purpose of this study was to review outpatient MRIs for TIA/stroke patients to assess the additional benefit, if any, of the MRA sequence in the detection of intracranial atherosclerotic disease in patients for whom CTA had already been performed. METHODS The radiology reports of outpatient MRIs of the brain for TIA/minor stroke patients were retrospectively reviewed via the hospital PACS system. Following this, the imaging report from the patient's initial presentation to the emergency department was reviewed. This index imaging and subsequent MRI were compared to assess the incidence of new vascular findings detected on the MRA sequence in patients for whom CTA had already been performed. Where new lesions had been identified at follow-up, the imaging was retroactively reviewed to assess if they were present on the index imaging. RESULTS Two hundred seven consecutive patients were reviewed. Significant (> 50%) intracranial atherosclerotic disease was present on MRA in 18 patients (8.7%). This was a new finding in 11 patients. Five had initial CTA where the atherosclerosis was not detected. All 5 of these cases were located in the posterior cerebral arteries. Incidental aneurysms were seen in 14 (6.7%); 12 were a new finding at time of MRI. CONCLUSION The MRA sequence provides additional value by increasing the detection of clinically important intracranial atherosclerotic disease which may inform management in patients with minor stroke and TIA.
Collapse
Affiliation(s)
- Philip J Dempsey
- Department of Radiology, Mater Misericordiae University Hospital, Eccles Street, Dublin 7, Ireland.
| | - Mark C Murphy
- Department of Radiology, Mater Misericordiae University Hospital, Eccles Street, Dublin 7, Ireland
| | - Michael Marnane
- Stroke Department, Dublin Neurovascular Institute, Mater Misericordiae University Hospital, Eccles Street, Dublin 7, Ireland
| | - Sean Murphy
- Stroke Department, Dublin Neurovascular Institute, Mater Misericordiae University Hospital, Eccles Street, Dublin 7, Ireland
| | - Eoin C Kavanagh
- Department of Radiology, Mater Misericordiae University Hospital, Eccles Street, Dublin 7, Ireland
| |
Collapse
|
56
|
Patterns of Screening Recall Behavior Among Subspecialty Breast Radiologists. Acad Radiol 2022; 30:798-806. [PMID: 35803888 DOI: 10.1016/j.acra.2022.06.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Revised: 05/22/2022] [Accepted: 06/08/2022] [Indexed: 11/22/2022]
Abstract
RATIONALE AND OBJECTIVES Determine whether there are patterns of lesion recall among breast imaging subspecialists interpreting screening mammography, and if so, whether recall patterns correlate to morphologies of screen-detected cancers. MATERIALS AND METHODS This Institutional Review Board-approved, retrospective review included all screening examinations January 3, 2012-October 1, 2018 interpreted by fifteen breast imaging subspecialists at a large academic medical center and two outpatient imaging centers. Natural language processing identified radiologist recalls by lesion type (mass, calcifications, asymmetry, architectural distortion); proportions of callbacks by lesion types were calculated per radiologist. Hierarchical cluster analysis grouped radiologists based on recall patterns. Groups were compared to overall practice and each other by proportions of lesion types recalled, and overall and lesion-specific positive predictive value-1 (PPV1). RESULTS Among 161,859 screening mammograms with 13,086 (8.1%) recalls, Hierarchical cluster analysis grouped 15 radiologists into five groups. There was substantial variation in proportions of lesions recalled: calcifications 13%-18% (Chi-square 45.69, p < 0.00001); mass 16%-44% (Chi-square 498.42, p < 0.00001); asymmetry 13%-47% (Chi-square 660.93, p < 0.00001) architectural distortion 6%-20% (Chi-square 283.81, p < 0.00001). Radiologist groups differed significantly in overall PPV1 (range 5.6%-8.8%; Chi-square 17.065, p = 0.0019). PPV1 by lesion type varied among groups: calcifications 9.2%-15.4% (Chi-square 2.56, p = 0.6339); mass 5.6%-8.5% (Chi-square 1.31, p = 0.8597); asymmetry 3.4%-5.9% (Chi-square 2.225, p = 0.6945); architectural distortion 5.6%-10.8% (Chi-square 5.810, p = 0.2138). Proportions of recalled lesions did not consistently correlate to proportions of screen-detected cancer. CONCLUSION Breast imaging subspecialists have patterns for screening mammography recalls, suggesting differential weighting of imaging findings for perceived malignant potential. Radiologist recall patterns are not always predictive of screen-detected cancers nor lesion-specific PPV1s.
Collapse
|
57
|
Glick A, Clayton M, Angelov N, Chang J. Impact of explainable artificial intelligence assistance on clinical decision-making of novice dental clinicians. JAMIA Open 2022; 5:ooac031. [PMID: 35651525 PMCID: PMC9150075 DOI: 10.1093/jamiaopen/ooac031] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 03/09/2022] [Accepted: 04/28/2022] [Indexed: 11/18/2022] Open
Abstract
Objective Despite artificial intelligence (AI) being used increasingly in healthcare, implementation challenges exist leading to potential biases during the clinical decision process of the practitioner. The interaction of AI with novice clinicians was investigated through an identification task, an important component of diagnosis, in dental radiography. The study evaluated the performance, efficiency, and confidence level of dental students on radiographic identification of furcation involvement (FI), with and without AI assistance. Materials and Methods Twenty-two third- and 19 fourth-year dental students (DS3 and DS4, respectively) completed remotely administered surveys to identify FI lesions on a series of dental radiographs. The control group received radiographs without AI assistance while the test group received the same radiographs and AI-labeled radiographs. Data were appropriately analyzed using the Chi-square, Fischer's exact, analysis of variance, or Kruskal-Wallis tests. Results Performance between groups with and without AI assistance was not statistically significant except for 1 question where tendency was to err with AI-generated answer (P < .05). The efficiency of task completion and confidence levels was not statistically significant between groups. However, both groups with and without AI assistance believed the use of AI would improve the clinical decision-making. Discussion Dental students detecting FI in radiographs with AI assistance had a tendency towards over-reliance on AI. Conclusion AI input impacts clinical decision-making, which might be particularly exaggerated in novice clinicians. As it is integrated into routine clinical practice, caution must be taken to prevent overreliance on AI-generated information.
Collapse
Affiliation(s)
- Aaron Glick
- General Practice and Dental Public Health, University of Texas Health Science Center at Houston School of Dentistry, Houston, Texas, USA
- Primary Care and Clinical Medicine, Sam Houston State University College of Osteopathic Medicine, Conroe, Texas, USA
| | - Mackenzie Clayton
- University of Texas Health Science Center at Houston School of Dentistry, Houston, Texas, USA
| | - Nikola Angelov
- Periodontics and Dental Hygiene, University of Texas Health Science Center at Houston School of Dentistry, Houston, Texas, USA
| | - Jennifer Chang
- Periodontics and Dental Hygiene, University of Texas Health Science Center at Houston School of Dentistry, Houston, Texas, USA
| |
Collapse
|
58
|
Nadkarni P, Merchant SA. Enhancing medical-imaging artificial intelligence through holistic use of time-tested key imaging and clinical parameters: Future insights. Artif Intell Med Imaging 2022; 3:55-69. [DOI: 10.35711/aimi.v3.i3.55] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 04/12/2022] [Accepted: 06/17/2022] [Indexed: 02/06/2023] Open
Abstract
Much of the published literature in Radiology-related Artificial Intelligence (AI) focuses on single tasks, such as identifying the presence or absence or severity of specific lesions. Progress comparable to that achieved for general-purpose computer vision has been hampered by the unavailability of large and diverse radiology datasets containing different types of lesions with possibly multiple kinds of abnormalities in the same image. Also, since a diagnosis is rarely achieved through an image alone, radiology AI must be able to employ diverse strategies that consider all available evidence, not just imaging information. Using key imaging and clinical signs will help improve their accuracy and utility tremendously. Employing strategies that consider all available evidence will be a formidable task; we believe that the combination of human and computer intelligence will be superior to either one alone. Further, unless an AI application is explainable, radiologists will not trust it to be either reliable or bias-free; we discuss some approaches aimed at providing better explanations, as well as regulatory concerns regarding explainability (“transparency”). Finally, we look at federated learning, which allows pooling data from multiple locales while maintaining data privacy to create more generalizable and reliable models, and quantum computing, still prototypical but potentially revolutionary in its computing impact.
Collapse
Affiliation(s)
- Prakash Nadkarni
- College of Nursing, University of Iowa, Iowa City, IA 52242, United States
| | - Suleman Adam Merchant
- Department of Radiology, LTM Medical College & LTM General Hospital, Mumbai 400022, Maharashtra, India
| |
Collapse
|
59
|
Mewes A, Burg S, Brademann G, Dambon JA, Hey M. Quality-assured training in the evaluation of cochlear implant electrode position: a prospective experimental study. BMC MEDICAL EDUCATION 2022; 22:386. [PMID: 35596162 PMCID: PMC9121556 DOI: 10.1186/s12909-022-03464-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Accepted: 05/13/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND The objective of this study was to demonstrate the utility of an approach in training predoctoral medical students, to enable them to measure electrode-to-modiolus distances (EMDs) and insertion-depth angles (aDOIs) in cochlear implant (CI) imaging at the performance level of a single senior rater. METHODS This prospective experimental study was conducted on a clinical training dataset comprising patients undergoing cochlear implantation with a Nucleus® CI532 Slim Modiolar electrode (N = 20) or a CI512 Contour Advance electrode (N = 10). To assess the learning curves of a single medical student in measuring EMD and aDOI, interrater differences (senior-student) were compared with the intrarater differences of a single senior rater (test-retest). The interrater and intrarater range were both calculated as the distance between the 0.1th and 99.9th percentiles. A "deliberate practice" training approach was used to teach knowledge and skills, while correctives were applied to minimize faulty data-gathering and data synthesis. RESULTS Intrarater differences of the senior rater ranged from - 0.5 to 0.5 mm for EMD and - 14° to 16° for aDOI (respective medians: 0 mm and 0°). Use of the training approach led to interrater differences that matched this after the 4th (EMD) and 3rd (aDOI) feedback/measurement series had been provided to the student. CONCLUSIONS The training approach enabled the student to evaluate the CI electrode position at the performance level of a senior rater. This finding may offer a basis for ongoing clinical quality assurance for the assessment of CI electrode position.
Collapse
Affiliation(s)
- Alexander Mewes
- Universitätsklinikum Schleswig-Holstein (UKSH), Campus Kiel, Department of Otorhinolaryngology, Head and Neck Surgery, Kiel, Germany.
| | - Sebastian Burg
- Christian-Albrechts-Universität (CAU) zu Kiel, Faculty of Medicine, Kiel, Germany
| | - Goetz Brademann
- Universitätsklinikum Schleswig-Holstein (UKSH), Campus Kiel, Department of Otorhinolaryngology, Head and Neck Surgery, Kiel, Germany
| | - Jan Andreas Dambon
- Universitätsklinikum Schleswig-Holstein (UKSH), Campus Kiel, Department of Otorhinolaryngology, Head and Neck Surgery, Kiel, Germany
| | - Matthias Hey
- Universitätsklinikum Schleswig-Holstein (UKSH), Campus Kiel, Department of Otorhinolaryngology, Head and Neck Surgery, Kiel, Germany
| |
Collapse
|
60
|
Kwok HCK, Brady MS, Agaram NP, Hwang S. Test yourself: Recurrent right groin lump. Skeletal Radiol 2022; 51:1099-1101. [PMID: 34825258 DOI: 10.1007/s00256-021-03964-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/13/2021] [Revised: 11/17/2021] [Accepted: 11/19/2021] [Indexed: 02/02/2023]
Affiliation(s)
- Henry Chi Kit Kwok
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA.
| | - Mary Susan Brady
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Narasimhan P Agaram
- Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, NY, USA
| | - Sinchun Hwang
- Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Ave, New York, NY, 10065, USA
| |
Collapse
|
61
|
Santos ÁM. Gestión de riesgos del informe radiológico. Especial referencia al error diagnóstico. RADIOLOGIA 2022. [DOI: 10.1016/j.rx.2022.01.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
62
|
Claus CMP, Cavalieiri M, Malcher F, Trippia C, Eiras-Araujo AL, Pauli E, Cavazzola LT. DECOMP Report: Answers surgeons expect from an abdominal wall imaging exam. Rev Col Bras Cir 2022; 49:e20223172. [PMID: 35588534 PMCID: PMC10578831 DOI: 10.1590/0100-6991e-20223172en] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2021] [Accepted: 11/03/2021] [Indexed: 11/22/2022] Open
Abstract
Abdominal wall (AW) hernias are a common problem faced by general surgeons. With an essentially clinical diagnosis, abdominal hernias have been considered a simple problem to be repaired. However, long-term follow-up of patients has shown disappointing results, both in terms of complications and recurrence. In this context, preoperative planning with control of comorbidities and full knowledge of the hernia and its anatomical relationships with the AW has gained increasing attention. Computed tomography (CT) appears to be the best option to determine the precise size and location of abdominal hernias, presence of rectus diastase and/or associated muscle atrophy, as well as the proportion of the hernia in relation to the AW itself. This information might help the surgeon to choose the best surgical technique (open vs MIS), positioning and fixation of the meshes, and eventual need for application of botulinum toxin, preoperative pneumoperitoneum or component separation techniques. Despite the relevance of the findings, they are rarely described in CT scans as radiologists are not used to report findings of the AW as well as to know what information is really needed. For these reasons, we gathered a group of surgeons and radiologists to establish which information about the AW is important in a CT. Finally, a structured report is proposed to facilitate the description of the findings and their interpretation.
Collapse
Affiliation(s)
| | - Marcio Cavalieiri
- - Hospital Municipal Lourenço Jorge, Clínica Cirúrgica - Rio de Janeiro - RJ - Brasil
| | - Flávio Malcher
- - New York University Grossman School of Medicine, Abdominal Core Health - New York - NY - Estados Unidos
| | - Carlos Trippia
- - Hospital Nossa Senhora das Graças, Radiologia - Curitiba - PR - Brasil
| | - Antonio Luis Eiras-Araujo
- - Universidade Federal do Rio de Janeiro e Instituto D'Or de Ensino e Pesquisa, Radiologia - Rio de Janeiro - RJ - Brasil
| | - Eric Pauli
- - Penn State Hershey Medical Center, Minimally Invasive and Bariatric Surgery - Hershey - PA - Estados Unidos
| | | |
Collapse
|
63
|
Cognitive Bias and Diagnostic Errors among Physicians in Japan: A Self-Reflection Survey. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19084645. [PMID: 35457511 PMCID: PMC9032995 DOI: 10.3390/ijerph19084645] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Received: 01/26/2022] [Revised: 04/01/2022] [Accepted: 04/06/2022] [Indexed: 02/01/2023]
Abstract
This cross-sectional study aimed to clarify how cognitive biases and situational factors related to diagnostic errors among physicians. A self-reflection questionnaire survey on physicians’ most memorable diagnostic error cases was conducted at seven conferences: one each in Okayama, Hiroshima, Matsue, Izumo City, and Osaka, and two in Tokyo. Among the 147 recruited participants, 130 completed and returned the questionnaires. We recruited primary care physicians working in various specialty areas and settings (e.g., clinics and hospitals). Results indicated that the emergency department was the most common setting (47.7%), and the highest frequency of errors occurred during night-time work. An average of 3.08 cognitive biases was attributed to each error. The participants reported anchoring bias (60.0%), premature closure (58.5%), availability bias (46.2%), and hassle bias (33.1%), with the first three being most frequent. Further, multivariate logistic regression analysis for cognitive bias showed that emergency room care can easily induce cognitive bias (adjusted odds ratio 3.96, 95% CI 1.16−13.6, p-value = 0.028). Although limited to a certain extent by its sample collection, due to the sensitive nature of information regarding physicians’ diagnostic errors, this study nonetheless shows correlations with environmental factors (emergency room care situations) that induce cognitive biases which, in turn, cause diagnostic errors.
Collapse
|
64
|
Learning from errors: Implementation of a resident-oriented radiology morbidity and mortality conference as an educational tool. Clin Imaging 2022; 84:98-103. [DOI: 10.1016/j.clinimag.2022.01.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2021] [Revised: 12/20/2021] [Accepted: 01/24/2022] [Indexed: 11/19/2022]
|
65
|
Reid A, Weig E, Dickinson K, Zafar F, Abid R, VanBeek M, Ferguson N. Hiding in Plain Sight: A Retrospective Review of Unrecognized Tumors During Dermatologic Surgery. Cureus 2022; 14:e23487. [PMID: 35475096 PMCID: PMC9035314 DOI: 10.7759/cureus.23487] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 03/24/2022] [Indexed: 12/01/2022] Open
Abstract
Background: Mohs micrographic surgery requires focused attention that may lead to tunnel vision bias, contributing to not recognizing skin cancer at nearby sites. Objective: It is to determine if a subsequently diagnosed skin cancer was visible at the time of Mohs surgery. Methods: A retrospective chart review was performed at a single academic center from 2008 to 2020. Patients who underwent at least two distinct MMS procedures, separated in time to capture subsequent tumors, were included. Results: Four hundred and four individual patients were identified with at least two distinct Mohs procedures, which generated 1,110 Mohs sequences. Fifty-one (4.6%) clinically apparent tumors went unrecognized and 127 (11.4%) tumors were identified and biopsied during the visit. High-risk tumor histology was identified in 10 (20%) unrecognized tumors and 31 (24%) recognized tumors (p-value 0.491). Conclusion: Our study suggests that Mohs surgeons may be overlooking adjacent skin cancers when focusing only on the tumor being surgically treated. Tunnel vision bias may account for part of this phenomenon.
Collapse
|
66
|
Kerr MV, Bryden P, Nguyen ET. Diagnostic Imaging and Mechanical Objectivity in Medicine. Acad Radiol 2022; 29:409-412. [PMID: 33485774 DOI: 10.1016/j.acra.2020.12.017] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2020] [Revised: 12/29/2020] [Accepted: 12/31/2020] [Indexed: 11/01/2022]
Abstract
BACKGROUND Before the advent of automatism in image-making practices, scientists, anatomists, and physicians artistically depicted simplified images for scientific atlas making. This technique conferred subjectivity to a supposedly objective scientific process, sparking confrontations between anatomists regarding accuracy that heralded a new concept in the late 19th century - mechanical objectivity - that would revolutionize scientific knowledge and the field of medicine OBJECTIVES: The purpose of this health history research study is to trace the evolution of mechanical objectivity from empirical studies of early anatomists in the 19th century to the advent of x-ray technology, digitization of imaging, and disruptive technological innovations such as artificial intelligence, while simultaneously unveiling the challenges of mitigating human bias, despite advancements in medical imaging practices. METHODS This narrative literature review was conducted using the Scopus® database under the guidance of both medical historians and practicing physicians to ensure its applicability and historical accuracy CONCLUSION: Despite a century-long quest for optimizing mechanical objectivity in diagnostic imaging to more accurately and efficiently interpret medical images, human bias remains an important factor. This historical review describes the development of medical imaging technologies over the last century with emphasis on the role played by human bias and subjectivity in a rapidly expanding field of medical imaging technology including artificial intelligence.
Collapse
|
67
|
Sayyouh MMH, Sella EC, Shankar PR, Marshall GE, Quint LE, Agarwal PP. Lessons Learned from Peer Learning Conference in Cardiothoracic Radiology. Radiographics 2022; 42:579-593. [PMID: 35148241 DOI: 10.1148/rg.210125] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/11/2022]
Abstract
Medical errors may lead to patient harm and may also have a devastating effect on medical providers, who may suffer from guilt and the personal impact of a given error (second victim experience). While it is important to recognize and remedy errors, it should be done in a way that leads to long-standing practice improvement and focuses on systems-level opportunities rather than in a punitive fashion. Traditional peer review systems are score based and have some undesirable attributes. The authors discuss the differences between traditional peer review systems and peer learning approaches and offer practical suggestions for transitioning to peer learning conferences. Peer learning conferences focus on learning opportunities and embrace errors as an opportunity to learn. The authors also discuss various types and sources of errors relevant to the practice of radiology and how discussions in peer learning conferences can lead to widespread system improvement. In the authors' experience, these strategies have resulted in practice improvement not only at a division level in radiology but in a broader multidisciplinary setting as well. The online slide presentation from the RSNA Annual Meeting is available for this article. ©RSNA, 2022.
Collapse
Affiliation(s)
- Mohamed M H Sayyouh
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| | - Edith C Sella
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| | - Prasad R Shankar
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| | - Giselle E Marshall
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| | - Leslie E Quint
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| | - Prachi P Agarwal
- From the Cardiothoracic Imaging Division, Department of Radiology, University of Michigan, Taubman Center B1-132D, 1500 E Medical Center Dr, Ann Arbor, MI 48109-5302 (M.M.H.S., E.C.S., G.E.M., L.E.Q., P.P.A.); and Abdominal Imaging Division and Michigan Radiology Quality Collaborative, Department of Radiology, University of Michigan, Ann Arbor, Mich (P.R.S.)
| |
Collapse
|
68
|
The Role of Intuitive Cognition in Radiologic Decision Making. J Am Coll Radiol 2022; 19:669-676. [DOI: 10.1016/j.jacr.2022.02.027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Accepted: 02/19/2022] [Indexed: 11/19/2022]
|
69
|
Jaspan O, Wysocka A, Sanchez C, Schweitzer AD. Improving the Relationship Between Confidence and Competence: Implications for Diagnostic Radiology Training From the Psychology and Medical Literature. Acad Radiol 2022; 29:428-438. [PMID: 33408052 DOI: 10.1016/j.acra.2020.12.006] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2020] [Revised: 11/23/2020] [Accepted: 12/11/2020] [Indexed: 12/24/2022]
Abstract
The focus of diagnostic radiology training is on creating competent professionals, whereas confidence and its calibration receive less attention. Appropriate confidence is critical for patient care both during and after training. Overconfidence can adversely affect patient care and underconfidence can create excessive costs. We reviewed the psychology and medical literature pertaining to confidence and competence to collect insights and best practices from the psychology and medical literature on confidence and apply them to radiology training. People are rarely accurate in assessments of their own competence. Among physicians, the correlation between perceived abilities and external assessments of those abilities is weak. Overconfidence is more prevalent than underconfidence, particularly at lower levels of competence. On the individual level, confidence can be calibrated to a more appropriate level through efforts to increase competence, including sub-specialization, and by gaining a better understanding of metacognitive processes. With feedback, high-fidelity simulation has the potential to improve both competence and metacognition. On the system level, systems that facilitate access to follow-up imaging, pathology, and clinical outcomes can help close the gap between perceived and actual performance. Appropriate matching of trainee confidence and competence should be a goal of radiology residency and fellowship training to help mitigate the adverse effects of both overconfidence and underconfidence during training and independent practice.
Collapse
|
70
|
Khan F, Chetan MR, D'Costa H. Giant duodenal diverticulum masquerading as a sealed perforation. BJR|CASE REPORTS 2022; 8:20210196. [PMID: 36101722 PMCID: PMC9461742 DOI: 10.1259/bjrcr.20210196] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 01/11/2022] [Accepted: 01/13/2022] [Indexed: 11/05/2022]
Abstract
Giant duodenal diverticula are large outpouchings involving all layers of the duodenal wall. Whilst often an incidental finding, giant duodenal diverticula can present with diverticulitis or biliary obstruction. We report a case of a giant duodenal diverticulum that was initially misdiagnosed as a localised duodenal perforation on CT. Additional ultrasound and fluoroscopic imaging demonstrated the final diagnosis of acute cholecystitis. The clinical course of this patient highlights the challenge of recognising a giant duodenal diverticulum and the limitations of solely relying on CT in the context of an acute abdominal presentation.
Collapse
Affiliation(s)
- Faraaz Khan
- University of Oxford Medical School, Oxford, United Kingdom
| | | | - Horace D'Costa
- Oxford University Hospitals NHS Trust, Oxford, United Kingdom
| |
Collapse
|
71
|
Ren M, Yi PH. Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern. Skeletal Radiol 2022; 51:345-353. [PMID: 33576861 DOI: 10.1007/s00256-021-03739-2] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/18/2020] [Revised: 01/25/2021] [Accepted: 02/07/2021] [Indexed: 02/02/2023]
Abstract
OBJECTIVE To develop and evaluate a two-stage deep convolutional neural network system that mimics a radiologist's search pattern for detecting two small fractures: triquetral avulsion fractures and Segond fractures. MATERIALS AND METHODS We obtained 231 lateral wrist radiographs and 173 anteroposterior knee radiographs from the Stanford MURA and LERA datasets and the public domain to train and validate a two-stage deep convolutional neural network system: (1) object detectors that crop the dorsal triquetrum or lateral tibial condyle, trained on control images, followed by (2) classifiers for triquetral and Segond fractures, trained on a 1:1 case:control split. A second set of classifiers was trained on uncropped images for comparison. External test sets of 50 lateral wrist radiographs and 24 anteroposterior knee radiographs were used to evaluate generalizability. Gradient-class activation mapping was used to inspect image regions of greater importance in deciding the final classification. RESULTS The object detectors accurately cropped the regions of interest in all validation and test images. The two-stage system achieved cross-validated area under the receiver operating characteristic curve values of 0.959 and 0.989 on triquetral and Segond fractures, compared with 0.860 (p = 0.0086) and 0.909 (p = 0.0074), respectively, for a one-stage classifier. Two-stage cross-validation accuracies were 90.8% and 92.5% for triquetral and Segond fractures, respectively. CONCLUSION A two-stage pipeline increases accuracy in the detection of subtle fractures on radiographs compared with a one-stage classifier and generalized well to external test data. Focusing attention on specific image regions appears to improve detection of subtle findings that may otherwise be missed.
Collapse
Affiliation(s)
- Mark Ren
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, MD, Baltimore, USA
| | - Paul H Yi
- The Russell H. Morgan Department of Radiology and Radiological Science, Johns Hopkins University School of Medicine, MD, Baltimore, USA. .,University of Maryland Intelligent Imaging Center, Department of Radiology, University of Maryland School of Medicine, MD, Baltimore, USA. .,Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, MD, USA.
| |
Collapse
|
72
|
Reed W. Clinical History - New Analysis Methods Provide Extra Insight Into the Effect of Clinical History on Diagnostic Performance. Acad Radiol 2022; 29:267-268. [PMID: 34465526 DOI: 10.1016/j.acra.2021.08.001] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2021] [Accepted: 08/03/2021] [Indexed: 11/29/2022]
Affiliation(s)
- Warren Reed
- Medical Image Optimisation and Perception Group, Discipline of Medical Imaging Science, Sydney School of Health, Sciences Faculty of Medicine and Health, The University of Sydney, Sydney, Australia.
| |
Collapse
|
73
|
Yapp KE, Brennan P, Ekpo E. The Effect of Clinical History on Diagnostic Imaging Interpretation - A Systematic Review. Acad Radiol 2022; 29:255-266. [PMID: 33183952 DOI: 10.1016/j.acra.2020.10.021] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2020] [Revised: 10/21/2020] [Accepted: 10/21/2020] [Indexed: 12/25/2022]
Abstract
RATIONALE AND OBJECTIVES To provide updated information on the effect of clinical history on diagnostic image interpretation and to provide study methodology and design recommendations for future studies assessing the effect of clinical history on diagnostic image performance. MATERIALS AND METHODS A literature search of Medline, Embase, Scopus, Web of Science, and the Cochrane Central Register of Controlled Trials (CENTRAL) databases was conducted from database inception to July 21, 2020. Studies comparing diagnostic imaging performance with and without clinical history, using observers reading images under both conditions that used an independent reference standard were included. RESULTS Twenty-two studies met the inclusion criteria, with 15 showing clinical history improved diagnostic performance. One study reported a decrease in diagnostic performance with clinical history and the remaining six studies found no significant change in performance. Two studies used the free response paradigm with both reporting clinical history increased location sensitivity, decreased specificity and had no overall change in diagnostic performance. The disease spectrum of included cases was largely unreported and a balanced reading design was not used in 19 studies. CONCLUSION Most published studies found that clinical history improved diagnostic performance. More recent studies accounting for abnormality location and multiple abnormalities showed an increase in false positives and no significant change in overall diagnostic performance with clinical history.
Collapse
Affiliation(s)
- Kehn E Yapp
- Medical Image Optimisation and Perception Group (MIOPeG), Discipline of Medical Imaging Science, School of Health Sciences, Faculty of Medicine and Health, The University of Sydney, Australia.
| | - Patrick Brennan
- Medical Image Optimisation and Perception Group (MIOPeG), Discipline of Medical Imaging Science, School of Health Sciences, Faculty of Medicine and Health, The University of Sydney, Australia
| | - Ernest Ekpo
- Medical Image Optimisation and Perception Group (MIOPeG), Discipline of Medical Imaging Science, School of Health Sciences, Faculty of Medicine and Health, The University of Sydney, Australia
| |
Collapse
|
74
|
PE MIMICS: a structured approach for the emergency radiologist in the evaluation of chest pain. Emerg Radiol 2022; 29:585-593. [DOI: 10.1007/s10140-022-02023-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2021] [Accepted: 01/10/2022] [Indexed: 11/30/2022]
|
75
|
Torres FS, Costa AF, Kagoma Y, Arrigan M, Scott M, Yemen B, Hurrell C, Kielar A. CAR Peer Learning Guide. Can Assoc Radiol J 2022; 73:491-498. [PMID: 35077247 DOI: 10.1177/08465371211065454] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Peer learning is a quality initiative used to identify potential areas of practice improvement, both on a patient level and on a systemic level. Opportunities for peer learning include review of prior imaging studies, evaluation of cases from multidisciplinary case conferences, and review of radiology trainees' call cases. Peer learning is non-punitive and focuses on promoting life-long learning. It seeks to identify and disseminate learning opportunities and areas for systems improvement compared to traditional peer review. Learning opportunities arise from peer learning through both individual communication of cases reviewed for routine work, as well as through anonymous presentation of aggregate cases in an educational format. In conjunction with other tools such as root cause analysis, peer learning can be used to guide future practice improvement opportunities. This guide provides definitions of terms and a synthetic evidence review regarding peer review and peer learning, as well as medicolegal and jurisdictional considerations. Important aspects of what makes an effective peer learning program and best practices for implementing such a program are presented. The guide is intended to be a living document that will be updated regularly as new data emerges and peer learning continues to evolve in radiology practices.
Collapse
Affiliation(s)
- Felipe Soares Torres
- Joint Department of Medical Imaging, Toronto General Hospital, 7938University of Toronto, Toronto, ON, Canada
| | - Andreu F Costa
- Department of Radiology, Queen Elizabeth II Health Sciences Centre, Dalhousie University, Halifax, NS, Canada
| | - Yoan Kagoma
- Hamilton Health Sciences, McMaster University Faculty of Health Sciences, Hamilton, ON, Canada
| | | | - Malcolm Scott
- Misericordia Community Hospital, University of Alberta, Edmonton, AB, Canada
| | - Brian Yemen
- Hamilton Health Sciences, 3710McMaster University, Hamilton, ON, Canada
| | - Casey Hurrell
- Canadian Association of Radiologists, Ottawa, ON, Canada
| | - Ania Kielar
- Joint Department of Medical Imaging, University of Toronto, Toronto, ON, Canada
| |
Collapse
|
76
|
CLAUS CHRISTIANOMARLOPAGGI, CAVALIEIRI MARCIO, MALCHER FLÁVIO, TRIPPIA CARLOS, EIRAS-ARAUJO ANTONIOLUIS, PAULI ERIC, CAVAZZOLA LEANDROTOTTI. Relatório DECOMP: Respostas que os cirurgiões esperam de um exame de imagem da parede abdominal. Rev Col Bras Cir 2022. [DOI: 10.1590/0100-6991e-20223172] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
RESUMO Hérnias da parede abdominal são um problema bastante comum enfrentado pelo cirurgiões gerais. De diagnóstico essencialmente clínico, as hérnias abdominais durante muito tempo têm sido consideradas um problema de simples reparo. Entretanto, o acompanhamento de longo prazo dos pacientes têm demonstrado resultados desapontadores, tanto em termos de complicações quanto risco de recidiva da hérnia. Neste contexto, o planejamento pré-operatório com controle de comorbidades e pleno conhecimento da hérnia e suas relações anatômicas com a parede abdominal têm ganho cada vez mais atenção. A tomografia de abdome parece ser a melhor opção para determinar o tamanho e localização precisos das hérnias abdominais, presença de diastase de músculo reto e/ou atrofia da parede associada, assim como proporção da hérnia em relação a parede abdominal. Essas informações podem auxiliar o cirurgião na escolha da melhor técnica cirúrgica (aberta vs. MIS), posicionamento e fixação das telas, e eventual necessidade de aplicação de toxina botulínica, pneumoperitônio pré-operatório ou técnicas de separação de componentes. Apesar da relevância dos achados, eles são raramente descritos em exames de tomografia uma vez que os radiologistas não estão acostumados a olhar para a parede abdominal assim como não sabem quais as informações são realmente necessárias. Por estes motivos, nós reunimos um grupo de cirurgiões e radiologistas visando estabelecer quais são as informações da parede abdominal mais importantes em um exame de tomografia assim como propor um laudo estruturado para facilitar a descrição dos achados e sua interpretação.
Collapse
Affiliation(s)
| | | | | | | | | | - ERIC PAULI
- Penn State Hershey Medical Center, Estados Unidos
| | | |
Collapse
|
77
|
|
78
|
Currie G, Rohren E. Social Asymmetry, Artificial Intelligence and the Medical Imaging Landscape. Semin Nucl Med 2021; 52:498-503. [PMID: 34972549 DOI: 10.1053/j.semnuclmed.2021.11.011] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2021] [Accepted: 11/23/2021] [Indexed: 12/22/2022]
Abstract
Social and health care equity and justice should be prioritized by the mantra of medicine, first do no harm. Despite highly motivated national and global health strategies, there remains significant health care inequity. Intrinsic and extrinsic factors, including a number of biases, are key drivers of ongoing health inequity including equity of access and opportunity for nuclear medicine and radiology services. There is a substantial gap in the global practice of nuclear medicine in particular, but also radiology, between developed health economies and those considered developing or undeveloped. At a local level, even in developed health economies, there can be a significant disparity between health services, including medical imaging, between communities based on socioeconomic, cultural or geographic differences. Artificial intelligence (AI) has the potential to either widen the health inequity divide or substantially reduce it. Distributed generally, AI technology could be used to overcome geographic boundaries to health care, thus bringing general and specialist care into underserved communities. However, should AI technology be limited to localities already enjoying ample healthcare access and direct access to health infrastructure, like radiology and nuclear medicine, it could then accentuate the gap. There are a number of challenges across the AI pipeline that need careful attention to ensure beneficence over maleficence. Fully realized, AI augmented health care could be crafted as an integral part of the broader strategy convergence on local, national and global health equity. The applications of AI in nuclear medicine and radiology could emerge as a powerful tool in social and health equity.
Collapse
Affiliation(s)
- Geoffrey Currie
- School of Dentistry & Medical Sciences, Charles Sturt University, Wagga Wagga, Australia; Department of Radiology, Baylor College of Medicine, Texas.
| | - Eric Rohren
- School of Dentistry & Medical Sciences, Charles Sturt University, Wagga Wagga, Australia; Department of Radiology, Baylor College of Medicine, Texas
| |
Collapse
|
79
|
Saif AFM, Imtiaz T, Rifat S, Shahnaz C, Zhu WP, Ahmad MO. CapsCovNet: A Modified Capsule Network to Diagnose COVID-19 From Multimodal Medical Imaging. IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE 2021; 2:608-617. [PMID: 35582431 PMCID: PMC8851432 DOI: 10.1109/tai.2021.3104791] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Accepted: 08/11/2021] [Indexed: 12/26/2022]
Abstract
Since the end of 2019, novel coronavirus disease (COVID-19) has brought about a plethora of unforeseen changes to the world as we know it. Despite our ceaseless fight against it, COVID-19 has claimed millions of lives, and the death toll exacerbated due to its extremely contagious and fast-spreading nature. To control the spread of this highly contagious disease, a rapid and accurate diagnosis can play a very crucial part. Motivated by this context, a parallelly concatenated convolutional block-based capsule network is proposed in this article as an efficient tool to diagnose the COVID-19 patients from multimodal medical images. Concatenation of deep convolutional blocks of different filter sizes allows us to integrate discriminative spatial features by simultaneously changing the receptive field and enhances the scalability of the model. Moreover, concatenation of capsule layers strengthens the model to learn more complex representation by presenting the information in a fine to coarser manner. The proposed model is evaluated on three benchmark datasets, in which two of them are chest radiograph datasets and the rest is an ultrasound imaging dataset. The architecture that we have proposed through extensive analysis and reasoning achieved outstanding performance in COVID-19 detection task, which signifies the potentiality of the proposed model.
Collapse
Affiliation(s)
- A F M Saif
- Department of Electrical and Electronic EngineeringBangladesh University of Engineering and Technology Dhaka 1000 Bangladesh
| | - Tamjid Imtiaz
- Department of Electrical and Electronic EngineeringBangladesh University of Engineering and Technology Dhaka 1000 Bangladesh
| | - Shahriar Rifat
- Department of Electrical and Electronic EngineeringBangladesh University of Engineering and Technology Dhaka 1000 Bangladesh
| | - Celia Shahnaz
- Department of Electrical and Electronic EngineeringBangladesh University of Engineering and Technology Dhaka 1000 Bangladesh
| | - Wei-Ping Zhu
- Department of Electrical and Computer EngineeringConcordia University Montreal QC H3G 2W1 Canada
| | - M Omair Ahmad
- Department of Electrical and Computer EngineeringConcordia University Montreal QC H3G 2W1 Canada
| |
Collapse
|
80
|
Li D, Pehrson LM, Lauridsen CA, Tøttrup L, Fraccaro M, Elliott D, Zając HD, Darkner S, Carlsen JF, Nielsen MB. The Added Effect of Artificial Intelligence on Physicians' Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review. Diagnostics (Basel) 2021; 11:diagnostics11122206. [PMID: 34943442 PMCID: PMC8700414 DOI: 10.3390/diagnostics11122206] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2021] [Revised: 11/18/2021] [Accepted: 11/23/2021] [Indexed: 12/20/2022] Open
Abstract
Our systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE, PubMed, Cochrane library, SCOPUS, and Web of Science were retrieved. Included articles were published within the last 20 years and used a device based on artificial intelligence (AI) technology to detect or diagnose pulmonary findings. The AI-based device had to be used in an observer test where the performance of human observers with and without addition of the device was measured as sensitivity, specificity, accuracy, AUC, or time spent on image reading. A total of 38 studies were included for final assessment. The quality assessment tool for diagnostic accuracy studies (QUADAS-2) was used for bias assessment. The average sensitivity increased from 67.8% to 74.6%; specificity from 82.2% to 85.4%; accuracy from 75.4% to 81.7%; and Area Under the ROC Curve (AUC) from 0.75 to 0.80. Generally, a faster reading time was reported when radiologists were aided by AI-based devices. Our systematic review showed that performance generally improved for the physicians when assisted by AI-based devices compared to unaided interpretation.
Collapse
Affiliation(s)
- Dana Li
- Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark; (L.M.P.); (C.A.L.); (J.F.C.); (M.B.N.)
- Department of Clinical Medicine, University of Copenhagen, 2100 Copenhagen, Denmark
- Correspondence:
| | - Lea Marie Pehrson
- Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark; (L.M.P.); (C.A.L.); (J.F.C.); (M.B.N.)
| | - Carsten Ammitzbøl Lauridsen
- Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark; (L.M.P.); (C.A.L.); (J.F.C.); (M.B.N.)
- Department of Technology, Faculty of Health and Technology, University College Copenhagen, 2200 Copenhagen, Denmark
| | - Lea Tøttrup
- Unumed Aps, 1055 Copenhagen, Denmark; (L.T.); (M.F.)
| | | | - Desmond Elliott
- Department of Computer Science, University of Copenhagen, 2100 Copenhagen, Denmark; (D.E.); (H.D.Z.); (S.D.)
| | - Hubert Dariusz Zając
- Department of Computer Science, University of Copenhagen, 2100 Copenhagen, Denmark; (D.E.); (H.D.Z.); (S.D.)
| | - Sune Darkner
- Department of Computer Science, University of Copenhagen, 2100 Copenhagen, Denmark; (D.E.); (H.D.Z.); (S.D.)
| | - Jonathan Frederik Carlsen
- Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark; (L.M.P.); (C.A.L.); (J.F.C.); (M.B.N.)
| | - Michael Bachmann Nielsen
- Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, Denmark; (L.M.P.); (C.A.L.); (J.F.C.); (M.B.N.)
- Department of Clinical Medicine, University of Copenhagen, 2100 Copenhagen, Denmark
| |
Collapse
|
81
|
Lee MH, Lubner MG, Mellnick VM, Menias CO, Bhalla S, Pickhardt PJ. The CT scout view: complementary value added to abdominal CT interpretation. Abdom Radiol (NY) 2021; 46:5021-5036. [PMID: 34075469 DOI: 10.1007/s00261-021-03135-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2021] [Revised: 05/16/2021] [Accepted: 05/21/2021] [Indexed: 12/30/2022]
Abstract
Computed tomography (CT) scout images, also known as CT localizer radiographs, topograms, or scanograms, are an important, albeit often overlooked part of the CT examination. Scout images may contain important findings outside of the scanned field of view on CT examinations of the abdomen and pelvis, such as unsuspected lung cancer at the lung bases. Alternatively, scout images can provide complementary information to findings within the scanned field of view, such as characterization of retained surgical foreign bodies. Assessment of scout images adds value and provides a complementary "opportunistic" review for interpretation of abdominopelvic CT examinations. Scout image review is a useful modern application of conventional abdominal radiograph interpretation that can help establish a diagnosis or narrow a differential diagnosis. This review discusses the primary purpose and intent of the CT scout images, addresses standard of care and bias related to scout image review, and presents a general systematic approach to assessing scout images with multiple illustrative examples, including potential pitfalls in interpreting scout images.
Collapse
Affiliation(s)
- Matthew H Lee
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA.
| | - Meghan G Lubner
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA
| | - Vincent M Mellnick
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, 510 S Kingshighway Blvd, Campus, Box 8131, St. Louis, USA
| | - Christine O Menias
- Department of Radiology, Mayo Clinic, 13400 E. Shea Blvd, Scottsdale, AZ, 85259, USA
| | - Sanjeev Bhalla
- Mallinckrodt Institute of Radiology, Washington University School of Medicine, 510 S Kingshighway Blvd, Campus, Box 8131, St. Louis, USA
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, 600 Highland Ave, Madison, WI, 53792, USA
| |
Collapse
|
82
|
Yoshida M, Makino Y, Hoshioka Y, Saito N, Yamaguchi R, Chiba F, Inokuchi G, Iwase H. Technical and interpretive pitfalls of postmortem CT: Five examples of errors revealed by autopsy. J Forensic Sci 2021; 67:395-403. [PMID: 34491573 DOI: 10.1111/1556-4029.14883] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2021] [Revised: 08/01/2021] [Accepted: 08/17/2021] [Indexed: 11/30/2022]
Abstract
Image acquisition of dead bodies, particularly using postmortem computed tomography (PMCT), has become common in forensic investigations worldwide. Meanwhile, in countries such as Japan which have an extremely low rate of autopsy, PMCT is being increasingly used in the clinical field to certify the cause of death (COD) without performing an autopsy or toxicological tests, even in cases of unnatural death. Additionally, these PMCT images are predominantly interpreted by clinical personnel such as emergency physicians or clinicians who are not trained in PMCT interpretation and who work for the police, that is, the so-called police doctors. Many potential pitfalls associated with the use of PMCT have been previously described in textbooks and published papers, including the pitfalls of not performing a complete forensic pathology investigation, and the use of physicians without appropriate PMCT training to interpret PMCT and direct death investigation and certification. We describe five examples in which apparent misdiagnosis of COD based on PMCT misinterpretation was revealed by autopsy. Here are the five examples of errors: (1) Postmortem changes were misinterpreted as COD, (2) resuscitation effects were misinterpreted as COD, (3) COD was determined after an incomplete examination, (4) fatal findings caused by external origin were wrongly interpreted as 'of internal origin' based on PMCT, and (5) non-fatal findings on PMCT were wrongly interpreted as fatal. Interpretation of PMCT by appropriately trained physicians and an accompanying complete forensic investigation, including autopsy when indicated, is necessary to prevent significant errors in COD determination and related potential adverse medicolegal consequences.
Collapse
Affiliation(s)
- Maiko Yoshida
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan.,Nippon Medical School Chiba Hokusoh Hospital, Chiba, Japan
| | - Yohsuke Makino
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan.,Department of Forensic Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Yumi Hoshioka
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan
| | - Naoki Saito
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan
| | - Rutsuko Yamaguchi
- Department of Forensic Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Fumiko Chiba
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan
| | - Go Inokuchi
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan
| | - Hirotaro Iwase
- Chiba University Center for Education and Research in Legal Medicine, Chiba, Japan.,Department of Forensic Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| |
Collapse
|
83
|
Tee QX, Nambiar M, Stuckey S. Error and cognitive bias in diagnostic radiology. J Med Imaging Radiat Oncol 2021; 66:202-207. [PMID: 34467643 DOI: 10.1111/1754-9485.13320] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2021] [Accepted: 08/16/2021] [Indexed: 11/29/2022]
Abstract
The above article was posted prematurely on 31 August 2021. The article will be made fully available at a later date.
Collapse
Affiliation(s)
- Qiao Xin Tee
- Department of Diagnostic Imaging, Monash Health, Clayton, Victoria, Australia
| | - Mithun Nambiar
- Department of Diagnostic Imaging, Monash Health, Clayton, Victoria, Australia
| | - Stephen Stuckey
- Department of Diagnostic Imaging, Monash Health, Clayton, Victoria, Australia
- School of Clinical Sciences at Monash Health, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Victoria, Australia
| |
Collapse
|
84
|
Rudie JD, Duda J, Duong MT, Chen PH, Xie L, Kurtz R, Ware JB, Choi J, Mattay RR, Botzolakis EJ, Gee JC, Bryan RN, Cook TS, Mohan S, Nasrallah IM, Rauschecker AM. Brain MRI Deep Learning and Bayesian Inference System Augments Radiology Resident Performance. J Digit Imaging 2021; 34:1049-1058. [PMID: 34131794 PMCID: PMC8455800 DOI: 10.1007/s10278-021-00470-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/16/2020] [Revised: 04/28/2021] [Accepted: 05/25/2021] [Indexed: 12/15/2022] Open
Abstract
Automated quantitative and probabilistic medical image analysis has the potential to improve the accuracy and efficiency of the radiology workflow. We sought to determine whether AI systems for brain MRI diagnosis could be used as a clinical decision support tool to augment radiologist performance. We utilized previously developed AI systems that combine convolutional neural networks and expert-derived Bayesian networks to distinguish among 50 diagnostic entities on multimodal brain MRIs. We tested whether these systems could augment radiologist performance through an interactive clinical decision support tool known as Adaptive Radiology Interpretation and Education System (ARIES) in 194 test cases. Four radiology residents and three academic neuroradiologists viewed half of the cases unassisted and half with the results of the AI system displayed on ARIES. Diagnostic accuracy of radiologists for top diagnosis (TDx) and top three differential diagnosis (T3DDx) was compared with and without ARIES. Radiology resident performance was significantly better with ARIES for both TDx (55% vs 30%; P < .001) and T3DDx (79% vs 52%; P = 0.002), with the largest improvement for rare diseases (39% increase for T3DDx; P < 0.001). There was no significant difference between attending performance with and without ARIES for TDx (72% vs 69%; P = 0.48) or T3DDx (86% vs 89%; P = 0.39). These findings suggest that a hybrid deep learning and Bayesian inference clinical decision support system has the potential to augment diagnostic accuracy of non-specialists to approach the level of subspecialists for a large array of diseases on brain MRI.
Collapse
Affiliation(s)
- Jeffrey D Rudie
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA.
- Department of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA.
| | - Jeffrey Duda
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Michael Tran Duong
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Po-Hao Chen
- Department of Radiology, Cleveland Clinic Imaging Institute, Cleveland, OH, USA
| | - Long Xie
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Robert Kurtz
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Jeffrey B Ware
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Joshua Choi
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Raghav R Mattay
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | | | - James C Gee
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - R Nick Bryan
- Department of Diagnostic Medicine, Dell Medical School, University of Texas, Austin, TX, USA
| | - Tessa S Cook
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Suyash Mohan
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Ilya M Nasrallah
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
| | - Andreas M Rauschecker
- Department of Radiology, Perelman School of Medicine at the University of Pennsylvania, PA, Philadelphia, USA
- Department of Radiology & Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA
| |
Collapse
|
85
|
Ariagno S, Jeeji A, Hull N, Absah I. Abdominal Discomfort, Altered Bowel Habits, and Weight Loss in a 13-year-old Girl. Pediatr Rev 2021; 42:457-462. [PMID: 34341088 DOI: 10.1542/pir.2020-000802] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
Affiliation(s)
| | | | - Nathan Hull
- Department of Radiology, Mayo Clinic, Rochester, MN
| | - Imad Absah
- Department of Pediatric and Adolescent Medicine
| |
Collapse
|
86
|
Jones CM, Buchlak QD, Oakden‐Rayner L, Milne M, Seah J, Esmaili N, Hachey B. Chest radiographs and machine learning - Past, present and future. J Med Imaging Radiat Oncol 2021; 65:538-544. [PMID: 34169648 PMCID: PMC8453538 DOI: 10.1111/1754-9485.13274] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2021] [Accepted: 06/08/2021] [Indexed: 01/15/2023]
Abstract
Despite its simple acquisition technique, the chest X-ray remains the most common first-line imaging tool for chest assessment globally. Recent evidence for image analysis using modern machine learning points to possible improvements in both the efficiency and the accuracy of chest X-ray interpretation. While promising, these machine learning algorithms have not provided comprehensive assessment of findings in an image and do not account for clinical history or other relevant clinical information. However, the rapid evolution in technology and evidence base for its use suggests that the next generation of comprehensive, well-tested machine learning algorithms will be a revolution akin to early advances in X-ray technology. Current use cases, strengths, limitations and applications of chest X-ray machine learning systems are discussed.
Collapse
Affiliation(s)
- Catherine M Jones
- I‐MED Radiology NetworkBrisbaneQueenslandAustralia
- Annalise.aiSydneyNew South WalesAustralia
| | - Quinlan D Buchlak
- Annalise.aiSydneyNew South WalesAustralia
- School of MedicineThe University of Notre Dame AustraliaSydneyNew South WalesAustralia
- Harrison.aiSydneyNew South WalesAustralia
| | - Luke Oakden‐Rayner
- Australian Institute for Machine LearningThe University of AdelaideAdelaideSouth AustraliaAustralia
| | - Michael Milne
- I‐MED Radiology NetworkBrisbaneQueenslandAustralia
- Annalise.aiSydneyNew South WalesAustralia
| | - Jarrel Seah
- Annalise.aiSydneyNew South WalesAustralia
- Harrison.aiSydneyNew South WalesAustralia
- Department of RadiologyAlfred HealthMelbourneVictoriaAustralia
| | - Nazanin Esmaili
- School of MedicineThe University of Notre Dame AustraliaSydneyNew South WalesAustralia
- Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyNew South WalesAustralia
| | - Ben Hachey
- Annalise.aiSydneyNew South WalesAustralia
- Harrison.aiSydneyNew South WalesAustralia
| |
Collapse
|
87
|
Hussien AR, Abdellatif W, Siddique Z, Mirchia K, El-Quadi M, Hussain A. Diagnostic Errors in Neuroradiology: A Message to Emergency Radiologists and Trainees. Can Assoc Radiol J 2021; 73:384-395. [PMID: 34227436 DOI: 10.1177/08465371211025738] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022] Open
Abstract
Diagnostic errors in neuroradiology are inevitable, yet potentially avoidable. Through extensive literature search, we present an up-to-date review of the psychology of human decision making and how such complex process can lead to radiologic errors. Our focus is on neuroradiology, so we augmented our review with multiple explanatory figures to show how different errors can reflect on real-life clinical practice. We propose a new thematic categorization of perceptual and cognitive biases in this article to simplify message delivery to our target audience: emergency/general radiologists and trainees. Additionally, we highlight individual and organizational remedy strategies to decrease error rate and potential harm.
Collapse
Affiliation(s)
| | - Waleed Abdellatif
- Department of Radiology, University of British Colombia, Vancouver, British Columbia, Canada
| | - Zaid Siddique
- Department of Radiology, SUNY Upstate Medical University, Syracuse, NY, USA
| | - Kavya Mirchia
- Department of Radiology, SUNY Upstate Medical University, Syracuse, NY, USA
| | | | - Ali Hussain
- Department of Imaging Sciences, University of Rochester, Rochester, NY, USA
| |
Collapse
|
88
|
Analysis of Literature Regarding Health Care Disparities in Radiology: Is Radiology Falling Behind? Acad Radiol 2021; 28:911-915. [PMID: 34006436 DOI: 10.1016/j.acra.2021.03.011] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2021] [Revised: 02/22/2021] [Accepted: 03/10/2021] [Indexed: 11/20/2022]
Abstract
PURPOSE To quantify the gap between radiology and other specialties regarding the amount of literature on healthcare disparities (HCD). METHODS Four different searches were conducted to evaluate the amount of literature on HCD in radiology as compared to internal medicine and surgery. Initially, the Journal Citation Report was utilized to search for the five highest ranking journals in each field and a second search used impact factor. A combination of search terms "health" AND "disparities" was used. Two additional searches were performed with PubMed using the terms "health" AND "disparities AND "radiology" with the final term changed for each specialty. The second PubMed search added the term "medical education" for each specialty. Articles were limited to years 2017 to 2020. RESULTS The initial search found 1817 articles discussing "health" and "disparities". 14.6% of these were radiology, 65.7% internal medicine, and 19.7% surgery. The subsequent search controlling for impact factor found 2176 articles. 12.2% were for radiology, 66.1% were for internal medicine, and 21.7% for surgery. The initial PubMed search found 6543 articles. 9.9% were for radiology, 32.4% for internal medicine, and 57.7% were for surgery. The addition of "medical education" decreased the articles to 807. Radiology had 9.9%, internal medicine was 44.2%, and surgery was 45.9 %. CONCLUSION A gap in HCD literature exists for radiology as compared to surgery and internal medicine. However, radiology has demonstrated a recent significant push towards understanding HCD. Radiology should continue to capitalize on its momentum and develop HCD curricula and research.
Collapse
|
89
|
Petscavage-Thomas J, Beatty-Chadha J, Chetlen A, Artrip R, Welkie J, Neutze J. Medical Student Elective to Improve Diagnosis in Health Care: Developing Solutions to Reduce Patient Harm. Acad Radiol 2021; 28:997-1001. [PMID: 34217491 DOI: 10.1016/j.acra.2020.12.027] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2020] [Revised: 11/30/2020] [Accepted: 12/03/2020] [Indexed: 11/29/2022]
Abstract
RATIONALE AND OBJECTIVES At our institution, a new medical student elective was designed and implemented by the department of radiology to teach medical students about diagnostic error. The purpose of this article is to describe the diagnostic error elective structure and implementation, present objective and subjective evaluations of the elective, and provide a model for other radiology departments to run their own electives. MATERIALS AND METHODS Starting in January 2018, a 2-week in-person career exploration session elective was offered for third year medical students. In 2020 due to the COVID pandemic, the elective was expanded to fourth year medical students. All students were required to complete a project that addressed diagnostic error. Subjective comments were recorded, and objective measurements obtained from student evaluations. RESULTS A total of 11 sessions were held, consisting of 3 fourth year and 26 third year students. A total of 12 projects (11 groups) were completed, seven of which have been accepted for presentation at national meetings. On a 1 to 5 scale (5 highest), students rated their educational experience at a mean score of 4.61. Subjective comments focused on the benefit of exposure to new topics, mentorship by radiologists, and ability to complete a project in such a short time. CONCLUSION Diagnostic errors and solutions are vague, new concepts to medical students and even facilitator faculty. This course allowed students to gain awareness of diagnostic error and could easily be replicated at other institutions with interested faculty and medical school support.
Collapse
Affiliation(s)
- Jonelle Petscavage-Thomas
- Department of Radiology, Division of Musculoskeletal Imaging, 500 University Drive, HG300B, Hershey, PA 17033.
| | - Jeanine Beatty-Chadha
- Woodward Center for Excellence in Health Sciences Education, Penn State College of Medicine, 500 University Drive, P.O. Box 850 - Mail Code H183, Hershey, PA 17033
| | - Alison Chetlen
- Department of Radiology, Division of Breast Imaging, Penn State Health, Hershey Medical Center, 30 Hope Drive, Suite 1800, EC 008, Hershey, PA 17033
| | - Rick Artrip
- Penn State College of Medicine, 500 University Drive, Hershey, Pennsylvania 17033
| | - Janelle Welkie
- Penn State College of Medicine, 500 University Drive, Hershey, Pennsylvania 17033
| | - Janet Neutze
- Penn State Hershey Medical Center, 500 University Drive, Dept. of Radiology HG300B, Hershey, Pennsylvania 17033
| |
Collapse
|
90
|
Tarkiainen T, Turpeinen M, Haapea M, Liukkonen E, Niinimäki J. Investigating errors in medical imaging: medical malpractice cases in Finland. Insights Imaging 2021; 12:86. [PMID: 34184113 PMCID: PMC8238384 DOI: 10.1186/s13244-021-01011-8] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2020] [Accepted: 05/06/2021] [Indexed: 12/01/2022] Open
Abstract
Objective The objectives of the study were to survey patient injury claims concerning medical imaging in Finland in 1991–2017, and to investigate the nature of the incidents, the number of claims, the reasons for the claims, and the decisions made concerning the claims. Materials and methods The research material consisted of patient claims concerning imaging, sent to the Finnish Patient Insurance Centre (PVK). The data contained information on injury dates, the examination code, the decision code, the description of the injury, and the medical grounds for decisions. Results The number of claims included in the study was 1054, and the average number per year was 87. The most common cause was delayed diagnosis (404 claims, 38.3%). Most of the claims concerned mammography (314, 29.8%), radiography (170, 16.1%), and MRI (162, 15.4%). According to the decisions made by the PVK, there were no delays in 54.6% of the examinations for which claims were made. About 30% of all patient claims received compensation, the most typical reason being medical malpractice (27.7%), followed by excessive injuries and injuries caused by infections, accidents and equipment (2.7%). Conclusion Patient injury in imaging examinations and interventions cannot be completely prevented. However, injury data are an important source of information for health care. By analysing claims, we can prevent harm, increase the quality of care, and improve patient safety in medical imaging.
Collapse
Affiliation(s)
- Tarja Tarkiainen
- Department of Diagnostic Radiology, Research Unit of Medical Imaging, Physics and Technology, Oulu University Hospital, Oulu, Finland.
| | - Miia Turpeinen
- Administrative Centre, Research Unit of Biomedicine, Oulu University Hospital and University of Oulu, Oulu, Finland
| | - Marianne Haapea
- Department of Diagnostic Radiology, Medical Research Center, Oulu University Hospital and University of Oulu, Oulu, Finland
| | - Esa Liukkonen
- Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland
| | - Jaakko Niinimäki
- Department of Diagnostic Radiology, Research Unit of Medical Imaging, Physics and Technology, Oulu University Hospital and University of Oulu, Oulu, Finland
| |
Collapse
|
91
|
Watura C, Kendall C, Sookur P. Direct Access and Skill Mix Can Reduce Telephone Interruptions and Imaging Wait Times: Improving Radiology Service Effectiveness, Safety and Sustainability. Curr Probl Diagn Radiol 2021; 51:6-11. [PMID: 34284928 DOI: 10.1067/j.cpradiol.2021.06.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2021] [Revised: 05/23/2021] [Accepted: 06/11/2021] [Indexed: 11/22/2022]
Abstract
Unnecessary telephone calls to reporting radiologists impede organizations' workflow and may be associated with a higher chance of errors in reports. We conducted a prospective study in two cycles, which identified vetting plain CT heads as the most common reason for these calls and vetting CT urinary tracts (KUB) was also frequent. Clear vetting and protocolling guidelines exist for both of these scans, which do not routinely require discussion with a radiologist. Therefore, our approach was to create new flow diagrams to allow radiographers to directly accept routine requests for plain CT head and CT KUB scans in- and out-of-hours. After this intervention, incoming calls to radiology for vetting CT heads decreased by 30% and for vetting CT KUBs by 100%. The average wait time between CT head request and scan completion was reduced by 40%. The number of CT head and CT KUB scans performed remained stable. In future, maximizing the benefit of direct access in-patient imaging pathways will rely on effective and sustained communication of the protocols to the junior clinical staff rotating through the organization, as they were responsible for requesting the vast majority of tests.
Collapse
Affiliation(s)
- Christopher Watura
- Chelsea and Westminster Hospital NHS Foundation Trust, Imaging Department, Chelsea and Westminster Hospital, Chelsea, London.
| | - Charlotte Kendall
- Chelsea and Westminster Hospital NHS Foundation Trust, Imaging Department, Chelsea and Westminster Hospital, Chelsea, London
| | - Paul Sookur
- Chelsea and Westminster Hospital NHS Foundation Trust, Imaging Department, Chelsea and Westminster Hospital, Chelsea, London
| |
Collapse
|
92
|
Cooper JA, Jenkinson D, Stinton C, Wallis MG, Hudson S, Taylor-Phillips S. Optimising breast cancer screening reading: blinding the second reader to the first reader's decisions. Eur Radiol 2021; 32:602-612. [PMID: 34117912 PMCID: PMC8660753 DOI: 10.1007/s00330-021-07965-z] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2021] [Revised: 03/02/2021] [Accepted: 03/30/2021] [Indexed: 11/22/2022]
Abstract
Objectives In breast cancer screening, two readers separately examine each woman’s mammograms for signs of cancer. We examined whether preventing the two readers from seeing each other’s decisions (blinding) affects behaviour and outcomes. Methods This cohort study used data from the CO-OPS breast-screening trial (1,119,191 women from 43 screening centres in England) where all discrepant readings were arbitrated. Multilevel models were fitted using Markov chain Monte Carlo to measure whether reader 2 conformed to the decisions of reader 1 when they were not blinded, and the effect of blinding on overall rates of recall for further tests and cancer detection. Differences in positive predictive value (PPV) were assessed using Pearson’s chi-squared test. Results When reader 1 recalls, the probability of reader 2 also recalling was higher when not blinded than when blinded, suggesting readers may be influenced by the other’s decision. Overall, women were less likely to be recalled when reader 2 was blinded (OR 0.923; 95% credible interval 0.864, 0.986), with no clear pattern in cancer detection rate (OR 1.029; 95% credible interval 0.970, 1.089; Bayesian p value 0.832). PPV was 22.1% for blinded versus 20.6% for not blinded (p < 0.001). Conclusions Our results suggest that when not blinded, reader 2 is influenced by reader 1’s decisions to recall (alliterative bias) which would result in bypassing arbitration and negate some of the benefits of double-reading. We found a relationship between blinding the second reader and slightly higher PPV of breast cancer screening, although this analysis may be confounded by other centre characteristics. Key Points • In Europe, it is recommended that breast screening mammograms are analysed by two readers but there is little evidence on the effect of ‘blinding’ the readers so they cannot see each other’s decisions. • We found evidence that when the second reader is not blinded, they are more likely to agree with a recall decision from the first reader and less likely to make an independent judgement (alliterative error). This may reduce overall accuracy through bypassing arbitration. • This observational study suggests an association between blinding the second reader and higher positive predictive value of screening, but this may be confounded by centre characteristics. Supplementary Information The online version contains supplementary material available at 10.1007/s00330-021-07965-z.
Collapse
Affiliation(s)
- Jennifer A Cooper
- Department of Health Sciences, Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL, UK.,Population Health Sciences; Bristol Medical School, University of Bristol, Bristol, BS8 2BN, UK
| | - David Jenkinson
- Department of Health Sciences, Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL, UK
| | - Chris Stinton
- Department of Health Sciences, Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL, UK
| | - Matthew G Wallis
- Cambridge Breast Unit, Cambridge University Hospitals National Health Service Foundation Trust, and National Institute for Health Research Cambridge Biomedical Research Centre, Cambridge, UK
| | - Sue Hudson
- Peel & Schriek Consulting Limited, London, UK
| | - Sian Taylor-Phillips
- Department of Health Sciences, Warwick Medical School, University of Warwick, Gibbet Hill Road, Coventry, CV4 7AL, UK. .,Warwick Screening, Warwick Medical School, University of Warwick, Coventry, CV4 7AL, UK.
| |
Collapse
|
93
|
Huang Z, Liu H, Huang W, Wang H, Liu J, Wu Z. Giant retroperitoneal paraganglioma: Challenges of misdiagnosis and high surgical risks, a case report. Int J Surg Case Rep 2021; 84:106081. [PMID: 34119947 PMCID: PMC8209176 DOI: 10.1016/j.ijscr.2021.106081] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2021] [Revised: 05/28/2021] [Accepted: 06/03/2021] [Indexed: 12/03/2022] Open
Abstract
Introduction and importance In surgery, misdiagnosis is not uncommon, usually a result of erroneous image interpretations and pathology diagnosis especially involving a tumor or cancer. Misdiagnosis may cause increased morbidity, mortality and surgical risks. Case presentation A 49-year-old man presented for the second time with a right upper abdominal mass of 7 months. Previous CT scan of abdomen and exploratory surgery made the diagnosis of liver cancer. Two other tertiary hospitals drew the similar conclusions. At a cancer hospital the needle biopsy was suspicious for gastrointestinal stromal tumor, Imatinib was recommended but not started due to high cost. During this re-admission, the diagnosis of liver cancer or GIST was challenged. A high risk surgery was done with successive removal of a giant tumor. A final diagnosis of paraganlioma was made and the patient is now tumor free for 6 years. Clinical discussion There are 4 lessons from this case. First, a paraganlioma may be misdiagnosed. Second, the misdiagnosis may be misled by CT scan and pathology. Third, a misdiagnosis can cause increased morbidity, mortality and surgical risks. Forth, massive intraoperative hemorrhage is a high risk of surgery. Conclusion Careful clinical evaluation combined with pathology diagnosis may reduce the misdiagnosis of some tumor/cancer. Surgical resection may be the only way to reach a diagnosis in patient with paraganlioma. Massive intraoperative hemorrhage is a high risk of surgery in such patients. Paraganglioma may be misdiagnosed as other tumor or cancer. Computed tomography of abdomen is not diagnostic for paraganglioma. Misdiagnosis can cause increased morbidity, mortality and surgical risks. Careful clinical evaluation combined with pathological diagnosis can prevent or reduce misdiagnosis of abdominal solid mass. Massive intraoperative hemorrhage is a high risk of surgery for large garaganglioma.
Collapse
Affiliation(s)
- Zhengbin Huang
- Department of General Surgery, Hanchuan People's Hospital, 1 Renmin Avenue, Hanchuan, Hubei 431600, China
| | - Hanzhong Liu
- Department of Pathology, Xiaogan Central Hospital, 6 Guangchang Road, Xiaogan, Hubei 432100, China
| | - Wenwei Huang
- Department of General Surgery, Hanchuan People's Hospital, 1 Renmin Avenue, Hanchuan, Hubei 431600, China
| | - Hui Wang
- Department of General Surgery, Hanchuan People's Hospital, 1 Renmin Avenue, Hanchuan, Hubei 431600, China
| | - Jun Liu
- Department of General Surgery, Hanchuan People's Hospital, 1 Renmin Avenue, Hanchuan, Hubei 431600, China
| | - Zhengqi Wu
- Department of Medicine, Winchester Medical Center, 1840 Amherst Street, Winchester, VA 22601, USA.
| |
Collapse
|
94
|
Brown SD. Ethical challenges in child abuse: what is the harm of a misdiagnosis? Pediatr Radiol 2021; 51:1070-1075. [PMID: 33999247 DOI: 10.1007/s00247-020-04845-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/23/2020] [Revised: 07/31/2020] [Accepted: 09/08/2020] [Indexed: 11/26/2022]
Abstract
In this article the author examines ethical tensions inherent to balancing harms of false-negative and false-positive child abuse diagnoses, and he describes how such tensions manifest in courtroom proceedings. Child abuse physicians, including pediatric radiologists, shoulder heavy responsibilities weighing the potential consequences of not diagnosing child abuse when it could have been diagnosed (false negatives) against the consequences of making the diagnosis when it has not occurred (false positives). These physicians, who practice under ethical obligations to serve children's best interests and protect them from harm, make daily practice decisions knowing that, on balance, abuse is substantially more underdiagnosed than over diagnosed. Legal justice advocates, however, emphasize that clinical decision-making around abuse is not disassociated from endemic injustices that unduly incriminate individuals from socioeconomically underprivileged populations. Some defense advocates charge that child abuse physicians are insufficiently sensitive to harms of erroneous diagnoses, and they have characterized these clinicians as frankly biased. To support their claims in court, defense advocates have enlisted likeminded physician witnesses whose credentials as experts flout professional standards and who provide consistently flawed testimony based upon deficiently peer-reviewed literature. This article concludes that, to help mitigate these unhealthy circumstances, child abuse physicians might build trust with criminal defense advocates by instituting measures to alleviate perceptions of biases and by more explicitly acknowledging the potential harms of erroneous diagnoses. Professional societies representing these physicians, such as the Society for Pediatric Radiology, could take concurrent measures to help better prepare their constituent clinicians for expert testimony and make them more available to testify.
Collapse
Affiliation(s)
- Stephen D Brown
- Department of Radiology, Boston Children's Hospital and Harvard Medical School, 300 Longwood Ave., Boston, MA, 02115, USA.
| |
Collapse
|
95
|
Onder O, Yarasir Y, Azizova A, Durhan G, Onur MR, Ariyurek OM. Errors, discrepancies and underlying bias in radiology with case examples: a pictorial review. Insights Imaging 2021; 12:51. [PMID: 33877458 PMCID: PMC8056102 DOI: 10.1186/s13244-021-00986-8] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2020] [Accepted: 03/19/2021] [Indexed: 01/12/2023] Open
Abstract
Interpretation differences between radiologists and diagnostic errors are significant issues in daily radiology practice. An awareness of errors and their underlying causes can potentially increase the diagnostic performance and reduce individual harm. The aim of this paper is to review both the classification of errors and the underlying biases. Case-based examples are presented and discussed for each type of error and bias to provide greater clarity and understanding.
Collapse
Affiliation(s)
- Omer Onder
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey
| | - Yasin Yarasir
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey
| | - Aynur Azizova
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey
| | - Gamze Durhan
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey
| | - Mehmet Ruhi Onur
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey
| | - Orhan Macit Ariyurek
- Department of Radiology, Hacettepe University School of Medicine, Ankara, 06100, Turkey.
| |
Collapse
|
96
|
van Hespen KM, Zwanenburg JJM, Dankbaar JW, Geerlings MI, Hendrikse J, Kuijf HJ. An anomaly detection approach to identify chronic brain infarcts on MRI. Sci Rep 2021; 11:7714. [PMID: 33833297 PMCID: PMC8032662 DOI: 10.1038/s41598-021-87013-4] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2020] [Accepted: 03/23/2021] [Indexed: 02/05/2023] Open
Abstract
The performance of current machine learning methods to detect heterogeneous pathology is limited by the quantity and quality of pathology in medical images. A possible solution is anomaly detection; an approach that can detect all abnormalities by learning how 'normal' tissue looks like. In this work, we propose an anomaly detection method using a neural network architecture for the detection of chronic brain infarcts on brain MR images. The neural network was trained to learn the visual appearance of normal appearing brains of 697 patients. We evaluated its performance on the detection of chronic brain infarcts in 225 patients, which were previously labeled. Our proposed method detected 374 chronic brain infarcts (68% of the total amount of brain infarcts) which represented 97.5% of the total infarct volume. Additionally, 26 new brain infarcts were identified that were originally missed by the radiologist during radiological reading. Our proposed method also detected white matter hyperintensities, anomalous calcifications, and imaging artefacts. This work shows that anomaly detection is a powerful approach for the detection of multiple brain abnormalities, and can potentially be used to improve the radiological workflow efficiency by guiding radiologists to brain anomalies which otherwise remain unnoticed.
Collapse
Affiliation(s)
- Kees M van Hespen
- Center for Image Sciences, University Medical Center Utrecht, Heidelberglaan 100, Postbox 85500, 3584 CX, Utrecht, The Netherlands.
| | - Jaco J M Zwanenburg
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Jan W Dankbaar
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Mirjam I Geerlings
- Julius Center for Health Sciences and Primary Care, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Jeroen Hendrikse
- Department of Radiology, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| | - Hugo J Kuijf
- Image Sciences Institute, UMC Utrecht, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands
| |
Collapse
|
97
|
Gaube S, Suresh H, Raue M, Merritt A, Berkowitz SJ, Lermer E, Coughlin JF, Guttag JV, Colak E, Ghassemi M. Do as AI say: susceptibility in deployment of clinical decision-aids. NPJ Digit Med 2021; 4:31. [PMID: 33608629 PMCID: PMC7896064 DOI: 10.1038/s41746-021-00385-9] [Citation(s) in RCA: 112] [Impact Index Per Article: 37.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2020] [Accepted: 01/07/2021] [Indexed: 02/07/2023] Open
Abstract
Artificial intelligence (AI) models for decision support have been developed for clinical settings such as radiology, but little work evaluates the potential impact of such systems. In this study, physicians received chest X-rays and diagnostic advice, some of which was inaccurate, and were asked to evaluate advice quality and make diagnoses. All advice was generated by human experts, but some was labeled as coming from an AI system. As a group, radiologists rated advice as lower quality when it appeared to come from an AI system; physicians with less task-expertise did not. Diagnostic accuracy was significantly worse when participants received inaccurate advice, regardless of the purported source. This work raises important considerations for how advice, AI and non-AI, should be deployed in clinical environments.
Collapse
Affiliation(s)
- Susanne Gaube
- Department of Psychology, University of Regensburg, Regensburg, Germany. .,MIT AgeLab, Massachusetts Institute of Technology, Cambridge, MA, USA.
| | - Harini Suresh
- MIT Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, USA.
| | - Martina Raue
- MIT AgeLab, Massachusetts Institute of Technology, Cambridge, MA, USA
| | | | - Seth J Berkowitz
- Department of Radiology, Beth Israel Deaconess Medical Center, Boston, MA, USA
| | - Eva Lermer
- LMU Center for Leadership and People Management, LMU Munich, Munich, Germany.,FOM University of Applied Sciences for Economics & Management, Munich, Germany
| | - Joseph F Coughlin
- MIT AgeLab, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - John V Guttag
- MIT Computer Science & Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
| | - Errol Colak
- Li Ka Shing Knowledge Institute, St. Michael's Hospital, Toronto, Canada.,Department of Medical Imaging, University of Toronto, Toronto, Canada
| | - Marzyeh Ghassemi
- Departments of Computer Science and Medicine, University of Toronto, Toronto, Canada.,Vector Institute, Toronto, Canada
| |
Collapse
|
98
|
Pot M, Kieusseyan N, Prainsack B. Not all biases are bad: equitable and inequitable biases in machine learning and radiology. Insights Imaging 2021; 12:13. [PMID: 33564955 PMCID: PMC7872878 DOI: 10.1186/s13244-020-00955-7] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2020] [Accepted: 12/14/2020] [Indexed: 11/10/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Mirjam Pot
- Department of Political Science, University of Vienna, Austria, Universitätsstraße 7, 1100, Wien, Austria
| | | | - Barbara Prainsack
- Department of Political Science, University of Vienna, Austria, Universitätsstraße 7, 1100, Wien, Austria. .,Department of Global Health and Social Medicine, King's College London, London, UK.
| |
Collapse
|
99
|
Shiang T, Tai R, Watts GJ. Absence of Posttraumatic Bone Marrow Edema in the Setting of Preeclampsia. J Am Podiatr Med Assoc 2021; 111:438705. [PMID: 32584976 DOI: 10.7547/19-185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
Magnetic resonance imaging is a powerful tool in the diagnosis of missed or occult fractures on radiographic and computed tomographic (CT) imaging, through the detection of bone marrow edema. Although radiologists often rely on bone marrow edema as a guide for diagnosing subtle underlying fractures, it is important to recognize its limitations as a diagnostic metric. We present a rare case demonstrating the absence of bone marrow edema after acute trauma and confirmed Lisfranc fracture in a patient with preeclampsia and propose an interesting physiologic mechanism to explain this manifestation.
Collapse
|
100
|
Radiologists and Clinical Trials: Part 1 The Truth About Reader Disagreements. Ther Innov Regul Sci 2021; 55:1111-1121. [PMID: 34228319 PMCID: PMC8259547 DOI: 10.1007/s43441-021-00316-6] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2020] [Accepted: 06/18/2021] [Indexed: 02/06/2023]
Abstract
The debate over human visual perception and how medical images should be interpreted have persisted since X-rays were the only imaging technique available. Concerns over rates of disagreement between expert image readers are associated with much of the clinical research and at times driven by the belief that any image endpoint variability is problematic. The deeper understanding of the reasons, value, and risk of disagreement are somewhat siloed, leading, at times, to costly and risky approaches, especially in clinical trials. Although artificial intelligence promises some relief from mistakes, its routine application for assessing tumors within cancer trials is still an aspiration. Our consortium of international experts in medical imaging for drug development research, the Pharma Imaging Network for Therapeutics and Diagnostics (PINTAD), tapped the collective knowledge of its members to ground expectations, summarize common reasons for reader discordance, identify what factors can be controlled and which actions are likely to be effective in reducing discordance. Reinforced by an exhaustive literature review, our work defines the forces that shape reader variability. This review article aims to produce a singular authoritative resource outlining reader performance's practical realities within cancer trials, whether they occur within a clinical or an independent central review.
Collapse
|