-
European Radiology Nov 2022There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and... (Review)
Review
OBJECTIVE
There has been a large amount of research in the field of artificial intelligence (AI) as applied to clinical radiology. However, these studies vary in design and quality and systematic reviews of the entire field are lacking.This systematic review aimed to identify all papers that used deep learning in radiology to survey the literature and to evaluate their methods. We aimed to identify the key questions being addressed in the literature and to identify the most effective methods employed.
METHODS
We followed the PRISMA guidelines and performed a systematic review of studies of AI in radiology published from 2015 to 2019. Our published protocol was prospectively registered.
RESULTS
Our search yielded 11,083 results. Seven hundred sixty-seven full texts were reviewed, and 535 articles were included. Ninety-eight percent were retrospective cohort studies. The median number of patients included was 460. Most studies involved MRI (37%). Neuroradiology was the most common subspecialty. Eighty-eight percent used supervised learning. The majority of studies undertook a segmentation task (39%). Performance comparison was with a state-of-the-art model in 37%. The most used established architecture was UNet (14%). The median performance for the most utilised evaluation metrics was Dice of 0.89 (range .49-.99), AUC of 0.903 (range 1.00-0.61) and Accuracy of 89.4 (range 70.2-100). Of the 77 studies that externally validated their results and allowed for direct comparison, performance on average decreased by 6% at external validation (range increase of 4% to decrease 44%).
CONCLUSION
This systematic review has surveyed the major advances in AI as applied to clinical radiology.
KEY POINTS
• While there are many papers reporting expert-level results by using deep learning in radiology, most apply only a narrow range of techniques to a narrow selection of use cases. • The literature is dominated by retrospective cohort studies with limited external validation with high potential for bias. • The recent advent of AI extensions to systematic reporting guidelines and prospective trial registration along with a focus on external validation and explanations show potential for translation of the hype surrounding AI from code to clinic.
Topics: Humans; Artificial Intelligence; Retrospective Studies; Prospective Studies; Radiology; Radiography
PubMed: 35420305
DOI: 10.1007/s00330-022-08784-6 -
BioMed Research International 2021The objective of this systematic review was to investigate the quality and outcome of studies into artificial intelligence techniques, analysis, and effect in dentistry.
OBJECTIVE
The objective of this systematic review was to investigate the quality and outcome of studies into artificial intelligence techniques, analysis, and effect in dentistry.
MATERIALS AND METHODS
Using the MeSH keywords: artificial intelligence (AI), dentistry, AI in dentistry, neural networks and dentistry, machine learning, AI dental imaging, and AI treatment recommendations and dentistry. Two investigators performed an electronic search in 5 databases: PubMed/MEDLINE (National Library of Medicine), Scopus (Elsevier), ScienceDirect databases (Elsevier), Web of Science (Clarivate Analytics), and the Cochrane Collaboration (Wiley). The English language articles reporting on AI in different dental specialties were screened for eligibility. Thirty-two full-text articles were selected and systematically analyzed according to a predefined inclusion criterion. These articles were analyzed as per a specific research question, and the relevant data based on article general characteristics, study and control groups, assessment methods, outcomes, and quality assessment were extracted.
RESULTS
The initial search identified 175 articles related to AI in dentistry based on the title and abstracts. The full text of 38 articles was assessed for eligibility to exclude studies not fulfilling the inclusion criteria. Six articles not related to AI in dentistry were excluded. Thirty-two articles were included in the systematic review. It was revealed that AI provides accurate patient management, dental diagnosis, prediction, and decision making. Artificial intelligence appeared as a reliable modality to enhance future implications in the various fields of dentistry, i.e., diagnostic dentistry, patient management, head and neck cancer, restorative dentistry, prosthetic dental sciences, orthodontics, radiology, and periodontics.
CONCLUSION
The included studies describe that AI is a reliable tool to make dental care smooth, better, time-saving, and economical for practitioners. AI benefits them in fulfilling patient demand and expectations. The dentists can use AI to ensure quality treatment, better oral health care outcome, and achieve precision. AI can help to predict failures in clinical scenarios and depict reliable solutions. However, AI is increasing the scope of state-of-the-art models in dentistry but is still under development. Further studies are required to assess the clinical performance of AI techniques in dentistry.
Topics: Artificial Intelligence; Dentistry; Diagnostic Imaging; Forecasting; Humans; Machine Learning; Neural Networks, Computer; Radiography, Dental
PubMed: 34258283
DOI: 10.1155/2021/9751564 -
Systematic literature review of imaging features of spinal degeneration in asymptomatic populations.AJNR. American Journal of Neuroradiology Apr 2015Degenerative changes are commonly found in spine imaging but often occur in pain-free individuals as well as those with back pain. We sought to estimate the prevalence,... (Review)
Review
BACKGROUND AND PURPOSE
Degenerative changes are commonly found in spine imaging but often occur in pain-free individuals as well as those with back pain. We sought to estimate the prevalence, by age, of common degenerative spine conditions by performing a systematic review studying the prevalence of spine degeneration on imaging in asymptomatic individuals.
MATERIALS AND METHODS
We performed a systematic review of articles reporting the prevalence of imaging findings (CT or MR imaging) in asymptomatic individuals from published English literature through April 2014. Two reviewers evaluated each manuscript. We selected age groupings by decade (20, 30, 40, 50, 60, 70, 80 years), determining age-specific prevalence estimates. For each imaging finding, we fit a generalized linear mixed-effects model for the age-specific prevalence estimate clustering in the study, adjusting for the midpoint of the reported age interval.
RESULTS
Thirty-three articles reporting imaging findings for 3110 asymptomatic individuals met our study inclusion criteria. The prevalence of disk degeneration in asymptomatic individuals increased from 37% of 20-year-old individuals to 96% of 80-year-old individuals. Disk bulge prevalence increased from 30% of those 20 years of age to 84% of those 80 years of age. Disk protrusion prevalence increased from 29% of those 20 years of age to 43% of those 80 years of age. The prevalence of annular fissure increased from 19% of those 20 years of age to 29% of those 80 years of age.
CONCLUSIONS
Imaging findings of spine degeneration are present in high proportions of asymptomatic individuals, increasing with age. Many imaging-based degenerative features are likely part of normal aging and unassociated with pain. These imaging findings must be interpreted in the context of the patient's clinical condition.
Topics: Aging; Back Pain; Female; Humans; Intervertebral Disc Degeneration; Magnetic Resonance Imaging; Male; Middle Aged; Prevalence; Tomography, X-Ray Computed
PubMed: 25430861
DOI: 10.3174/ajnr.A4173 -
European Journal of Nuclear Medicine... Mar 2021In recent years, the clinical availability of scanners for integrated positron emission tomography (PET) and magnetic resonance imaging (MRI) has enabled the practical... (Meta-Analysis)
Meta-Analysis Review
AIM
In recent years, the clinical availability of scanners for integrated positron emission tomography (PET) and magnetic resonance imaging (MRI) has enabled the practical potential of multimodal, combined metabolic-receptor, anatomical, and functional imaging to be explored. The present systematic review and meta-analysis summarize the diagnostic information provided by PET/MRI in patients with prostate cancer (PCa).
MATERIALS AND METHODS
A literature search was conducted in three different databases. The terms used were "choline" or "prostate-specific membrane antigen - PSMA" AND "prostate cancer" or "prostate" AND "PET/MRI" or "PET MRI" or "PET-MRI" or "positron emission tomography/magnetic resonance imaging." All relevant records identified were combined, and the full texts were retrieved. Reports were excluded if (1) they did not consider hybrid PET/MRI; or (2) the sample size was < 10 patients; or (3) the raw data were not enough to enable the completion of a 2 × 2 contingency table.
RESULTS
Fifty articles were eligible for systematic review, and 23 for meta-analysis. The pooled data concerned 2104 patients. Initial disease staging was the main indication for PET/MRI in 24 studies. Radiolabeled PSMA was the tracer most frequently used. In primary tumors, the pooled sensitivity for the patient-based analysis was 94.9%. At restaging, the pooled detection rate was 80.9% and was higher for radiolabeled PSMA than for choline (81.8% and 77.3%, respectively).
CONCLUSIONS
PET/MRI proved highly sensitive in detecting primary PCa, with a high detection rate for recurrent disease, particularly when radiolabeled PSMA was used.
Topics: Humans; Magnetic Resonance Imaging; Male; Positron Emission Tomography Computed Tomography; Positron-Emission Tomography; Prostatic Neoplasms; Radiopharmaceuticals; Tomography, X-Ray Computed
PubMed: 32901351
DOI: 10.1007/s00259-020-05025-0 -
Journal of Vascular Surgery. Venous and... Jan 2024The Society for Vascular Surgery, the American Venous Forum, and the American Vein and Lymphatic Society recently published Part I of the 2022 clinical practice... (Meta-Analysis)
Meta-Analysis
The 2023 Society for Vascular Surgery, American Venous Forum, and American Vein and Lymphatic Society clinical practice guidelines for the management of varicose veins of the lower extremities. Part II: Endorsed by the Society of Interventional Radiology and the Society for Vascular Medicine.
The Society for Vascular Surgery, the American Venous Forum, and the American Vein and Lymphatic Society recently published Part I of the 2022 clinical practice guidelines on varicose veins. Recommendations were based on the latest scientific evidence researched following an independent systematic review and meta-analysis of five critical issues affecting the management of patients with lower extremity varicose veins, using the patients, interventions, comparators, and outcome system to answer critical questions. Part I discussed the role of duplex ultrasound scanning in the evaluation of varicose veins and treatment of superficial truncal reflux. Part II focuses on evidence supporting the prevention and management of varicose vein patients with compression, on treatment with drugs and nutritional supplements, on evaluation and treatment of varicose tributaries, on superficial venous aneurysms, and on the management of complications of varicose veins and their treatment. All guidelines were based on systematic reviews, and they were graded according to the level of evidence and the strength of recommendations, using the GRADE method. All ungraded Consensus Statements were supported by an extensive literature review and the unanimous agreement of an expert, multidisciplinary panel. Ungraded Good Practice Statements are recommendations that are supported only by indirect evidence. The topic, however, is usually noncontroversial and agreed upon by most stakeholders. The Implementation Remarks contain technical information that supports the implementation of specific recommendations. This comprehensive document includes a list of all recommendations (Parts I-II), ungraded consensus statements, implementation remarks, and best practice statements to aid practitioners with appropriate, up-to-date management of patients with lower extremity varicose veins.
Topics: Humans; United States; Venous Insufficiency; Radiology, Interventional; Sclerotherapy; Saphenous Vein; Treatment Outcome; Varicose Veins; Vascular Surgical Procedures; Lower Extremity; Cardiology
PubMed: 37652254
DOI: 10.1016/j.jvsv.2023.08.011 -
European Spine Journal : Official... Jul 2021Idiopathic scoliosis, defined as a > 10° curvature of the spine in the frontal plane, is one of the most common spinal deformities. Age, initial curve magnitude and... (Review)
Review
INTRODUCTION
Idiopathic scoliosis, defined as a > 10° curvature of the spine in the frontal plane, is one of the most common spinal deformities. Age, initial curve magnitude and other parameters define whether a scoliotic deformity will progress or not. Still, their interactions and amounts of individual contribution are not fully elaborated and were the aim of this systematic review.
METHODS
A systematic literature search was conducted in the common databases using MESH terms, searching for predictive factors of curve progression in adolescent idiopathic scoliosis ("adolescent idiopathic scoliosis" OR "ais" OR "idiopathic scoliosis") AND ("predictive factors" OR "progression" OR "curve progression" OR "prediction" OR "prognosis"). The identified and analysed factors of each study were rated to design a top five scale of the most relevant factors.
RESULTS
Twenty-eight investigations with 8255 patients were identified by literature search. Patient-specific risk factors for curve progression from initial curve were age (at diagnosis < 13 years), family history, bone mineral status (< 110 mg/cm in quantitative CT) and height velocity (7-8 cm/year, peak 11.6 ± 1.4 years). Relevant radiological criteria indicating curve progression included skeletal maturity, marked by Risser stages (Risser < 1) or Sanders Maturity Scale (SMS < 5), the initial extent of the Cobb angle (> 25° progression) and curve location (thoracic single or double curve).
DISCUSSION
This systematic review summarised the current state of knowledge as the basis for creation of patient-specific algorithms regarding a risk calculation for a progressive scoliotic deformity. Curve magnitude is the most relevant predictive factor, followed by status of skeletal maturity and curve location.
Topics: Adolescent; Disease Progression; Humans; Prognosis; Radiography; Retrospective Studies; Scoliosis; Spine
PubMed: 33772381
DOI: 10.1007/s00586-021-06817-0 -
Radiotherapy and Oncology : Journal of... Jul 2020Recognizing the rapidly increasing interest and evidence in using metastasis-directed radiotherapy (MDRT) for oligometastatic disease (OMD), ESTRO and ASTRO convened a...
BACKGROUND
Recognizing the rapidly increasing interest and evidence in using metastasis-directed radiotherapy (MDRT) for oligometastatic disease (OMD), ESTRO and ASTRO convened a committee to establish consensus regarding definitions of OMD and define gaps in current evidence.
METHODS
A systematic literature review focused on curative intent MDRT was performed in Medline, Embase and Cochrane. Subsequent consensus opinion, using a Delphi process, highlighted the current state of evidence and the limitations in the available literature.
RESULTS
Available evidence regarding the use of MDRT for OMD mostly derives from retrospective, single-centre series, with significant heterogeneity in patient inclusion criteria, definition of OMD, and outcomes reported. Consensus was reached that OMD is largely independent of primary tumour, metastatic location and the presence or length of a disease-free interval, supporting both synchronous and metachronous OMD. In the absence of clinical data supporting a maximum number of metastases and organs to define OMD, and of validated molecular biomarkers, consensus supported the ability to deliver safe and clinically meaningful radiotherapy with curative intent to all metastatic sites as a minimum requirement for defining OMD in the context of radiotherapy. Systemic therapy induced OMD was identified as a distinct state of OMD. High-resolution imaging to assess and confirm OMD is crucial, including brain imaging when indicated. Minimum common endpoints such as progression-free and overall survival, local control, toxicity and quality-of-life should be reported; uncommon endpoints as deferral of systemic therapy and cost were endorsed.
CONCLUSION
While significant heterogeneity exists in the current OMD definitions in the literature, consensus was reached on multiple key questions. Based on available data, OMD can to date be defined as 1-5 metastatic lesions, a controlled primary tumor being optional, but where all metastatic sites must be safely treatable. Consistent definitions and reporting are warranted and encouraged in ongoing trials and reports generating further evidence to optimize patient benefits.
Topics: Consensus; Diagnostic Imaging; Humans; Neoplasm Metastasis; Neoplasms; Radiation Oncology; Retrospective Studies
PubMed: 32388150
DOI: 10.1016/j.radonc.2020.04.003 -
Clinical Oral Investigations Jul 2021Deep learning (DL) has been increasingly employed for automated landmark detection, e.g., for cephalometric purposes. We performed a systematic review and meta-analysis... (Meta-Analysis)
Meta-Analysis Review
OBJECTIVES
Deep learning (DL) has been increasingly employed for automated landmark detection, e.g., for cephalometric purposes. We performed a systematic review and meta-analysis to assess the accuracy and underlying evidence for DL for cephalometric landmark detection on 2-D and 3-D radiographs.
METHODS
Diagnostic accuracy studies published in 2015-2020 in Medline/Embase/IEEE/arXiv and employing DL for cephalometric landmark detection were identified and extracted by two independent reviewers. Random-effects meta-analysis, subgroup, and meta-regression were performed, and study quality was assessed using QUADAS-2. The review was registered (PROSPERO no. 227498).
DATA
From 321 identified records, 19 studies (published 2017-2020), all employing convolutional neural networks, mainly on 2-D lateral radiographs (n=15), using data from publicly available datasets (n=12) and testing the detection of a mean of 30 (SD: 25; range.: 7-93) landmarks, were included. The reference test was established by two experts (n=11), 1 expert (n=4), 3 experts (n=3), and a set of annotators (n=1). Risk of bias was high, and applicability concerns were detected for most studies, mainly regarding the data selection and reference test conduct. Landmark prediction error centered around a 2-mm error threshold (mean; 95% confidence interval: (-0.581; 95 CI: -1.264 to 0.102 mm)). The proportion of landmarks detected within this 2-mm threshold was 0.799 (0.770 to 0.824).
CONCLUSIONS
DL shows relatively high accuracy for detecting landmarks on cephalometric imagery. The overall body of evidence is consistent but suffers from high risk of bias. Demonstrating robustness and generalizability of DL for landmark detection is needed.
CLINICAL SIGNIFICANCE
Existing DL models show consistent and largely high accuracy for automated detection of cephalometric landmarks. The majority of studies so far focused on 2-D imagery; data on 3-D imagery are sparse, but promising. Future studies should focus on demonstrating generalizability, robustness, and clinical usefulness of DL for this objective.
Topics: Cephalometry; Deep Learning; Radiography; Reproducibility of Results
PubMed: 34046742
DOI: 10.1007/s00784-021-03990-w -
AJR. American Journal of Roentgenology Mar 2021Imaging plays a critical role in the assessment of patients with femoroacetabular impingement (FAI). With better understanding of the underlying pathomechanics and...
Imaging plays a critical role in the assessment of patients with femoroacetabular impingement (FAI). With better understanding of the underlying pathomechanics and advances in joint-preserving surgery, there is an increasing need to define the most appropriate imaging workup. The purpose of this article is to provide guidance on best practices for imaging of patients with FAI in light of recent advances in corrective FAI surgery. Pelvic radiography with dedicated hip projections is the basis of the diagnostic workup of patients with suspected FAI to assess arthritic changes and acetabular coverage and to screen for cam deformities. Chondrolabral lesions should be evaluated with unenhanced MRI or MR arthrography. The protocol should include a large-FOV fluid-sensitive sequence to exclude conditions that can mimic or coexist with FAI, radial imaging to accurately determine the presence of a cam deformity, and imaging of the distal femoral condyles for measurement of femoral torsion. CT remains a valuable tool for planning of complex surgical corrections. Advanced imaging, such as 3D simulation, biochemical MRI, and MR arthrography with application of leg traction, has great potential to improve surgical decision-making. Further research is needed to assess the added clinical value of these techniques.
Topics: Acetabulum; Adult; Arthrography; Diagnosis, Differential; Evidence-Based Medicine; Female; Femoracetabular Impingement; Femur Head; Femur Neck; Hip Dislocation, Congenital; Hip Joint; Humans; Magnetic Resonance Imaging; Male; Organ Sparing Treatments; Osteoarthritis, Hip; Practice Guidelines as Topic; Tomography, X-Ray Computed; Torsion Abnormality; Traction; Young Adult
PubMed: 33474984
DOI: 10.2214/AJR.20.22783 -
Journal of Otolaryngology - Head & Neck... May 2016The purpose of the present review is to systematically and critically analyze the available literature regarding the importance, applicability, and practicality of... (Review)
Review
PURPOSE
The purpose of the present review is to systematically and critically analyze the available literature regarding the importance, applicability, and practicality of (MRI), computerized tomography (CT) or cone-beam CT (CBCT) image registration for TMJ anatomy and assessment.
DATA SOURCES
A systematic search of 4 databases; MEDLINE, EMBASE, EBM reviews and Scopus, was conducted by 2 reviewers. An additional manual search of the bibliography was performed.
INCLUSION CRITERIA
All articles discussing the magnetic resonance imaging MRI and CT or CBCT image registration for temporomandibular joint (TMJ) visualization or assessment were included.
RESULTS AND INCLUDED ARTICLES' CHARACTERISTICS
Only 3 articles satisfied the inclusion criteria. All included articles were published within the last 7 years. Two articles described MRI to CT multimodality image registration as a complementary tool to visualize TMJ. Both articles used images of one patient only to introduce the complementary concept of MRI-CT fused image. One article assessed the reliability of using MRI-CBCT registration to evaluate the TMJ disc position and osseous pathology for 10 temporomandibular disorder (TMD) patients.
CONCLUSION
There are very limited studies of MRI-CT/CBCT registration to reach a conclusion regarding its accuracy or clinical use in the temporomandibular joints.
Topics: Cone-Beam Computed Tomography; Humans; Image Processing, Computer-Assisted; Magnetic Resonance Imaging; Temporomandibular Joint; Temporomandibular Joint Disorders; Tomography, X-Ray Computed
PubMed: 27164975
DOI: 10.1186/s40463-016-0144-4