Purpose
We aimed to assess the role of radiologists, cardiologists, and other medical and non-medical figures in cardiac magnetic resonance imaging (MRI) research in the last 34 years, focusing on ...first and last authorship, number of published studies, and journal impact factors (IF).
Methods
Articles in the field of cardiac MRI were considered in this systematic review and retrospective bibliometric analysis. For included studies, the first and last authors were categorized as cardiologists, radiologists/nuclear medicine physicians, medical doctors (MD) with specialties in both cardiology and radiology/nuclear medicine, and other MD and non-MD. Differences in the number of papers published overall and by year and institution location for the first and last author category were assessed. Mean IF differences between author categories were also investigated.
Results
A total of 2053 articles were included in the final analysis. For the first authors (
n
= 2011), 52% were cardiologists, 22% radiologists/nuclear medicine physicians, 16% other MD, 10% other non-MD, and 1% both cardiologists and radiologists/nuclear medicine physicians. Similarly, the last authors (
n
= 2029) resulted 54% cardiologists, 22% radiologists/nuclear medicine physicians, 15% other MD, 8% other non-MD, and 2% both cardiologists and radiologists/nuclear medicine physicians. No significant differences due to institution location in the first and last authorship proportions were found. Average journal IF was significantly higher for cardiologist first and last authors when compared to that of radiologists/nuclear medicine physicians (both
p
< 0.0001).
Conclusion
Over 50% of studies in the field of cardiac MRI published in the last 34 years are conducted by cardiologists.
Atypical cartilaginous tumour (ACT) and grade II chondrosarcoma (CS2) of long bones are respectively managed with watchful waiting or curettage and wide resection. Preoperatively, imaging diagnosis ...can be challenging due to interobserver variability and biopsy suffers from sample errors. The aim of this study is to determine diagnostic performance of MRI radiomics-based machine learning in differentiating ACT from CS2 of long bones.
One-hundred-fifty-eight patients with surgically treated and histology-proven cartilaginous bone tumours were retrospectively included at two tertiary bone tumour centres. The training cohort consisted of 93 MRI scans from centre 1 (n=74 ACT; n=19 CS2). The external test cohort consisted of 65 MRI scans from centre 2 (n=45 ACT; n=20 CS2). Bidimensional segmentation was performed on T1-weighted MRI. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, a machine-learning classifier (Extra Trees Classifier) was tuned on the training cohort using 10-fold cross-validation and tested on the external test cohort. In centre 2, its performance was compared with an experienced musculoskeletal oncology radiologist using McNemar's test.
After tuning on the training cohort (AUC=0.88), the machine-learning classifier had 92% accuracy (60/65, AUC=0.94) in identifying the lesions in the external test cohort. Its accuracies in correctly classifying ACT and CS2 were 98% (44/45) and 80% (16/20), respectively. The radiologist had 98% accuracy (64/65) with no difference compared to the classifier (p=0.134).
Machine learning showed high accuracy in classifying ACT and CS2 of long bones based on MRI radiomic features.
ESSR Young Researchers Grant.
Indeterminate adrenal masses (AM) pose a diagnostic challenge, and 2-
FFDG PET-CT serves as a problem-solving tool. Aim of this study was to investigate whether CT radiomics features could be used to ...predict the 2-
FFDG SUVmax of AM.
Patients with AM on 2-
FFDG PET-CT scan were grouped based on iodine contrast injection as CT contrast-enhanced (CE) or CT unenhanced (NCE). Two-dimensional segmentations of AM were manually obtained by multiple operators on CT images. Image resampling and discretization (bin number = 16) were performed. 919 features were calculated using PyRadiomics. After scaling, unstable, redundant, and low variance features were discarded. Using linear regression and the Uniform Manifold Approximation and Projection technique, a CT radiomics synthetic value (RadSV) was obtained. The correlation between CT RadSV and 2-
FFDG SUVmax was assessed with Pearson test.
A total of 725 patients underwent PET-CT from April 2020 to April 2021. In 150 (21%) patients, a total of 179 AM (29 bilateral) were detected. Group CE consisted of 84 patients with 108 AM (size = 18.1 ± 4.9 mm) and Group NCE of 66 patients with 71 AM (size = 18.5 ± 3.8 mm). In both groups, 39 features were selected. No statisticallyf significant correlation between CT RadSV and 2-
FFDG SUVmax was found (Group CE,
= 0.18 and
= 0.058; Group NCE,
= 0.13 and
= 0.27).
It might not be feasible to predict 2-
FFDG SUVmax of AM using CT RadSV. Its role as a problem-solving tool for indeterminate AM remains fundamental.
Purpose
The clinical presentation of idiopathic normal pressure hydrocephalus (iNPH) may overlap with progressive supranuclear palsy (PSP). The Magnetic Resonance Parkinsonism Index (MRPI), MRPI 2.0, ...and the interpeduncular angle (IPA) have been investigated to differentiate PSP from healthy controls (HC) and other parkinsonisms. We aimed to assess equivalences and differences in MRPI, MRPI 2.0, and IPA in iNPH, PSP, and HC groups.
Methods
We retrospectively recruited 99 subjects (30 iNPH, 32 PSP, 37 HC) from two institutions. MRI exams, acquired on either 1.5 T or 3 T scanners, included 3D T1-weighted images to measure MRPI, MRPI 2.0, and IPA. Inter- and intra-rater reliability was investigated with the intra-class correlation coefficient (ICC), and the two one-sided
t
tests (TOST) procedure was used to assess these markers in iNPH, PSP, and HC.
Results
For all the three measures, intra-rater and inter-rater ICC were excellent (range = 0.91–0.93).
In the comparison of iNPH and PSP with HC, differences for MRPI and MRPI 2.0 (
p
< 0.01 in all cases) and no equivalence (
p
= 1.00 in all cases) were found at TOST. iNPH and PSP MRPI showed no difference (
p
= 0.06) and no equivalence (
p
= 0.08). MRPI 2.0 was not equivalent (
p
= 0.06) and not different (
p
= 0.09) in the same two populations. PSP and HC IPA proved equivalent (
p
< 0.01) while iNPH IPA was different (
p
< 0.01) and not equivalent (
p
= 0.96 and 0.82) from both PSP and HC.
Conclusion
MRPI and MRPI 2.0 significantly overlap in iNPH and PSP, with risk of misdiagnosis, and for this reason may not be helpful in the differential diagnosis.
In the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques that allow machines to learn and get ...better at tasks such as recognition and prediction, which form the basis of clinical practice, are referred to as machine learning, which is a subfield of artificial intelligence. The number of artificial intelligence-and machine learnings-related publications in clinical journals has grown exponentially, driven by recent developments in computation and the accessibility of simple tools. However, clinicians are often not included in data science teams, which may limit the clinical relevance, explanability, workflow compatibility, and quality improvement of artificial intelligence solutions. Thus, this results in the language barrier between clinicians and artificial intelligence developers. Healthcare practitioners sometimes lack a basic understanding of artificial intelligence research because the approach is difficult for non-specialists to understand. Furthermore, many editors and reviewers of medical publications might not be familiar with the fundamental ideas behind these technologies, which may prevent journals from publishing high-quality artificial intelligence studies or, worse still, could allow for the publication of low-quality works. In this review, we aim to improve readers’ artificial intelligence literacy and critical thinking. As a result, we concentrated on what we consider the 10 most important qualities of artificial intelligence research: valid scientific purpose, high-quality data set, robust reference standard, robust input, no information leakage, optimal bias-variance tradeoff, proper model evaluation, proven clinical utility, transparent reporting, and open science. Before designing a study, one should have defined a sound scientific purpose. Then, it should be backed by a high-quality data set, robust input, and a solid reference standard. The artificial intelligence development pipeline should prevent information leakage. For the models, optimal bias-variance tradeoff should be achieved, and generalizability assessment must be adequately performed. The clinical value of the final models must also be established. After the study, thought should be given to transparency in publishing the process and results as well as open science for sharing data, code, and models. We hope this work may improve the artificial intelligence literacy and mindset of the readers.
Background
White matter hyperintensities (WMHs) of the brain are observed in normal aging, in various subtypes of dementia and in chronic pain, playing a crucial role in pain processing. The aim of ...the study has been to assess the WMHs in Burning Mouth Syndrome (BMS) patients by means of the Age-Related White Matter Changes scale (ARWMCs) and to analyze their predictors.
Methods
One hundred BMS patients were prospectively recruited and underwent magnetic resonance imaging (MRI) of the brain. Their ARWMCs scores were compared with those of an equal number of healthy subjects matched for age and sex. Intensity and quality of pain, psychological profile, and blood biomarkers of BMS patients were further investigated to find potential predictors of WMHs. Specifically, the Numeric Rating Scale (NRS), Short-Form McGill Pain Questionnaire (SF-MPQ), Hamilton rating scale for Depression and Anxiety (HAM-D and HAM-A), Pittsburgh Sleep Quality Index (PSQI), Epworth Sleepiness Scale (ESS) were administered.
Results
The BMS patients presented statistically significant higher scores on the ARWMCs compared to the controls, especially in the right frontal, left frontal, right parietal-occipital, left parietal-occipital, right temporal and left temporal lobes (
p
-values: <0.001, <0.001, 0.005, 0.002, 0.009, 0.002, and <0.001, respectively). Age, a lower educational level, unemployment, essential hypertension, and hypercholesterolemia were correlated to a higher total score on the ARWMCs (
p
-values: <0.001, 0.016, 0.014, 0.001, and 0.039, respectively). No correlation was found with the blood biomarkers, NRS, SF-MPQ, HAM-A, HAM-D, PSQI, and ESS.
Conclusion
Patients with BMS showed a higher frequency of WMHs of the brain as suggested by the higher ARWCs scores compared with the normal aging of the healthy subjects. These findings could have a role in the pathophysiology of the disease and potentially affect and enhance pain perception.
Clinical management ranges from surveillance or curettage to wide resection for atypical to higher-grade cartilaginous tumours, respectively. Our aim was to investigate the performance of computed ...tomography (CT) radiomics-based machine learning for classification of atypical cartilaginous tumours and higher-grade chondrosarcomas of long bones.
One-hundred-twenty patients with histology-proven lesions were retrospectively included. The training cohort consisted of 84 CT scans from centre 1 (n=55 G1 or atypical cartilaginous tumours; n=29 G2-G4 chondrosarcomas). The external test cohort consisted of the CT component of 36 positron emission tomography-CT scans from centre 2 (n=16 G1 or atypical cartilaginous tumours; n=20 G2-G4 chondrosarcomas). Bidimensional segmentation was performed on preoperative CT. Radiomic features were extracted. After dimensionality reduction and class balancing in centre 1, the performance of a machine-learning classifier (LogitBoost) was assessed on the training cohort using 10-fold cross-validation and on the external test cohort. In centre 2, its performance was compared with preoperative biopsy and an experienced radiologist using McNemar's test.
The classifier had 81% (AUC=0.89) and 75% (AUC=0.78) accuracy in identifying the lesions in the training and external test cohorts, respectively. Specifically, its accuracy in classifying atypical cartilaginous tumours and higher-grade chondrosarcomas was 84% and 78% in the training cohort, and 81% and 70% in the external test cohort, respectively. Preoperative biopsy had 64% (AUC=0.66) accuracy (p=0.29). The radiologist had 81% accuracy (p=0.75).
Machine learning showed good accuracy in classifying atypical and higher-grade cartilaginous tumours of long bones based on preoperative CT radiomic features.
ESSR Young Researchers Grant.
Idiopathic Parkinson's Disease (iPD) is a common motor neurodegenerative disorder. It affects more frequently the elderly population, causing a significant emotional burden both for the patient and ...caregivers, due to the disease-related onset of motor and cognitive disabilities. iPD's clinical hallmark is the onset of cardinal motor symptoms such as bradykinesia, rest tremor, rigidity, and postural instability. However, these symptoms appear when the neurodegenerative process is already in an advanced stage. Furthermore, the greatest challenge is to distinguish iPD from other similar neurodegenerative disorders, "atypical parkinsonisms", such as Multisystem Atrophy, Progressive Supranuclear Palsy and Cortical Basal Degeneration, since they share many phenotypic manifestations, especially in the early stages. The diagnosis of these neurodegenerative motor disorders is essentially clinical. Consequently, the diagnostic accuracy mainly depends on the professional knowledge and experience of the physician. Recent advances in artificial intelligence have made it possible to analyze the large amount of clinical and instrumental information in the medical field. The application machine learning algorithms to the analysis of neuroimaging data appear to be a promising tool for identifying microstructural alterations related to the pathological process in order to explain the onset of symptoms and the spread of the neurodegenerative process. In this context, the search for quantitative biomarkers capable of identifying parkinsonian patients in the prodromal phases of the disease, of correctly distinguishing them from atypical parkinsonisms and of predicting clinical evolution and response to therapy represent the main goal of most current clinical research studies. Our aim was to review the recent literature and describe the current knowledge about the contribution given by machine learning applications to research and clinical management of parkinsonian syndromes.
Purpose
To assess the feasibility and reproducibility of T2 relaxation time measurements of the trapeziometacarpal joint (TM) and triangular fibrocartilage complex (TFCC) on healthy subjects at 1.5 T ...MR.
Materials and methods
Thirty-four healthy volunteers underwent an axial oblique multislice multiecho spin-echo sequence of the wrist at 1.5 T, with 10 of them having performed another MR scan on a different 1.5 T scanner. Regions of interest were independently manually drawn by two musculoskeletal radiologists to include the cartilaginous part of the TM and TFCC. Intra-observer, inter-observer and inter-scanner reproducibility of T2 relaxation time measurements was tested using the Bland–Altman method.
Results
The mean T2 values obtained by the two radiologists were 29.9 ± 6.5 ms and 30.0 ± 6.1 ms in the TM and 24.5 ± 2.3 ms and 24.6 ± 2.8 ms in the TFCC, respectively. The mean values of the second series of T2 measurements obtained by the senior radiologist were 29.9 ± 6.5 ms and 30.0 ± 6.3 ms in the TM and 24.3 ± 2.9 ms in the TFCC. Inter-observer reproducibility in the TM and in the TFCC was 76% and 82%, respectively. Intra-observer reproducibility in the TM and TFCC was 71% and 76%, respectively. Inter-scanner reproducibility of T2 measurements was 36% in the TM and 85% in the TFCC, respectively.
Conclusion
The assessment of T2 relaxation time measurements of the cartilage of the TM and the TFCC seems to be feasible and reproducible, although the inter-scanner reproducibility of T2 measurements of the TM is suboptimal. Further studies including patients are warranted to prove the utility of this tool.