Comparable Diagnostic Performance Research Articles

A deep learning-based approach toward differentiating scalp psoriasis and seborrheic dermatitis from dermoscopic images.

This study aims to develop a new diagnostic method for discriminating scalp psoriasis and seborrheic dermatitis based on a deep learning (DL) model, which uses the dermatoscopic image as input and achieved higher accuracy than dermatologists trained with dermoscopy. A total of 1,358 pictures (obtained from 617 patients) with pathological and diagnostic confirmed skin diseases (508 psoriases, 850 seborrheic dermatitides) were randomly allocated into the training, validation, and testing datasets (1,088/134/136) in this study. A DL model concerning dermatoscopic images was established using the transfer learning technique and trained for diagnosing two diseases. The developed DL model exhibits good sensitivity, specificity, and Area Under Curve (AUC) (96.1, 88.2, and 0.922%, respectively), it outperformed all dermatologists in the diagnosis of scalp psoriasis and seborrheic dermatitis when compared to five dermatologists with various levels of experience. Furthermore, non-proficient doctors with the assistance of the DL model can achieve comparable diagnostic performance to dermatologists proficient in dermoscopy. One dermatology graduate student and two general practitioners significantly improved their diagnostic performance, where their AUC values increased from 0.600, 0.537, and 0.575 to 0.849, 0.778, and 0.788, respectively, and their diagnosis consistency was also improved as the kappa values went from 0.191, 0.071, and 0.143 to 0.679, 0.550, and 0.568, respectively. DL enjoys favorable computational efficiency and requires few computational resources, making it easy to deploy in hospitals. The developed DL model has favorable performance in discriminating two skin diseases and can improve the diagnosis, clinical decision-making, and treatment of dermatologists in primary hospitals.

CT Extracellular Volume Fraction versus Myocardium-to-Lumen Signal Ratio for Cardiac Amyloidosis.

Background Large studies on the diagnostic performance of CT-derived myocardial extracellular volume fraction (ECV) for detecting cardiac amyloidosis are lacking. A simple and practical index as a surrogate for CT ECV would be clinically useful. Purpose To compare the diagnostic performances between CT-derived myocardial ECV and myocardium-to-lumen signal ratio for the detection of cardiac amyloidosis in a large patient sample. Materials and Methods This retrospective study included patients who underwent CT ECV analysis because of suspected heart failure or cardiomyopathy between January 2018 and July 2021. CT ECV was quantified using routine pre-transcatheter aortic valve replacement planning cardiac CT, pre-atrial fibrillation ablation planning cardiac CT, or coronary CT angiography with the addition of unenhanced and delayed phase cardiac CT scans. The diagnostic performances of CT ECV and myocardium-to-lumen signal ratio in delayed phase cardiac CT (a simplified index not requiring unenhanced CT and hematocrit) for detecting cardiac amyloidosis were evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results Of 552 patients (mean age, 69 years ± 14 [SD]; 295 men), 41 had cardiac amyloidosis. The sensitivity of CT ECV for amyloidosis was 90% (37 of 41 patients [95% CI: 77, 97]), with a specificity of 92% (472 of 511 patients [95% CI: 90, 95]) and optimal ECV cutoff value of 37% (AUC, 0.97 [95% CI: 0.96, 0.99]). The sensitivity of myocardium-to-lumen signal ratio was 88% (36 of 41 patients [95% CI: 74, 96]), with a specificity of 92% (469 of 511 patients [95% CI: 89, 94]) and optimal myocardium-to-lumen signal ratio cutoff value of 0.87 (AUC, 0.96 [95% CI: 0.94, 0.97]; P = .27 for comparison with ECV). Conclusion CT-derived myocardial extracellular volume fraction and myocardium-to-lumen signal ratio showed comparable and excellent diagnostic performance in detecting cardiac amyloidosis in a large patient sample. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Williams in this issue.

0/1h-algorithm using a new high-sensitivity cardiac troponin I assay for early diagnosis of myocardial infarction

Abstract Background The clinical performance of the novel high-sensitivity cardiac troponin I EXL (hs-cTnI-EXL) assay is unknown so far. Purpose We aimed to validate the clinical performance of the hs-cTnI-EXL assay and to derive and validate an hs-cTnI-EXL-specific 0/1h-algorithm for the early diagnosis of myocardial infarction (MI). Methods This multicenter study included patients presenting to the emergency department with symptoms suggestive of myocardial infarction. Central adjudication of final diagnoses was performed by two independent cardiologists using all clinical information including cardiac imaging twice: first, using serial hs-cTnI-Architect (primary analysis) and second, using serial hs-cTnT-Elecsys (secondary analysis) concentrations in addition to those clinically used (hs)-cTn. Hs-cTnI-EXL was measured at presentation and at 1h. The primary objective was to directly compare diagnostic accuracy quantified by the area under the receiver-operating-characteristic curve (AUC) of hs-cTnI-EXL, hs-cTnI-Architect and hs-cTnT-Elecsys. Secondary objectives included the derivation and validation of an hs-cTnI- EXL-specific 0/1h-algorithm. Results MI was the adjudicated final diagnosis in 204/1454 (14%) patients. At presentation, the AUC for hs-cTnI-EXL was 0.94 (95% CI, 0.93–0.96), being comparable to hs-cTnI-Architect (0.95; 95% CI, 0.93–0.96) and hs-cTnT-Elecsys (0.93; 95% CI, 0.91–0.95; Figure 1). In the derivation cohort (n=813), an optimal hs-cTnI-EXL-0/1h-algorithm was rule-out of MI with <9ng/L if onset of chest pain >3h or <9ng/L & 0h-1h-change <5ng/L, and rule-in with ≥160ng/L or 0h-1h-change ≥100ng/L. In the validation cohort (n=345), this hs-cTnI-EXL-0/1h-algorithm also performed well: rule-out in 56% of patients, negative predictive value 99.5% (95% CI, 97.1–99.9), sensitivity 97.8% (95% CI, 88.7–99.6), rule-in in 9% of patients, positive predictive value 83.3% (95% CI, 66.4–92.7), specificity 98.3% (95% CI, 96.1–99.3; Figure 2). Secondary analyses confirmed the findings using adjudication including serial measurements of hs-cTnT-Elecsys. Conclusions Hs-cTnI-EXL has comparable diagnostic performance to the currently best-validated hs-cTnT/I assays. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): Swiss National Foundation, Swiss Heart Foundation

Diagnostic evaluation of nCoV-QS, nCoV-QM-N, and nCoV-OM detection kits based on rRT-PCR for detection of SARS-CoV-2 in Ecuador

BackgroundEcuador was harshly impacted by COVID-19, in the region was the epicenter of the pandemic with the highest mortality rates and with the lowest rates of processed samples. Real-time reverse transcription PCR assays are essential to identify and manage the SARS-CoV-2 outbreak. Because of the global emergency, in Ecuador several commercial kits were introduced for use without clinical validation. In this manner, having the need to perform an evaluation with clinical samples before use for population screening. ObjectiveThis study aimed to evaluate the diagnostic performance of the nCoV-QS, nCoV-QM-N, nCoV-OM detection kits lately available in Ecuador, against the LightMix E/RdRp kit using nasopharyngeal swab (NPS) samples. Materials and methods198 nasopharyngeal samples were used (66 fresh NPS and 132 RNA stored samples). All samples were analyzed for SARS-CoV-2 with nCoV-QS, nCoV-QM-N, nCoV-OM detection kits and compared the concordance (Cohen's Kappa index, positive percentage agreement and negative percentage agreement) to LightMix E/RdRp as reference detection kit. ResultsThe 198 samples presented strong concordance (96% nCoV-QM-N, 100% nCoV-OM and 100% nCoV-QS). The individual performance of each gene showed that the nCoV-OM kit had a higher number of samples detected with the ORF3a (52.5%) and N (53.5%) genes. The combined genes demonstrated that ORF3a/N of nCoV-OM and nCoV-QS kits presented a higher percentage of detection with 52.5% and 48.5%, respectively. Finally, the detection rate and cycle threshold were not different between ORF3a, N, and E target genes. ConclusionThe nCoV-QS, nCoV-QM-N, and nCoV-OM Detection kits have comparable diagnostic performance to the emergency approved LightMix E/RdRp kit for SARS-CoV-2 detection in suspected COVID-19 patients.

State of the Art: Lung Cancer Staging Using Updated Imaging Modalities.

Lung cancer is among the most common mortality causes worldwide. This scientific article is a comprehensive review of current knowledge regarding screening, subtyping, imaging, staging, and management of treatment response for lung cancer. The traditional imaging modality for screening and initial lung cancer diagnosis is computed tomography (CT). Recently, a dual-energy CT was proven to enhance the categorization of variable pulmonary lesions. The National Comprehensive Cancer Network (NCCN) recommends usage of fluorodeoxyglucose positron emission tomography (FDG PET) in concert with CT to properly stage lung cancer and to prevent fruitless thoracotomies. Diffusion MR is an alternative to FDG PET/CT that is radiation-free and has a comparable diagnostic performance. For response evaluation after treatment, FDG PET/CT is a potent modality which predicts survival better than CT. Updated knowledge of lung cancer genomic abnormalities and treatment regimens helps to improve the radiologists’ skills. Incorporating the radiologic experience is crucial for precise diagnosis, therapy planning, and surveillance of lung cancer.

Differential diagnosis and feature visualization for thyroid nodules using computer-aided ultrasonic diagnosis system: initial clinical assessment

BackgroundTo assess the diagnostic efficacy of the computer-aided ultrasonic diagnosis system (CAD system) in differentiating benign and malignant thyroid nodules.MethodsThe images of 296 thyroid nodules were included in validation sets. The diagnostic efficacy of the CAD system was compared with that of junior physicians and senior physicians, as well as that of the combination diagnosis of the CAD system with junior physicians. The diagnostic efficacy of the CAD system for different sizes of thyroid nodules was compared.ResultsThe diagnostic sensitivity and accuracy of the CAD system were higher than those of junior physicians (83.4% vs. 72.2%, 73.0% vs. 69.6%), but the diagnostic specificity of the CAD system was lower than that of junior physicians (62.1% vs. 66.9%). The diagnostic accuracy of the CAD system was lower than that of senior physicians (73.0% vs. 83.8%). However, the combination diagnosis of the CAD system with junior physicians had higher accuracy (81.8%) and AUC (0.842) than those of either the CAD system or junior physicians alone, and comparable diagnostic performance with those of senior physicians. The Kappa was 0.635 in the combination diagnosis of the CAD system with junior physicians, showing good consistency with the pathological results. The accuracy (76.4%) of the CAD system was the highest for nodules of 1–2 cm.ConclusionThe CAD system can effectively assist physicians to identify malignant and benign thyroid nodules, reduce the overdiagnosis and overtreatment of thyroid nodules, avoid unnecessary invasive fine needle aspiration, and improve the diagnostic accuracy of junior physicians.

Comparison of imaging findings of macrotrabecular-massive hepatocellular carcinoma using CT and gadoxetic acid-enhanced MRI.

To investigate the imaging findings of macrotrabecular-massive hepatocellular carcinoma (MTM-HCC) on CT and MRI, and examine their diagnostic performance and prognostic significance. We retrospectively enrolled 220 consecutive patients who underwent hepatic resection between June 2009 and December 2013 for single treatment-naïve HCC, who have preoperative CT and gadoxetic acid-enhanced MRI. Independent reviews of histopathology and imaging were performed by two reviewers. Previously reported imaging findings, LI-RADS category, and CT attenuation of MTM-HCC were investigated. The diagnostic performance of the MTM-HCC diagnostic criteria was compared across imaging modalities. MTM-HCC was associated with ≥ 50% arterial phase hypovascular component, intratumoral artery, arterial phase peritumoral enhancement, and non-smooth tumor margin on CT and MRI (p < .05). Arterial phase hypovascular components were less commonly observed on MRI subtraction images than on CT or MRI, while non-rim arterial phase hyperenhancement and LR-5 were more commonly observed on MRI subtraction images than on MRI (p < .05). MTM-HCC showed lower tumor attenuation in the CT arterial phase (p = .01). Rhee's criteria, defined as ≥ 50% hypovascular component and ≥ 2 ancillary findings (intratumoral artery, arterial phase peritumoral enhancement, and non-smooth tumor margin), showed similar diagnostic performance for MRI (sensitivity, 41%; specificity, 97%) and CT (sensitivity, 31%; specificity, 94%). Rhee's criteria on CT were independent prognostic factors for overall survival. The MRI diagnostic criteria for MTM-HCC are applicable on CT, showing similar diagnostic performance and prognostic significance. For MTM-HCC, arterial phase subtraction images can aid in the HCC diagnosis by depicting subtle arterial hypervascularity. • MTM-HCC on CT demonstrated previously described MRI findings, including arterial phase hypovascular component, intratumoral artery, arterial phase peritumoral enhancement, and necrosis. • The MRI diagnostic criteria for MTM-HCC were also applicable to CT, showing comparable diagnostic performance and prognostic significance. • On arterial phase subtraction imaging, MTM-HCC more frequently demonstrated non-rim enhancement and LR-5 and less frequently LR-M than MRI arterial phase, which may aid in the diagnosis of HCC.

Comparison of compressed sensing-sensitivity encoding (CS-SENSE) accelerated 3D T2W TSE sequence versus conventional 3D and 2D T2W TSE sequences in rectal cancer: a prospective study

PurposeThis study aimed to evaluate the image quality and diagnostic value of compressed sensing-sensitivity encoding (CS-SENSE) accelerated 3-dimensional (3D) T2-weighted turbo spin-echo (T2W TSE) sequence in patients with rectal cancer compared with conventional 3D and 2-dimensional (2D) sequences.MethodsA total of 54 patients who underwent the above three sequences were enrolled. Two radiologists independently reviewed the image quality using an ordinal 5-point Likert scale. The quantitative measurement was performed to calculate the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The diagnostic value was assessed using TN staging, extramural vascular invasion and mesorectal fascia status. Friedman and McNemar’s tests were applied for comparative analysis.ResultsForty-two patients were successfully included. Compared with 3D and 2D sequences, the CS-SENSE 3D sequence speeded up by 39% and 23%, respectively. The edge sharpness of CS-SENSE 3D images was similar to that of 3D and 2D images. The noise of CS-SENSE 3D images was comparable to that of 3D images but higher than that of 2D images. The SNRtumor and SNRrectal wall of CS-SENSE 3D images were considerably lower than those of 3D and 2D images. The CNR of CS-SENSE 3D images was similar to that of 3D images but lower than that of 2D images. However, no considerable differences were noted in diagnostic value among the three sequences.ConclusionsCS-SENSE 3D T2 sequence provided comparable diagnostic performance, with substantially reduced imaging time and no significant sacrifices in image quality. This technique may serve as a reliable tool for evaluating rectal cancer.Graphical abstract

Simultaneous liver steatosis, fibrosis and iron deposition quantification with mDixon quant based on radiomics analysis in a rabbit model

PurposeTo evaluate the feasibility of simultaneous quantification of liver fibrosis, liver steatosis and abnormal iron deposition using mDixon Quant based on radiomics analysis, and to eliminate the interference among different histopathologic features. MethodsOne hundred and twenty rabbits that were administered CCl4 for 4–16 weeks and a cholesterol rich diet for the initial 4 weeks in the experimental group and 20 rabbits in the control group were examined using mDixon. Radiomics features of the whole liver were extracted from PDFF and R2* and radiomics models for discriminating steatosis: S0-S1 vs. S2-S4, fibrosis: F0–F2 vs. F3–F4 and iron deposition: normal vs. abnormal were constructed respectively and evaluated using receiver operating characteristic (ROC) curves with the histopathological results as reference standard. Combined corrected models merging the radscore and the other two histopathologic features were evaluated using multiple logistic regression analyses and compared with radiomics models. ResultsThe area under the ROC curve (AUC) of the radiomics model with PDFF features was 0.886 and 0.843 in the training and the test set, respectively, for the diagnosis of liver steatosis grade S0–1 and S2-S4. The radiomics model based on R2* features were 0.815 and 0.801 for distinguishing F0-F2 and F3-F4 and 0.831 and 0.738 for discriminating abnormal iron deposition in the training and test set, respectively. The corrected model for liver steatosis and fibrosis (0.944 and 0.912 in the test set) outperformed the radiomics models by eliminating the interference of histopathologic features(P < 0.05), but had comparable diagnostic performance for abnormal iron deposition(P > 0.05). ConclusionsIt is feasible for mDixon to simultaneously quantify whole liver steatosis, fibrosis and iron deposition based on radiomics analysis. It is valuable to minimize the interference of different pathological features for the assessment of liver steatosis and fibrosis.

Diagnostic value of multi-model high-resolution diffusion-weighted MR imaging in breast lesions: Based on simultaneous multi-slice readout-segmented echo-planar imaging

PurposeTo investigate the diagnostic value of multi-model high-resolution diffusion-weighted MR imaging (DWI) in breast lesions, with a comparison of simultaneous multi-slice readout-segmented echo-planar imaging (SMS rs-EPI) and single-shot EPI (ss-EPI). Materials and MethodsThis retrospective study was approved by the institutional ethics committee and included 120 patients with 122 breast lesions (25 benign and 97 malignant). All patients underwent breast DWI with multi-b values (0, 50, 100, 200, 400, 800, 1200, and 2000 s/mm2) based on both SMS rs-EPI and ss-EPI on a 3.0 T MR scanner. Quantitative DWI-derived parameters including ADC, MK, MD, D, D*, and f were calculated based on mono-exponential (Mono), intravoxel incoherent motion (IVIM), diffusion kurtosis (DKI) models. Meanwhile, both DWI sequences were qualitatively evaluated with respect to overall image quality, lesion conspicuity, image artifact, geometric distortion, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and lesion contrast. The differences in DW-derived parameters, image quality, and diagnostic performance were statistically compared between SMS rs-EPI and ss-EPI groups. ResultsThe SMS rs-EPI produced higher Contrast, CNR and lower SNR than ss-EPI (p < 0.01). The image quality of SMS rs-EPI was superior to ss-EPI either in subjective or objective evaluation. There was no significant difference between the SMS rs-EPI and ss-EPI for either MD or the D* (p > 0.05). However, the MK and f between the two sequences showed significant differences (p < 0.05). Spearman’s correlation coefficient displayed good linear correlation for MK values (r = 0.73, 95% CI 0.617–0.857), MD values (r = 0.88, 95% CI 0.814–0.926), ADC values (r = 0.93, 95% CI 0.869–0.948) and D values (r = 0.93, 95% CI 0.856–0.948) between SMS rs-EPI and ss-EPI. Spearman’s correlation coefficient for f values (r = 0.25, 95% CI 0.226–0.559) and D* values (r = 0.22, 95% CI 0.025–0.348) were fair and no correlation between the two sequences. MK values have the highest diagnostic value in differentiating benign and malignant breast lesions. ConclusionsHigh-resolution multi-model DWI based on SMS rs-EPI technique can provide superior image quality and lesion characterization, with comparable diagnostic performance as compared with ss-EPI DWI in differentiating benign and malignant breast lesions. Of different DWI-derived parameters, MK values showed the best diagnostic performance.

Development and Clinical Applications of a 5-Plex Real-Time RT-PCR for Swine Enteric Coronaviruses.

A PEDV/PDCoV/TGEV/SADS-CoV/XIPC 5-plex real-time RT-PCR was developed and validated for the simultaneous detection and differentiation of four swine enteric coronaviruses (PEDV, PDCoV, TGEV and SADS-CoV) in one PCR reaction (XIPC serves as an exogenous internal positive control). The 5-plex PCR had excellent analytical specificity, analytical sensitivity, and repeatability based on the testing of various viral and bacterial pathogens, serial dilutions of virus isolates, and in vitro transcribed RNAs. The 5-plex PCR had comparable diagnostic performance to a commercial PEDV/TGEV/PDCoV reference PCR, based on the testing of 219 clinical samples. Subsequently, 1807 clinical samples collected from various U.S. states during 2019–2021 were tested by the 5-plex PCR to investigate the presence of SADS-CoV in U.S. swine and the frequency of detecting swine enteric CoVs. All 1807 samples tested negative for SADS-CoV. Among the samples positive for swine enteric CoVs, there was a low frequency of detecting TGEV, an intermediate frequency of detecting PDCoV, and a high frequency of detecting PEDV. Although there is no evidence of SADS-CoV presence in the U.S. at present, the availability of the 5-plex PCR will enable us to conduct ongoing surveillance to detect and differentiate these viruses in swine samples and other host species samples as some of these coronaviruses can cause cross-species infection.

Tissue volume estimation and age prediction using rapid structural brain scans

The multicontrast EPImix sequence generates six contrasts, including a T1-weighted scan, in ~1 min. EPImix shows comparable diagnostic performance to conventional scans under qualitative clinical evaluation, and similarities in simple quantitative measures including contrast intensity. However, EPImix scans have not yet been compared to standard MRI scans using established quantitative measures. In this study, we compared conventional and EPImix-derived T1-weighted scans of 64 healthy participants using tissue volume estimates and predicted brain-age. All scans were pre-processed using the SPM12 DARTEL pipeline, generating measures of grey matter, white matter and cerebrospinal fluid volume. Brain-age was predicted using brainageR, a Gaussian Processes Regression model previously trained on a large sample of standard T1-weighted scans. Estimates of both global and voxel-wise tissue volume showed significantly similar results between standard and EPImix-derived T1-weighted scans. Brain-age estimates from both sequences were significantly correlated, although EPImix T1-weighted scans showed a systematic offset in predictions of chronological age. Supplementary analyses suggest that this is likely caused by the reduced field of view of EPImix scans, and the use of a brain-age model trained using conventional T1-weighted scans. However, this systematic error can be corrected using additional regression of T1-predicted brain-age onto EPImix-predicted brain-age. Finally, retest EPImix scans acquired for 10 participants demonstrated high test-retest reliability in all evaluated quantitative measurements. Quantitative analysis of EPImix scans has potential to reduce scanning time, increasing participant comfort and reducing cost, as well as to support automation of scanning, utilising active learning for faster and individually-tailored (neuro)imaging.

Comparable Detection of SARS-CoV-2 in Sputum and Oropharyngeal Swab Samples of Suspected COVID-19 Patients

The accurate detection of SARS-CoV-2 through respiratory sampling is critical for the prevention of further transmission and timely initiation of treatment. There is a diverse range of SARS-CoV-2 detection rates in reported studies, with uncertainty regarding the optimal sampling method for COVID-19 diagnosis and monitoring. Oropharyngeal sampling (OPS) is one of the most commonly used methods of respiratory sampling in Ghana and other parts of the world for the detection of SARS-CoV-2 viral RNA. However, this sampling technique has a number of drawbacks, which include difficulty in obtaining high-quality swab samples, increased risk of infection to healthcare workers, and increased cost from a regular supply of swabs, transport media, and personal protective equipment (PPE). This study, therefore, sought to evaluate the diagnostic performance of sputum specimens in the diagnosis of COVID-19. This was a cross-sectional analytical study conducted in two health facilities in Kumasi, Ghana, between April and September 2021. Paired samples (an oropharyngeal swab and sputum) were taken from each recruited patient and run concurrently for the detection of SARS-CoV-2 genes (the N and ORF1ab genes) using RT-qPCR. Of the 317 patients recruited, 50.8% were males, and 60.4% were young adults aged 20–39 years. A significant proportion (65.9%) of the patients did not have any co-morbidity, and the majority were with symptoms; predominantly cough (36.3%), headache (31.5%), general weakness (24.0%), fever (20.2%), and sore throat (16.1%). Being symptomatic (p = 0.003), having comorbidity (p = 0.001), and the reporting facility (p = 0.010) were significantly associated with the COVID-19 status. The sputum samples yielded more COVID-positive, 120/317 (37.9%), as compared to OPS, 83/317 (26.2%). The sputum samples were 85.5% (95% CI, 76.4–91.5) sensitive, 79.1% (95% CI, 73.4–83.7) specific, and with positive and negative predictive values of 59.2% and 93.9%, respectively, when compared with OPS. The overall median of the SARS-CoV-2 viral loads for sputum (3.70 × 103 copies/mL) were significantly higher than in OPS (1.18 × 102 copies/mL) (p = 0.003). Findings from the study suggest self-collected sputum as a useful alternative to OPS for the diagnosis of COVID-19, providing a comparable diagnostic performance and, thereby, easing the uncomfortable process and mitigating risk of aerosol transmission to healthcare workers.

Peripapillary and Macular Vascular Density in Patients With Preperimetric and Early Primary Open Angle Glaucoma.

Decreased circumpapillary vascular density (cpVD) and average retinal nerve fiber layer (RNFL) thickness were detected at different locations in eyes with preperimetric glaucoma (PPG). Although RNFL loss was more prominent in preperimetric eyes, in early glaucoma, both cpVD and RNFL thickness showed comparable diagnostic ability. To evaluate changes in circumpapillary and macular vascular density and investigate correlations between vascular and structural parameters in PPG and early glaucoma. This cross-sectional study included a total of 27 patients with PPG in 1 eye and early primary open angle glaucoma in the fellow eye, as well as a control group consisting of 27 eyes of 27 healthy volunteers. All subjects underwent optical coherence tomography angiography (OCTA) imaging. RNFL and macular ganglion cell complex measurements were obtained simultaneously with vascular parameters by AngioVue OCTA using the single-scan protocol. cpVD was examined in 8 sectors. Diagnostic accuracy was evaluated using the area under the receiver operating characteristic curve. In preperimetric eyes, average RNFL thickness and whole-image vessel density had comparable diagnostic performance (area under the receiver operating characteristic curve =0.853 and 0.753, respectively). Compared with the control group, PPG eyes had significantly lower RNFL thickness in all quadrants (P<0.001-0.003) except for the temporal quadrant, whereas cpVD differed only in the nasal inferior and nasal superior sectors (P=0.001 and 0.041, respectively). In early glaucoma eyes, cpVD differed significantly from controls in all sectors except for the inferotemporal, temporal inferior, and temporal superior sectors, whereas perifoveal macular vascular parameters differed in all quadrants (all P<0.05). cpVD was strongly correlated with RNFL thickness in the superior, nasal, and temporal quadrants (r=0.664, 0.698, and 0.649, respectively, P<0.001) and moderately correlated in the inferior quadrant (r=0.450, P<0.001). Although RNFL involvement is valuable in the diagnosis and follow-up of PPG, the change in nasal cpVD has an important place in these patients. The role of macular vascular parameters and macular ganglion cell complex in glaucoma follow-up becomes important in early glaucoma. Longitudinal studies are needed to determine the place of OCTA in the diagnosis and follow-up of glaucoma.

Point-of-Care Tests for Rapid Detection of Porcine Epidemic Diarrhea Virus: A Systematic Review and Meta-Analysis.

The timely and accurate diagnosis of porcine epidemic diarrhea virus (PEDV) infection is crucial to reduce the risk of viral transmission. Therefore, the objective of this review was to evaluate the overall diagnostic accuracy of rapid point-of-care tests (POCTs) for PEDV. Studies published before 7 January 2022 were identified by searching PubMed, EMBASE, Springer Link, and Web of Science databases, using subject headings or keywords related to point of care and rapid test diagnostic for PEDV and PED. Two investigators independently extracted data, rated risk of bias, and assessed the quality using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. The bivariate model and the hierarchical summary receiver operating characteristic (HSROC) model were used for performing the meta-analysis. Threshold effect, subgroup analysis, and meta-regression were applied to explore heterogeneity. Of the 2908 records identified, 24 eligible studies involving 3264 specimens were enrolled in the meta-analysis, including 11 studies on evaluation of lateral flow immunochromatography assay (ICA)-based, and 13 on nucleic acid isothermal amplification (NAIA)-based POCTs. The overall pooled sensitivity, specificity and diagnostic odds ratio (DOR) were 0.95 (95% CI: 0.92–0.97), 0.96 (95% CI 0.88–0.99) and 480 (95% CI 111–2074), respectively; for ICA-based POCTs and the corresponding values for NAIA-based, POCTs were 0.97 (95% CI 0.94–0.99), 0.98 (95% CI 0.91–0.99) and 1517 (95% CI 290–7943), respectively. The two tests showed highly comparable and satisfactory diagnostic performance in clinical utility. These results support current recommendations for the use of rapid POC tests when PEDV is suspected.

Meta-analysis of diagnostic cell-free circulating microRNAs for breast cancer detection

BackgroundBreast cancer (BC) is the most frequently diagnosed cancer among women. Numerous studies explored cell-free circulating microRNAs as diagnostic biomarkers of BC. As inconsistent and rarely intersecting microRNA panels have been reported thus far, we aim to evaluate the overall diagnostic performance as well as the sources of heterogeneity between studies.MethodsBased on the search of three online search engines performed up to March 21st 2022, 56 eligible publications that investigated diagnostic circulating microRNAs by utilizing Real-Time Quantitative Reverse Transcription PCR (qRT-PCR) were obtained. Primary studies’ potential for bias was evaluated with the revised tool for the quality assessment of diagnostic accuracy studies (QUADAS-2). A bivariate generalized linear mixed-effects model was applied to obtain pooled sensitivity and specificity. A novel methodology was utilized in which the sample and study models’ characteristics were analysed to determine the potential preference of studies for sensitivity or specificity.ResultsPooled sensitivity and specificity of 0.85 [0.81—0.88] and 0.83 [0.79—0.87] were obtained, respectively. Subgroup analysis showed a significantly better performance of multiple (sensitivity: 0.90 [0.86—0.93]; specificity: 0.86 [0.80—0.90]) vs single (sensitivity: 0.82 [0.77—0.86], specificity: 0.83 [0.78—0.87]) microRNA panels and a comparable pooled diagnostic performance between studies using serum (sensitivity: 0.87 [0.81—0.91]; specificity: 0.83 [0.78—0.87]) and plasma (sensitivity: 0.83 [0.77—0.87]; specificity: 0.85 [0.78—0.91]) as specimen type. In addition, based on bivariate and univariate analyses, miRNA(s) based on endogenous normalizers tend to have a higher diagnostic performance than miRNA(s) based on exogenous ones. Moreover, a slight tendency of studies to prefer specificity over sensitivity was observed.ConclusionsIn this study the diagnostic ability of circulating microRNAs to diagnose BC was reaffirmed. Nonetheless, some subgroup analyses showed between-study heterogeneity. Finally, lack of standardization and of result reproducibility remain the biggest issues regarding the diagnostic application of circulating cell-free microRNAs.

Usefulness of Wave-CAIPI for Postcontrast 3D T1-SPACE in the Evaluation of Brain Metastases.

High-resolution postcontrast 3D T1WI is a widely used sequence for evaluating brain metastasis, despite the long scan time. This study aimed to compare highly accelerated postcontrast 3D T1-weighted sampling perfection with application-optimized contrasts by using different flip angle evolution by using wave-controlled aliasing in parallel imaging (wave-T1-SPACE) with the commonly used standard high-resolution postcontrast 3D T1-SPACE for the evaluation of brain metastases. Among the 387 patients who underwent postcontrast wave-T1-SPACE and standard SPACE, 56 patients with suspected brain metastases were retrospectively included. Two neuroradiologists assessed the number of enhancing lesions according to lesion size, contrast-to-noise ratiolesion/parenchyma, contrast-to-noise ratiowhite matter/gray matter, contrast ratiolesion/parenchyma, and overall image quality for the 2 different sequences. Although there was no significant difference in the evaluation of larger enhancing lesions (>5 mm) between the 2 different sequences (P = .66 for observer 1, P = .26 for observer 2), wave-T1-SPACE showed a significantly lower number of smaller enhancing lesions (<5 mm) than standard SPACE (1.61 [SD, 0.29] versus 2.84 [SD, 0.47] for observer 1; 1.41 [SD, 0.19] versus 2.68 [SD, 0.43] for observer 2). Furthermore, mean contrast-to-noise ratiolesion/parenchyma and overall image quality of wave-T1-SPACE were significantly lower than those in standard SPACE. Postcontrast wave-T1-SPACE showed comparable diagnostic performance for larger enhancing lesions (>5 mm) and marked scan time reduction compared with standard SPACE. However, postcontrast wave-T1-SPACE showed underestimation of smaller enhancing lesions (<5 mm) and lower image quality than standard SPACE. Therefore, postcontrast wave-T1-SPACE should be interpreted carefully in the evaluation of brain metastasis.

Computed Tomography-Based Radiomics for Differentiation of Thymic Epithelial Tumors and Lymphomas in Anterior Mediastinum.

ObjectiveTo investigate the differential diagnostic performance of computed tomography (CT)-based radiomics in thymic epithelial tumors (TETs) and lymphomas in anterior mediastinum.MethodsThere were 149 patients with TETs and 93 patients with lymphomas enrolled. These patients were assigned to a training set (n = 171) and an external validation set (n = 71). Dedicated radiomics prototype software was used to segment lesions on preoperative chest enhanced CT images and extract features. The multivariable logistic regression algorithm was used to construct three models according to clinico-radiologic features, radiomics features, and combined features, respectively. Performance of the three models was compared by using the area under the receiver operating characteristic curves (AUCs). Decision curve analysis was used to evaluate clinical utility of the three models.ResultsFor clinico-radiologic model, radiomics signature model, and combined model, the AUCs were 0.860, 0.965, 0.975 and 0.843, 0.961, 0.955 in the training cohort and the test cohort, respectively (all P<0.05). The accuracies of each model were 0.836, 0.895, 0.918 and 0.845, 0.901, 0.859 in the two cohorts, respectively (all P<0.05). Compared with the clinico-radiologic model, better diagnostic performances were found in the radiomics signature model and the combined model.ConclusionsRadiomics signature model and combined model exhibit outstanding and comparable differential diagnostic performances between TETs and lymphomas. The CT-based radiomics analysis might serve as an effective tool for accurately differentiating TETs from lymphomas before treatment.

Digital health in medicine: Important considerations in evaluating health economic analysis

Digital health in medicine: Important considerations in evaluating health economic analysis

Deep convolutional neural network for classification of thyroid nodules on ultrasound: Comparison of the diagnostic performance with that of radiologists

PurposeThis study aimed to train and validate deep learning (DL) models for differentiating malignant from benign thyroid nodules on US images and compare their performance with that of radiologists. MethodsImages of thyroid nodules in patients who underwent US-guided fine-needle aspiration biopsy at our institution between January 2010 and March 2020 were retrospectively reviewed. Four radiologists independently classified the images. Images of thyroid nodules were trained using three different image classification DL models (VGG16, VGG19, and ResNet). The diagnostic performances of the DL models were calculated for the internal and external datasets and compared with the diagnoses of the four radiologists. Pairwise comparisons of the AUCs between the radiologists and DL models were made using bootstrap-based tests. ResultsIn total, 15,409 images from 7,321 patients (mean age, 60 ± 13 years; malignant nodules, 20.7%) were randomly grouped into training (n = 12,327) and validation (n = 3,082) sets. Independent internal (n = 432; 197 patients) and external (n = 168; 59 patients) test sets were also acquired. The DL models demonstrated a higher diagnostic performance than the radiologists in the internal test set (AUC, 0.83 – 0.86 vs. 0.71 – 0.76, P < 0.05), but not in the external test set. The VGG16 model demonstrated the highest diagnostic performance in internal (AUC, 0.86; sensitivity, 91.8%; specificity, 73.2%) and external (AUC: 0.83; sensitivity: 78.6%; specificity: 76.8%) test sets. However, no statistical differences were found in the AUCs among the DL models. ConclusionsThe DL models demonstrated comparable diagnostic performance to radiologists in distinguishing benign from malignant thyroid nodules on US images and may play a potential role in augmenting radiologists’ diagnosis of thyroid nodules.