Diagnostic Performance Parameters Research Articles

External validation of a stepwise 0/1/3h algorithm to triage patients with suspected myocardial infarction

Abstract Background In patients with suspected myocardial infarction (MI), application of 0/1h-algorithms is recommended by guidelines of the European Society of Cardiology. Depending on assay-specific changes of high-sensitivity troponin (hs-Tn), these algorithms allow for rule-in or rule-out of MI at presentation or after 1 hour (h). Yet, a relevant proportion of patients remain in the observe group at 1h in need for further diagnostic. Recently, specific cutoffs at 3h were suggested for hs-TnT, enabling an additional 3h triage option in conjunction with the 0/1h algorithm to further reduce the proportion of patients in the observe zone. Objective We aimed to externally validate the diagnostic performance of the 0/1/3h algorithm in patients with suspected MI. Methods We consecutively enrolled patients with symptoms suggestive of MI in the emergency department of a tertiary hospital in Germany. Patients with STEMI were excluded. Concentrations of hs-TnT were measured at presentation, after 1h and 3h. Final diagnoses were adjudicated by two cardiologists according to the 4th Universal Definition of MI. Applying the 0/1/3h algorithm, patients were triaged into rule-in, rule-out- and observe-group. We assessed the diagnostic performance parameters in the overall sample as well as for predefined subgroups including sex, age ≥65 vs. <65 years, glomerular filtration rate (GFR) ≥60ml/min/m² vs. <60ml/min/m², and symptom onset time <1h vs. 1-3h vs. >3h). Results In 2,514 patients (median age 64 years, 36.4% female), prevalence of NSTEMI was 14.4%. Application of the 0/1/3h algorithm ruled-out 1511 (60.1%) and ruled-in 587 (23.3%) patients. Only 416 (16.6%) remained in the observe group at 3h. Safety of rule-out was high with a sensitivity of 98.6% (95%CI 96.8%, 99.4%) and a corresponding negative predictive value of 99.7% (95%CI 99.2%, 99.9%). Rule-in performance was acceptable with a specificity of 89.3% (95%CI 87.9%, 90.5%) and positive predictive value (PPV) of 60.8% (95%CI 56.8, 64.7, Figure 1). Regarding subgroup analyses, sensitivity and NPV were marginally but statistically lower in patients with normal as compared with impaired renal function (p both <0.001). Further, specificity was substantially lower in older patients (84.8% vs. 93.3%, p<0.001), patients with GFR<60ml/min/m² (78.3% vs. 93.0%, p<0.001) as well as in male patients (88.1% vs. 91.2%, p=0.028) (Figure 2). A relevantly larger proportion of patients remained in the observe group after 3h in patients with impaired renal function (32.3% vs. 10.9%), as well as in patients aged ≥ 65 years (26.8% vs. 6.8%). Conclusion Application of the 0/1/3h algorithm in patients with suspected MI resulted in good diagnostic performance with excellent rule-out safety and moderate rule-in capacity. In patients with impaired renal function as well as elderly patients, specificity was significantly lower while observing a larger proportion of patients remaining in the observe zone at three hours.Figure 1:Diagnostic flowFigure 2:Forest Plots

The Performance of GeneXpert in the Diagnosis of Lymph Node Tuberculosis: A Prospective Study Comparing GeneXpert and Culture Findings.

Background and objective Lymph node tuberculosis (LNTB) is a common manifestation of extrapulmonary tuberculosis (EPTB). GeneXpert is a rapid diagnostic molecular test that simultaneously detects tuberculosis and rifampicin (RIF) resistance. In this study, we aimed to assess the epidemiology of LNTB and diagnostic performance parameters of the GeneXpert in routineENT practice. Methods We conducted a cross-sectional prospective study from January to July 2019,in the Department of Otorhinolaryngology and Head Neck Surgery at the Hassan II University Hospital Center of Fez, Morocco. The samples were collected using lymph node biopsy and subjected to GeneXpert assay, culture, and histopathology. Diagnostic performance parameters of the GeneXpert were calculated and compared with culture. Results All patients with cervical adenopathy were included. Lymph node biopsies were performed for all patients. The performance of the GeneXpert was assessed according to culture findings. Among the 75 cases, the mean age was 21.6 ± 12.7 years with a female predominance (60%). GeneXpert was positive in 66.7% of specimens. The sensitivity and specificity of the GeneXpert assay were 78.6% and 40.4% respectively. GeneXpert accuracy was 54.6%. The positive predictive value (PPV) and negative predictive value (NPV) were found to be 44% (95% CI: 30.2-57.8) and 76% (95% CI: 59.3-92.7) respectively. Mycobacterium bovis was isolated in all samples, with no case of resistance to RIF found. Conclusions The performance of GeneXpert was found to be superior in terms of establishing the diagnosis of LNTB. It offers speedy and prompt results and clinicians should adopt it in routine clinical practice.

AI-based automated evaluation of image quality and protocol tailoring in patients undergoing MRI for suspected prostate cancer

PurposeTo develop and validate an artificial intelligence (AI) application in a clinical setting to decide whether dynamic contrast-enhanced (DCE) sequences are necessary in multiparametric prostate MRI. MethodsThis study was approved by the institutional review board and requirement for study-specific informed consent was waived. A mobile app was developed to integrate AI-based image quality analysis into clinical workflow. An expert radiologist provided reference decisions. Diagnostic performance parameters (sensitivity and specificity) were calculated and inter-reader agreement was evaluated. ResultsFully automated evaluation was possible in 87% of cases, with the application reaching a sensitivity of 80% and a specificity of 100% in selecting patients for multiparametric MRI. In 2% of patients, the application falsely decided on omitting DCE. With a technician reaching a sensitivity of 29% and specificity of 98%, and resident radiologists reaching sensitivity of 29% and specificity of 93%, the use of the application allowed a significant increase in sensitivity. ConclusionThe presented AI application accurately decides on a patient-specific MRI protocol based on image quality analysis, potentially allowing omission of DCE in the diagnostic workup of patients with suspected prostate cancer. This could streamline workflow and optimize time utilization of healthcare professionals.

Electrocardiogram Signal Analysis With a Machine Learning Model Predicts the Presence of Pulmonary Embolism With Accuracy Dependent on Embolism Burden

ObjectiveTo develop an artificial intelligence deep neural network (AI-DNN) algorithm to analyze 12-lead electrocardiogram (ECG) for detection of acute pulmonary embolism (PE) and PE categories. Patients and MethodsA cohort of patients seen between January 1, 1999, and December 31, 2020, from across the Mayo Clinic Enterprise with computed tomography pulmonary angiogram (CTPA) and ECG performed ±6 hours was identified. Natural language processing algorithms were applied to radiology reports to determine the diagnosis of acute PE, acute right ventricular strain pulmonary embolism (RVSPE), saddle pulmonary embolism (SADPE), or no PE. Diagnostic performance parameters of the AI-DNN reported were area under the receiver operating characteristics curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). ResultsA cohort of patients with CTPA report and ECG consisted of 79,894 patients including 7423 (9.3%) with acute PE, among whom 1138 patients had RVSPE or SADPE. Artificial intelligence deep neural network predicted acute PE with a modest accuracy of AUROC of 0.69 (95% CI, 0.68-0.71), sensitivity of 63.5%, specificity of 64.7%, PPV of 15.6%, and NPV of 94.5%. The AI-DNN prediction using the same algorithm for RVSPE or SADPE was higher (AUROC, 0.84; 95% CI, 0.81-0.86) with a sensitivity of 80.8%, specificity of 64.7.8%, PPV of 3.5%, and NPV of 99.5%. ConclusionAn AI-based analysis of 12-lead ECG shows modest detection power for acute PE in patients who underwent CTPA, with higher accuracy for high-risk PE. Moreover, with the high NPV, it has the clinical potential to exclude high-risk PE quickly and correctly.

Prediction of bowel necrosis by reduced bowel wall enhancement in closed-loop small bowel obstruction: Quantitative methods

PurposeTo assess diagnostic performance and reproducibility of reduced bowel wall enhancement evaluated by quantitative methods using CT to identify bowel necrosis among closed-loop small bowel obstruction (CL-SBO) patients. MethodsThis retrospective single-center study included patients who diagnosed with CL-SBO caused by adhesion or internal hernia during January 2016 and May 2022. Patients were divided into necrotic group (n = 41) and non-necrotic group (n = 67) according to surgical exploration and postoperative pathology. Two doctors independently measured the attenuation of bowel wall and consensus was reached through panel discussion with a third gastrointestinal radiologist. Reduced bowel wall enhancement was assessed by four quantitative methods. Univariate analyses were used to evaluate the association between each method and bowel necrosis, and kappa/intraclass correlation coefficient values were used to assess interobserver agreement. Diagnostic performance parameters were calculated for each method. ResultsReduced bowel wall enhancement in arterial phase (OR 8.98, P < 0.0001), reduced bowel wall enhancement in portal phase (OR 16.84, P < 0.001), adjusted reduced bowel wall enhancement in arterial phase (OR 29.48, P < 0.001), adjusted reduced bowel wall enhancement in portal phase (OR 145.69, P < 0.001) were significantly associated with bowel necrosis. Adjusted reduced bowel wall enhancement in portal phase had the best diagnostic performance (AUC: 0.92; Youden index: 0.84; specificity: 94.03 %) and interobserver agreement (kappa value of 0.59–0.73) to predict bowel necrosis. ConclusionWhen assessing reduced bowel enhancement to predict bowel necrosis among CL-SBO patients, using unenhanced CT images and proximal dilated loop as standard references in portal phase is the most accurate quantitative method among those tested.

Reproducibility and Accuracy of the PRIMARY Score on PSMA PET and of PI-RADS on Multiparametric MRI for Prostate Cancer Diagnosis Within a Real-World Database.

The PRIMARY score is a 5-category scale developed to identify clinically significant intraprostate malignancy (csPCa) on 68Ga-prostate-specific membrane antigen (PSMA)-11 PET/CT (68Ga-PSMA PET) using a combination of anatomic site, pattern, and intensity. Developed within the PRIMARY trial, the score requires evaluation in external datasets. This study aimed to assess the reproducibility and diagnostic accuracy of the PRIMARY score in a cohort of patients who underwent multiparametric MRI (mpMRI) and 68Ga-PSMA PET before prostate biopsy for the diagnosis of prostate cancer. Methods: In total, data from 242 men who had undergone 68Ga-PSMA PET and mpMRI before transperineal prostate biopsy were available for this ethics-approved retrospective study. 68Ga-PSMA PET and mpMRI data were centrally collated in a cloud-based deidentified image database. Six experienced prostate-focused nuclear medicine specialists were trained (1 h) in applying the PRIMARY score with 30 sample images. Six radiologists experienced in prostate mpMRI read images as per the Prostate Imaging-Reporting and Data System (PI-RADS), version 2.1. All images were read (with masking of clinical information) at least twice, with discordant findings sent to a masked third (or fourth) reader as necessary. Cohen κ was determined for both imaging scales as 5 categories and then collapsed to binary (negative and positive) categories (score 1 or 2 vs. 3, 4, or 5). Diagnostic performance parameters were calculated, with an International Society of Urological Pathology grade group of at least 2 (csPCa) on biopsy defined as the gold standard. Combined-imaging-positive results were defined as any PI-RADS score of 4 or 5 or as a PI-RADS score of 1-3 with a PRIMARY score of 3-5. Results: In total, 227 patients with histopathology, 68Ga-PSMA PET, and mpMRI imaging before prostate biopsy were included; 33% had no csPCa, and 67% had csPCa. Overall interrater reliability was higher for the PRIMARY scale (κ = 0.70) than for PI-RADS (κ = 0.58) when assessed as a binary category (benign vs. malignant). This was similar for all 5 categories (κ = 0.65 vs. 0.48). Diagnostic performance to detect csPCa was comparable between PSMA PET and mpMRI (sensitivity, 86% vs. 89%; specificity, 76% vs. 74%; positive predictive value, 88% vs. 88%; negative predictive value, 72% vs. 76%). Using combined imaging, sensitivity was 94%, specificity was 68%, positive predictive value was 86%, and negative predictive value was 85%. Conclusion: The PRIMARY score applied by first-user nuclear medicine specialists showed substantial interrater reproducibility, exceeding that of PI-RADS applied by mpMRI-experienced radiologists. Diagnostic performance was similar between the 2 modalities. The PRIMARY score should be considered when interpreting intraprostatic PSMA PET images.

A Review of Recent Advances in Computer-Aided Detection Methods Using Hyperspectral Imaging Engineering to Detect Skin Cancer

Skin cancer, a malignant neoplasm originating from skin cell types including keratinocytes, melanocytes, and sweat glands, comprises three primary forms: basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and malignant melanoma (MM). BCC and SCC, while constituting the most prevalent categories of skin cancer, are generally considered less aggressive compared to MM. Notably, MM possesses a greater capacity for invasiveness, enabling infiltration into adjacent tissues and dissemination via both the circulatory and lymphatic systems. Risk factors associated with skin cancer encompass ultraviolet (UV) radiation exposure, fair skin complexion, a history of sunburn incidents, genetic predisposition, immunosuppressive conditions, and exposure to environmental carcinogens. Early detection of skin cancer is of paramount importance to optimize treatment outcomes and preclude the progression of disease, either locally or to distant sites. In pursuit of this objective, numerous computer-aided diagnosis (CAD) systems have been developed. Hyperspectral imaging (HSI), distinguished by its capacity to capture information spanning the electromagnetic spectrum, surpasses conventional RGB imaging, which relies solely on three color channels. Consequently, this study offers a comprehensive exploration of recent CAD investigations pertaining to skin cancer detection and diagnosis utilizing HSI, emphasizing diagnostic performance parameters such as sensitivity and specificity.

Diagnostic performance of bedside transthoracic echocardiography in the management of patients with suspected myocardial infarction

Abstract Introduction The diagnostic management of patients with symptoms indicative of acute myocardial infarction (MI) is largely based on the clinical assessment of symptoms, ECG and diagnostic algorithms based on high-sensitivity cardiac troponin (hs-cTn). Additionally, guidelines recommend transthoracic echocardiography (TTE) for patients neither eligible for rule-out nor rule-in. Purpose To assess the diagnostic performance of TTE in the diagnostic management of patients with suspected MI. Methods We conducted a prospective, observational cohort study enrolling consecutive patients presenting with symptoms suggestive of MI to the emergency department of a tertiary care hospital. Management was at the discretion of the treating physician. The final diagnosis was adjudicated by two independent cardiologists according to the 4th Universal Definition of MI. Evaluation in the emergency department included TTE with an assessment of left-ventricular (LV) function and regional wall motion abnormalities (WMA). We calculated diagnostic performance parameters (sensitivity, specificity, and negative and positive predictive value [NPV, PPV] with 95% confidence intervals) to rule-out or rule-in MI, respectively, for the presence of WMA. Performance was calculated for patients stratified to the observe and rule-in groups after application the ESC 0/1-hour algorithm using hs-cTnI. Patients without available TTE and those with STEMI were excluded. WMA were only reported if the acoustic window allowed a reasonable evaluation. Variables associated with the conduction of coronary angiography were studied using logistic regression. Results Overall, 2,163 patients with available TTE were included, of those 1,707 (78.9%) patients had data on WMA available, with 360 (21.1%) having any WMA (hypokinesia or akinesia) detected. Median age was 64 (51, 75) years, 1,383 (63.9%) were males and 383 (17.7%) were diagnosed with MI. Application of the ESC 0/1-hour algorithm resulted in assignment of 729 (42.9%) and 308 (18.6%) patients to the rule-out and -in groups, respectively, with 599 (38.5%) patients remaining in the observe group. Of these, 45 (7.5%) had MI. Performance of the ESC 0/1-hour algorithm was good and is shown in Figure 1. In the observe group, detection of WMA poorly identified patients with MI (PPV 12.7%, Figure 1). Absence of WMA resulted in moderate performance to rule-out MI (NPV 94.0%, Figure 1). Adjusted for age, sex, symptoms, baseline hs-cTnI, presence of ischemic signs on ECG and cardiovascular risk factors, the presence of WMA was significantly associated with the conduction of coronary angiography at index presentation (OR 2.7 [1.8, 4.0], p &amp;lt; 0.001). Conclusion The diagnostic value of bedside TTE is limited for the rule-out or -in of MI. Still, patients with prevalent WMA were significantly more likely to undergo coronary angiography.Performance of TTE in ESC 0/1-hour alg.

Cancer Detection Rate and Abnormal Interpretation Rate of Prostate MRI in Patients With Low-Grade Cancer

PurposeThe aim of this study was to evaluate the utility of cancer detection rate (CDR) and abnormal interpretation rate (AIR) in prostate MRI for patients with low-grade prostate cancer (PCa). MethodsThis three-center retrospective study included patients who underwent prostate MRI from 2017 to 2021 with known low-grade PCa (Gleason score 6) without prior treatment. Patient-level highest Prostate Imaging Reporting & Data System (PI-RADS®) score and pathologic diagnosis within 1 year after MRI were used to evaluate the diagnostic performance of prostate MRI in detecting clinically significant PCa (csPCa; Gleason score ≥ 7). The metrics AIR, CDR, and CDR adjusted for pathologic confirmation rate were calculated. Radiologist-level AIR-CDR plots were shown. Simulation AIR-CDR lines were created to assess the effects of different diagnostic performances of prostate MRI and the prevalence of csPCa. ResultsA total of 3,207 examinations were interpreted by 33 radiologists. Overall AIR, CDR, and CDR adjusted for pathologic confirmation rate at PI-RADS 3 to 5 (PI-RADS 4 and 5) were 51.7% (36.5%), 22.1% (18.8%), and 30.7% (24.6%), respectively. Radiologist-level AIR and CDR at PI-RADS 3 to 5 (PI-RADS 4 and 5) were in the 36.8% to 75.6% (21.9%-57.5%) range and the 16.3%-28.7% (10.9%-26.5%) range, respectively. In the simulation, changing parameters of diagnostic performance or csPCa prevalence shifted the AIR-CDR line. ConclusionsThe authors propose CDR and AIR as performance metrics in prostate MRI and report reference performance values in patients with known low-grade PCa. There was variability in radiologist-level AIR and CDR. Combined use of AIR and CDR could provide meaningful feedback for radiologists to improve their performance by showing relative performance to other radiologists.

Supplemental Optoacoustic Imaging of Breast Masses: A Cost-Effectiveness Analysis

To evaluate the cost-effectiveness of utilizing supplemental optoacoustic ultrasound (OA/US) versus gray-scale ultrasound (US) alone to differentiate benign and malignant breast masses in a diagnostic setting. We created a decision-tree model to compare the cost-effectiveness of OA/US and US from the perspective of the UShealthcare system. We utilized diagnostic test performance parameters from the PIONEER-01(NCT01943916) clinical trial and cost parameters (USD) from the Truven Health MarketScanDatabases. Utility (quality adjusted life year,QALY) values were determined following published patient-reported outcomes. Cost-effectiveness was calculated through incremental cost-effectiveness ratio (USD/QALY, ICER) and net monetary benefit (NMB) in a Markov chain model. Deterministic and probabilistic sensitivity analyses were performed to determine the significance of variation in input parameters. A willingness-to-pay (WTP) threshold of $100,000/QALY was used for the study. OA/US had an estimated cumulative cost of $16,617.36 and the outcome of 16.85 QALYs in the 25-year period. The incremental NMB for OA/US was $1495.36, and the ICER was -$31,715.82/QALY, indicating that supplemental use of OA/US was more cost-effective than US alone. In the deterministic sensitivity analysis, when the cost of OA/US exceeded $1030.61 or the sensitivity of OA/US fell below 79.7%, or the specificity fell below 30.5%, the US alone strategy yielded higher NMB values compared to supplemental OA/US. According to probabilistic sensitivity analysis, OA/US was the better strategy in 98.69% of 10,000 iterations. OA/US is more cost-effective than US to differentiate benign or malignant breast masses in the diagnostic setting. It can reduce costs while improving patients' quality of life, primarily by reducing false-positive results with consequent benign biopsies.

Acceptability and feasibility of HIV self-testing in Southeast Asia: A scoping review.

HIV self-testing (HIVST) policies in Southeast Asia are under development. This scoping review aimed to systematically synthesize the available literature on the acceptability and feasibility of HIVST in Southeast Asia. Systematic search was conducted on January 20, 2022, in eight databases: PubMed/MEDLINE, CINAHL, Web of Science, Academic Search Complete, SocINDEX, PsycINFO, PsycArticles, and CENTRAL. Acceptability (HIV testing frequency, willingness to pay, use, and recommend the test, ease of use, preference over standard tests, and partner testing) and feasibility (error rate, readability, and diagnostic performance) parameters were followed for the inclusion of articles. A narrative synthesis was done to present findings from included studies on the acceptability and feasibility of HIVST. A total of 5091 records were identified through database search, and 362 were deleted after deduplication. The screening process resulted in 18 studies that met the inclusion criteria. Results indicated a high acceptability rate due to convenience, increasing awareness about HIVST, availability, and affordability of test kits, and confidentiality of test results. A high feasibility rate was reported due to a low occurrence of errors in self-testing, interpretability of results, and a low percentage of invalid and false-reactive results. Issues identified include costs of HIVST for individual use, distribution mode, type of supervision, counseling, geographic location, and socioeconomic status. Evidence supports the acceptability and feasibility of HIVST in Southeast Asia. There is a need to regulate and license HIVST in Southeast Asia to have better recognition as a supplement to HTS.

The accuracy of the FIT in detecting advanced neoplasm is highest in young people aged 40 to 49 years: an analysis based on sex and age

BackgroundColorectal cancer (CRC) is one of the most common cancers and is associated with high incidence and mortality rates worldwide. CRC has caused a tremendous loss of human health and wealth. The incidence and mortality of colorectal carcinoma are increasing in young adults. Early cancer detection and prevention are made possible through screening. At present, the faecal immunochemical test (FIT) is a noninvasive method that can be used for the large-scale clinical screening of CRC status. Therefore, this study, based on CRC screening results in Tianjin from 2012 to 2020, was conducted to analyse the major differences in diagnostic performance parameters according to sex and age.MethodsThis study was based on 39,991 colonoscopies performed for individuals in the Tianjin CRC screening program from 2012 to 2020. Of these individuals, they had complete FIT and colonoscopy results. The differences in FIT results were analysed by sex and age.ResultsAccording to this study, males were generally more likely to develop advanced neoplasms (ANs) than females, and the prevalence increased with age. Males with negative FIT results were more likely to have advanced neoplasms than females with positive results. The accuracy of the FIT in detecting ANs in each age group was 54.9%, 45.5%, 48.6% and 49.5% in the 40–49, 50–59, 60–69, and ≥ 70 age groups, respectively.ConclusionsThe FIT detected ANs with highest accuracy in the 40–49 age group. Our research can provide guidance to formulate CRC screening strategies.

Performance of five serological tests in the diagnosis of visceral and cryptic leishmaniasis: a comparative study.

Leishmaniasis is a major health problem and its diagnosis still represents a challenge. Since consistent evidence on the comparison of serological methods is lacking, our work aims to compare five serological tests for the diagnosis of visceral and asymptomatic leishmaniasis in southern France, a region where leishmaniasis is endemic. Serum samples from 75 patients living in Nice, France were retrospectively analyzed. They included patients affected by visceral leishmaniasis (VL; n = 25), asymptomatic carriers (AC; n = 25) and negative controls (n = 25). Each sample was tested using two immunochromatographic tests (ICT; IT LEISH® and TruQuick IgG/IgM®), an indirect fluorescent antibody test (IFAT) and two Western Blotting (WB; LDBio BIORAD® and an in-house method). Diagnosis of VL with IFAT and TruQuick® showed the highest diagnostic performance parameters. IFAT had 100% sensitivity and specificity, while TruQuick had 96% sensitivity and 100% specificity. Finally, the two tests showed high accuracy (100% for IFAT and 98% for TruQuick) for the AC group. WB LDBio® was the only method able to detect Leishmania latent infection, with a sensitivity of 92%, and a specificity of 100%, with a Negative Predictive Value (NPV) of 93%. This performance is reflected in the high accuracy of the test. The data obtained with TruQuick® supports its application in the rapid diagnosis of leishmaniasis in endemic areas, a feature not shown by IFAT despite its high diagnostic performance. Regarding the diagnosis of asymptomatic leishmaniasis, the best results were obtained with WB LDBio®, confirming previous studies.

Preoperative subcategorization based on magnetic resonance imaging in intrahepatic cholangiocarcinoma

BackgroundAppropriate preoperative identification of iCCA subtype is essential for personalized management, so the aim of this study is to investigate the role of MR imaging features in preoperatively differentiating the iCCA subtype.MethodsNinety-three patients with mass-forming intrahepatic cholangiocarcinoma (iCCA, 63 small duct type and 30 large duct type) were retrospectively enrolled according to the latest 5th WHO classification (mean age, males vs. females: 60.66 ± 10.53 vs. 61.88 ± 12.82, 50 men). Significant imaging features for differentiating large duct iCCA and small duct iCCA were identified using univariate and multivariate logistic regression analyses, and a regression-based predictive model was then generated. Furthermore, diagnostic performance parameters of single significant imaging features and the predictive model were obtained, and corresponding receiver operating characteristic (ROC) curves were subsequently presented.ResultsThe univariate analysis showed that tumor in vein, arterial phase hypoenhancement, intrahepatic duct dilatation, lack of targetoid restriction and lack of targetoid appearance in T2 were predictors of large duct type iCCA. Arterial phase hypoenhancement, intrahepatic duct dilatation and lack of targetoid restriction were independent predictors for large duct type iCCA in multivariate analysis. The regression-based predictive model has achieved the best preoperative prediction performance in iCCA subcategorization so far. The area under the ROC curve of the regression-based predictive model was up to 0.91 (95% CI: 0.85, 0.98), and it was significantly higher than every single significant imaging feature.ConclusionsArterial phase hypoenhancement, intrahepatic duct dilatation and lack of targetoid restriction could be considered reliable MR imaging indicators of large duct type iCCA. MR imaging features can facilitate noninvasive prediction of iCCA subtype with satisfactory predictive performance.

Automation of generative adversarial network-based synthetic data-augmentation for maximizing the diagnostic performance with paranasal imaging

Thus far, there have been no reported specific rules for systematically determining the appropriate augmented sample size to optimize model performance when conducting data augmentation. In this paper, we report on the feasibility of synthetic data augmentation using generative adversarial networks (GAN) by proposing an automation pipeline to find the optimal multiple of data augmentation to achieve the best deep learning-based diagnostic performance in a limited dataset. We used Waters’ view radiographs for patients diagnosed with chronic sinusitis to demonstrate the method developed herein. We demonstrate that our approach produces significantly better diagnostic performance parameters than models trained using conventional data augmentation. The deep learning method proposed in this study could be implemented to assist radiologists in improving their diagnosis. Researchers and industry workers could overcome the lack of training data by employing our proposed automation pipeline approach in GAN-based synthetic data augmentation. This is anticipated to provide new means to overcome the shortage of graphic data for algorithm training.

Diagnostic performance of F-18 FDG PET/CT in recurrent adenocarcinoma gallbladder and its impact on post-recurrence survival.

To analyze diagnostic performance of F-18 FDG PET/CT in recurrent adenocarcinoma gallbladder (GBC) and to establish its possible impact on post-recurrence survival. FDG PET/CT studies of suspected recurrent GBC were retrospectively analyzed alongside tumor markers serum CEA and CA 19-9. Abnormal FDG-avid lesions and abnormal morphological lesions were considered positive for recurrence, and were categorized as isolated abdominal wall recurrence, loco-regional recurrence, and distant metastatic disease. Histopathology, definite progression on imaging and positive response to treatment was considered as reference standard. Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy were used as diagnostic performance parameters. Post-recurrence survival was calculated whenever appropriate follow-up was available, based on the abovementioned categories of sites of recurrence using survival curves and log-rank test. Out of 117 PET/CT studies, 93 (79.5%) were positive and 24 (20.5%) were negative for recurrence. 86 out of 93 were true positive and 23 of 24 were true negative. PET/CT demonstrated sensitivity, specificity, PPV, NPV and accuracy of 98.8%, 76.7%, 92.5%, 95.8% and 93.1%, respectively. Diagnostic performance of PET/CT was significantly better than combination tumor markers. Of 66 cases with available follow-up, isolated abdominal wall (port/scar site) recurrence and loco-regional recurrence demonstrated significantly higher post-recurrence survival as compared to distant metastasis; median survival being 39, 25 and 12 months, respectively. F-18 FDG PET/CT has better diagnostic performance than tumor markers combination. Isolated abdominal wall (port/scar site) recurrence and loco-regional recurrence on PET/CT demonstrated better survival than non-regional metastatic disease. These results suggest a possible role of PET/CT as a surveillance modality, as well as a guide to therapeutic decision-making in cases of recurrent GBC.

Axillary lymph node response to neoadjuvant systemic therapy with dedicated axillary hybrid 18F-FDG PET/MRI in clinically node-positive breast cancer patients: a pilot study

To investigate the diagnostic performance of dedicated axillary hybrid 18F-2-[18F]-fluoro-2-deoxy-d-glucose (FDG) positron emission tomography (PET)/magnetic resonance imaging (MRI) in detecting axillary pathological complete response (pCR) following neoadjuvant systemic therapy (NST) in clinically node-positive breast cancer patients. Ten prospectively included clinically node-positive breast cancer patients underwent dedicated axillary hybrid 18F-FDG PET/MRI after completing NST followed by axillary surgery. PET images were reviewed by a nuclear medicine physician and coronal T1-weighted and T2-weighted MRI images by a radiologist. All axillary lymph nodes visible on PET/MRI were matched with those removed during axillary surgery. Diagnostic performance parameters were calculated based on patient-by-patient and node-by-node validation with histopathology of the axillary surgical specimen as the reference standard. Six patients achieved axillary pCR at final histopathology. A total of 84 surgically harvested axillary lymph nodes were matched with axillary lymph nodes depicted on PET/MRI. Histopathological examination of the matched axillary lymph nodes resulted in 10 lymph nodes with residual axillary disease of which eight contained macrometastases and two micrometastases. The patient-by-patient analysis yielded a sensitivity, specificity, positive predictive value, and negative predictive value of 25%, 100%, 100%, and 67%, respectively. The diagnostic performance parameters of the node-by-node analysis were 0%, 96%, 0%, and 88%, respectively. Excluding micrometastases from the node-by-node analysis increased the negative predictive value to 90%. This pilot study suggests that the negative predictive value and sensitivity of dedicated axillary 18F-FDG PET/MRI are insufficiently accurate to detect axillary pCR or exclude residual axillary disease following NST in clinically node-positive breast cancer patients.

Comparison of Multiparametric and Fast MRI Protocols in Detecting Clinically Significant Prostate Cancer and a Detailed Cost Analysis.

Due to the long acquisition time and high cost of multiparametric magnetic resonance imaging (mpMRI), biparametric and, more recently, fast prostate magnetic resonance imaging (fpMRI) protocols have been described. However, there is insufficient data about the diagnostic performance and cost of fpMRI. To compare the diagnostic performances and cost analysis of fpMRI and mpMRI in clinically significant prostate cancer (csPCA). Retrospective. A total of 103 patients (63 had csPCA) with a mean age of 66.83 (± 7.22) years were included. A 1.5-T; T1- and T2-weighted turbo spin-echo imaging (T1WI and T2WI), echo-planar diffusion-weighted images, and dynamic contrast-enhanced T1W imaging. Three readers independently evaluated the fpMRI and mpMRI images in different sessions blinded to all patient information. Diagnostic performances of fpMRI and mpMRI were evaluated. Kappa coefficient (κ) was used to determine the interreader and intrareader agreement. A detailed cost analysis was performed for each protocol. Receiver operating characteristics analysis, area under the curve (AUC), and κ test were used. Diagnostic performance parameters were also calculated. Of the 63 malignant index lesions (csPCA), 53/63 of those (84.1%) originated from the peripheral zone and 10/63 lesions (15.9%) originated from the transition zone. The AUC values for fpMRI were 0.878 for reader 1, 0.937 for reader 2, and 0.855 for reader 3. For mpMRI, the AUC values were 0.893 for reader 1, 0.94 for reader 2, and 0.862 for reader 3. Inter and intrareader agreements were moderate to substantial (κ range, 0.5-0.79). The total cost per examination was calculated as €12.39 and €30.10 for fpMRI and mpMRI, respectively. Fast MRI protocol has similar diagnostic performance with mpMRI in detecting csPCA, and fpMRI can be considered an alternative protocol that could create a lower financial burden on health-care systems. 4 TECHNICAL EFFICACY STAGE: 6.

A Retrospective Cohort Study of the Utility of Ultrasound, 99mTc-Sestamibi Scintigraphy, and Four-Dimensional Computed Tomography for Pre-Operative Localization of Parathyroid Disease To Facilitate Minimally Invasive Parathyroidectomy.

BackgroundThis study investigated the utility of ultrasound (US), 99mTc-Sestamibi scintigraphy (Sestamibi), and four-dimensional computed tomography (4DCT) for pre-operative localization of a single abnormal parathyroid gland prior to minimally invasive parathyroidectomy (MIP) to determine the optimum pre-operative scans to facilitate a MIP.MethodsPatients with primary hyperparathyroidism who underwent curative parathyroidectomy at Broomfield Hospital, Mid and South Essex NHS Foundation Trust between 2009 and 2018 were included. Diagnostic performance parameters and the agreement between US, Sestamibi, and 4DCT were evaluated. Cohen’s κ was used to assess the strength of agreement between imaging modalities.ResultsAt localizing pathology to the correct side of the neck, Sestamibi had the highest sensitivity (87%), followed by US (76%) and 4DCT (64%). 4DCT had a positive predictive value (PPV) of 95%, similar to Sestamibi (96%), but higher than US (92%). Amongst patients who underwent both US and Sestamibi, the abnormal parathyroid gland was localized to the same area by both imaging modalities in 77% of patients (Cohen’s κ: 0.383). Following an inconclusive US or Sestamibi scan, or discordance between the two modalities, 4DCT was correct at localization in 63% of patients.ConclusionSestamibi has the highest sensitivity and PPV for accurately localizing parathyroid pathology. The addition of US to a positive Sestamibi scan adds little additional value. 4DCT is the preferred imaging modality following an inconclusive Sestamibi or US.

FDA-approved deep learning software application versus radiologists with different levels of expertise: detection of intracranial hemorrhage in a retrospective single-center study.

To assess an FDA-approved and CE-certified deep learning (DL) software application compared to the performance of human radiologists in detecting intracranial hemorrhages (ICH). Within a 20-week trial from January to May 2020, 2210 adult non-contrast head CT scans were performed in a single center and automatically analyzed by an artificial intelligence (AI) solution with workflow integration. After excluding 22 scans due to severe motion artifacts, images were retrospectively assessed for the presence of ICHs by a second-year resident and a certified radiologist under simulated time pressure. Disagreements were resolved by a subspecialized neuroradiologist serving as the reference standard. We calculated interrater agreement and diagnostic performance parameters, including the Breslow-Day and Cochran-Mantel-Haenszel tests. An ICH was present in 214 out of 2188 scans. The interrater agreement between the resident and the certified radiologist was very high (κ = 0.89) and even higher (κ = 0.93) between the resident and the reference standard. The software has delivered 64 false-positive and 68 false-negative results giving an overall sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 68.2%, 96.8%, 69.5%, 96.6%, and 94.0%, respectively. Corresponding values for the resident were 94.9%, 99.2%, 93.1%, 99.4%, and 98.8%. The accuracy of the DL application was inferior (p < 0.001) to that of both the resident and the certified neuroradiologist. A resident under time pressure outperformed an FDA-approved DL program in detecting ICH in CT scans. Our results underline the importance of thoughtful workflow integration and post-approval validation of AI applications in various clinical environments.