Classification of True-progression after Radiotherapy of Brain Metastasis on MRI using Artificial Intelligence: a Systematic Review and Meta-Analysis

Abstract Background Classification of true-progression from non-progression (e.g., radiation-necrosis) after stereotactic radiotherapy/radiosurgery of brain metastasis is known to be a challenging diagnostic task on conventional magnetic resonance imaging (MRI). The scope and status of research using artificial intelligence (AI) on classifying true-progression is yet unknown. Methods We performed a systematic literature search of MEDLINE and EMBASE databases to identify studies that investigated the performance of AI-assisted MRI in classifying true-progression after stereotactic radiotherapy/radiosurgery of brain metastasis, published before November 11th, 2020. Pooled sensitivity and specificity were calculated using bivariate random-effects modeling. Meta-regression was performed for identification of factors contributing to the heterogeneity among the studies. We assessed the quality of the studies using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria and a modified version of the radiomics quality score (RQS). Results 7 studies were included, with a total of 485 patients and 907 tumors. The pooled sensitivity and specificity were 77% (95% CI, 70–83%) and 74% (64–82%), respectively. All 7 studies used radiomics, and none used deep learning. Several covariates including the proportion of lung cancer as the primary site, MR field strength, and radiomics segmentation slice showed a statistically significant association with the heterogeneity. Study quality was overall favorable in terms of the QUADAS-2 criteria, but not in terms of the RQS. Conclusion The diagnostic performance of AI-assisted MRI seems yet inadequate to be used reliably in clinical practice. Future studies with improved methodologies and a larger training set are needed.

Download Full-text

Differentiating PSP from MSA using MR planimetric measurements: a systematic review and meta-analysis

Journal of Neural Transmission ◽

10.1007/s00702-021-02362-8 ◽

2021 ◽

Author(s):

Beatrice Heim ◽

Florian Krismer ◽

Klaus Seppi

Keyword(s):

Sensitivity And Specificity ◽

Meta Analysis ◽

Risk Of Bias ◽

Index Test ◽

Study Quality ◽

Parkinsonian Syndromes ◽

Quantitative Mr ◽

Meta Analyses ◽

Planimetric Measurements

AbstractDifferential diagnosis of parkinsonian syndromes is considered one of the most challenging in neurology. Quantitative MR planimetric measurements were reported to discriminate between progressive supranuclear palsy (PSP) and non-PSP-parkinsonism. Several studies have used midbrain to pons ratio (M/P) and the Magnetic Resonance Parkinsonism Index (MRPI) in distinguishing PSP patients from those with Parkinson's disease. The current meta-analysis aimed to compare the performance of these measures in discriminating PSP from multiple system atrophy (MSA). A systematic MEDLINE review identified 59 out of 2984 studies allowing a calculation of sensitivity and specificity using the MRPI or M/P. Meta-analyses of results were carried out using random effects modelling. To assess study quality and risk of bias, the QUADAS-2 tool was used. Eight studies were suitable for analysis. The meta‐analysis showed a pooled sensitivity and specificity for the MRPI of PSP versus MSA of 79.2% (95% CI 72.7–84.4%) and 91.2% (95% CI 79.5–96.5%), and 84.1% (95% CI 77.2–89.2%) and 89.2% (95% CI 81.8–93.8%), respectively, for the M/P. The QUADAS-2 toolbox revealed a high risk of bias regarding the methodological quality of patient selection and index test, as all patients were seen in a specialized outpatient department without avoiding case control design and no predefined threshold was given regarding MRPI or M/P cut-offs. Planimetric brainstem measurements, in special the MRPI and M/P, yield high diagnostic accuracy for the discrimination of PSP from MSA. However, there is an urgent need for well-designed, prospective validation studies to ameliorate the concerns regarding the risk of bias.

Download Full-text

Can Serum Glypican-3 Be a Biomarker for Effective Diagnosis of Hepatocellular Carcinoma? A Meta-Analysis of the Literature

Disease Markers ◽

10.1155/2014/127831 ◽

2014 ◽

Vol 2014 ◽

pp. 1-11 ◽

Cited By ~ 3

Author(s):

Sheng-Li Yang ◽

Xiefan Fang ◽

Zao-Zao Huang ◽

Xiang-Jie Liu ◽

Zhi-Fan Xiong ◽

...

Keyword(s):

Hepatocellular Carcinoma ◽

Liver Cirrhosis ◽

Sensitivity And Specificity ◽

Meta Analysis ◽

Diagnostic Value ◽

Healthy Individuals ◽

Subgroup Analyses ◽

Effective Diagnosis ◽

Diagnostic Index

Objective. This review is to evaluate the diagnostic value of serum GPC3 for hepatocellular carcinoma (HCC) due to conflicting results reported.Methods. NCBI PubMed and Embase were comprehensively searched for studies that have used serum GPC3 level as a diagnostic index for HCC. The quality of the included studies was assessed. Subgroup analyses were conducted to evaluate the sensitivity and specificity of GPC3 as a HCC marker. Statistical analysis was performed with the software STATA version 12.0.Results. A total of 22 studies were included. The qualities of included studies were relatively poor. Among them, 18 studies have shown that serum GPC3 is a specific biomarker for HCC, and the pooled sensitivity and specificity of these studies were 69 and 93%, respectively. The other 4 studies have reported conflicting results, which were not caused by races, infection status of HBV and HCV, or assay reagents but due to one common experimental design of enrolling liver cirrhosis patients as control subjects.Conclusions. This meta-analysis indicates that serum GPC3 is elevated in HCC patients compared with healthy individuals, but more studies are needed to evaluate its effectiveness to differentially diagnose HCC and liver cirrhosis.

Download Full-text

A study of the sensitivity and specificity of the Magnetic Resonance Imaging (MRI) technique used in the diagnosis of endometriosis versus the intraoperative appearance considered the reference standard in the diagnosis of endometriosis

Medicina Moderna - Modern Medicine ◽

10.31689/rmm.2021.28.1.55 ◽

2021 ◽

Vol 28 (1) ◽

pp. 55-61

Author(s):

Alexandra RADU ◽

◽

Elvira BRATILA ◽

Keyword(s):

Magnetic Resonance Imaging ◽

Magnetic Resonance ◽

Sensitivity And Specificity ◽

Reference Standard ◽

Resonance Imaging ◽

First Line ◽

Magnetic Resonance Imaging Mri ◽

Asymptomatic Women ◽

Bladder Invasion

Endometriosis is a gynecological pathology with chronic symptoms, which negatively affects the patient’s quality of life. The prevalence of endometriosis in asymptomatic women is between 2% and 50%, depending on the populations studied and the method of diagnosis. The severity of the symptoms as well as the probability of diagnosing endometriosis increases with age9. Because endometriosis is a gynecological condition with a nonspecific clinical picture, sometimes even asymptomatic, imaging technology can be considered the first line of diagnosis for this pathology. The main objective of this study is to evaluate the sensitivity and specificity of nuclear magnetic resonance imaging (MRI) used in the diagnosis of endometriotic lesions depending on their location, and compare the results obtained with the intraoperative appearance considered a reference standard in the diagnosis of endometriosis. Our study revealed the highest specificity for MRI in the case of endometriotic bladder invasion, respectively the highest sensitivity for endometriotic rectal nodules.

Download Full-text

Rapid diagnostic test for antenatal syphilis screening in low-income and middle-income countries: a systematic review and meta-analysis

BMJ Open ◽

10.1136/bmjopen-2017-018132 ◽

2018 ◽

Vol 8 (2) ◽

pp. e018132 ◽

Cited By ~ 5

Author(s):

Carmen Phang Romero Casas ◽

Marrissa Martyn-St James ◽

Jean Hamilton ◽

Daniel S Marinho ◽

Rodolfo Castro ◽

...

Keyword(s):

Systematic Review ◽

High Risk ◽

Diagnostic Accuracy ◽

Pregnant Women ◽

Sensitivity And Specificity ◽

Methodological Quality ◽

Meta Analysis ◽

Risk Of Bias ◽

Antenatal Clinics

ObjectivesTo undertake a systematic review and meta-analysis to evaluate the test performance including sensitivity and specificity of rapid immunochromatographic syphilis (ICS) point-of-care (POC) tests at antenatal clinics compared with reference standard tests (non-treponemal (TP) and TP tests) for active syphilis in pregnant women.MethodsFive electronic databases were searched (PubMed, EMBASE, CRD, Cochrane Library and LILACS) to March 2016 for diagnostic accuracy studies of ICS test and standard reference tests for syphilis in pregnant women. Methodological quality was assessed using QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies). A bivariate meta-analysis was undertaken to generate pooled estimates of diagnostic parameters. Results were presented using a coupled forest plot of sensitivity and specificity and a scatter plot.ResultsThe methodological quality of the five included studies with regards to risk of bias and applicability concern judgements was either low or unclear. One study was judged as high risk of bias for patient selection due to exclusion of pregnant women with a previous history of syphilis, and one study was judged at high risk of bias for study flow and timing as not all patients were included in the analysis. Five studies contributed to the meta-analysis, providing a pooled sensitivity and specificity for ICS of 0.85 (95% CrI: 0.73 to 0.92) and 0.98 (95% CrI: 0.95 to 0.99), respectively.ConclusionsThis review and meta-analysis observed that rapid ICS POC tests have a high sensitivity and specificity when performed in pregnant women at antenatal clinics. However, the methodological quality of the existing evidence base should be taken into consideration when interpreting these results.PROSPERO registration numberCRD42016036335.

Download Full-text

1267 Utility of Artificial Intelligence in the Cystoscopic Detection of Bladder Cancer: A Systematic Review and Meta-Analysis

British Journal of Surgery ◽

10.1093/bjs/znab258.053 ◽

2021 ◽

Vol 108 (Supplement_6) ◽

Author(s):

S Ganesananthan ◽

B S Simpson ◽

J M Norris

Keyword(s):

Artificial Intelligence ◽

Bladder Cancer ◽

Sensitivity And Specificity ◽

Meta Analysis ◽

External Validation ◽

High Sensitivity ◽

Diagnostic Odds Ratio ◽

Pooled Analysis ◽

Likelihood Ratios ◽

Novel Technology

Abstract Aim Detection of suspected bladder cancer at diagnostic cystoscopy is challenging and is dependent on clinician skill. Artificial Intelligence (AI) algorithms, specifically, machine learning and deep learning, have shown promise in accurate classification of pathological images in various specialties. However, utility of AI for urothelial cancer diagnosis is unknown. Here, we aimed to systematically review the extant literature in this field and quantitively summarise the role of these algorithms in bladder cancer detection. Method The EMBASE, PubMed and CENTRAL databases were searched up to December 22nd 2020 , in accordance with the PRISMA guidelines, for studies that evaluated AI algorithms for cystoscopic diagnosis of bladder cancer. Random-effects meta-analysis was performed to summarise eligible studies. Risk of Bias was assessed using the QUADAS-2 tool. Results Five from 6715 studies met criteria for inclusion. Pooled sensitivity and specificity values were 0.93 (95% CI 0.89–0.95) and 0.93 (95% CI 0.80–0.89) respectively. Pooled positive likelihood and negative likelihood ratios were 14 (95% CI 4.3–44) and 0.08 (95% CI: 0.05–0.11), respectively. Pooled diagnostic odds ratio was 182 (95% CI 61–546). Summary AUC curve value was 0.95 (95% CI 0.93–0.97). No significant publication bias was noted. Conclusions In summary, AI algorithms performed very well in detection of bladder cancer in this pooled analysis, with high sensitivity and specificity values. However, as with other clinical AI usage, further external validation through deployment in real clinical situations is essential to assess true applicability of this novel technology.

Download Full-text

A Bayesian network meta-analysis of whole brain radiotherapy and stereotactic radiotherapy for brain metastasis

Medicine ◽

10.1097/md.0000000000007698 ◽

2017 ◽

Vol 96 (34) ◽

pp. e7698 ◽

Cited By ~ 4

Author(s):

Xi Yuan ◽

Wen-Jie Liu ◽

Bing Li ◽

Ze-Tian Shen ◽

Jun-shu Shen ◽

...

Keyword(s):

Brain Metastasis ◽

Bayesian Network ◽

Stereotactic Radiotherapy ◽

Meta Analysis ◽

Whole Brain Radiotherapy ◽

Whole Brain ◽

Brain Radiotherapy

Download Full-text

Incidence of intraspinal abnormalities in congenital scoliosis: a systematic review and meta-analysis

Journal of Orthopaedic Surgery and Research ◽

10.1186/s13018-020-02015-8 ◽

2020 ◽

Vol 15 (1) ◽

Author(s):

Xudong Wang ◽

Yangke Yu ◽

Ningning Yang ◽

Lei Xia

Keyword(s):

Systematic Review ◽

Meta Analysis ◽

Tethered Cord ◽

Congenital Scoliosis ◽

Cochrane Library ◽

Resonance Imaging ◽

R Software ◽

Dural Ectasia ◽

Magnetic Resonance Imaging Mri

Abstract Objective This is the first systematic review and meta-analysis on the overall incidence of intraspinal abnormalities in patients with congenital scoliosis (CS) and potential influencing factors. Methods We searched three large electronic databases (PubMed, EMBASE, and Cochrane Library) for potentially relevant studies. The quality of the included studies was assessed independently by two authors using the Methodological Index for Non-Randomized Studies (MINORS) criteria. Data on the number of CS patients, number of CS patients with intraspinal abnormalities, sex of the patients, and CS types were extracted from the included studies. R software was used to pool and analyze all the extracted data. Results This meta-analysis included 10 articles, and 671 of 1863 CS patients undergoing magnetic resonance imaging (MRI) examinations were identified to have intraspinal abnormalities. The overall incidence of intraspinal abnormalities in the patients with CS was 37% (95% CI, 29–45%). Diastematomyelia was the most common intraspinal abnormality and was detected in 45.60% of the patients with intraspinal abnormalities (306/671). The remaining intraspinal abnormalities included syringomyelia (273/671, 40.69%), tethered cord (190/671, 28.32%), low conus (58/671, 8.64%), intraspinal mass (39/671, 5.81%), Chiari malformation (32/671, 4.77%), fatty filum (27/671, 4.02%), spina bifida (occulta excluded) (17/671, 2.53%), tumor (17/671, 2.53%), cyst (12/671, 1.79%), syringomyelus (4/671, 0.60%), dural ectasia (1/671, 0.15%), and undiagnosed cord MRI hyperintensity (1/671, 0.15%). The patient’s sex and CS type were not factors that affected the incidence of intraspinal abnormalities in CS patients (all P > 0.05). Conclusions This meta-analysis revealed that the overall incidence of intraspinal abnormalities detected by MRI in CS patients was 37%. Diastematomyelia was the most common intraspinal abnormality. The patient’s sex and CS type were not factors that affected the incidence of intraspinal abnormalities in CS patients.

Download Full-text

Meta-analysis of Comparative Therapy Outcome Studies: a Reply to Wilson

Behavioural and Cognitive Psychotherapy ◽

10.1017/s0141347300008181 ◽

1982 ◽

Vol 10 (4) ◽

pp. 307-310 ◽

Cited By ~ 26

Author(s):

David A. Shapiro ◽

Diana Shapiro

Keyword(s):

Meta Analysis ◽

Outcome Studies ◽

Therapy Outcome ◽

Meta Analyses ◽

Selection Of

Wilson's recent critique of the authors' appraisal of meta-analysis appears to misunderstand them as claiming more for meta-analysis than they intended. The present paper seeks to clarify consequent confusions concerning selection of studies, the quality of the literature reviewed, the classification of therapies, and the non-identical results of different meta-analyses. It is acknowledged that no single meta-analysis is definitive.

Download Full-text

Automated Brain Imaging Diagnosis and Classification Model using Rat Swarm Optimization with Deep Learning based Capsule Network

International Journal of Image and Graphics ◽

10.1142/s0219467822400010 ◽

2021 ◽

pp. 2240001

Author(s):

A. Vasantharaj ◽

Pacha Shoba Rani ◽

Sirajul Huque ◽

K. S. Raghuram ◽

R. Ganeshkumar ◽

...

Keyword(s):

Deep Learning ◽

Classification Model ◽

Swarm Optimization ◽

Diagnosis And Classification ◽

Enhance Efficiency ◽

Magnetic Resonance Imaging Mri ◽

Learning Machine ◽

The Brain

Earlier identification of brain tumor (BT) is essential to increase the survival rate of the patients. The commonly used imaging technique for BT diagnosis is magnetic resonance imaging (MRI). Automated BT classification model is required for assisting the radiologists to save time and enhance efficiency. The classification of BT is difficult owing to the non-uniform shapes of tumors and location of tumors in the brain. Therefore, deep learning (DL) models can be employed for the effective identification, prediction, and diagnosis of diseases. In this view, this paper presents an automated BT diagnosis using rat swarm optimization (RSO) with deep learning based capsule network (DLCN) model, named RSO-DLCN model. The presented RSO-DLCN model involves bilateral filtering (BF) based preprocessing to enhance the quality of the MRI. Besides, non-iterative grabcut based segmentation (NIGCS) technique is applied to detect the affected tumor regions. In addition, DLCN model based feature extractor with RSO algorithm based parameter optimization processes takes place. Finally, extreme learning machine with stacked autoencoder (ELM-SA) based classifier is employed for the effective classification of BT. For validating the BT diagnostic performance of the presented RSO-DLCN model, an extensive set of simulations were carried out and the results are inspected under diverse dimensions. The simulation outcome demonstrated the promising results of the RSO-DLCN model on BT diagnosis with the sensitivity of 98.4%, specificity of 99%, and accuracy of 98.7%.

Download Full-text

The Value of Pepsinogen in GC Screening: A Systematic Review and Meta-Analysis

Gastroenterology Research and Practice ◽

10.1155/2019/7087232 ◽

2019 ◽

Vol 2019 ◽

pp. 1-11 ◽

Cited By ~ 1

Author(s):

Ling Liu ◽

Junjie Lang ◽

Yuelong Jin ◽

Yan Chen ◽

Weiwei Chang ◽

...

Keyword(s):

Sensitivity And Specificity ◽

Meta Analysis ◽

Barium Meal ◽

Cochrane Library ◽

Likelihood Ratios ◽

Exclusion Criteria ◽

High Quality Research ◽

Wide Range ◽

The Cochrane Library

Background. The current gold standard for gastric cancer (GC) screening is pathology or a barium meal followed by X-ray. This is not applicable to a wide range of screening capabilities due to the lack of operability. This article used a meta-analysis to evaluate the value of pepsinogen (PG) screening for GC.Methods. PubMed, EMbase, the Cochrane Library, CNKI, WanFang, VIP, and CBM databases were systematically searched for published studies that used serum PG to diagnose GC. Articles were searched from January 2003 to January 2018. Two reviewers independently screened the literature according to specified inclusion and exclusion criteria. The data were extracted and evaluated, and the quality of the methodologies evaluated using the QUADAS entry. The meta-analysis (MA) was performed using Meta-DiSc 1.4 software. Stata 12.0 software was used to assess publication bias.Results. A total of 19 studies were finally included from a total of 169,009 cases. The MA showed a combined sensitivity and specificity of 0.56 (95% CI (0.53–0.59),P<0.01) and 0.71 (95% CI (0.70-0.71),P<0.01), respectively. The combined likelihood ratios were +LR = 2.82 (95% CI (2.06–3.86),P<0.01) and −LR = 0.56 (95% CI (0.45–0.68),P<0.01). The combined DOR was 5.41 (95% CI (3.64~ 8.06),P<0.01), and the area under the SROC curve was 0.7468.Conclusions. Serum PG provides medium levels of sensitivity and specificity for GC assessment. To be used in a clinical setting, further high-quality research must be performed and verified.

Download Full-text