Confocal Laser Microscopy for in vivo Intraoperative Application: Diagnostic Accuracy of Investigator and Machine Learning Strategies

2021 ◽  
pp. 1-9
Author(s):  
David Benjamin Ellebrecht ◽  
Nicole Heßler ◽  
Alexander Schlaefer ◽  
Nils Gessert
Keyword(s):  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Cancer Metastasis ◽  
Interobserver Variability ◽  
Confocal Laser ◽  
Predictive Values ◽  
Clinical Reality ◽  
Peritoneal Tissue ◽  
Trained Observers

<b><i>Background:</i></b> Confocal laser microscopy (CLM) is one of the optical techniques that are promising methods of intraoperative in vivo real-time tissue examination based on tissue fluorescence. However, surgeons might struggle interpreting CLM images intraoperatively due to different tissue characteristics of different tissue pathologies in clinical reality. Deep learning techniques enable fast and consistent image analysis and might support intraoperative image interpretation. The objective of this study was to analyze the diagnostic accuracy of newly trained observers in the evaluation of normal colon and peritoneal tissue and colon cancer and metastasis, respectively, and to compare it with that of convolutional neural networks (CNNs). <b><i>Methods:</i></b> Two hundred representative CLM images of the normal and malignant colon and peritoneal tissue were evaluated by newly trained observers (surgeons and pathologists) and CNNs (VGG-16 and Densenet121), respectively, based on tissue dignity. The primary endpoint was the correct detection of the normal and cancer/metastasis tissue measured by sensitivity and specificity of both groups. Additionally, positive predictive values (PPVs) and negative predictive values (NPVs) were calculated for the newly trained observer group. The interobserver variability of dignity evaluation was calculated using kappa statistic. The F1-score and area under the curve (AUC) were used to evaluate the performance of image recognition of the CNNs’ training scenarios. <b><i>Results:</i></b> Sensitivity and specificity ranged between 0.55 and 1.0 (pathologists: 0.66–0.97; surgeons: 0.55–1.0) and between 0.65 and 0.96 (pathologists: 0.68–0.93; surgeons: 0.65–0.96), respectively. PPVs were 0.75 and 0.90 in the pathologists’ group and 0.73–0.96 in the surgeons’ group, respectively. NPVs were 0.73 and 0.96 for pathologists’ and between 0.66 and 1.00 for surgeons’ tissue analysis. The overall interobserver variability was 0.54. Depending on the training scenario, cancer/metastasis tissue was classified with an AUC of 0.77–0.88 by VGG-16 and 0.85–0.89 by Densenet121. Transfer learning improved performance over training from scratch. <b><i>Conclusions:</i></b> Newly trained investigators are able to learn CLM images features and interpretation rapidly, regardless of their clinical experience. Heterogeneity in tissue diagnosis and a moderate interobserver variability reflect the clinical reality more realistic. CNNs provide comparable diagnostic results as clinical observers and could improve surgeons’ intraoperative tissue assessment.

scholarly journals Diagnostic Accuracy of Confocal Laser Endomicroscopy for the Diagnosis of Oral Squamous Cell Carcinoma: A Systematic Review and Meta-Analysis

2021 ◽  
Vol 18 (23) ◽  
pp. 12390
Author(s):  
Sneha Sethi ◽  
Xiangqun Ju ◽  
Richard M. Logan ◽  
Paul Sambrook ◽  
Robert A. McLaughlin ◽  
...  
Keyword(s):  
Systematic Review ◽  
Squamous Cell Carcinoma ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Meta Analysis ◽  
High Sensitivity ◽  
Risk Of Bias ◽  
Confocal Laser Endomicroscopy ◽  
Confocal Laser ◽  
Likelihood Ratios

Background: Advances in treatment approaches for patients with oral squamous cell carcinoma (OSCC) have been unsuccessful in preventing frequent recurrences and distant metastases, leading to a poor prognosis. Early detection and prevention enable an improved 5-year survival and better prognosis. Confocal Laser Endomicroscopy (CLE) is a non-invasive imaging instrument that could enable an earlier diagnosis and possibly help in reducing unnecessary invasive surgical procedures. Objective: To present an up to date systematic review and meta-analysis assessing the diagnostic accuracy of CLE in diagnosing OSCC. Materials and Methods. PubMed, Scopus, and Web of Science databases were explored up to 30 June 2021, to collect articles concerning the diagnosis of OSCC through CLE. Screening: data extraction and appraisal was done by two reviewers. The quality of the methodology followed by the studies included in this review was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. A random effects model was used for the meta-analysis. Results: Six studies were included, leading to a total number of 361 lesions in 213 patients. The pooled sensitivity and specificity were 95% (95% CI, 92–97%; I2 = 77.5%) and 93% (95% CI, 90–95%; I2 = 68.6%); the pooled positive likelihood ratios and negative likelihood ratios were 10.85 (95% CI, 5.4–21.7; I2 = 55.9%) and 0.08 (95% CI, 0.03–0.2; I2 = 83.5%); and the pooled diagnostic odds ratio was 174.45 (95% CI, 34.51–881.69; I2 = 73.6%). Although risk of bias and heterogeneity is observed, this study validates that CLE may have a noteworthy clinical influence on the diagnosis of OSCC, through its high sensitivity and specificity. Conclusions: This review indicates an exceptionally high sensitivity and specificity of CLE for diagnosing OSCC. Whilst it is a promising diagnostic instrument, the limited number of existing studies and potential risk of bias of included studies does not allow us to draw firm conclusions. A conclusive inference can be drawn when more studies, possibly with homogeneous methodological approach, are performed.

Endoscopic molecular imaging of early gastric cancer targeting transferrin receptor 1.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e23093-e23093
Author(s):  
Jie Tian ◽  
Yang Du
Keyword(s):  
Gastric Cancer ◽  
Molecular Imaging ◽  
Early Gastric Cancer ◽  
Diagnostic Accuracy ◽  
Transferrin Receptor ◽  
Confocal Laser Endomicroscopy ◽  
Confocal Laser ◽  
Human Gastric Cancer ◽  
Transferrin Receptor 1

e23093 Background: Gastric cancer is primarily managed endoscopically by white light gastroscope with suboptimal diagnostic accuracy. Emerging optical imaging technologies possess great potential for improving diagnostic accuracy but currently lack imaging agents for molecular specificity. In this study, a novel ligand of transferrin receptor 1 (TfR1), human H-ferritin (HFn), was labeled with fluorescent agents to enable in vivo real-time imaging by confocal laser endomicroscopy (CLE). Methods: In vivo fluorescence imaging was performed in tumor-bearing mice from human gastric cancer cell lines using fluorescently labeled HFn nanoprobe. The HFn-FITC as molecular imaging agent was applied to the gastric cancer with confocal laser endomicroscopy (CLE) in fresh endoscopic submucosal dissection (ESD) of early gastric cancer. Results: Intravital imaging of gastric xenograft tumors revealed a specific tumor targeting effects of HFn-IRDye800CW, whereas no specific signal was observed in mice injected with free dye. An ex vivo experiment on human specimens using a rigid confocal probe showed positive fluorescent staining in ESD samples diagnosed as early gastric cancers. Our CLE evaluation correlated well with immunohistochemical findings. Conclusions: CLE can be used for in vivo, molecular analysis of early gastric cancer and to identify TfR1 expression in xenografts and human tissue samples. HFn-targeted molecular imaging could improve early detection of gastric cancer.

Endoscopic confocal laser-microscopy for the intraoperative nerve recognition: is it feasible?

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
David Benjamin Ellebrecht ◽  
Sönke von Weihe
Keyword(s):  
Diagnostic Accuracy ◽  
Nervous Tissue ◽  
Interobserver Variability ◽  
Nerve Fibers ◽  
Fluorescent Dye ◽  
Image Contrast ◽  
Confocal Laser Microscopy ◽  
Confocal Laser ◽  
Laser Microscopy ◽  
Pleural Tissue

Abstract Surgeons lose most of their tactile tissue information during minimal invasive surgery and need an additional tool of intraoperative tissue recognition. Confocal laser microscopy (CLM) is a well-established method of tissue investigation. The objective of this study was to analyze the feasibility and diagnostic accuracy of CLM nervous tissue recognition. Images taken with an endoscopic CLM system of sympathetic ganglions, nerve fibers and pleural tissue were characterized in terms of specific signal-patterns ex-vivo. No fluorescent dye was used. Diagnostic accuracy of tissue classification was evaluated by newly trained observers (sensitivity, specificity, PPV, NPV and interobserver variability). Although CLM images showed low CLM image contrast, assessment of nerve tissue was feasible without any fluorescent dye. Sensitivity and specificity ranged between 0.73 and 0.9 and 0.55–1.0, respectively. PPVs were 0.71–1.0 and the NPV range was between 0.58 and 0.86. The overall interobserver variability was 0.36. The eCLM enables to evaluate nervous tissue and to distinguish between nerve fibers, ganglions and pleural tissue based on backscattered light. However, the low image contrast and the heterogeneity in correct tissue diagnosis and a fair interobserver variability indicate the limit of CLM imaging without any fluorescent dye.

scholarly journals A PROSPECTIVE STUDY COMPARING GLASGOW SCALE WITH CT SEVERITY INDEX IN RELATION TO SEVERITY OF ACUTE PANCREATITIS

2020 ◽  
pp. 71-73
Author(s):  
Swapnil Sen ◽  
Subir Kumar Kanjilal ◽  
Dipak Chakraborty
Keyword(s):  
Acute Pancreatitis ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Scoring System ◽  
Prognostic Score ◽  
Glasgow Prognostic Score ◽  
Severity Index ◽  
Categorical Variables ◽  
Predictive Values ◽  
Severity Scoring

Acute pancreatitis includes a wide spectrum of disease which can range from mild self-limiting symptoms to a fulminant process and may result in multiple organ failure and high mortality. No highly sensitive and specific test or severity scoring system exists that can accurately measure prognosis at admission and a lack of consensus still prevails as to which severity scoring system is the best predictor of prognosis and final outcome in a case of acute pancreatitis. AIM: To study the efficacy of prediction of severity of Acute Pancreatitis using Glasgow Prognostic Scale and CT Severity Index and to determine whether Glasgow Prognostic Scale and CT Severity Index correlate in predicting the severity of Acute Pancreatitis. MATERIALS AND METHODS: Hospital based prospective observational study on 102 patients admitted in General Surgical wards with features of Acute Pancreatitis at a tertiary care centre of Eastern India. Categorical variables are expressed as Number and percentage of patients and compared across the groups using Pearson’s Chi Square test for Independence of Attributes. The statistical software SPSS version 20 has been used for the analysis. An alpha level of 5% has been taken, i.e. if any p value is less than 0.05, it has been considered as significant. RESULTS: 1. The correlation between Glasgow Prognostic score and the Ranson’s score was found to be statistically significant. 2. The correlation between CT severity index score and Ranson’s score was found to be statistically significant. 3. The sensitivity and specificity of the CT Severity Index was found to be 81.48% and 61.33% respectively. The positive and negative predictive values were found to be 43.14% and 90.20% respectively. The diagnostic accuracy was 66.67%. The sensitivity and specificity of the Glasgow Prognostic Score was found to be 74.07% and 62.67% respectively. The positive and negative predictive values were found to be 41.67% and 87.04% respectively. The diagnostic accuracy was 65.69%. CONCLUSION: Ranson’s Prognostic Score, Glasgow Prognostic Score and the CT Severity Index correlate with each other in cases of Acute Pancreatitis.

Prospective Trial on Probe-Based Confocal Laser Endomicroscopy for the Identification of the Distal Limit in Rectal Adenocarcinoma

2018 ◽  
Vol 25 (4) ◽  
pp. 313-322 ◽  
Author(s):  
Arthur R. Wijsmuller ◽  
Jean-Pierre Ghnassia ◽  
Sharmini Varatharajah ◽  
Mickael Schaeffer ◽  
Joel Leroy ◽  
...  
Keyword(s):  
Correlation Coefficient ◽  
Sensitivity And Specificity ◽  
Intraclass Correlation Coefficient ◽  
Intraclass Correlation ◽  
Prospective Trial ◽  
Rectal Adenocarcinoma ◽  
Neoadjuvant Chemoradiation ◽  
Confocal Laser Endomicroscopy ◽  
Confocal Laser

Background. Intraoperative decision of the level of distal resection in rectal cancer is often imprecise, based exclusively on digital examination and pretherapeutic imaging. Design. Prospective, single institution, nonrandomized trial ( ClinicalTrial.gov identification no. NCT01887509) to evaluate the contribution of probe-based confocal laser endomicroscopy (pCLE) to establish the optimal resection margin of rectal adenocarcinoma. The primary outcome was the concordance in the identification of lower tumor margins between pCLE and histopathology. For each patient, pCLE examination was performed on nonneoplastic and neoplastic aspects of the distal tumor margin, before and after neoadjuvant chemoradiation, or preceding surgery, if chemoradiation was not required. Biopsies were taken at the same locations. The intraclass correlation coefficient was determined. Results. Twenty-one patients were enrolled. Thirteen patients completed the full study. Six patients completed imaging only before chemoradiation. Two patients retracted their consent after inclusion. A total of 134 videos and corresponding histopathology samplings were analyzed. The sensitivity and specificity of in vivo pCLE interpretation were 0.915 (95% confidence interval [CI] = 0.840-0.970) and 0.736 (95% CI = 0.657-0.821), respectively. The sensitivity and specificity of the blinded pCLE reinterpretation were 0.930 (95% CI = 0.858-0.980) and 0.688 (95% CI = 0.600-0.770), respectively. No deep layer tumor infiltration was encountered in the samplings with superficial healthy layers. The intraclass correlation coefficient for in vivo pCLE interpretation and blinded pCLE reinterpretation were 0.747 (95% CI = 0.257-0.993) and 0.766 (95% CI = 0.280-0.995), respectively. Conclusions. This supports the concordance between pCLE and histopathology in identifying the “tumor-free” limit of a rectal tumor preceding resection.

Diagnostic Accuracy of a Confocal Laser Endomicroscope for In Vivo Differentiation Between Normal Injured And Tumor Tissue During Fluorescein-Guided Glioma Resection: Laboratory Investigation

2018 ◽  
Vol 115 ◽  
pp. e337-e348 ◽  
Author(s):  
Evgenii Belykh ◽  
Eric J. Miller ◽  
Arpan A. Patel ◽  
Mohammedhassan Izady Yazdanabadi ◽  
Nikolay L. Martirosyan ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Laboratory Investigation ◽  
Tumor Tissue ◽  
Confocal Laser ◽  
In Vivo Differentiation ◽  
Glioma Resection

Can Preoperative Imaging Predict Tumor Involvement of the Anterior Clinoid in Clinoid Region Meningiomas?

Neurosurgery ◽  
2015 ◽  
Vol 77 (4) ◽  
pp. 525-530 ◽  
Author(s):  
William R. Copeland ◽  
Jamie J. Van Gompel ◽  
Caterina Giannini ◽  
Laurence J. Eckel ◽  
Kelly K. Koeller ◽  
...  
Keyword(s):  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Interobserver Agreement ◽  
Final Analysis ◽  
Preoperative Imaging ◽  
Likelihood Ratios ◽  
Predictive Values ◽  
Pathological Analysis ◽  
Simpson Grade ◽  
Tumor Involvement

BACKGROUND: Anterior clinoid region meningiomas may infiltrate the bone over which they arise, therefore requiring an anterior clinoidectomy to achieve a Simpson grade 1 resection. A clinoidectomy, however, is not without risks. OBJECTIVE: We performed a study of diagnostic accuracy investigating whether preoperative imaging could predict tumor involvement of the clinoid, and thereby tailor the degree of bony removal. METHODS: Patients having undergone resection of a clinoid region meningioma between 2001 and 2011 were identified. Included in further analysis were those patients in whom a clinoidectomy was performed with subsequent pathologically confirmed presence or absence of tumor in the clinoid process on decalcified specimens. Two neuroradiologists, blinded to pathology results, independently reviewed available preoperative imaging and stated whether or not they anticipated the clinoid to be involved by tumor. Interobserver agreement and the ability to accurately predict tumor involvement of the clinoid were then analyzed. RESULTS: Sixty-two patients were included in the final analysis. Interobserver agreement was 100%. Sensitivity and specificity of preoperative imaging to predict tumor involvement was 89% and 52%, respectively, with positive and negative likelihood ratios of 1.85 and 0.20. Positive and negative predictive values were 73% and 76%, respectively. CONCLUSION: Preoperative imaging of clinoid region meningiomas can accurately predict the presence or absence of tumor involvement of the clinoid in only approximately 75% of cases. In light of the fact that a quarter of patients with radiographically negative clinoids will have tumor present on pathological analysis, we recommend a clinoidectomy for all clinoid region meningiomas.

scholarly journals Sensitivity and specificity of malaria rapid diagnostic test (mRDT CareStatTM) compared with microscopy amongst under five children attending a primary care clinic in southern Nigeria

2020 ◽  
Vol 12 (1) ◽  
Author(s):  
Oluwagbenga Ogunfowokan ◽  
Bamidele A. Ogunfowokan ◽  
Anthony I. Nwajei
Keyword(s):  
Primary Care ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Parasite Density ◽  
Primary Care Clinic ◽  
Malaria Diagnosis ◽  
Malaria Prevalence ◽  
Cross Sectional ◽  
Care Clinic ◽  
Predictive Values

Background: Malaria diagnosis using microscopy is currently the gold standard. However, malaria rapid diagnostic tests (mRDTs) were developed to simplify the diagnosis in regions without access to functional microscopy.Aim: The objective of this study was to compare the diagnostic accuracy of mRDT CareStatTM with microscopy.Setting: This study was conducted in the paediatric primary care clinic of the Federal Medical Centre, Asaba, Nigeria.Methods: A cross-sectional study for diagnostic accuracy was conducted from May 2016 to October 2016. Ninety-eight participants were involved to obtain a precision of 5%, sensitivity of mRDT CareStatTM of 95% from published work and 95% level of confidence after adjusting for 20% non-response rate or missing data. Consecutive participants were tested using both microscopy and mRDT. The results were analysed using EPI Info Version 7.Results: A total of 98 children aged 3–59 months were enrolled. Malaria prevalence was found to be 53% (95% confidence interval [CI] = 46% – 60%), whilst sensitivity and specificity were 29% (95% CI = 20% – 38%) and 89% (95% CI = 83% – 95%), respectively. The positive and negative predictive values were 75% (95% CI = 66.4% – 83.6%) and 53% (95% CI = 46% – 60%), respectively.Conclusion: Agreement between malaria parasitaemia using microscopy and mRDT positivity increased with increase in the parasite density. The mRDT might be negative when malaria parasite density using microscopy is low.

Sign in / Sign up

Export Citation Format

Share Document