scholarly journals Machine Learning Facilitates Hotspot Classification in PSMA-PET/CT with Nuclear Medicine Specialist Accuracy

Diagnostics ◽  
2020 ◽  
Vol 10 (9) ◽  
pp. 622
Author(s):  
Sobhan Moazemi ◽  
Zain Khurshid ◽  
Annette Erle ◽  
Susanne Lütje ◽  
Markus Essler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Positron Emission Tomography ◽  
Low Dose ◽  
Emission Tomography ◽  
Textural Features ◽  
Low Dose Ct ◽  
Positron Emission ◽  
Psma Pet ◽  
Pet Ct ◽  
Ct Data

Gallium-68 prostate-specific membrane antigen positron emission tomography (68Ga-PSMA-PET) is a highly sensitive method to detect prostate cancer (PC) metastases. Visual discrimination between malignant and physiologic/unspecific tracer accumulation by a nuclear medicine (NM) specialist is essential for image interpretation. In the future, automated machine learning (ML)-based tools will assist physicians in image analysis. The aim of this work was to develop a tool for analysis of 68Ga-PSMA-PET images and to compare its efficacy to that of human readers. Five different ML methods were compared and tested on multiple positron emission tomography/computed tomography (PET/CT) data-sets. Forty textural features extracted from both PET- and low-dose CT data were analyzed. In total, 2419 hotspots from 72 patients were included. Comparing results from human readers to those of ML-based analyses, up to 98% area under the curve (AUC), 94% sensitivity (SE), and 89% specificity (SP) were achieved. Interestingly, textural features assessed in native low-dose CT increased the accuracy significantly. Thus, ML based on 68Ga-PSMA-PET/CT radiomics features can classify hotspots with high precision, comparable to that of experienced NM physicians. Additionally, the superiority of multimodal ML-based analysis considering all PET and low-dose CT features was shown. Morphological features seemed to be of special additional importance even though they were extracted from native low-dose CTs.

scholarly journals Can 68Ga-prostate specific membrane antigen positron emission tomography/computerized tomography provide an accurate lymph node staging for patients with medium/high risk prostate cancer? A diagnostic meta-analysis

2020 ◽  
Vol 15 (1) ◽  
Author(s):  
Lei Peng ◽  
Jinze Li ◽  
Chunyang Meng ◽  
Jinming Li ◽  
Chengyu You ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Positron Emission Tomography ◽  
Lymph Node ◽  
High Risk ◽  
Meta Analysis ◽  
Diagnostic Value ◽  
Emission Tomography ◽  
Positron Emission ◽  
Psma Pet ◽  
Pet Ct

Abstract Objective This article aims to evaluate the diagnostic value of 68Gallium-PSMA positron emission tomography/computerized tomography (68Ga-PSMA PET/CT) for lymph node (LN) staging in patients with prostate cancer (PCa) by a meta-analysis of diagnostic tests. Methods We systematically retrieved articles from Web of Science, EMBASE, Cochrane Database, PubMed. The time limit is from the creation of the database until June 2019, and Stata 15 was used for calculation and statistical analyses. Results Sensitivity, specificity, positive and negative likelihood ratio (PLR, NLR), diagnostic odds ratio (DOR) and 95% confidence intervals (CI) be used to evaluate the diagnostic value. A total of 10 studies were included in our meta-analysis, which included 701 individuals. The results of each consolidated summary are as follows: sensitivity of 0.84 (95% CI 0.55–0.95), specificity of 0.95 (95% CI 0.87–0.98), PLR and NLR was 17.19 (95% CI 6.27, 47.17) and 0.17 (95% CI 0.05–0.56), respectively. DOR of 100 (95% CI 18–545), AUC of 0.97 (95% CI 0.95–0.98). Conclusion Our study demonstrates that 68Ga-PSMA PET/CT has a high overall diagnostic value for LN staging in patients with moderate and high-risk PCa. But our conclusions still require a larger sample size, multi-center prospective randomized controlled trial to verify.

scholarly journals Can 68Ga-prostate specific membrane antigen positron emission tomography / computerized tomography provide an accurate lymph node staging for patients with medium / high risk prostate cancer? A Diagnostic Meta-Analysis

2020 ◽  
Author(s):  
Lei Peng ◽  
Jinze Li ◽  
Chuanyang Meng ◽  
Jinming Li ◽  
Chengyu You ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Positron Emission Tomography ◽  
Lymph Node ◽  
High Risk ◽  
Meta Analysis ◽  
Diagnostic Value ◽  
Emission Tomography ◽  
Positron Emission ◽  
Psma Pet ◽  
Pet Ct

Abstract Objective: This article aims to evaluate the diagnostic value of 68Gallium-PSMA positron emission tomography/computerized tomography (68Ga-PSMA PET/CT) for lymph node (LN) staging in patients with prostate cancer (PCa) by a meta-analysis of diagnostic tests.Methods: We systematically retrieved articles from Web of Science, EMBASE, Cochrane Database, PubMed. The time limit is from the creation of the database until June 2019, and Stata 15 was used for calculation and statistical analyses.Results: Sensitivity, specificity, positive and negative likelihood ratio (PLR, NLR), diagnostic odds ratio (DOR) and 95% confidence intervals (CI) be used to evaluate the diagnostic value. A total of 10 studies were included in our meta-analysis, which included 701 individuals. The results of each consolidated summary are as follows: sensitivity of 0.84 (95% CI: 0.55-0.95), specificity of 0.95 (95% CI: 0.87-0.98), PLR and NLR was 17.19 (95% CI: 6.27, 47.17) and 0.17 (95% CI: 0.05-0.56), respectively. DOR of 100 (95% CI: 18-545), AUC of 0.97 (95% CI: 0.95-0.98). Conclusion: Our study demonstrates that 68Ga-PSMA PET/CT has a high overall diagnostic value for LN staging in patients with moderate and high-risk PCa. But our conclusions still require a larger sample size, multi-center prospective randomized controlled trial to verify.

scholarly journals Can 68Ga-prostate specific membrane antigen positron emission tomography / computerized tomography provide an accurate lymph node staging for patients with medium / high risk prostate cancer? A Diagnostic Meta-Analysis

2020 ◽  
Author(s):  
Lei Peng ◽  
Jinze Li ◽  
Chuanyang Meng ◽  
Jinming Li ◽  
Chengyu You ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Positron Emission Tomography ◽  
Lymph Node ◽  
High Risk ◽  
Meta Analysis ◽  
Diagnostic Value ◽  
Emission Tomography ◽  
Positron Emission ◽  
Psma Pet ◽  
Pet Ct

Abstract Objective: This article aims to evaluate the diagnostic value of68Gallium-PSMA positron emission tomography/computerized tomography (68Ga-PSMA PET/CT) for lymph node (LN) staging in patients with prostate cancer (PCa) by a meta-analysis of diagnostic tests.Methods: We systematically retrieved articles from PubMed, Embase, Web of Science with a limited period from January 1, 2016, to December 1, 2019, and Stata 15 was used for calculation and statistical analyses.Results: Sensitivity, specificity, positive and negative likelihood ratio (PLR, NLR), diagnostic odds ratio (DOR) and 95% confidence intervals (CI) be used to evaluate the diagnostic value. A total of 10 studies were included in our meta-analysis, which included 701 individuals. The results of each consolidated summary are as follows: sensitivity of 0.84 (95% CI: 0.55-0.95), specificity of 0.95 (95% CI: 0.87-0.98), PLR and NLR was 17.19 (95% CI: 6.27, 47.17) and 0.17 (95% CI: 0.05-0.56), respectively. DOR of 4.6 (95% CI: 2.91-6.30), AUC of 0.97 (95% CI: 0.95-0.98).Conclusion: Our study demonstrates that 68Ga-PSMA PET/CT has a high overall diagnostic value for LN staging in patients with moderate and high-risk PCa. But our conclusions still require a larger sample size, multi-center prospective randomized controlled trial to verify.

The Potential Value of Hybrid Positron Emission Tomography/Dual-Source Computed Tomography Imaging in Coronary Bypass Surgery

2011 ◽  
Vol 14 (5) ◽  
pp. 283 ◽  
Author(s):  
Andre Plass ◽  
Maximilian Y. Emmert ◽  
Oliver Gaemperli ◽  
Hatem Alkadhi ◽  
Philipp Kaufmann ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Positron Emission Tomography ◽  
Coronary Artery ◽  
Coronary Angiography ◽  
Myocardial Perfusion ◽  
Predictive Value ◽  
Bypass Surgery ◽  
Emission Tomography ◽  
Positron Emission ◽  
Pet Ct

<p><b>Background:</b> We evaluated how comprehensive assessment of coronary artery lesions and their hemodynamic relevance by means of hybrid positron emission tomography (PET) and computed tomography (CT) imaging would affect decision-making in coronary artery bypass surgery (CABG), compared with using invasive coronary angiography (ICA) alone.</p><p><b>Methods:</b> After undergoing ICA, 27 patients (21 men and 6 women; mean SD age, 66 � 10 years) planned for cardiac surgery were scheduled for myocardial perfusion stress/rest evaluation with [13N]ammonia PET and CT coronary angiography. Only ICA was available to the surgeon. Postoperatively, the performed CABG was compared with the hypothetical strategy based on hybrid PET/CT findings (regional coronary flow reserve [CFR], myocardial perfusion defects). Procedures included CABG (n = 18) alone, CABG combined with valve replacement (n = 6), and CABG combined with isolated valve replacement (n = 3). A total of 56 bypass grafts (28 venous and 28 arterial) and 66 distal anastomoses were placed.</p><p><b>Results:</b> CT evaluation showed 93% concordance (66/71) with ICA regarding significant stenoses, with sensitivity, specificity, positive predictive value, and negative predictive value of 93.1%, 98.7%, 94.4%, and 98.4%, respectively. In the PET scan, 16 patients had 1 ischemic region, and 12 patients had 1 scar region, including 5 patients who presented with mixed conditions (scar and ischemia). One patient had a completely normal myocardium. Compared with the performed surgery, PET/CT fusion evaluation showed that of the performed anastomoses, 48% had documented ischemia (with a CFR <2 in 86%), 38% were nonischemic (although a CFR value <2 was found in 78%), and 14% had scar tissue (fixed perfusion defect).</p><p><b>Conclusions:</b> Although <50% of bypasses were placed to areas with myocardial ischemia, the CFR was low in the majority of nonischemic regions, a finding that may have important prognostic relevance. PET/CT fusion imaging could potentially influence planning for CABG and provide incremental prognostic information.</p>

Sign in / Sign up

Export Citation Format

Share Document