دورية أكاديمية
How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review.
| العنوان: | How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review. |
|---|---|
| المؤلفون: | Guha A; Department of Radio-diagnosis, Tata Memorial Hospital, Parel, Mumbai, 400012, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India. Electronic address: amritaguha85@gmail.com., Halder S; Centre for Cancer Epidemiology, Advanced Centre for Treatment Research & Education in Cancer, Tata Memorial Centre, Kharghar, Navi Mumbai, 410210, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India., Shinde SH; Department of Radio-diagnosis, Tata Memorial Hospital, Parel, Mumbai, 400012, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India., Gawde J; Centre for Cancer Epidemiology, Advanced Centre for Treatment Research & Education in Cancer, Tata Memorial Centre, Kharghar, Navi Mumbai, 410210, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India., Munnolli S; Librarian and Officer In-Charge, Advanced Centre for Treatment Research & Education in Cancer, Tata Memorial Centre, Kharghar, Navi Mumbai, 410210, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India., Talole S; Biostatistician, Centre for Cancer Epidemiology, Advanced Centre for Treatment Research & Education in Cancer, Tata Memorial Centre, Kharghar, Navi Mumbai, 410210, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India., Goda JS; Department of Radiation Oncology, Advanced Centre for Treatment Research & Education in Cancer, Tata Memorial Centre, Kharghar, Navi Mumbai, 410210, India; Homi Bhabha National Institute, Anushakti Nagar, Trombay, 400094, India. Electronic address: godajayantsastri@gmail.com. |
| المصدر: | Clinical radiology [Clin Radiol] 2024 Jun; Vol. 79 (6), pp. 460-472. Date of Electronic Publication: 2024 Mar 19. |
| نوع المنشور: | Journal Article; Systematic Review; Meta-Analysis; Comparative Study |
| اللغة: | English |
| بيانات الدورية: | Publisher: Blackwell Scientific Publications Ltd Country of Publication: England NLM ID: 1306016 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1365-229X (Electronic) Linking ISSN: 00099260 NLM ISO Abbreviation: Clin Radiol Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: Oxford : Blackwell Scientific Publications Ltd Original Publication: Edinburgh, Livingstone. |
| مواضيع طبية MeSH: | Deep Learning* , Machine Learning* , Glioblastoma*/diagnostic imaging , Glioblastoma*/pathology , Lymphoma*/diagnostic imaging , Magnetic Resonance Imaging*/methods, Humans ; Diagnosis, Differential ; Brain Neoplasms/diagnostic imaging ; Brain Neoplasms/pathology ; Sensitivity and Specificity ; Radiologists ; Central Nervous System Neoplasms/diagnostic imaging ; Astrocytoma/diagnostic imaging |
| مستخلص: | Background: Several studies have been published comparing deep learning (DL)/machine learning (ML) to radiologists in differentiating PCNSLs from GBMs with equivocal results. We aimed to perform this meta-analysis to evaluate the diagnostic accuracy of ML/DL versus radiologists in classifying PCNSL versus GBM using MRI. Methodology: The study was performed in accordance with PRISMA guidelines. Data was extracted and interpreted by two researchers with 12 and 23 years' experience, respectively, and QUADAS-2 tool was used for quality and risk-bias assessment. We constructed contingency tables to derive sensitivity, specificity accuracy, summary receiver operating characteristic (SROC) curve, and the area under the curve (AUC). Results: Our search identified 11 studies, of which 8 satisfied our inclusion criteria and restricted the analysis in each study to reporting the model showing highest accuracy, with a total sample size of 1159 patients. The random effects model showed a pooled sensitivity of 0.89 [95% CI:0.84-0.92] for ML and 0.82 [95% CI:0.76-0.87] for radiologists. Pooled specificity was 0.88 [95% CI: 0.84-0.91] for ML and 0.90 [95% CI: 0.81-0.95] for radiologists. Pooled accuracy was 0.88 [95% CI: 0.86-0.90] for ML and 0.86 [95% CI: 0.78-0.91] for radiologists. Pooled AUC of ML was 0.94 [95% CI:0.92-0.96]and for radiologists, it was 0.90 [95% CI: 0.84-0.93]. Conclusions: MRI-based ML/DL techniques can complement radiologists to improve the accuracy of classifying GBMs from PCNSL, possibly reduce the need for a biopsy, and avoid any unwanted neurosurgical resection of a PCNSL. (Copyright © 2024 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.) |
| تواريخ الأحداث: | Date Created: 20240413 Date Completed: 20240505 Latest Revision: 20240627 |
| رمز التحديث: | 20240628 |
| DOI: | 10.1016/j.crad.2024.03.007 |
| PMID: | 38614870 |
| قاعدة البيانات: | MEDLINE |
Full Text via ClinicalKey 
Full Text Finder | تدمد: | 1365-229X |
|---|---|
| DOI: | 10.1016/j.crad.2024.03.007 |