Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis.
Ontology highlight
ABSTRACT:
SUBMITTER: Sun W
PROVIDER: S-EPMC10209541 | biostudies-literature | 2023 Jun
REPOSITORIES: biostudies-literature
Publications
Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis.
Sun Wanyi W Song Cheng C Tang Chao C Pan Chenghao C Xue Peng P Fan Jinhu J Qiao Youlin Y
iScience 20230505 6
This study aims to evaluate deep learning (DL) performance in differentiating low- and high-grade glioma. Search online database for studies continuously published from 1st January 2015 until 16th August 2022. The random-effects model was used for synthesis, based on pooled sensitivity (SE), specificity (SP), and area under the curve (AUC). Heterogeneity was estimated using the Higgins inconsistency index (I<sup>2</sup>). 33 were ultimately included in the meta-analysis. The overall pooled SE an ...[more]
Similar Datasets
Project description:ObjectivesDifferent machine learning algorithms (MLAs) for automated segmentation of gliomas have been reported in the literature. Automated segmentation of different tumor characteristics can be of added value for the diagnostic work-up and treatment planning. The purpose of this study was to provide an overview and meta-analysis of different MLA methods.MethodsA systematic literature review and meta-analysis was performed on the eligible studies describing the segmentation of gliomas. Meta-analysis of the performance was conducted on the reported dice similarity coefficient (DSC) score of both the aggregated results as two subgroups (i.e., high-grade and low-grade gliomas). This study was registered in PROSPERO prior to initiation (CRD42020191033).ResultsAfter the literature search (n = 734), 42 studies were included in the systematic literature review. Ten studies were eligible for inclusion in the meta-analysis. Overall, the MLAs from the included studies showed an overall DSC score of 0.84 (95% CI: 0.82-0.86). In addition, a DSC score of 0.83 (95% CI: 0.80-0.87) and 0.82 (95% CI: 0.78-0.87) was observed for the automated glioma segmentation of the high-grade and low-grade gliomas, respectively. However, heterogeneity was considerably high between included studies, and publication bias was observed.ConclusionMLAs facilitating automated segmentation of gliomas show good accuracy, which is promising for future implementation in neuroradiology. However, before actual implementation, a few hurdles are yet to be overcome. It is crucial that quality guidelines are followed when reporting on MLAs, which includes validation on an external test set.Key points• MLAs from the included studies showed an overall DSC score of 0.84 (95% CI: 0.82-0.86), indicating a good performance. • MLA performance was comparable when comparing the segmentation results of the high-grade gliomas and the low-grade gliomas. • For future studies using MLAs, it is crucial that quality guidelines are followed when reporting on MLAs, which includes validation on an external test set.
| S-EPMC8589805 | biostudies-literature
Project description:BackgroundOptimum management of low-grade gliomas remains controversial, and widespread practice variation exists. This evidence-based meta-analysis evaluates the association of extent of resection, radiation, and chemotherapy with mortality and progression-free survival at 2, 5, and 10 years in patients with low-grade glioma.MethodsA quantitative systematic review was performed. Inclusion criteria included controlled trials of newly diagnosed low-grade (World Health Organization Grades I and II) gliomas in adults. Eligible studies were identified, assigned a level of evidence for every endpoint considered, and analyzed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The relative risk of mortality and of progression at 2, 5, and 10 years was calculated for patients undergoing resection (gross total, subtotal, or biopsy), radiation, or chemotherapy.ResultsGross total resection was significantly associated with decreased mortality and likelihood of progression at all time points compared to subtotal resection. Early radiation was not associated with decreased mortality; however, progression-free survival was better at 5 years compared to patients receiving delayed or no radiation. Chemotherapy was associated with decreased mortality at 5 and 10 years in the high-quality literature. Progression-free survival was better at 5 and 10 years compared to patients who did not receive chemotherapy. In patients with isocitrate dehydrogenase 1 gene (IDH1) R132H mutations receiving chemotherapy, progression-free survival was better at 2 and 5 years than in patients with IDH1 wild-type gliomas.ConclusionsResults from this review, the first to quantify differences in outcome associated with surgery, radiation, and chemotherapy in patients with low-grade gliomas, can be used to inform evidence-based management and future clinical trials.
| S-EPMC6660818 | biostudies-literature
Project description:Determining the optimal course of treatment for low grade glioma (LGG) patients is challenging and frequently reliant on subjective judgment and limited scientific evidence. Our objective was to develop a comprehensive deep learning assisted radiomics model for assessing not only overall survival in LGG, but also the likelihood of future malignancy and glioma growth velocity. Thus, we retrospectively included 349 LGG patients to develop a prediction model using clinical, anatomical, and preoperative MRI data. Before performing radiomics analysis, a U2-model for glioma segmentation was utilized to prevent bias, yielding a mean whole tumor Dice score of 0.837. Overall survival and time to malignancy were estimated using Cox proportional hazard models. In a postoperative model, we derived a C-index of 0.82 (CI 0.79-0.86) for the training cohort over 10 years and 0.74 (Cl 0.64-0.84) for the test cohort. Preoperative models showed a C-index of 0.77 (Cl 0.73-0.82) for training and 0.67 (Cl 0.57-0.80) test sets. Our findings suggest that we can reliably predict the survival of a heterogeneous population of glioma patients in both preoperative and postoperative scenarios. Further, we demonstrate the utility of radiomics in predicting biological tumor activity, such as the time to malignancy and the LGG growth rate.
| S-EPMC10258197 | biostudies-literature
Project description:Deep learning-based radiomics (DLR) was developed to extract deep information from multiple modalities of magnetic resonance (MR) images. The performance of DLR for predicting the mutation status of isocitrate dehydrogenase 1 (IDH1) was validated in a dataset of 151 patients with low-grade glioma. A modified convolutional neural network (CNN) structure with 6 convolutional layers and a fully connected layer with 4096 neurons was used to segment tumors. Instead of calculating image features from segmented images, as typically performed for normal radiomics approaches, image features were obtained by normalizing the information of the last convolutional layers of the CNN. Fisher vector was used to encode the CNN features from image slices of different sizes. High-throughput features with dimensionality greater than 1.6*104 were obtained from the CNN. Paired t-tests and F-scores were used to select CNN features that were able to discriminate IDH1. With the same dataset, the area under the operating characteristic curve (AUC) of the normal radiomics method was 86% for IDH1 estimation, whereas for DLR the AUC was 92%. The AUC of IDH1 estimation was further improved to 95% using DLR based on multiple-modality MR images. DLR could be a powerful way to extract deep information from medical images.
| S-EPMC5511238 | biostudies-literature
Project description:We conducted a systematic review and meta-analysis of the diagnostic performance of current deep learning algorithms for the diagnosis of lung cancer. We searched major databases up to June 2022 to include studies that used artificial intelligence to diagnose lung cancer, using the histopathological analysis of true positive cases as a reference. The quality of the included studies was assessed independently by two authors based on the revised Quality Assessment of Diagnostic Accuracy Studies. Six studies were included in the analysis. The pooled sensitivity and specificity were 0.93 (95% CI 0.85-0.98) and 0.68 (95% CI 0.49-0.84), respectively. Despite the significantly high heterogeneity for sensitivity (I2 = 94%, p < 0.01) and specificity (I2 = 99%, p < 0.01), most of it was attributed to the threshold effect. The pooled SROC curve with a bivariate approach yielded an area under the curve (AUC) of 0.90 (95% CI 0.86 to 0.92). The DOR for the studies was 26.7 (95% CI 19.7-36.2) and heterogeneity was 3% (p = 0.40). In this systematic review and meta-analysis, we found that when using the summary point from the SROC, the pooled sensitivity and specificity of DL algorithms for the diagnosis of lung cancer were 93% and 68%, respectively.
| S-EPMC9405626 | biostudies-literature
Project description:Grading hydronephrosis severity relies on subjective interpretation of renal ultrasound images. Deep learning is a data-driven algorithmic approach to classifying data, including images, presenting a promising option for grading hydronephrosis. The current study explored the potential of deep convolutional neural networks (CNN), a type of deep learning algorithm, to grade hydronephrosis ultrasound images according to the 5-point Society for Fetal Urology (SFU) classification system, and discusses its potential applications in developing decision and teaching aids for clinical practice. We developed a five-layer CNN to grade 2,420 sagittal hydronephrosis ultrasound images [191 SFU 0 (8%), 407 SFU I (17%), 666 SFU II (28%), 833 SFU III (34%), and 323 SFU IV (13%)], from 673 patients ranging from 0 to 116.29 months old (M age = 16.53, SD = 17.80). Five-way (all grades) and two-way classification problems [i.e., II vs. III, and low (0-II) vs. high (III-IV)] were explored. The CNN classified 94% (95% CI, 93-95%) of the images correctly or within one grade of the provided label in the five-way classification problem. Fifty-one percent of these images (95% CI, 49-53%) were correctly predicted, with an average weighted F1 score of 0.49 (95% CI, 0.47-0.51). The CNN achieved an average accuracy of 78% (95% CI, 75-82%) with an average weighted F1 of 0.78 (95% CI, 0.74-0.82) when classifying low vs. high grades, and an average accuracy of 71% (95% CI, 68-74%) with an average weighted F1 score of 0.71 (95% CI, 0.68-0.75) when discriminating between grades II vs. III. Our model performs well above chance level, and classifies almost all images either correctly or within one grade of the provided label. We have demonstrated the applicability of a CNN approach to hydronephrosis ultrasound image classification. Further investigation into a deep learning-based clinical adjunct for hydronephrosis is warranted.
| S-EPMC7000524 | biostudies-literature
Project description:BackgroundLong-lasting efforts have been made to reduce radiation dose and thus the potential radiation risk to the patient for computed tomography (CT) acquisitions without severe deterioration of image quality. To this end, various techniques have been employed over the years including iterative reconstruction methods and noise reduction algorithms.PurposeRecently, deep learning-based methods for noise reduction became increasingly popular and a multitude of papers claim ever improving performance both quantitatively and qualitatively. However, the lack of a standardized benchmark setup and inconsistencies in experimental design across studies hinder the verifiability and reproducibility of reported results.MethodsIn this study, we propose a benchmark setup to overcome those flaws and improve reproducibility and verifiability of experimental results in the field. We perform a comprehensive and fair evaluation of several state-of-the-art methods using this standardized setup.ResultsOur evaluation reveals that most deep learning-based methods show statistically similar performance, and improvements over the past years have been marginal at best.ConclusionsThis study highlights the need for a more rigorous and fair evaluation of novel deep learning-based methods for low-dose CT image denoising. Our benchmark setup is a first and important step towards this direction and can be used by future researchers to evaluate their algorithms.
| S-EPMC11656299 | biostudies-literature
Project description:Ultrasonic vocalizations (USVs) analysis represents a fundamental tool to study animal communication. It can be used to perform a behavioral investigation of mice for ethological studies and in the field of neuroscience and neuropharmacology. The USVs are usually recorded with a microphone sensitive to ultrasound frequencies and then processed by specific software, which help the operator to identify and characterize different families of calls. Recently, many automated systems have been proposed for automatically performing both the detection and the classification of the USVs. Of course, the USV segmentation represents the crucial step for the general framework, since the quality of the call processing strictly depends on how accurately the call itself has been previously detected. In this paper, we investigate the performance of three supervised deep learning methods for automated USV segmentation: an Auto-Encoder Neural Network (AE), a U-NET Neural Network (UNET) and a Recurrent Neural Network (RNN). The proposed models receive as input the spectrogram associated with the recorded audio track and return as output the regions in which the USV calls have been detected. To evaluate the performance of the models, we have built a dataset by recording several audio tracks and manually segmenting the corresponding USV spectrograms generated with the Avisoft software, producing in this way the ground-truth (GT) used for training. All three proposed architectures demonstrated precision and recall scores exceeding [Formula: see text], with UNET and AE achieving values above [Formula: see text], surpassing other state-of-the-art methods that were considered for comparison in this study. Additionally, the evaluation was extended to an external dataset, where UNET once again exhibited the highest performance. We suggest that our experimental results may represent a valuable benchmark for future works.
| S-EPMC10336146 | biostudies-literature
Project description:Low-grade gliomas (LGGs) are optimally treated with up-front maximal safe surgical resection, typically defined as maximizing the extent of tumor resection while minimizing neurologic risks of surgery. Supratotal resection of LGG may improve outcomes beyond gross total resection by removing tumor cells invading beyond the tumor border as defined on MRI. However, the evidence regarding supratotal resection of LGG, in terms of impact on clinical outcomes, such as overall survival and neurologic morbidities, remains unclear. Authors independently searched the PubMed, Medline, Ovid, CENTRAL (Cochrane Central Register of Controlled Trials), and Google Scholar databases for studies evaluating overall survival, time to progression, seizure outcomes, and postoperative neurologic and medical complications of supratotal resection/FLAIRectomy of WHO-defined LGGs. Papers in languages other than English, lacking full-text availability, evaluating supratotal resection of WHO-defined high-grade gliomas only, and nonhuman studies were excluded. After literature search, reference screening, and initial exclusions, 65 studies were screened for relevancy, of which 23 were evaluated via full-text review, and 10 were ultimately included in the final evidence review. Studies were evaluated for quality using the MINORS criteria. After data extraction, a total of 1301 LGG patients were included in the analysis, with 377 (29.0%) undergoing supratotal resection. The main measured outcomes were extent of resection, pre- and postoperative neurological deficits, seizure control, adjuvant treatment, neuropsychological outcomes, ability to return to work, progression-free survival, and overall survival. Overall, low- to moderate-quality evidence was supportive of aggressive, functional boundary-based resection of LGGs due to improvements in progression-free survival and seizure control. The published literature provides a moderate amount of low-quality evidence supporting supratotal surgical resection along functional boundaries for low-grade glioma. Among patients included in this analysis, the occurrence of postoperative neurological deficits was low, and nearly all patients recovered within 3 to 6 months after surgery. Notably, the surgical centers represented in this analysis have significant experience in glioma surgery in general, and supratotal resection specifically. In this setting, supratotal surgical resection along functional boundaries appears to be appropriate for both symptomatic and asymptomatic low-grade glioma patients. Larger clinical studies are needed to better define the role of supratotal resection in LGG.
| S-EPMC10177219 | biostudies-literature
Project description:BackgroundSurgical resection offers survival benefits in patients with diffuse low-grade glioma (DLGG) but its association with functional outcomes is uncertain. This systematic review assessed functional outcomes associated with extent of resection (EoR) in adults with DLGG.MethodsWe searched Medline, Embase and CENTRAL on the 19th of February 2021 for observational studies reporting functional outcomes after surgical resection for patients aged ≥ 18 years with a new diagnosis of supratentorial DLGG according to any World Health Organization classification of primary brain tumors. The Newcastle-Ottawa Scale (NOS) informed our risk of bias assessments. The proportion of patients returning to work within 12 months entered a random-effects meta-analysis. PROSPERO registration number CRD42021238387.ResultsThere were seven eligible moderate to high-quality (NOS > 6) observational studies identified from 1,183 records involving 234 patients with DLGG. Functional outcomes reported included neurocognition (n = 2 studies), performance status (n = 3), quality of life (QoL) (n = 1) and return to work (n = 6). The proportion of patients who returned to work within 12 months of surgery was 84% (95% confidence interval [CI] 50-96%, I-squared = 38%, 5 studies) for gross total resection, 66% (95% CI 14-96%, I2 = 57%, 5 studies) for subtotal resection, and 31% (95% CI 4-82%, I2 = 0%, 4 studies) for partial resection. There was insufficient data on other functional outcomes for quantitative synthesis.ConclusionA higher proportion of DLGG patients returned to work following gross total resection compared with those who had a subtotal or partial resection. Further studies with standardized assessments can clarify the association between EoR and different functional outcomes.
| S-EPMC9758089 | biostudies-literature