The Current Diagnostic Performance of MRI-Based Radiomics for Glioma Grading: A Meta-Analysis.

BACKGROUND: Multiple radiomics models have been proposed for grading glioma using different algorithms, features, and sequences of magnetic resonance imaging. The research seeks to assess the present overall performance of radiomics for grading glioma. METHODS: A systematic literature review of the databases Ovid MEDLINE PubMed, and Ovid EMBASE for publications published on radiomics for glioma grading between 2012 and 2023 was performed. The systematic review was carried out following the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analysis. RESULTS: In the meta-analysis, a total of 7654 patients from 40 articles, were assessed. R-package mada was used for modeling the joint estimates of specificity (SPE) and sensitivity (SEN). Pooled event rates across studies were performed with a random-effects meta-analysis. The heterogeneity of SPE and SEN were based on the χ2 test. Overall values for SPE and SEN in the differentiation between high-grade gliomas (HGGs) and low-grade gliomas (LGGs) were 84% and 91%, respectively. With regards to the discrimination between World Health Organization (WHO) grade 4 and WHO grade 3, the overall SPE was 81% and the SEN was 89%. The modern non-linear classifiers showed a better trend, whereas textural features tend to be the best-performing (29%) and the most used. CONCLUSIONS: Our findings confirm that present radiomics' diagnostic performance for glioma grading is superior in terms of SEN and SPE for the HGGs vs. LGGs discrimination task when compared to the WHO grade 4 vs. 3 task.

Radiomics for differentiation of gliomas from primary central nervous system lymphomas: a systematic review and meta-analysis.

Background and objective: Numerous radiomics-based models have been proposed to discriminate between central nervous system (CNS) gliomas and primary central nervous system lymphomas (PCNSLs). Given the heterogeneity of the existing models, we aimed to define their overall performance and identify the most critical variables to pilot future algorithms. Methods: A systematic review of the literature and a meta-analysis were conducted, encompassing 12 studies and a total of 1779 patients, focusing on radiomics to differentiate gliomas from PCNSLs. A comprehensive literature search was performed through PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus databases. Overall sensitivity (SEN) and specificity (SPE) were estimated. Event rates were pooled using a random-effects meta-analysis, and the heterogeneity was assessed using the χ2 test. Results: The overall SEN and SPE for differentiation between CNS gliomas and PCNSLs were 88% (95% CI = 0.83 - 0.91) and 87% (95% CI = 0.83 - 0.91), respectively. The best-performing features were the ones extracted from the Gray Level Run Length Matrix (GLRLM; ACC 97%), followed by those obtained from the Neighboring Gray Tone Difference Matrix (NGTDM; ACC 93%), and shape-based features (ACC 91%). The 18F-FDG-PET/CT was the best-performing imaging modality (ACC 97%), followed by the MRI CE-T1W (ACC 87% - 95%). Most studies applied a cross-validation analysis (92%). Conclusion: The current SEN and SPE of radiomics to discriminate CNS gliomas from PCNSLs are high, making radiomics a helpful method to differentiate these tumor types. The best-performing features are the GLRLM, NGTDM, and shape-based features. The 18F-FDG-PET/CT imaging modality is the best-performing, while the MRI CE-T1W is the most used.

Radiomics for Differentiation of Pediatric Posterior Fossa Tumors: A Meta-Analysis and Systematic Review of the Literature.

PURPOSE: To better define the overall performance of the current radiomics-based models for the discrimination of pediatric posterior fossa tumors. METHODS: A comprehensive literature search of the databases PubMed, Ovid MEDLINE, Ovid EMBASE, Web of Science, and Scopus was designed and conducted by an experienced librarian. We estimated overall sensitivity (SEN) and specificity (SPE). Event rates were pooled across studies using a random-effects meta-analysis, and the χ2 test was performed to assess the heterogeneity. RESULTS: Overall SEN and SPE for differentiation between MB, PA, and EP were found to be promising, with SEN values of 93% (95% CI = 0.88-0.96), 83% (95% CI = 0.66-0.93), and 85% (95% CI = 0.71-0.93), and corresponding SPE values of 87% (95% CI = 0.82-0.90), 95% (95% CI = 0.90-0.98) and 90% (95% CI = 0.84-0.94), respectively. For MB, there is a better trend for LR classifiers, while textural features are the most used and the best performing (ACC 96%). As for PA and EP, a synergistic employment of LR and NN classifiers, accompanied by geometrical or morphological features, demonstrated superior performance (ACC 94% and 96%, respectively). CONCLUSIONS: The diagnostic performance is high, making radiomics a helpful method to discriminate these tumor types. In the forthcoming years, we expect even more precise models.

Cigarette Smoking and Intracranial Aneurysms: A Pilot Analysis of SNPs in the CYP2A6 Gene in the Italian Population.

BACKGROUND: Cigarette smoking is a modifiable risk factor associated with formation and rupture of intracranial aneurysms (IAs). Cytochrome P450 2A6 (CYP2A6) is the main enzyme implied in catabolism of nicotine and xenobiotics, giving rise to oxidative stress products. Our study investigated the associations between specific single-nucleotide polymorphisms (SNPs) in the CYP2A6 gene and the presence of sporadic IAs in a cluster of Italian patients, as well as their rupture regarding cigarette smoking habit. METHODS: Three hundred and thirty-one Italian patients with sporadic IAs were recruited in a single institution. We recorded data on clinical onset with subarachnoid hemorrhage (SAH) and smoking habit. Genetic analysis was performed with a standard procedure on peripheral blood samples: CYP2A6 ∗1B2, CYP2A6 ∗2, and CYP2A6 ∗14 SNPs were analyzed in the study group along with 150 healthy control subjects. Statistical analysis was conducted according to genetic association study guidelines. RESULTS: In the patient cohort, the frequency of aSAH was significantly higher in current smokers (P < 0.001; OR=17.45), regardless of the pattern of CYP2A6 SNPs. There was a correlation between IA rupture and cigarette smoking in patients with the heterozygous CYP2A6 ∗1B2 allele (P < 0.001; OR=15.47). All patients carrying the heterozygous CYP2A6 ∗14 allele had an aSAH event (100%), regardless of smoking habit, although this correlation was not statistically significant (P = 1). CONCLUSIONS: According to our findings, a cigarette smoker carrying a fully active CYP2A6 enzyme (heterozygous ∗1B2 allele) may have an increased risk of IA rupture compared to those with functionally less active variants: further investigation on a larger sample is needed to verify this result. The role of the heterozygous CYP2A6 ∗14 allele in aSAH is yet to be clarified.

Improving CNNs classification with pathologist-based expertise: the renal cell carcinoma case study.

The prognosis of renal cell carcinoma (RCC) malignant neoplasms deeply relies on an accurate determination of the histological subtype, which currently involves the light microscopy visual analysis of histological slides, considering notably tumor architecture and cytology. RCC subtyping is therefore a time-consuming and tedious process, sometimes requiring expert review, with great impact on diagnosis, prognosis and treatment of RCC neoplasms. In this study, we investigate the automatic RCC subtyping classification of 91 patients, diagnosed with clear cell RCC, papillary RCC, chromophobe RCC, or renal oncocytoma, through deep learning based methodologies. We show how the classification performance of several state-of-the-art Convolutional Neural Networks (CNNs) are perfectible among the different RCC subtypes. Thus, we introduce a new classification model leveraging a combination of supervised deep learning models (specifically CNNs) and pathologist's expertise, giving birth to a hybrid approach that we termed ExpertDeepTree (ExpertDT). Our findings prove ExpertDT's superior capability in the RCC subtyping task, with respect to traditional CNNs, and suggest that introducing some expert-based knowledge into deep learning models may be a valuable solution for complex classification cases.

Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations.

MOTIVATION: Computer-aided analysis of biological images typically requires extensive training on large-scale annotated datasets, which is not viable in many situations. In this paper, we present Generative Adversarial Network Discriminator Learner (GAN-DL), a novel self-supervised learning paradigm based on the StyleGAN2 architecture, which we employ for self-supervised image representation learning in the case of fluorescent biological images. RESULTS: We show that Wasserstein Generative Adversarial Networks enable high-throughput compound screening based on raw images. We demonstrate this by classifying active and inactive compounds tested for the inhibition of SARS-CoV-2 infection in two different cell models: the primary human renal cortical epithelial cells (HRCE) and the African green monkey kidney epithelial cells (VERO). In contrast to previous methods, our deep learning-based approach does not require any annotation, and can also be used to solve subtle tasks it was not specifically trained on, in a self-supervised manner. For example, it can effectively derive a dose-response curve for the tested treatments. AVAILABILITY AND IMPLEMENTATION: Our code and embeddings are available at https://gitlab.com/AlesioRFM/gan-dl StyleGAN2 is available at https://github.com/NVlabs/stylegan2 .