Application of Apparent Diffusion Coefficient Histogram Metrics for Differentiation of Pediatric Posterior Fossa Tumors : A Large Retrospective Study and Brief Review of Literature

A Combination of Amide Proton Transfer, Tumor Blood Flow, and Apparent Diffusion Coefficient Histogram Analysis Is Useful for Differentiating Malignant from Benign Intracranial Tumors in Young Patients: A Preliminary Study

PURPOSE

To evaluate the amide proton transfer (APT), tumor blood flow (TBF), and apparent diffusion coefficient (ADC) combined diagnostic value for differentiating intracranial malignant tumors (MTs) from benign tumors (BTs) in young patients, as defined by the 2021 World Health Organization classification of central nervous system tumors.

METHODS

Fifteen patients with intracranial MTs and 10 patients with BTs aged 0-30 years underwent MRI with APT, pseudocontinuous arterial spin labeling (pCASL), and diffusion-weighted imaging. All tumors were evaluated through the use of histogram analysis and the Mann-Whitney U test to compare 10 parameters for each sequence between the groups. The diagnostic performance was evaluated using receiver operating characteristic (ROC) curve analysis.

RESULTS

The APT maximum, mean, 10th, 25th, 50th, 75th, and 90th percentiles were significantly higher in MTs than in BTs; the TBF minimum (min) was significantly lower in MTs than in BTs; TBF kurtosis was significantly higher in MTs than in BTs; the ADC min, 10th, and 25th percentiles were significantly lower in MTs than in BTs (all p < 0.05). The APT 50th percentile (0.900), TBF min (0.813), and ADC min (0.900) had the highest area under the curve (AUC) values of the parameters in each sequence. The AUC for the combination of these three parameters was 0.933.

CONCLUSIONS

The combination of APT, TBF, and ADC evaluated through histogram analysis may be useful for differentiating intracranial MTs from BTs in young patients.

Cluster-based prognostication in glioblastoma: Unveiling heterogeneity based on diffusion and perfusion similarities

BACKGROUND

While the association between diffusion and perfusion magnetic resonance imaging (MRI) and survival in glioblastoma is established, prognostic models for patients are lacking. This study employed clustering of functional imaging to identify distinct functional phenotypes in untreated glioblastomas, assessing their prognostic significance for overall survival.

METHODS

A total of 289 patients with glioblastoma who underwent preoperative multimodal MR imaging were included. Mean values of apparent diffusion coefficient normalized relative cerebral blood volume and relative cerebral blood flow were calculated for different tumor compartments and the entire tumor. Distinct imaging patterns were identified using partition around medoids (PAM) clustering on the training dataset, and their ability to predict overall survival was assessed. Additionally, tree-based machine-learning models were trained to ascertain the significance of features pertaining to cluster membership.

RESULTS

Using the training dataset (231/289) we identified 2 stable imaging phenotypes through PAM clustering with significantly different overall survival (OS). Validation in an independent test set revealed a high-risk group with a median OS of 10.2 months and a low-risk group with a median OS of 26.6 months (P = 0.012). Patients in the low-risk cluster had high diffusion and low perfusion values throughout, while the high-risk cluster displayed the reverse pattern. Including cluster membership in all multivariate Cox regression analyses improved performance (P ≤ 0.004 each).

CONCLUSIONS

Our research demonstrates that data-driven clustering can identify clinically relevant, distinct imaging phenotypes, highlighting the potential role of diffusion, and perfusion MRI in predicting survival rates of glioblastoma patients.

Preoperative CT histogram analysis to predict the expression of Ki-67 in solid pseudopapillary tumours of the pancreas

AIM

To explore the value of preoperative computed tomography (CT) histogram features in predicting the expression status of Ki-67 in patients with solid pseudopapillary pancreatic tumours (SPTP).

MATERIALS AND METHODS

This retrospective study analysed venous phase CT images of 39 patients with SPTP confirmed at surgery and histopathology and measured using the Ki-67 proliferation index from November 2015 to February 2022. According to the Ki-67 proliferation index, they were divided into high expression (Ki-67 ≥ 4%) and low expression (Ki-67 < 4%) groups. The histogram features of quantitative parameters were extracted using MaZda software, and the quantitative parameters of CT histograms were compared between groups. The receiver operating characteristic (ROC) curves of the patients were plotted according to the parameters, with statistically significant differences. The area under the curve (AUC), sensitivity, and specificity were calculated, and the effectiveness of the histogram parameters in predicting Ki-67 expression was analysed and evaluated.

RESULTS

In total, 27 SPTP patients were enrolled, including 11 with high expression of Ki-67 and 16 with low expression. Comparative analysis of the Ki-67 high- and low-expression groups revealed a statistically significant in necrosis and variance (p<0.05). ROC curve analysis showed that the AUC of necrosis and variance predicting Ki-67 expression status were 0.753 and 0.841, the sensitivities were 81.8% and 81.3%, and the specificities were 68.7% and 81.8%, respectively.

CONCLUSION

Preoperative CT histogram features help predict Ki-67 expression status in patients with SPTP.

Advancing noninvasive glioma classification with diffusion radiomics: Exploring the impact of signal intensity normalization

Background

This study investigates the influence of diffusion-weighted Magnetic Resonance Imaging (DWI-MRI) on radiomic-based prediction of glioma types according to molecular status and assesses the impact of DWI intensity normalization on model generalizability.

Methods

Radiomic features, compliant with image biomarker standardization initiative standards, were extracted from preoperative MRI of 549 patients with diffuse glioma, known IDH, and 1p19q-status. Anatomical sequences (T1, T1c, T2, FLAIR) underwent N4-Bias Field Correction (N4) and WhiteStripe normalization (N4/WS). Apparent diffusion coefficient (ADC) maps were normalized using N4 or N4/z-score. Nine machine-learning algorithms were trained for multiclass prediction of glioma types (IDH-mutant 1p/19q codeleted, IDH-mutant 1p/19q non-codeleted, IDH-wild type). Four approaches were compared: Anatomical, anatomical + ADC naive, anatomical + ADC N4, and anatomical + ADC N4/z-score. The University of California San Francisco (UCSF)-glioma dataset (n = 409) was used for external validation.

Results

Naïve-Bayes algorithms yielded overall the best performance on the internal test set. Adding ADC radiomics significantly improved AUC from 0.79 to 0.86 (P = .011) for the IDH-wild-type subgroup, but not for the other 2 glioma subgroups (P > .05). In the external UCSF dataset, the addition of ADC radiomics yielded a significantly higher AUC for the IDH-wild-type subgroup (P ≤ .001): 0.80 (N4/WS anatomical alone), 0.81 (anatomical + ADC naive), 0.81 (anatomical + ADC N4), and 0.88 (anatomical + ADC N4/z-score) as well as for the IDH-mutant 1p/19q non-codeleted subgroup (P < .012 each).

Conclusions

ADC radiomics can enhance the performance of conventional MRI-based radiomic models, particularly for IDH-wild-type glioma. The benefit of intensity normalization of ADC maps depends on the type and context of the used data.

Deciphering Machine Learning Decisions to Distinguish between Posterior Fossa Tumor Types Using MRI Features: What Do the Data Tell Us?

Machine learning (ML) models have become capable of making critical decisions on our behalf. Nevertheless, due to complexity of these models, interpreting their decisions can be challenging, and humans cannot always control them. This paper provides explanations of decisions made by ML models in diagnosing four types of posterior fossa tumors: medulloblastoma, ependymoma, pilocytic astrocytoma, and brainstem glioma. The proposed methodology involves data analysis using kernel density estimations with Gaussian distributions to examine individual MRI features, conducting an analysis on the relationships between these features, and performing a comprehensive analysis of ML model behavior. This approach offers a simple yet informative and reliable means of identifying and validating distinguishable MRI features for the diagnosis of pediatric brain tumors. By presenting a comprehensive analysis of the responses of the four pediatric tumor types to each other and to ML models in a single source, this study aims to bridge the knowledge gap in the existing literature concerning the relationship between ML and medical outcomes. The results highlight that employing a simplistic approach in the absence of very large datasets leads to significantly more pronounced and explainable outcomes, as expected. Additionally, the study also demonstrates that the pre-analysis results consistently align with the outputs of the ML models and the clinical findings reported in the existing literature.

The Diagnostic Efficiency of Quantitative Diffusion Weighted Imaging in Differentiating Medulloblastoma from Posterior Fossa Tumors: A Systematic Review and Meta-Analysis

Medulloblastoma (MB) is considered the most common and highly malignant posterior fossa tumor (PFT) in children. The accurate preoperative diagnosis of MB is beneficial in choosing the appropriate surgical methods and treatment strategies. Diffusion-weighted imaging (DWI) has improved the accuracy of differential diagnosis of posterior fossa tumors. Nonetheless, further studies are needed to confirm its value for clinical application. This study aimed to evaluate the performance of DWI in differentiating MB from other PFT. A literature search was conducted using databases PubMed, Embase, and Web of Science for studies reporting the diagnostic performance of DWI for PFT from January 2000 to January 2022. A bivariate random-effects model was employed to evaluate the pooled sensitivities and specificities. A univariable meta-regression analysis was used to assess relevant factors for heterogeneity, and subgroup analyses were performed. A total of 15 studies with 823 patients were eligible for data extraction. Overall pooled sensitivity and specificity of DWI were 0.94 (95% confident interval [CI]: 0.89-0.97) and 0.94 (95% CI: 0.90-0.96) respectively. The area under the curve (AUC) of DWI was 0.98 (95% CI: 0.96-0.99). Heterogeneity was found in the sensitivity (I² = 62.59%) and the specificity (I² = 35.94%). Magnetic field intensity, region of interest definition and DWI diagnostic parameters are the factors that affect the diagnostic performance of DWI. DWI has excellent diagnostic accuracy for differentiating MB from other PFT. Hence, it is necessary to set DWI as a routine examination sequence for posterior fossa tumors.