Normalization of ADC does not improve correlation with overall survival in patients with high-grade glioma (HGG)

Integrated MRI radiomics, tumor microenvironment, and clinical risk factors for improving survival prediction in patients with glioblastomas

PURPOSE

To construct a comprehensive model for predicting the prognosis of patients with glioblastoma (GB) using a radiomics method and integrating clinical risk factors, tumor microenvironment (TME), and imaging characteristics.

MATERIALS AND METHODS

In this retrospective study, we included 148 patients (85 males and 63 females; median age 53 years) with isocitrate dehydrogenase-wildtype GB between January 2016 and April 2022. Patients were randomly divided into the training (n = 104) and test (n = 44) sets. The best feature combination related to GB overall survival (OS) was selected using LASSO Cox regression analyses. Clinical, radiomics, clinical-radiomics, clinical-TME, and clinical-radiomics-TME models were established. The models' concordance index (C-index) was evaluated. The survival curve was drawn using the Kaplan-Meier method, and the prognostic stratification ability of the model was tested.

RESULTS

LASSO Cox analyses were used to screen the factors related to OS in patients with GB, including MGMT (hazard ratio [HR] = 0.642; 95% CI 0.414-0.997; P = 0.046), TERT (HR = 1.755; 95% CI 1.095-2.813; P = 0.019), peritumoral edema (HR = 1.013; 95% CI 0.999-1.027; P = 0.049), tumor purity (TP; HR = 0.982; 95% CI 0.964-1.000; P = 0.054), CD163 + tumor-associated macrophages (TAMs; HR = 1.049; 95% CI 1.021-1.078; P < 0.001), CD68 + TAMs (HR = 1.055; 95% CI 1.018-1.093; P = 0.004), and the six radiomics features. The clinical-radiomics-TME model had the best survival prediction ability, the C‑index was 0.768 (0.717-0.819). The AUC of 1‑, 2‑, and 3‑year OS prediction in the test set was 0.842, 0.844, and 0.795, respectively.

CONCLUSION

The clinical-radiomics-TME model is the most effective for predicting the survival of patients with GB. Radiomics features, TP, and TAMs play important roles in the prognostic model.

A multi-reader comparison of normal-appearing white matter normalization techniques for perfusion and diffusion MRI in brain tumors

PURPOSE

There remains no consensus normal-appearing white matter (NAWM) normalization method to compute normalized relative cerebral blood volume (nrCBV) and apparent diffusion coefficient (nADC) in brain tumors. This reader study explored nrCBV and nADC differences using different NAWM normalization methods.

METHODS

Thirty-five newly diagnosed glioma patients were studied. For each patient, two readers created four NAWM regions of interests: (1) a single plane in the centrum semiovale (CSOp), (2) 3 spheres in the centrum semiovale (CSOs), (3) a single plane in the slice of the tumor center (TUMp), and (4) 3 spheres in the slice of the tumor center (TUMs). Readers repeated NAWM segmentations 1 month later. Differences in nrCBV and nADC of the FLAIR hyperintense tumor, inter-/intra-reader variability, and time to segment NAWM were assessed. As a validation step, the diagnostic performance of each method for IDH-status prediction was evaluated.

RESULTS

Both readers obtained significantly different nrCBV (P < .001), nADC (P < .001), and time to segment NAWM (P < .001) between the four normalization methods. nrCBV and nADC were significantly different between CSO and TUM methods, but not between planar and spherical methods in the same NAWM region. Broadly, CSO methods were quicker than TUM methods, and spherical methods were quicker than planar methods. For all normalization techniques, inter-reader reproducibility and intra-reader repeatability were excellent (intraclass correlation coefficient > 0.9), and the IDH-status predictive performance remained similar.

CONCLUSION

The selected NAWM region significantly impacts nrCBV and nADC values. CSO methods, particularly CSOs, may be preferred because of time reduction, similar reader variability, and similar diagnostic performance compared to TUM methods.

Peritumoral ADC Values Correlate with the MGMT Methylation Status in Patients with Glioblastoma

Different results have been reported concerning the relationship of the apparent diffusion coefficient (ADC) values and the status of methylation as the promoter gene for the enzyme methylguanine-DNA methyltransferase (MGMT) in patients with glioblastomas (GBs). The aim of this study was to investigate if there were correlations between the ADC values of the enhancing tumor and peritumoral areas of GBs and the MGMT methylation status. In this retrospective study, we included 42 patients with newly diagnosed unilocular GB with one MRI study prior to any treatment and histopathological data. After co-registration of ADC maps with T1-weighted sequences after contrast administration and dynamic susceptibility contrast (DSC) perfusion, we manually selected one region-of-interest (ROI) in the enhancing and perfused tumor and one ROI in the peritumoral white matter. Both ROIs were mirrored in the healthy hemisphere for normalization. In the peritumoral white matter, absolute and normalized ADC values were significantly higher in patients with MGMT-unmethylated tumors, as compared to patients with MGMT-methylated tumors (absolute values p = 0.002, normalized p = 0.0007). There were no significant differences in the enhancing tumor parts. The ADC values in the peritumoral region correlated with MGMT methylation status, confirmed by normalized ADC values. In contrast to other studies, we could not find a correlation between the ADC values or the normalized ADC values and the MGMT methylation status in the enhancing tumor parts.

Nomogram for predicting early recurrence in patients with high-grade gliomas

OBJECTIVE

To develop a nomogram to predict early recurrence of high-grade glioma (HGG) based on clinical pathology, genetic factors and MRI parameters.

METHODS

154 patients with HGG were classified into recurrence and non-recurrence groups based on the pathological diagnosis and RANO criteria. Clinical pathology information included age, sex, preoperative Karnofsky performance status (KPS) scores,grade, and cell proliferation index (Ki-67). Gene information included P53, IDH1, MGMT, and TERT expression status. All patients underwent baseline MRIs before treatment, including T1WI, T2WI, T1C, Flair, and DWI examinations. Tumor location, single/multiple tumors, tumor diameter, peritumoral edema, necrotic cyst, hemorrhage, average apparent diffusion coefficient(ADC) value, and minimum ADC values were evaluated. Univariate and multivariate logistic regression analyses were used to determine the predictors of early recurrence and build nomogram.

RESULTS

Univariate analysis showed that the number of tumors (OR, 0.258; 95% CI: 0.104, 0.639; P = 0.003) and peritumoral edema (OR, 0.965; 95% CI 0.942, 0.988; P = 0.003; mean in the recurrence group 22.04±17.21 mm; mean in the non-recurrence group 14.22±12.84 mm) were statistically significantly different in patients with early recurrence. Genetic factors associated with early recurrence included IDH1 (OR, 4.405; 95% CI 1.874, 10.353; P= 0.001), and MGMT (OR, 2.389; 95% CI 1.234, 4.628; P= 0.010). Multivariate logistic regression analysis revealed that the number of tumors (OR, 0.227; 95% CI 0.084, 0.616; P = 0.004), peritumoral edema (OR, 0.969; 95% CI 0.945, 0.993; P = 0.013), and IDH1 (OR, 4.200; 95% CI 1.602, 10.013; P= 0.004) were independent risk factors for early recurrence. The nomogram showed the highest net benefit when the threshold probability was less than 60%.

CONCLUSION

A nomogram prediction model can effectively aid in clinical treatment decisions for patients with newly diagnosed HGG .

MRI-based radiomics to predict response in locally advanced rectal cancer: comparison of manual and automatic segmentation on external validation in a multicentre study

Background

Pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer (LARC) is achieved in 15–30% of cases. Our aim was to implement and externally validate a magnetic resonance imaging (MRI)-based radiomics pipeline to predict response to treatment and to investigate the impact of manual and automatic segmentations on the radiomics models.

Methods

Ninety-five patients with stage II/III LARC who underwent multiparametric MRI before chemoradiotherapy and surgical treatment were enrolled from three institutions. Patients were classified as responders if tumour regression grade was 1 or 2 and nonresponders otherwise. Sixty-seven patients composed the construction dataset, while 28 the external validation. Tumour volumes were manually and automatically segmented using a U-net algorithm. Three approaches for feature selection were tested and combined with four machine learning classifiers.

Results

Using manual segmentation, the best result reached an accuracy of 68% on the validation set, with sensitivity 60%, specificity 77%, negative predictive value (NPV) 63%, and positive predictive value (PPV) 75%. The automatic segmentation achieved an accuracy of 75% on the validation set, with sensitivity 80%, specificity 69%, and both NPV and PPV 75%. Sensitivity and NPV on the validation set were significantly higher (p = 0.047) for the automatic versus manual segmentation.

Conclusion

Our study showed that radiomics models can pave the way to help clinicians in the prediction of tumour response to chemoradiotherapy of LARC and to personalise per-patient treatment. The results from the external validation dataset are promising for further research into radiomics approaches using both manual and automatic segmentations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41747-022-00272-2.

Prediction of Glioma Grade Using Intratumoral and Peritumoral Radiomic Features From Multiparametric MRI Images

The accurate prediction of glioma grade before surgery is essential for treatment planning and prognosis. Since the gold standard (i.e., biopsy)for grading gliomas is both highly invasive and expensive, and there is a need for a noninvasive and accurate method. In this study, we proposed a novel radiomics-based pipeline by incorporating the intratumoral and peritumoral features extracted from preoperative mpMRI scans to accurately and noninvasively predict glioma grade. To address the unclear peritumoral boundary, we designed an algorithm to capture the peritumoral region with a specified radius. The mpMRI scans of 285 patients derived from a multi-institutional study were adopted. A total of 2153 radiomic features were calculated separately from intratumoral volumes (ITVs)and peritumoral volumes (PTVs)on mpMRI scans, and then refined using LASSO and mRMR feature ranking methods. The top-ranking radiomic features were entered into the classifiers to build radiomic signatures for predicting glioma grade. The prediction performance was evaluated with five-fold cross-validation on a patient-level split. The radiomic signatures utilizing the features of ITV and PTV both show a high accuracy in predicting glioma grade, with AUCs reaching 0.968. By incorporating the features of ITV and PTV, the AUC of IPTV radiomic signature can be increased to 0.975, which outperforms the state-of-the-art methods. Additionally, our proposed method was further demonstrated to have strong generalization performance in an external validation dataset with 65 patients. The source code of our implementation is made publicly available at https://github.com/chengjianhong/glioma_grading.git.

Treatment Response and Prognosis Evaluation in High-Grade Glioma: An Imaging Review Based on MRI

In recent years, the development of advanced magnetic resonance imaging (MRI) technology and machine learning (ML) have created new tools for evaluating treatment response and prognosis of patients with high-grade gliomas (HGG); however, patient prognosis has not improved significantly. This is mainly due to the heterogeneity between and within HGG tumors, resulting in standard treatment methods not benefitting all patients. Moreover, the survival of patients with HGG is not only related to tumor cells, but also to noncancer cells in the tumor microenvironment (TME). Therefore, during preoperative diagnosis and follow-up treatment of patients with HGG, noninvasive imaging markers are needed to characterize intratumoral heterogeneity, and then to evaluate treatment response and predict prognosis, timeously adjust treatment strategies, and achieve individualized diagnosis and treatment. In this review, we summarize the research progress of conventional MRI, advanced MRI technology, and ML in evaluation of treatment response and prognosis of patients with HGG. We further discuss the significance of the TME in the prognosis of HGG patients, associate imaging features with the TME, indirectly reflecting the heterogeneity within the tumor, and shifting treatment strategies from tumor cells alone to systemic therapy of the TME, which may be a major development direction in the future. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY STAGE: 4.

Diffusion MRI is an early biomarker of overall survival benefit in IDH wild-type recurrent glioblastoma treated with immune checkpoint inhibitors

BACKGROUND

Diffusion MRI estimates of the apparent diffusion coefficient (ADC) have been shown to be useful in predicting treatment response in patients with glioblastoma (GBM), with ADC elevations indicating tumor cell death. We aimed to investigate whether the ADC values measured before and after treatment with immune checkpoint inhibitors (ICIs) and the changes in these ADC values could predict overall survival (OS) in patients with recurrent IDH wild-type GBM.

METHODS

Forty-four patients who met the following inclusion criteria were included in this retrospective study: (i) diagnosed with recurrent IDH wild-type GBM and treated with either pembrolizumab or nivolumab and (ii) availability of diffusion data on pre- and post-ICI MRI. Tumor volume and the median relative ADC (rADC) with respect to the normal-appearing white matter within the enhancing tumor were calculated.

RESULTS

Median OS among all patients was 8.1 months (range, 1.0-22.5 months). Log-rank test revealed that higher post-treatment rADC was associated with a significantly longer OS (median, 10.3 months for rADC ≧ 1.63 versus 6.1 months for rADC < 1.63; P = 0.02), whereas tumor volume, pre-treatment rADC, and changes in rADC after treatment were not significantly associated with OS. Cox regression analysis revealed that post-treatment rADC significantly influenced OS (P = 0.02, univariate analysis), even after controlling for age and sex (P =0.01, multivariate analysis), and additionally controlling for surgery after ICI treatment (P = 0.045, multivariate analysis).

CONCLUSIONS

Elevated post-treatment rADC may be an early imaging biomarker for OS benefits in GBM patients receiving ICI treatment.

Multimodal Disentangled Variational Autoencoder with Game Theoretic Interpretability for Glioma grading

Effective fusion of multimodal magnetic resonance imaging (MRI) is of great significance to boost the accuracy of glioma grading thanks to the complementary information provided by different imaging modalities. However, how to extract the common and distinctive information from MRI to achieve complementarity is still an open problem in information fusion research. In this study, we propose a deep neural network model termed as multimodal disentangled variational autoencoder (MMD-VAE) for glioma grading based on radiomics features extracted from preoperative multimodal MRI images. Specifically, the radiomics features are quantized and extracted from the region of interest for each modality. Then, the latent representations of variational autoencoder for these features are disentangled into common and distinctive representations to obtain the shared and complementary data among modalities. Afterward, cross-modality reconstruction loss and common-distinctive loss are designed to ensure the effectiveness of the disentangled representations. Finally, the disentangled common and distinctive representations are fused to predict the glioma grades, and SHapley Additive exPlanations (SHAP) is adopted to quantitatively interpret and analyze the contribution of the important features to grading. Experimental results on two benchmark datasets demonstrate that the proposed MMD-VAE model achieves encouraging predictive performance (AUC:0.9939) on a public dataset, and good generalization performance (AUC:0.9611) on a cross-institutional private dataset. These quantitative results and interpretations may help radiologists understand gliomas better and make better treatment decisions for improving clinical outcomes.

Intravoxel incoherent motion (IVIM) modeling of diffusion MRI during chemoradiation predicts therapeutic response in IDH wildtype glioblastoma

Background:

Prediction of early progression in glioblastoma may provide an opportunity to personalize treatment. Simplified intravoxel incoherent motion (IVIM) MRI offers quantitative estimates of diffusion and perfusion metrics. We investigated whether these metrics, during chemoradiation, could predict treatment outcome.

Methods:

38 patients with newly diagnosed IDH-wildtype glioblastoma undergoing 6-week/30-fraction chemoradiation had standardized post-operative MRIs at baseline (radiation planning), and at the 10th and 20th fractions. Non-overlapping T1-enhancing (T1C) and non-enhancing T2-FLAIR hyperintense regions were independently segmented. Apparent diffusion coefficient (ADC_T1C, ADC_T2-FLAIR) and perfusion fraction (f_T1C, f_T2-FLAIR) maps were generated with simplified IVIM modelling. Parameters associated with progression before or after 6.9 months (early vs late progression, respectively), overall survival (OS) and progression-free survival (PFS) were investigated.

Results:

Higher ADC_T2-FLAIR at baseline [Odds Ratio (OR) = 1.06, 95% CI 1.01–1.15, p = 0.025], lower f_T2-FLAIR at fraction 10 (OR = 2.11, 95% CI 1.04–4.27, p = 0.018), and lack of increase in ADC_T2-FLAIR at fraction 20 compared to baseline (OR = 1.12, 95% CI 1.02–1.22, p = 0.02) were associated with early progression. Combining ADC_T2-FLAIR at baseline, f_T2-FLAIR at fraction 10, ECOG and MGMT promoter methylation status significantly improved AUC to 90.3% compared to a model with only ECOG and MGMT promoter methylation status (p = 0.001). Using multivariable analysis, neither IVIM metrics were associated with OS but higher f_T2-FLAIR at fraction 10 (HR = 0.72, 95% CI 0.56–0.95, p = 0.018) was associated with longer PFS.

Conclusion:

ADC_T2-FLAIR at baseline, its lack of increase from baseline to fraction 20, or f_T2-FLAIR at fraction 10 significantly predicted early progression. f_T2-FLAIR at fraction 10 was associated with PFS.

Application of Magnetic Resonance Imaging in the Evaluation of Disease Activity in Graves' Ophthalmopathy

OBJECTIVE

To evaluate magnetic resonance imaging parameters, T2 signal intensity ratios (SIRs), and normalized apparent diffusion coefficients (n-ADC) of the extraocular muscles (EOMs) in the identification of different stages of Graves' ophthalmopathy (GO) and to find out the correlation of T2-SIRs and n-ADC values with disease changes after anti-inflammatory treatment.

METHODS

Altogether, 43 patients (86 orbits) were enrolled and classified into "active" or "inactive" stages by clinical activity score (CAS). Twenty-three (53.5%) patients received anti-inflammatory treatment and underwent a follow-up evaluation. Fifteen age- and gender-matched control participants (30 orbits) were included. T2-SIRs and n-ADC values of EOMs were calculated among GO and healthy controls and were correlated with CAS. Changes in these parameters were also evaluated before and after anti-inflammatory treatment.

RESULTS

Mean T2-SIRs and n-ADC values were both significantly higher in GO patients than in controls and higher in active GO than in inactive GO. In the inactive stage, n-ADC values of inferior rectus muscles were still higher than those in healthy controls. Both T2-SIRs and n-ADC values decreased after intravenous steroid pulse therapy. The cutoff value of pretreatment n-ADC was 1.780 to detect stages with specificity of 93.7% and sensitivity of 48.3% (P = .035).

CONCLUSION

T2-SIRs and n-ADC values are valuable magnetic resonance imaging indicators of the inflammatory activity in GO by detecting involvement of EOMs. They are also ideal tools to monitor the efficacy of anti-inflammatory treatment in patients with active stage GO. n-ADC values, when combined with CAS, can be promising predictive factors in the detection of stages of diseases.

Apparent diffusion coefficients for predicting primary cholesteatoma risk of recurrence after surgical clearance

PURPOSE

Beside the well-known accuracy of non-EPI DWI techniques and relative ADC maps in detecting cholesteatomatous tissue, ADC can also represent a useful tool for stratifying cholesteatoma risk of recurrence. Aim of this study is to test the role of ADC in determining risk of recurrence for primary middle ear cholesteatoma, proposing stratification based on pre-operative mean (mADC) and normalized (nADC) ADC values.

METHODS

In this prospective study, 60 patients with primary unilateral middle ear cholesteatoma underwent a three-years-long follow-up to assess the presence of recurrent disease after macroscopically complete excisional surgery. Baseline MRI examination mADC and nADC values in the group with early evidence of recurrent cholesteatoma were compared to the group with no evidence of recurrence by using T statistics.

RESULTS

ADC values on pre-operative MRI examination were lower in cholesteatomas with early evidence of recurrence, and statistical significance was slightly higher for nADC compared to mADC measurements. We also determined a cut-off between the two groups, proposing stratification in high-risk of recurrence cholesteatomas (mADC≤ 1000 or nADC< 1.3) and low-risk cholesteatomas (mADC>1000 or nADC≥1.3).

CONCLUSIONS

ADC values resulted discriminating in identifying cholesteatomas with higher risk of early recurrence, both for mean and normalized ADC, with optimized tissue characterization and outcome prediction.

Deep Transfer Learning and Radiomics Feature Prediction of Survival of Patients with High-Grade Gliomas

BACKGROUND AND PURPOSE

Patient survival in high-grade glioma remains poor, despite the recent developments in cancer treatment. As new chemo-, targeted molecular, and immune therapies emerge and show promising results in clinical trials, image-based methods for early prediction of treatment response are needed. Deep learning models that incorporate radiomics features promise to extract information from brain MR imaging that correlates with response and prognosis. We report initial production of a combined deep learning and radiomics model to predict overall survival in a clinically heterogeneous cohort of patients with high-grade gliomas.

MATERIALS AND METHODS

Fifty patients with high-grade gliomas from our hospital and 128 patients with high-grade glioma from The Cancer Genome Atlas were included. For each patient, we calculated 348 hand-crafted radiomics features and 8192 deep features generated by a pretrained convolutional neural network. We then applied feature selection and Elastic Net-Cox modeling to differentiate patients into long- and short-term survivors.

RESULTS

In the 50 patients with high-grade gliomas from our institution, the combined feature analysis framework classified the patients into long- and short-term survivor groups with a log-rank test P value < .001. In the 128 patients from The Cancer Genome Atlas, the framework classified patients into long- and short-term survivors with a log-rank test P value of .014. For the mixed cohort of 50 patients from our institution and 58 patients from The Cancer Genome Atlas, it yielded a log-rank test P value of .035.

CONCLUSIONS

A deep learning model combining deep and radiomics features can dichotomize patients with high-grade gliomas into long- and short-term survivors.

Diffusion tensor imaging radiomics in lower-grade glioma: improving subtyping of isocitrate dehydrogenase mutation status

PURPOSE

To evaluate whether diffusion tensor imaging (DTI) radiomics with machine learning improves the prediction of isocitrate dehydrogenase (IDH) mutation status of lower-grade gliomas beyond radiomic features from conventional MRI and DTI histogram parameters.

METHODS

A total of 168 patients with pathologically confirmed lower-grade gliomas were retrospectively enrolled. A total of 158 and 253 radiomic features were extracted from DTI (DTI radiomics) and conventional MRI (T1-weighted image with contrast enhancement, T2-weighted image, and FLAIR [conventional radiomics]), respectively. The random forest models for predicting IDH status were trained with variable combinations as follows: (1) DTI radiomics, (2) conventional radiomics, (3) conventional radiomics + DTI radiomics, and (4) conventional radiomics + DTI histogram. The models were validated with nested cross-validation. The predictive performances of those models were compared by using area under the curve (AUC) from receiver operating characteristic analysis, and 95% confidence interval (CI) was calculated.

RESULTS

Adding DTI radiomics to conventional radiomics significantly improved the accuracy of IDH status subtyping (AUC, 0.900 [95% CI, 0.855-0.945], p = 0.006), whereas adding DTI histogram parameters yielded nonsignificant trend toward improvement (0.869 [95% CI, 0.816-0.922], p = 0.150) compared with the model with conventional radiomics alone (0.835 [95% CI, 0.773-0.896]). The performance of the model consisting of both DTI and conventional radiomics was significantly superior than that of model consisting of both DTI histogram parameters and conventional radiomics (0.900 vs 0.869, p = 0.040).

CONCLUSION

DTI radiomics with machine learning can help improve the subtyping of IDH status beyond conventional radiomics and DTI histogram parameters in patients with lower-grade gliomas.