An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI.

Noninvasive differential diagnosis of brain tumors is currently based on the assessment of magnetic resonance imaging (MRI) coupled with dynamic susceptibility contrast (DSC). However, a definitive diagnosis often requires neurosurgical interventions that compromise patients' quality of life. We apply deep learning on DSC images from histology-confirmed patients with glioblastoma, metastasis, or lymphoma. The convolutional neural network trained on ∼50,000 voxels from 40 patients provides intratumor probability maps that yield clinical-grade diagnosis. Performance is tested in 400 additional cases and an external validation cohort of 128 patients. The tool reaches a three-way accuracy of 0.78, superior to the conventional MRI metrics cerebral blood volume (0.55) and percentage of signal recovery (0.59), showing high value as a support diagnostic tool. Our open-access software, Diagnosis In Susceptibility Contrast Enhancing Regions for Neuro-oncology (DISCERN), demonstrates its potential in aiding medical decisions for brain tumor diagnosis using standard-of-care MRI.

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer.

Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Differentiating IDH-mutant astrocytomas and 1p19q-codeleted oligodendrogliomas using DSC-PWI: high performance through cerebral blood volume and percentage of signal recovery percentiles.

OBJECTIVE: Presurgical differentiation between astrocytomas and oligodendrogliomas remains an unresolved challenge in neuro-oncology. This research aims to provide a comprehensive understanding of each tumor's DSC-PWI signatures, evaluate the discriminative capacity of cerebral blood volume (CBV) and percentage of signal recovery (PSR) percentile values, and explore the synergy of CBV and PSR combination for pre-surgical differentiation. METHODS: Patients diagnosed with grade 2 and 3 IDH-mutant astrocytomas and IDH-mutant 1p19q-codeleted oligodendrogliomas were retrospectively retrieved (2010-2022). 3D segmentations of each tumor were conducted, and voxel-level CBV and PSR were extracted to compute mean, minimum, maximum, and percentile values. Statistical comparisons were performed using the Mann-Whitney U test and the area under the receiver operating characteristic curve (AUC-ROC). Lastly, the five most discriminative variables were combined for classification with internal cross-validation. RESULTS: The study enrolled 52 patients (mean age 45-year-old, 28 men): 28 astrocytomas and 24 oligodendrogliomas. Oligodendrogliomas exhibited higher CBV and lower PSR than astrocytomas across all metrics (e.g., mean CBV = 2.05 and 1.55, PSR = 0.68 and 0.81 respectively). The highest AUC-ROCs and the smallest p values originated from CBV and PSR percentiles (e.g., PSRp70 AUC-ROC = 0.84 and p value = 0.0005, CBVp75 AUC-ROC = 0.8 and p value = 0.0006). The mean, minimum, and maximum values yielded lower results. Combining the best five variables (PSRp65, CBVp70, PSRp60, CBVp75, and PSRp40) achieved a mean AUC-ROC of 0.87 for differentiation. CONCLUSIONS: Oligodendrogliomas exhibit higher CBV and lower PSR than astrocytomas, traits that are emphasized when considering percentiles rather than mean or extreme values. The combination of CBV and PSR percentiles results in promising classification outcomes. CLINICAL RELEVANCE STATEMENT: The combination of histogram-derived percentile values of cerebral blood volume and percentage of signal recovery from DSC-PWI enhances the presurgical differentiation between astrocytomas and oligodendrogliomas, suggesting that incorporating these metrics into clinical practice could be beneficial. KEY POINTS: • The unsupervised selection of percentile values for cerebral blood volume and percentage of signal recovery enhances presurgical differentiation of astrocytomas and oligodendrogliomas. • Oligodendrogliomas exhibit higher cerebral blood volume and lower percentage of signal recovery than astrocytomas. • Cerebral blood volume and percentage of signal recovery combined provide a broader perspective on tumor vasculature and yield promising results for this preoperative classification.

MR dynamic-susceptibility-contrast perfusion metrics in the presurgical discrimination of adult solitary intra-axial cerebellar tumors.

OBJECTIVES: Adult solitary intra-axial cerebellar tumors are uncommon. Their presurgical differentiation based on neuroimaging is crucial, since management differs substantially. Comprehensive full assessment of MR dynamic-susceptibility-contrast perfusion-weighted imaging (DSC-PWI) may reveal key differences between entities. This study aims to provide new insights on perfusion patterns of these tumors and to explore the potential of DSC-PWI in their presurgical discrimination. METHODS: Adult patients with a solitary cerebellar tumor on presurgical MR and confirmed histological diagnosis of metastasis, medulloblastoma, hemangioblastoma, or pilocytic astrocytoma were retrospectively retrieved (2008-2023). Volumetric segmentation of tumors and normal-appearing white matter (for normalization) was semi-automatically performed on CE-T1WI and coregistered with DSC-PWI. Mean normalized values per patient tumor-mask of relative cerebral blood volume (rCBV), percentage of signal recovery (PSR), peak height (PH), and normalized time-intensity curves (nTIC) were extracted. Statistical comparisons were done. Then, the dataset was split into training (75%) and test (25%) cohorts and a classifier was created considering nTIC, rCBV, PSR, and PH in the model. RESULTS: Sixty-eight patients (31 metastases, 13 medulloblastomas, 13 hemangioblastomas, and 11 pilocytic astrocytomas) were included. Relevant differences between tumor types' nTICs were demonstrated. Hemangioblastoma showed the highest rCBV and PH, pilocytic astrocytoma the highest PSR. All parameters showed significant differences on the Kruskal-Wallis tests (p < 0.001). The classifier yielded an accuracy of 98% (47/48) in the training and 85% (17/20) in the test sets. CONCLUSIONS: Intra-axial cerebellar tumors in adults have singular and significantly different DSC-PWI signatures. The combination of perfusion metrics through data-analysis rendered excellent accuracies in discriminating these entities. CLINICAL RELEVANCE STATEMENT: In this study, the authors constructed a classifier for the non-invasive imaging presurgical diagnosis of adult intra-axial cerebellar tumors. The resultant tool can be a support for decision-making in the clinical practice and enables optimal personalized patient management. KEY POINTS: • Adult intra-axial cerebellar tumors exhibit specific, singular, and statistically significant different MR dynamic-susceptibility-contrast perfusion-weighted imaging (DSC-PWI) signatures. • Data-analysis, applied to MR DSC-PWI, could provide added value in the presurgical diagnosis of solitary cerebellar metastasis, medulloblastoma, hemangioblastoma, and pilocytic astrocytoma. • A classifier based on DSC-PWI metrics yields excellent accuracy rates and could be used as a support tool for radiologic diagnosis with clinician-friendly displays.

Voxel-level analysis of normalized DSC-PWI time-intensity curves: a potential generalizable approach and its proof of concept in discriminating glioblastoma and metastasis.

OBJECTIVE: Standard DSC-PWI analyses are based on concrete parameters and values, but an approach that contemplates all points in the time-intensity curves and all voxels in the region-of-interest may provide improved information, and more generalizable models. Therefore, a method of DSC-PWI analysis by means of normalized time-intensity curves point-by-point and voxel-by-voxel is constructed, and its feasibility and performance are tested in presurgical discrimination of glioblastoma and metastasis. METHODS: In this retrospective study, patients with histologically confirmed glioblastoma or solitary-brain-metastases and presurgical-MR with DSC-PWI (August 2007-March 2020) were retrieved. The enhancing tumor and immediate peritumoral region were segmented on CE-T1wi and coregistered to DSC-PWI. Time-intensity curves of the segmentations were normalized to normal-appearing white matter. For each participant, average and all-voxel-matrix of normalized-curves were obtained. The 10 best discriminatory time-points between each type of tumor were selected. Then, an intensity-histogram analysis on each of these 10 time-points allowed the selection of the best discriminatory voxel-percentile for each. Separate classifier models were trained for enhancing tumor and peritumoral region using binary logistic regressions. RESULTS: A total of 428 patients (321 glioblastomas, 107 metastases) fulfilled the inclusion criteria (256 men; mean age, 60 years; range, 20-86 years). Satisfactory results were obtained to segregate glioblastoma and metastases in training and test sets with AUCs 0.71-0.83, independent accuracies 65-79%, and combined accuracies up to 81-88%. CONCLUSION: This proof-of-concept study presents a different perspective on brain MR DSC-PWI evaluation by the inclusion of all time-points of the curves and all voxels of segmentations to generate robust diagnostic models of special interest in heterogeneous diseases and populations. The method allows satisfactory presurgical segregation of glioblastoma and metastases. KEY POINTS: • An original approach to brain MR DSC-PWI analysis, based on a point-by-point and voxel-by-voxel assessment of normalized time-intensity curves, is presented. • The method intends to extract optimized information from MR DSC-PWI sequences by impeding the potential loss of information that may represent the standard evaluation of single concrete perfusion parameters (cerebral blood volume, percentage of signal recovery, or peak height) and values (mean, maximum, or minimum). • The presented approach may be of special interest in technically heterogeneous samples, and intrinsically heterogeneous diseases. Its application enables satisfactory presurgical differentiation of GB and metastases, a usual but difficult diagnostic challenge for neuroradiologist with vital implications in patient management.

A CT-based Radiomics Signature Is Associated with Response to Immune Checkpoint Inhibitors in Advanced Solid Tumors.

Background Reliable predictive imaging markers of response to immune checkpoint inhibitors are needed. Purpose To develop and validate a pretreatment CT-based radiomics signature to predict response to immune checkpoint inhibitors in advanced solid tumors. Materials and Methods In this retrospective study, a radiomics signature was developed in patients with advanced solid tumors (including breast, cervix, gastrointestinal) treated with anti-programmed cell death-1 or programmed cell death ligand-1 monotherapy from August 2012 to May 2018 (cohort 1). This was tested in patients with bladder and lung cancer (cohorts 2 and 3). Radiomics variables were extracted from all metastases delineated at pretreatment CT and selected by using an elastic-net model. A regression model combined radiomics and clinical variables with response as the end point. Biologic validation of the radiomics score with RNA profiling of cytotoxic cells (cohort 4) was assessed with Mann-Whitney analysis. Results The radiomics signature was developed in 85 patients (cohort 1: mean age, 58 years ± 13 [standard deviation]; 43 men) and tested on 46 patients (cohort 2: mean age, 70 years ± 12; 37 men) and 47 patients (cohort 3: mean age, 64 years ± 11; 40 men). Biologic validation was performed in a further cohort of 20 patients (cohort 4: mean age, 60 years ± 13; 14 men). The radiomics signature was associated with clinical response to immune checkpoint inhibitors (area under the curve [AUC], 0.70; 95% CI: 0.64, 0.77; P < .001). In cohorts 2 and 3, the AUC was 0.67 (95% CI: 0.58, 0.76) and 0.67 (95% CI: 0.56, 0.77; P < .001), respectively. A radiomics-clinical signature (including baseline albumin level and lymphocyte count) improved on radiomics-only performance (AUC, 0.74 [95% CI: 0.63, 0.84; P < .001]; Akaike information criterion, 107.00 and 109.90, respectively). Conclusion A pretreatment CT-based radiomics signature is associated with response to immune checkpoint inhibitors, likely reflecting the tumor immunophenotype. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Summers in this issue.

Precise enhancement quantification in post-operative MRI as an indicator of residual tumor impact is associated with survival in patients with glioblastoma.

Glioblastoma is the most common primary brain tumor. Standard therapy consists of maximum safe resection combined with adjuvant radiochemotherapy followed by chemotherapy with temozolomide, however prognosis is extremely poor. Assessment of the residual tumor after surgery and patient stratification into prognostic groups (i.e., by tumor volume) is currently hindered by the subjective evaluation of residual enhancement in medical images (magnetic resonance imaging [MRI]). Furthermore, objective evidence defining the optimal time to acquire the images is lacking. We analyzed 144 patients with glioblastoma, objectively quantified the enhancing residual tumor through computational image analysis and assessed the correlation with survival. Pathological enhancement thickness on post-surgical MRI correlated with survival (hazard ratio: 1.98, p < 0.001). The prognostic value of several imaging and clinical variables was analyzed individually and combined (radiomics AUC 0.71, p = 0.07; combined AUC 0.72, p < 0.001). Residual enhancement thickness and radiomics complemented clinical data for prognosis stratification in patients with glioblastoma. Significant results were only obtained for scans performed between 24 and 72 h after surgery, raising the possibility of confounding non-tumor enhancement in very early post-surgery MRI. Regarding the extent of resection, and in agreement with recent studies, the association between the measured tumor remnant and survival supports maximal safe resection whenever possible.

Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis.

OBJECTIVE: To identify CT-acquisition parameters accounting for radiomics variability and to develop a post-acquisition CT-image correction method to reduce variability and improve radiomics classification in both phantom and clinical applications. METHODS: CT-acquisition protocols were prospectively tested in a phantom. The multi-centric retrospective clinical study included CT scans of patients with colorectal/renal cancer liver metastases. Ninety-three radiomics features of first order and texture were extracted. Intraclass correlation coefficients (ICCs) between CT-acquisition protocols were evaluated to define sources of variability. Voxel size, ComBat, and singular value decomposition (SVD) compensation methods were explored for reducing the radiomics variability. The number of robust features was compared before and after correction using two-proportion z test. The radiomics classification accuracy (K-means purity) was assessed before and after ComBat- and SVD-based correction. RESULTS: Fifty-three acquisition protocols in 13 tissue densities were analyzed. Ninety-seven liver metastases from 43 patients with CT from two vendors were included. Pixel size, reconstruction slice spacing, convolution kernel, and acquisition slice thickness are relevant sources of radiomics variability with a percentage of robust features lower than 80%. Resampling to isometric voxels increased the number of robust features when images were acquired with different pixel sizes (p < 0.05). SVD-based for thickness correction and ComBat correction for thickness and combined thickness-kernel increased the number of reproducible features (p < 0.05). ComBat showed the highest improvement of radiomics-based classification in both the phantom and clinical applications (K-means purity 65.98 vs 73.20). CONCLUSION: CT-image post-acquisition processing and radiomics normalization by means of batch effect correction allow for standardization of large-scale data analysis and improve the classification accuracy. KEY POINTS: • The voxel size (accounting for the pixel size and slice spacing), slice thickness, and convolution kernel are relevant sources of CT-radiomics variability. • Voxel size resampling increased the mean percentage of robust CT-radiomics features from 59.50 to 89.25% when comparing CT scans acquired with different pixel sizes and from 71.62 to 82.58% when the scans were acquired with different slice spacings. • ComBat batch effect correction reduced the CT-radiomics variability secondary to the slice thickness and convolution kernel, improving the capacity of CT-radiomics to differentiate tissues (in the phantom application) and the primary tumor type from liver metastases (in the clinical application).

Correlation of the tumour-stroma ratio with diffusion weighted MRI in rectal cancer.

OBJECTIVE: This study evaluated the correlation between intratumoural stroma proportion, expressed as tumour-stroma ratio (TSR), and apparent diffusion coefficient (ADC) values in patients with rectal cancer. METHODS: This multicentre retrospective study included all consecutive patients with rectal cancer, diagnostically confirmed by biopsy and MRI. The training cohort (LUMC, Netherlands) included 33 patients and the validation cohort (VHIO, Spain) 69 patients. Two observers measured the mean and minimum ADCs based on single-slice and whole-volume segmentations. The TSR was determined on diagnostic haematoxylin & eosin stained slides of rectal tumour biopsies. The correlation between TSR and ADC was assessed by Spearman correlation (rs). RESULTS: The ADC values between stroma-low and stroma-high tumours were not significantly different. Intra-class correlation (ICC) demonstrated a good level of agreement for the ADC measurements, ranging from 0.84-0.86 for single slice and 0.86-0.90 for the whole-volume protocol. No correlation was observed between the TSR and ADC values, with ADCmeanrs= -0.162 (p= 0.38) and ADCminrs= 0.041 (p= 0.82) for the single-slice and rs= -0.108 (p= 0.55) and rs= 0.019 (p= 0.92) for the whole-volume measurements in the training cohort, respectively. Results from the validation cohort were consistent; ADCmeanrs= -0.022 (p= 0.86) and ADCminrs = 0.049 (p= 0.69) for the single-slice and rs= -0.064 (p= 0.59) and rs= -0.063 (p= 0.61) for the whole-volume measurements. CONCLUSIONS: Reproducibility of ADC values is good. Despite positive reports on the correlation between TSR and ADC values in other tumours, this could not be confirmed for rectal cancer.

Capturing Hyperprogressive Disease with Immune-Checkpoint Inhibitors Using RECIST 1.1 Criteria.

PURPOSE: Most hyperprogression disease (HPD) definitions are based on tumor growth rate (TGR). However, there is still no consensus on how to evaluate this phenomenon. PATIENTS AND METHODS: We investigated two independent cohorts of patients with advanced solid tumors treated in phase I trials with (i) programmed cell death 1 (PD-1)/PD-L1 antibodies in monotherapy or combination and (ii) targeted agents (TA) in unapproved indications. A Response Evaluation Criteria in Solid Tumors (RECIST) 1.1-based definition of hyperprogression was developed. The primary endpoint was the assessment of the rate of HPD in patients treated with ICIs or TAs using both criteria (RECIST and TGR) and the impact on overall survival (OS) in patients who achieved PD as best response. RESULTS: Among 270 evaluable patients treated with PD-1/PD-L1 inhibitors, 29 PD-1/PD-L1-treated patients (10.7%) had HPD by RECIST definition. This group had a significantly lower OS (median of 5.23 months; 95% CI, 3.97-6.45) when compared with the non-HPD progressor group (median, 7.33 months; 95% CI, 4.53-10.12; HR = 1.73, 95% CI, 1.05-2.85; P = 0.04). In a subset of 221 evaluable patients, 14 (6.3%) were categorized as HPD using TGR criteria, differences in median OS (mOS) between this group (mOS 4.2 months; 95% IC, 2.07-6.33) and non-HPD progressors (n = 44) by TGR criteria (mOS 6.27 months; 95% CI, 3.88-8.67) were not statistically significant (HR 1.4, 95% IC, 0.70-2.77; P = 0.346). Among 239 evaluable patients treated with TAs, 26 (10.9%) were classified as having HPD by RECIST and 14 using TGR criteria in a subset of patients. No differences in OS were observed between HPD and non-HPD progressors treated with TAs. CONCLUSIONS: HPD measured by TGR or by RECIST was observed in both cohorts of patients; however, in our series, there was an impact on survival only in the immune-checkpoint inhibitor cohort when evaluated by RECIST. We propose a new way to capture HPD using RECIST criteria that is intuitive and easy to use in daily clinical practice.