Tumor Subregions Research Articles

Automated post-operative brain tumour segmentation: A deep learning model based on transfer learning from pre-operative images

Automated brain tumour segmentation from post-operative images is a clinically relevant yet challenging problem. In this study, an automated method for segmenting brain tumour into its subregions has been developed. The dataset consists of multimodal post-operative brain scans (T1 MRI, post-Gadolinium T1 MRI, and T2-FLAIR images) of 15 patients who were treated with post-operative radiation therapy, along with manual annotations of their tumour subregions. A 3D densely-connected U-net was developed for segmentation of brain tumour regions and extensive experiments were conducted to enhance model accuracy. A model was initially developed using the publicly available BraTS dataset consisting of pre-operative brain scans. This model achieved Dice Scores of 0.90, 0.83 and 0.78 for predicting whole tumour, tumour core, and enhancing tumour subregions when tested on BraTS20 blind validation dataset. The acquired knowledge from BraTS was then transferred to the local dataset. For augmentation purpose, the local dataset was registered to a dataset of MRI brain scans of healthy subjects. To improve the robustness of the model and enhance its accuracy, ensemble learning was used to combine the outputs of all the trained models. Even though the size of the dataset is very small, the final model can segment brain tumours with a high Dice Score of 0.83, 0.77 and 0.60 for whole tumour, tumour core and enhancing core respectively.

Combining 18F-DOPA PET and MRI with perfusion-weighted imaging improves delineation of high-grade subregions in enhancing and non-enhancing gliomas prior treatment: a biopsy-controlled study.

We aimed to compare spatial extent of high-grade subregions detected with combined [18F]-dihydroxyphenylalanine (18F-DOPA) PET and MRI to the one provided by advanced multimodal MRI alone including Contrast-enhanced (CE) and Perfusion weighted imaging (PWI). Then, we compared the accuracy between imaging modalities, in a per biopsy analysis. Participants with suspected diffuse glioma were prospectively included between June 2018 and September 2019. Volumes of high-grade subregions were delineated respectively on 18F-DOPA PET and MRI (CE and PWI). Up to three per-surgical neuronavigation-guided biopsies were performed per patient. Thirty-eight biopsy samples from sixteen participants were analyzed. Six participants (38%) had grade IV IDH wild-type glioblastoma, six (38%) had grade III IDH-mutated astrocytoma and four (24%) had grade II IDH-mutated gliomas. Three patients had intratumoral heterogeneity with coexisting high- and low-grade tumor subregions. High-grade volumes determined with combined 18F-DOPA PET/MRI (median of 1.7 [interquartile range (IQR) 0.0, 19.1] mL) were larger than with multimodal MRI alone (median 1.3 [IQR 0.0, 12.8] mL) with low overlap (median Dice's coefficient 0.24 [IQR 0.08, 0.59]). Delineation volumes were substantially increased in five (31%) patients. In a per biopsy analysis, combined 18F-DOPA PET/MRI detected high-grade subregions with an accuracy of 58% compared to 42% (p = 0.03) with CE MRI alone and 50% (p = 0.25) using multimodal MRI (CE + PWI). The addition of 18F-DOPA PET to multimodal MRI (CE and PWI) enlarged the delineation volumes and enhanced overall accuracy for detection of high-grade subregions. Thus, combining 18F-DOPA with advanced MRI may improve treatment planning in newly diagnosed gliomas.

Robust imaging habitat computation using voxel-wise radiomics features

Tumor heterogeneity has been postulated as a hallmark of treatment resistance and a cure constraint in cancer patients. Conventional quantitative medical imaging (radiomics) can be extended to computing voxel-wise features and aggregating tumor subregions with similar radiological phenotypes (imaging habitats) to elucidate the distribution of tumor heterogeneity within and among tumors. Despite the promising applications of imaging habitats, they may be affected by variability of radiomics features, preventing comparison and generalization of imaging habitats techniques. We performed a comprehensive repeatability and reproducibility analysis of voxel-wise radiomics features in more than 500 lung cancer patients with computed tomography (CT) images and demonstrated the effect of voxel-wise radiomics variability on imaging habitats computation in 30 lung cancer patients with test–retest images. Repeatable voxel-wise features characterized texture heterogeneity and were reproducible regardless of the applied feature extraction parameters. Imaging habitats computed using robust radiomics features were more stable than those computed using all features in test–retest CTs from the same patient. Nine voxel-wise radiomics features (joint energy, joint entropy, sum entropy, maximum probability, difference entropy, Imc1, Imc2, Idn and Idmn) were repeatable and reproducible. This supports their application for computing imaging habitats in lung tumors towards the discovery of previously unseen tumor heterogeneity and the development of novel non-invasive imaging biomarkers for precision medicine.

Radiomics in Oncology: A Practical Guide

Radiomics refers to the extraction of mineable data from medical imaging and has been applied within oncology to improve diagnosis, prognostication, and clinical decision support, with the goal of delivering precision medicine. The authors provide a practical approach for successfully implementing a radiomic workflow from planning and conceptualization through manuscript writing. Applications in oncology typically are either classification tasks that involve computing the probability of a sample belonging to a category, such as benign versus malignant, or prediction of clinical events with a time-to-event analysis, such as overall survival. The radiomic workflow is multidisciplinary, involving radiologists and data and imaging scientists, and follows a stepwise process involving tumor segmentation, image preprocessing, feature extraction, model development, and validation. Images are curated and processed before segmentation, which can be performed on tumors, tumor subregions, or peritumoral zones. Extracted features typically describe the distribution of signal intensities and spatial relationship of pixels within a region of interest. To improve model performance and reduce overfitting, redundant and nonreproducible features are removed. Validation is essential to estimate model performance in new data and can be performed iteratively on samples of the dataset (cross-validation) or on a separate hold-out dataset by using internal or external data. A variety of noncommercial and commercial radiomic software applications can be used. Guidelines and artificial intelligence checklists are useful when planning and writing up radiomic studies. Although interest in the field continues to grow, radiologists should be familiar with potential pitfalls to ensure that meaningful conclusions can be drawn. Online supplemental material is available for this article. Published under a CC BY 4.0 license.

Asymmetric Ensemble of Asymmetric U-Net Models for Brain Tumor Segmentation With Uncertainty Estimation.

Accurate brain tumor segmentation is crucial for clinical assessment, follow-up, and subsequent treatment of gliomas. While convolutional neural networks (CNN) have become state of the art in this task, most proposed models either use 2D architectures ignoring 3D contextual information or 3D models requiring large memory capacity and extensive learning databases. In this study, an ensemble of two kinds of U-Net-like models based on both 3D and 2.5D convolutions is proposed to segment multimodal magnetic resonance images (MRI). The 3D model uses concatenated data in a modified U-Net architecture. In contrast, the 2.5D model is based on a multi-input strategy to extract low-level features from each modality independently and on a new 2.5D Multi-View Inception block that aims to merge features from different views of a 3D image aggregating multi-scale features. The Asymmetric Ensemble of Asymmetric U-Net (AE AU-Net) based on both is designed to find a balance between increasing multi-scale and 3D contextual information extraction and keeping memory consumption low. Experiments on 2019 dataset show that our model improves enhancing tumor sub-region segmentation. Overall, performance is comparable with state-of-the-art results, although with less learning data or memory requirements. In addition, we provide voxel-wise and structure-wise uncertainties of the segmentation results, and we have established qualitative and quantitative relationships between uncertainty and prediction errors. Dice similarity coefficient for the whole tumor, tumor core, and tumor enhancing regions on BraTS 2019 validation dataset were 0.902, 0.815, and 0.773. We also applied our method in BraTS 2018 with corresponding Dice score values of 0.908, 0.838, and 0.800.

Joint Modeling of RNAseq and Radiomics Data for Glioma Molecular Characterization and Prediction.

RNA sequencing (RNAseq) is a recent technology that profiles gene expression by measuring the relative frequency of the RNAseq reads. RNAseq read counts data is increasingly used in oncologic care and while radiology features (radiomics) have also been gaining utility in radiology practice such as disease diagnosis, monitoring, and treatment planning. However, contemporary literature lacks appropriate RNA-radiomics (henceforth, radiogenomics) joint modeling where RNAseq distribution is adaptive and also preserves the nature of RNAseq read counts data for glioma grading and prediction. The Negative Binomial (NB) distribution may be useful to model RNAseq read counts data that addresses potential shortcomings. In this study, we propose a novel radiogenomics-NB model for glioma grading and prediction. Our radiogenomics-NB model is developed based on differentially expressed RNAseq and selected radiomics/volumetric features which characterize tumor volume and sub-regions. The NB distribution is fitted to RNAseq counts data, and a log-linear regression model is assumed to link between the estimated NB mean and radiomics. Three radiogenomics-NB molecular mutation models (e.g., IDH mutation, 1p/19q codeletion, and ATRX mutation) are investigated. Additionally, we explore gender-specific effects on the radiogenomics-NB models. Finally, we compare the performance of the proposed three mutation prediction radiogenomics-NB models with different well-known methods in the literature: Negative Binomial Linear Discriminant Analysis (NBLDA), differentially expressed RNAseq with Random Forest (RF-genomics), radiomics and differentially expressed RNAseq with Random Forest (RF-radiogenomics), and Voom-based count transformation combined with the nearest shrinkage classifier (VoomNSC). Our analysis shows that the proposed radiogenomics-NB model significantly outperforms (ANOVA test, p < 0.05) for prediction of IDH and ATRX mutations and offers similar performance for prediction of 1p/19q codeletion, when compared to the competing models in the literature, respectively.

Overall Survival Prediction for Gliomas Using a Novel Compound Approach.

As a highly malignant tumor, the incidence and mortality of glioma are not optimistic. Predicting the survival time of patients with glioma by extracting the feature information from gliomas is beneficial for doctors to develop more targeted treatments. Magnetic resonance imaging (MRI) is a way to quickly and clearly capture the details of brain tissue. However, manually segmenting brain tumors from MRI will cost doctors a lot of energy, and doctors can only vaguely estimate the survival time of glioma patients, which are not conducive to the formulation of treatment plans. Therefore, automatically segmenting brain tumors and accurately predicting survival time has important significance. In this article, we first propose the NLSE-VNet model, which integrates the Non-Local module and the Squeeze-and-Excitation module into V-Net to segment three brain tumor sub-regions in multimodal MRI. Then extract the intensity, texture, wavelet, shape and other radiological features from the tumor area, and use the CNN network to extract the deep features. The factor analysis method is used to reduce the dimensionality of features, and finally the dimensionality-reduced features and clinical features such as age and tumor grade are combined into the random forest regression model to predict survival. We evaluate the effect on the BraTS 2019 and BraTS 2020 datasets. The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5. The results indicate that the method in this paper has great advantages in segmentation and survival prediction of gliomas.

Perfusion imaging of neuroblastoma and nephroblastoma in a paediatric population using pseudo-continuous arterial spin-labelling magnetic resonance imaging

ObjectivesTo examine the feasibility of performing ASL-MRI in paediatric patients with solid abdominal tumours.MethodsMulti-delay ASL data sets were acquired in ten paediatric patients diagnosed with either a neuroblastoma (n = 4) or nephroblastoma (n = 6) during a diagnostic MRI examination at a single visit (n = 4 at initial staging, n = 2 neuroblastoma and n = 2 nephroblastoma patients; n = 6 during follow-up, n = 2 neuroblastoma and n = 4 nephroblastoma patients). Visual evaluation and region-of-interest (ROI) analyses were performed on the processed perfusion-weighted images to assess ASL perfusion signal dynamics in the whole tumour, contralateral kidney, and tumour sub-regions with/without contrast enhancement.ResultsThe majority of the included abdominal tumours presented with relatively low perfusion-weighted signal (PWS), especially compared with the highly perfused kidneys. Within the tumours, regions with high PWS were observed which, at short PLD, are possibly related to labelled blood inside vessels and at long PLD, reflect labelled blood accumulating inside tumour tissue over time. Conversely, comparison of ASL perfusion-weighted image findings with T1w enhancement after contrast administration showed that regions lacking contrast enhancement also were void of PWS.DiscussionThis pilot study demonstrates the feasibility of utilizing ASL-MRI in paediatric patients with solid abdominal tumours and provides a basis for further research on non-invasive perfusion measurements in this study population.

Interactive Machine Learning-Based Multi-Label Segmentation of Solid Tumors and Organs.

We seek the development and evaluation of a fast, accurate, and consistent method for general-purpose segmentation, based on interactive machine learning (IML). To validate our method, we identified retrospective cohorts of 20 brain, 50 breast, and 50 lung cancer patients, as well as 20 spleen scans, with corresponding ground truth annotations. Utilizing very brief user training annotations and the adaptive geodesic distance transform, an ensemble of SVMs is trained, providing a patient-specific model applied to the whole image. Two experts segmented each cohort twice with our method and twice manually. The IML method was faster than manual annotation by 53.1% on average. We found significant (p < 0.001) overlap difference for spleen (DiceIML/DiceManual = 0.91/0.87), breast tumors (DiceIML/DiceManual = 0.84/0.82), and lung nodules (DiceIML/DiceManual = 0.78/0.83). For intra-rater consistency, a significant (p = 0.003) difference was found for spleen (DiceIML/DiceManual = 0.91/0.89). For inter-rater consistency, significant (p < 0.045) differences were found for spleen (DiceIML/DiceManual = 0.91/0.87), breast (DiceIML/DiceManual = 0.86/0.81), lung (DiceIML/DiceManual = 0.85/0.89), the non-enhancing (DiceIML/DiceManual = 0.79/0.67) and the enhancing (DiceIML/DiceManual = 0.79/0.84) brain tumor sub-regions, which, in aggregation, favored our method. Quantitative evaluation for speed, spatial overlap, and consistency, reveals the benefits of our proposed method when compared with manual annotation, for several clinically relevant problems. We publicly release our implementation through CaPTk (Cancer Imaging Phenomics Toolkit) and as an MITK plugin.

Fully automated segmentation of brain tumor from multiparametric MRI using 3D context deep supervised U-Net.

Owing to histologic complexities of brain tumors, its diagnosis requires the use of multimodalities to obtain valuable structural information so that brain tumor subregions can be properly delineated. In current clinical workflow, physicians typically perform slice-by-slice delineation of brain tumor subregions, which is a time-consuming process and also more susceptible to intra- and inter-rater variabilities possibly leading to misclassification. To deal with this issue, this study aims to develop an automatic segmentation of brain tumor in MR images using deep learning. In this study, we develop a context deep-supervised U-Net to segment brain tumor subregions. A context block which aggregates multiscale contextual information for dense segmentation was proposed. This approach enlarges the effective receptive field of convolutional neural networks, which, in turn, improves the segmentation accuracy of brain tumor subregions. We performed the fivefold cross-validation on the Brain Tumor Segmentation Challenge (BraTS) 2020 training dataset. The BraTS 2020 testing datasets were obtained via BraTS online website as a hold-out test. For BraTS, the evaluation system divides the tumor into three regions: whole tumor (WT), tumor core (TC), and enhancing tumor (ET). The performance of our proposed method was compared against two state-of-the-arts CNN networks in terms of segmentation accuracy via Dice similarity coefficient (DSC) and Hausdorff distance (HD). The tumor volumes generated by our proposed method were compared with manually contoured volumes via Bland-Altman plots and Pearson analysis. The proposed method achieved the segmentation results with a DSC of 0.923±0.047, 0.893±0.176, and 0.846±0.165 and a 95% HD95 of 3.946±7.041, 3.981±6.670, and 10.128±51.136mm on WT, TC, and ET, respectively. Experimental results demonstrate that our method achieved comparable to significantly (p<0.05) better segmentation accuracies than other two state-of-the-arts CNN networks. Pearson correlation analysis showed a high positive correlation between the tumor volumes generated by proposed method and manual contour. Overall qualitative and quantitative results of this work demonstrate the potential of translating proposed technique into clinical practice for segmenting brain tumor subregions, and further facilitate brain tumor radiotherapy workflow.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review.

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI‐based tumor subregion analysis in medical imaging. We summarize the latest AI‐based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI‐based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

Multispectral co-occurrence of wavelet coefficients for malignancy assessment of brain tumors.

Brain tumor is not most common, but truculent type of cancer. Therefore, correct prediction of its aggressiveness nature at an early stage would influence the treatment strategy. Although several diagnostic methods based on different modalities exist, a pre-operative method for determining tumor malignancy state still remains as an active research area. In this regard, the paper presents a new method for the assessment of tumor grades using conventional MR sequences namely, T1, T1 with contrast enhancement, T2 and FLAIR. The proposed method for tumor gradation is mainly based on feature extraction using multiresolution image analysis and classification using support vector machine. Since the wavelet features of different tumor subregions, obtained from single MR sequence, do not carry equally important information, a wavelet fusion technique is proposed based on the texture information content of each voxel. The concept of texture gradient, used in the proposed algorithm, fuses the wavelet coefficients of the given MR sequences. The feature vector is then derived from the co-occurrence of fused wavelet coefficients. As each wavelet subband contains distinct detail information, a novel concept of multispectral co-occurrence of wavelet coefficients is introduced to capture the spatial correlation among different subbands. It enables to convey more informative features to characterize the tumor type. The effectiveness of the proposed method is analyzed, with respect to six classification performance indices, on BRATS 2012 and BRATS 2014 data sets. The classification accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under curve assessed by the ten-fold cross-validation are 91.3%, 96.8%, 66.7%, 92.4%, 88.4%, and 92.0%, respectively, on real brain MR data.

DFP-ResUNet:Convolutional Neural Network with a Dilated Convolutional Feature Pyramid for Multimodal Brain Tumor Segmentation

Manual brain tumor segmentation by radiologists is time consuming and subjective. Therefore, fully automatic segmentation of different brain tumor subregions is essential to the treatment of patients. In this paper, we propose a neural network for automatically segmenting the enhancing tumor (ET), whole tumor (WT), and tumor core (TC) brain tumor subregions. The network is based on a U-Net with encoding and decoding structure, a residual module, and a spatial dilated feature pyramid (DFP) module, namely, DFP-ResUNet. First, we propose using a spatial DFP module composed of multiple parallel dilated convolution layers to extract the multiscale image features. This spatial DFP structure improves the ability of the neural network to extract and utilize the multiscale image features. Then, we use the residual module to deepen the network structure. Further, we propose using a multiclass Dice loss function to suppress the impact of class imbalance on brain tumor segmentation. We carried out a large number of ablation experiments to verify the feasibility and superiority of our approach using the Multimodal Brain Tumor Segmentation (BraTS) challenge dataset. The mean Dice score of different subregions was ET 0.8431, WT 0.897 and TC 0.9068 using the proposed method on the BraTS 2018 challenge validation set and 0.7985, 0.90281, 0.8453 on the BraTS 2019 challenge, respectively. Further, we got a high Sensitivity and Specificity and low Hausdorff distance. Through the analysis of the experimental results, it can be seen that the proposed approach DFP-ResUNet has a great potential in segmenting different subregions of brain tumors and can be applied in clinical practice.

Radiomic Based Machine Learning Performance for a Three Class Problem in Neuro-Oncology: Time to Test the Waters?

Simple SummaryPrior radiomic studies have addressed a two-class tumor classification problem (glioblastoma (GBM) versus primary CNS lymphoma (PCNSL) or GBM versus metastasis). However, this approach is prone to bias and excludes other common brain tumor types. We addressed a real-life clinical problem by including the three most common brain tumor types (GBM, PCNSL, and metastasis). We investigated two key issues using different MRI sequence combinations: performance variation based on tumor subregions (necrotic, enhancing, edema and combined enhancing, and necrotic masks), and performance metrics based on the chosen classifier model/feature selection combination. Our study provides evidence that radiomics-based three-class tumor differentiation is feasible, and that embedded models perform better than those with a priori feature selection. We found that T1 contrast enhanced is the single best sequence with comparable performance to that of multiparametric MRI, and model performance varies based on tumor subregion and the combination of model/feature selection methods.Prior radiomics studies have focused on two-class brain tumor classification, which limits generalizability. The performance of radiomics in differentiating the three most common malignant brain tumors (glioblastoma (GBM), primary central nervous system lymphoma (PCNSL), and metastatic disease) is assessed; factors affecting the model performance and usefulness of a single sequence versus multiparametric MRI (MP-MRI) remain largely unaddressed. This retrospective study included 253 patients (120 metastatic (lung and brain), 40 PCNSL, and 93 GBM). Radiomic features were extracted for whole a tumor mask (enhancing plus necrotic) and an edema mask (first pipeline), as well as for separate enhancing and necrotic and edema masks (second pipeline). Model performance was evaluated using MP-MRI, individual sequences, and the T1 contrast enhanced (T1-CE) sequence without the edema mask across 45 model/feature selection combinations. The second pipeline showed significantly high performance across all combinations (Brier score: 0.311–0.325). GBRM fit using the full feature set from the T1-CE sequence was the best model. The majority of the top models were built using a full feature set and inbuilt feature selection. No significant difference was seen between the top-performing models for MP-MRI (AUC 0.910) and T1-CE sequence with (AUC 0.908) and without edema masks (AUC 0.894). T1-CE is the single best sequence with comparable performance to that of multiparametric MRI (MP-MRI). Model performance varies based on tumor subregion and the combination of model/feature selection methods.

Elevated fibroblast growth factor-inducible 14 expression transforms proneural-like gliomas into more aggressive and lethal brain cancer.

High-grade gliomas (HGGs) are aggressive, treatment-resistant, and often fatal human brain cancers. The TNF-like weak inducer of apoptosis (TWEAK)/fibroblast growth factor-inducible 14 (Fn14) signaling axis is involved in tissue repair after injury and constitutive signaling has been implicated in the pathogenesis of numerous solid cancers. The Fn14 gene is expressed at low levels in the normal, uninjured brain but is highly expressed in primary isocitrate dehydrogenase wild-type and recurrent HGGs. Fn14 signaling is implicated in numerous aspects of glioma biology including brain invasion and chemotherapy resistance, but whether Fn14 overexpression can directly promote tumor malignancy has not been reported. Here, we used the replication-competent avian sarcoma-leukosis virus/tumor virus A system to examine the impact of Fn14 expression on glioma development and pathobiology. We found that the sole addition of Fn14 to an established oncogenic cocktail previously shown to generate proneural-like gliomas led to the development of highly invasive and lethal brain cancer with striking biological features including extensive pseudopalisading necrosis, constitutive canonical and noncanonical NF-κB pathway signaling, and high plasminogen activator inhibitor-1 (PAI-1) expression. Analyses of HGG patient datasets revealed that high human PAI-1 gene (SERPINE1) expression correlates with shorter patient survival, and that the SERPINE1 and Fn14 (TNFRSF12A) genes are frequently co-expressed in bulk tumor tissues, in tumor subregions, and in malignant cells residing in the tumor microenvironment. These findings provide new insights into the potential importance of Fn14 in human HGG pathobiology and designate both the NF-κB signaling node and PAI-1 as potential targets for therapeutic intervention. MAIN POINTS: This work demonstrates that elevated levels of the TWEAK receptor Fn14 in tumor-initiating, neural progenitor cells leads to the transformation of proneural-like gliomas into more aggressive and lethal tumors that exhibit constitutive NF-κB pathway activation and plasminogen activator inhibitor-1 overexpression.

An Improvement of Survival Stratification in Glioblastoma Patients via Combining Subregional Radiomics Signatures.

PurposeTo investigate whether combining multiple radiomics signatures derived from the subregions of glioblastoma (GBM) can improve survival prediction of patients with GBM.MethodsIn total, 129 patients were included in this study and split into training (n = 99) and test (n = 30) cohorts. Radiomics features were extracted from each tumor region then radiomics scores were obtained separately using least absolute shrinkage and selection operator (LASSO) COX regression. A clinical nomogram was also constructed using various clinical risk factors. Radiomics nomograms were constructed by combing a single radiomics signature from the whole tumor region with clinical risk factors or combining three radiomics signatures from three tumor subregions with clinical risk factors. The performance of these models was assessed by the discrimination, calibration and clinical usefulness metrics, and was compared with that of the clinical nomogram.ResultsIncorporating the three radiomics signatures, i.e., Radscores for ET, NET, and ED, into the radiomics-based nomogram improved the performance in estimating survival (C-index: training/test cohort: 0.717/0.655) compared with that of the clinical nomogram (C-index: training/test cohort: 0.633/0.560) and that of the radiomics nomogram based on single region radiomics signatures (C-index: training/test cohort: 0.656/0.535).ConclusionThe multiregional radiomics nomogram exhibited a favorable survival stratification accuracy.

A Multiparametric MRI-Based Radiomics Analysis to Efficiently Classify Tumor Subregions of Glioblastoma: A Pilot Study in Machine Learning

Glioblastoma multiforme (GBM) carries a poor prognosis and usually presents with heterogenous regions of a necrotic core, solid part, peritumoral tissue, and peritumoral edema. Accurate demarcation on magnetic resonance imaging (MRI) between the active tumor region and perifocal edematous extension is essential for planning stereotactic biopsy, GBM resection, and radiotherapy. We established a set of radiomics features to efficiently classify patients with GBM and retrieved cerebral multiparametric MRI, including contrast-enhanced T1-weighted (T1-CE), T2-weighted, T2-weighted fluid-attenuated inversion recovery, and apparent diffusion coefficient images from local patients with GBM. A total of 1316 features on the raw MR images were selected for each annotated area. A leave-one-out cross-validation was performed on the whole dataset, the different machine learning and deep learning techniques tested; random forest achieved the best performance (average accuracy: 93.6% necrosis, 90.4% solid part, 95.8% peritumoral tissue, and 90.4% peritumoral edema). The features from the enhancing tumor and the tumor shape elongation of peritumoral edema region for high-risk groups from T1-CE. The multiparametric MRI-based radiomics model showed the efficient classification of tumor subregions of GBM and suggests that prognostic radiomic features from a routine MRI exam may also be significantly associated with key biological processes that affect the response to chemotherapy in GBM.

Radiomics-Based Differentiation between Glioblastoma, CNS Lymphoma, and Brain Metastases: Comparing Performance across MRI Sequences and Machine Learning Models

Prior radiomics studies have focused on two-class brain tumor classification, which limits generalizability. The performance of radiomics in differentiating the three most common malignant brain tumors (glioblastoma (GBM), primary central nervous system lymphoma (PCNSL), and metastatic disease) is assessed; factors affecting the model performance and usefulness of a single sequence versus multiparametric MRI (MP-MRI) remain largely unaddressed. This retrospective study included 253 patients (120 metastatic (lung and brain), 40 PCNSL, and 93 GBM). Radiomic features were extracted for whole a tumor mask (enhancing plus necrotic) and an edema mask (first pipeline), as well as for separate enhancing and necrotic and edema masks (second pipeline). Model performance was evaluated using MP-MRI, individual sequences, and the T1 contrast enhanced (T1-CE) sequence without the edema mask across 45 model/feature selection combinations. The second pipeline showed significantly high performance across all combinations (Brier score: 0.311–0.325). GBRM fit using the full feature set from the T1-CE sequence was the best model. The majority of the top models were built using a full feature set and inbuilt feature selection. No significant difference was seen between the top-performing models for MP-MRI (AUC 0.910) and T1-CE sequence with (AUC 0.908) and without edema masks (AUC 0.894). T1-CE is the single best sequence with comparable performance to that of multiparametric MRI (MP-MRI). Model performance varies based on tumor subregion and the combination of model/feature selection methods.

A systematic evaluation of learning rate policies in training CNNs for brain tumor segmentation

Convolutional neural networks (CNNs) have recently emerged as a powerful approach for automatic segmentation of brain tumor subregions on 3D multi-parametric MRI scans. Learning rate is a crucial hyperparameter in the training of CNNs, impacting the performance of the learned model. Different learning rate policies trace unique trajectories in the optimization landscape that converge to local minima with varying generalization properties. In this work, we empirically evaluated nine learning rate policy-optimizer pairs with two state-of-the-art architectures, namely 2D slice-based U-Net and 3D DeepMedicRes, on an augmented brain tumor dataset of 534 subjects. Segmentation performance was quantified in terms of Dice similarity coefficient and Hausdorff distance metrics. The policies were ranked based on the final ranking score (FRS) employed by the BraTS challenge, with the statistical significance of the rankings evaluated by random permutation test. For 2D slice-based U-Net architecture, an overall ranking of learning rate policies showed that the polynomial decay policy with Adam optimizer significantly outperformed other policies for the task of individual and hierarchical segmentation of tumor subregions (p < 10−4). For 3D segment-based DeepMedicRes architecture, polynomial decay policy with Adam optimizer performed significantly better than all other policies, with the exception of polynomial decay with SGD optimizer for the same task (p < 10−4). Based on the FRS, polynomial decay policy with Adam and SGD optimizer occupied the top two positions respectively, but the difference was not statistically significant (p > 0.3). These findings were also validated on the BraTS 2019 Validation dataset which comprised of an additional 125 subjects.

Using the R Package Spatstat to Assess Inhibitory Effects of Microregional Hypoxia on the Infiltration of Cancers of the Head and Neck Region by Cytotoxic T Lymphocytes.

(1) Background: The immune system has physiological antitumor activity, which is partially mediated by cytotoxic T lymphocytes (CTL). Tumor hypoxia, which is highly prevalent in cancers of the head and neck region, has been hypothesized to inhibit the infiltration of tumors by CTL. In situ data validating this concept have so far been based solely upon the visual assessment of the distribution of CTL. Here, we have established a set of spatial statistical tools to address this problem mathematically and tested their performance. (2) Patients and Methods: We have analyzed regions of interest (ROI) of 22 specimens of cancers of the head and neck region after 4-plex immunofluorescence staining and whole-slide scanning. Single cell-based segmentation was carried out in QuPath. Specimens were analyzed with the endpoints clustering and interactions between CTL, normoxic, and hypoxic tumor areas, both visually and using spatial statistical tools implemented in the R package Spatstat. (3) Results: Visual assessment suggested clustering of CTL in all instances. The visual analysis also suggested an inhibitory effect between hypoxic tumor areas and CTL in a minority of the whole-slide scans (9 of 22, 41%). Conversely, the objective mathematical analysis in Spatstat demonstrated statistically significant inhibitory interactions between hypoxia and CTL accumulation in a substantially higher number of specimens (16 of 22, 73%). It showed a similar trend in all but one of the remaining samples. (4) Conclusion: Our findings provide non-obvious but statistically rigorous evidence of inhibition of CTL infiltration into hypoxic tumor subregions of cancers of the head and neck. Importantly, these shielded sites may be the origin of tumor recurrences. We provide the methodology for the transfer of our statistical approach to similar questions. We discuss why versions of the Kcross and pcf.cross functions may be the methods of choice among the repertoire of statistical tests in Spatstat for this type of analysis.