Correlation between Multimodal Radiographic Features and Preoperative Seizure in Brain Tumor using Machine Learning

Gamma knife treatment is a clinically effective, safe, and cost-effective adjunctive therapy for primary malignant brain tumors. For most brain metastases, radiosurgery is the treatment of choice and will result in effective tumor control in more than 90% of treated tumors.

Role of mass effect, tumor volume and peritumoral edema volume in the differential diagnosis of primary brain tumor and metastasis

Introduction. Tumor-related epilepsy is a prevalent condition in patients with gliomas. Accurate prediction of epilepsy is crucial for early treatment. This study aimed to evaluate the novel application of the eXtreme Gradient Boost (XGBoost) machine learning (ML) algorithm into a radiomics model predicting preoperative tumor-related epilepsy (PTRE). Its performance was compared with 4 conventional ML algorithms, including the least absolute shrinkage and selection operator (LASSO), elastic net, random forest, and support vector machine.Methods.This study used four magnetic resonance imaging (MRI) images consisting of four sequences (T1-weighted [T1W], T1-weighted contrast [T1WC], T2-weighted [T2W], and T2-weighted fluid-attenuated inversion recovery [T2W FLAIR]) acquired from 74 glioma patients, 30 with PTRE and 44 without PTRE. 394 radiomics features were extracted from the MRI scans usingPyradiomics, alongside 12 clinical features from the medical records. The ML algorithms were mixed and matched to create 20 radiomics models with two stages for: (1) feature selection and (2) prediction of PTRE. Nested cross-validation was used to tune the algorithms and select the stable features.Results.The XGBoost radiomics model demonstrated the second-highest balanced accuracy and F1-score of 0.81 ± 0.01 and 0.80 ± 0.01 respectively. It also achieved the highest recall of 0.81 ± 0.02. It used mostly textural radiomics features from the T1W, T2W and T2W FLAIR sequences to make the predictions.Conclusion.This study demonstrates that XGBoost is a viable alternative to conventional ML algorithms for developing a radiomics model to predict PTRE, as the model produced from XGBoost had among the highest metrics. XGBoost selected features with a higher predictive value than other models. The features selected by XGBoost were more stable, which is a useful property for radiomics analysis. Features selected from multiple MRI sequences were important in the model's decision.

Accurate detection and classification of brain tumors are essential for timely diagnosis and effective treatment planning. This study presents an integrated framework leveraging both machine learning (ML) and deep learning (DL) models for brain tumor detection and classification using MRI images. Two publicly available datasets are utilized: one for binary classification (tumor vs. no tumor) and another for multiclass classification (glioma, meningioma, and pituitary tumors). Comprehensive preprocessing steps, including resizing, feature extraction using the Gray Level Co-occurrence Matrix (GLCM), and feature selection via Chi-square testing, were employed to optimize the dataset for modeling. Machine learning models such as Decision Trees, K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and AdaBoost were compared with deep learning architectures like Convolutional Neural Networks (CNNs) and the pre-trained VGG16 model. Hyperparameter optimization techniques, including grid search and the Adam optimizer, were used to enhance model performance. The models were evaluated using metrics such as accuracy, precision, recall, F1-score, Mean Squared Error (MSE), and Mean Absolute Error (MAE). Results indicate that the VGG16 model consistently outperformed other approaches, achieving high validation accuracy. This study highlights the potential of integrating ML and DL techniques for accurate and efficient brain tumor detection and classification, offering valuable tools for medical diagnostics.

Brain tumours are considered one of the deadliest tumours in humans and have a low survival rate due to their heterogeneous nature. Several types of benign and malignant brain tumours need to be diagnosed early to administer appropriate treatment. Magnetic resonance (MR) images provide details of the brain’s internal structure, which allow radiologists and doctors to diagnose brain tumours. However, MR images contain complex details that require highly qualified experts and a long time to analyse. Artificial intelligence techniques solve these challenges. This paper presents four proposed systems, each with more than one technology. These techniques vary between machine, deep and hybrid learning. The first system comprises artificial neural network (ANN) and feedforward neural network (FFNN) algorithms based on the hybrid features between local binary pattern (LBP), grey-level co-occurrence matrix (GLCM) and discrete wavelet transform (DWT) algorithms. The second system comprises pre-trained GoogLeNet and ResNet-50 models for dataset classification. The two models achieved superior results in distinguishing between the types of brain tumours. The third system is a hybrid technique between convolutional neural network and support vector machine. This system also achieved superior results in distinguishing brain tumours. The fourth proposed system is a hybrid of the features of GoogLeNet and ResNet-50 with the LBP, GLCM and DWT algorithms (handcrafted features) to obtain representative features and classify them using the ANN and FFNN. This method achieved superior results in distinguishing between brain tumours and performed better than the other methods. With the hybrid features of GoogLeNet and hand-crafted features, FFNN achieved an accuracy of 99.9%, a precision of 99.84%, a sensitivity of 99.95%, a specificity of 99.85% and an AUC of 99.9%.

Nitrogen (N) concentration is a significant parameter to check the status of health in rice crop. Nitrogen (N) plays an essential role in the growth and productivity of rice plant. This paper proposes a convolutional neural network (CNN) based approach for prediction of rice nitrogen deficiency. The pre-trained CNN architecture is modified to improve the classification accuracy with the inclusion of pre-eminent classifier like support vector machine (SVM) by replacing the last output layer of CNN. Here, six leading deep learning architectures such as ResNet-18, ResNet-50, GoogleNet, AlexNet, VGG-16 and VGG-19 with SVM are used for prediction of nitrogen deficiency with 5790 number image samples. The performance of each classifier is measured and compared in terms of accuracy, sensitivity, specificity, false positive rate (FPR) and F1 score. Again, the statistical analysis is performed to choose the better classification model considering the results of 100 independent simulations. The statistical analysis confirmed the superiority of ResNet-50+SVM than the other five CNN-based classification models with an accuracy of 99.84%. Besides, the accuracy score of CNN classification models is compared with other traditional image classification models such as bag-of-feature, colour feature + SVM, local binary patterns (LBP) + SVM, histogram of oriented gradients (HOG)+SVM and Gray Level Co-occurrence Matrix (GLCM)+SVM.

A novel extended Kalman filter with support vector machine based method for the automatic diagnosis and segmentation of brain tumors

Classifying brain tumors in magnetic resonance images (MRI) is a critical endeavor in medical image processing, given the challenging nature of automated tumor recognition. The variability and complexity in the location, size, shape, and texture of these lesions, coupled with the intensity similarities between brain lesions and normal tissues, pose significant hurdles. This study focuses on the importance of brain tumor detection and its challenges within the context of medical image processing. Presently, researchers have devised various interventions aimed at developing models for brain tumor classification to mitigate human involvement. However, there are limitations on time and cost for this task, as well as some other challenges that can identify tumor tissues. This study reviews many publications that classify brain tumors. Mostly employed supervised machine learning algorithms like support vector machine (SVM), random forest (RF), Gaussian Naive Bayes (GNB), k-Nearest Neighbors (K-NN), and k-means and some researchers employed convolutional neural network methods, transfer learning, deep learning, and ensemble learning. Every classification algorithm aims to provide an accurate and effective system, allowing for the fastest and most precise tumor detection possible. Usually, a pre-processing approach is employed to assess the system's accuracy; other techniques, such as the Gabor discrete wavelet transform (DWT), Local Binary Pattern (LBP), Gray Level Co-occurrence Matrix (GLCM), Principal Component Analysis (PCA), Scale-Invariant Feature Transform (SIFT) and the descriptor histogram of oriented gradients (HOG). In this study, we examine prior research on feature extraction techniques, discussing various classification methods and highlighting their respective advantages, providing statistical analysis on their performance.

The aim of this study was to evaluate the effect of cervical cancer volume on PET/magnetic resonance (MR) texture heterogeneity. We retrospectively analyzed the PET/MR images of 138 patients with pathologically diagnosed cervical squamous cell carcinoma, including 50 patients undergoing surgery and 88 patients receiving concurrent chemoradiotherapy. Fluorodeoxyglucose 18 (18FDG)-PET/MR examination were performed for each patient before treatment, and the PET and MR texture analysis were undertaken. The texture features of the tumor based on gray-level co-occurrence matrices were extracted, and the correlation between tumor texture features and volume parameters was analyzed using Spearman's rank correlation coefficient. Finally, the variation trend of tumor texture heterogeneity was analyzed as tumor volumes increased. PET texture features were highly correlated with metabolic tumor volume (MTV), including entropy-log2, entropy-log10, energy, homogeneity, dissimilarity, contrast, correlation, and the correlation coefficients (rs) were 0.955, 0.955, -0.897, 0.883, -0.881, -0.876, and 0.847 (P < 0.001), respectively. In the range of smaller MTV, the texture heterogeneity of energy, entropy-log2, and entropy-log10 increases with an increase in tumor volume, whereas the texture heterogeneity of homogeneity, dissimilarity, contrast, and correlation decreases with an increase in tumor volume. Only homogeneity, contrast, correlation, and dissimilarity had high correlation with tumor volume on MRI. The correlation coefficients (rs) were 0.76, -0.737, 0.644, and -0.739 (P < 0.001), respectively. The texture heterogeneity of MRI features that are highly correlated with tumor volume decreases with increasing tumor volume. In the small tumor volume range, the heterogeneity variation trend of PET texture features is inconsistent as the tumor volume increases, but the variation trend of MRI texture heterogeneity is consistent, and MRI texture heterogeneity decreases as tumor volume increases. These results suggest that MRI is a better imaging modality when compared with PET in determining tumor texture heterogeneity in the small tumor volume range.

Radiotherapy target volume definition in newly diagnosed high grade glioma using 18F-FET PET imaging and multiparametric perfusion MRI: A prospective study (IMAGG)

Tumor.

Correctly classifying the brain tumor images is a matter of utmost importance for protecting the lives of brain cancer patients. The individual infliction of deep learning and machine learning algorithms has shown a diminutive impact on accurate brain tumor classification. This study goals to create a hybrid classifier based on deep learning (DL) and machine learning (ML) algorithms to differentiate MRI images of brain tumors into multiple categories such as meningioma, glioma, and pituitary. A simple convolutional neural network (CNN) based DL model consisting of ten layers is developed to extract precise features of tumors. Then various ML algorithms such as support vector machine (SVM), K-nearest neighbors (KNN), random forest (RF), gaussian naive bayes (G-NB), decision tree (DT), logistic regression (LR), and linear discrimination (LD) are utilized to enhance the accurate classification rate than normally used softmax classifier. The effectiveness of the modeled hybrid classifiers is evaluated based on four verification statistical metrics such as accuracy, precision, recall, and F1-score. The results exhibit that among the seven several hybrid classifiers, the CNN-KNN classifier shows an improved testing performance in terms of classifying brain tumor images with 99.45% accuracy, 99.40% accuracy, 99.34% recall, and 99.37% F1-score. Among seven different classifiers, the CNN-KNN classifier outperformed other existing state-of-art methods with an improved classification accuracy of 1.45%.

Fluid attenuated inversion recovery (FLAIR) MRI sequences have become an indispensible tool for defining the malignant boundary in patients with brain tumors by nulling the signal contribution from cerebrospinal fluid allowing both regions of edema and regions of non-enhancing, infiltrating tumor to become hyperintense on resulting images. In the current study we examined the utility of a three-dimensional double inversion recovery (DIR) sequence that additionally nulls the MR signal associated with white matter, implemented either pre-contrast or post-contrast, in order to determine whether this sequence allows for better differentiation between tumor and normal brain tissue. T1- and T2-weighted, FLAIR, dynamic susceptibility contrast (DSC)-MRI estimates of cerebral blood volume (rCBV), contrast-enhanced T1-weighted images (T1+C), and DIR data (pre- or post-contrast) were acquired in 22 patients with glioblastoma. Contrast-to-noise (CNR) and tumor volumes were compared between DIR and FLAIR sequences. Line profiles across regions of tumor were generated to evaluate similarities between image contrasts. Additionally, voxel-wise associations between DIR and other sequences were examined. Results suggested post-contrast DIR images were hyperintense (bright) in regions spatially similar those having FLAIR hyperintensity and hypointense (dark) in regions with contrast-enhancement or elevated rCBV due to the high sensitivity of 3D turbo spin echo sequences to susceptibility differences between different tissues. DIR tumor volumes were statistically smaller than tumor volumes as defined by FLAIR (Paired t test, P = 0.0084), averaging a difference of approximately 14 mL or 24 %. DIR images had approximately 1.5× higher lesion CNR compared with FLAIR images (Paired t test, P = 0.0048). Line profiles across tumor regions and scatter plots of voxel-wise coherence between different contrasts confirmed a positive correlation between DIR and FLAIR signal intensity and a negative correlation between DIR and both post-contrast T1-weighted image signal intensity and rCBV. Additional discrepancies between FLAIR and DIR abnormal regions were also observed, together suggesting DIR may provide additional information beyond that of FLAIR.

Background Distinguish between radiation necrosis (RN) and tumor progression, in patients with irradiated primary or metastatic brain tumors, is a diagnostic challenge. Also the use of new MRI sequences, like diffusion, perfusion-weighted and spectroscopy, or PET with new amino acid tracers, is not always able to differentiate these two entities.To overcome this crucial problem, encouraging results have been obtained using the analysis of delayed contrast extravasation MRI to calculate high resolution maps, called “treatment response assessment maps” (TRAMs). Aim of this exploratory analysis is to assess TRAM ability in differentiate between radiation effect and tumor progression in a small cohort of brain tumor patients treated with radiation therapy (RT). Material and Methods Thirty-four patients irradiated for primary and metastatic brain tumors were evaluated. 12 patients have primary brain tumors, 22 patients have brain metastases from different solid tumors. Distinguish by histological subtypes and type of treatment, the 12 patients with primary brain tumors were: 8 glioblastoma, 2 anaplastic astrocitoma, 1 pleomorphic xanthoastrocytoma WHO grade II, and 1 anaplastic xanthoastrocytoma WHO grade III, treated with surgery followed by RT and concomitant and\or adjuvant chemotherapy with temozolomide. Among brain metastatic patients, primary tumor was: 18 non-small cell lung cancer, 2 malignant melanoma, 1 breast cancer and 1 renal cell carcinoma. All of them were treated with stereotactic radiosurgery at the dose of 20-24Gy in 1fraction, or with hypofractionated stereotactic radiotherapy at the dose of 27-30Gy in 3fractions. All images were uploaded and elaborate into the image workstation ([Brainlab AG, Olof-Palme-Straße 9, 81829 Munich]). TRAMs were calculated by subtracting T1 MRI images acquired 5 minutes after contrast injection from the T1 MRI images acquired 60-105 minutes later. On TRAMs, radiation effects appeared as red areas whereas persistent tumoral lesion appeared as blue areas. Results From February 2021, 34 patients have been evaluated, in a prospective study, with this novel MRI modality. During their follow-up, 13patients (38%) showed a clinicoradiologic suspicion of a persistent tumoral lesion or progressive disease, and 21 (62%) a suspicion of RN. For 14patients a brain MET-PET has been performed. TRAMs analysis have shown a fair agreement with clinicoradiologic diagnosis, perfusion-weighted MRI, and PET imaging. Moreover, 7 patients underwent surgical resection, with histopathological confirm of persistent disease in 4 and radionecrosis in 3. Conclusion These preliminary results show the ability of TRAMs evaluation in distinguish between RN and progressive disease. The recruitment of new patients continues, and further evaluations are ongoing to evaluate sensitivity and positive predictive value of TRAMs analysis.

Prostate MRI: Who, when, and how? Report from a UK consensus meeting