Diagnostic performance of radiomics and machine learning algorithms in differentiating grade 2-3 gliomas from glioblastomas among adult-type diffuse gliomas.

Accurate brain tumor classification is crucial for advancing diagnostic precision and streamlining treatment strategies. This chapter presents a brain tumor image classification methodology leveraging deep learning techniques, specifically convolutional neural networks (CNNs). Our method exploits CNNs to autonomously extract salient features from medical imaging data, enabling the differentiation of tumor types, including gliomas, meningiomas, and metastatic tumors. The architecture of our CNN comprises several convolutional layers, pooling layers, and fully connected layers designed to capture and interpret complex patterns in brain tumor imagery effectively. We enhance the model's performance through comprehensive data augmentation and rigorous hyperparameter tuning, achieving significant improvements in classification accuracy. Extensive experimental evaluations demonstrate the efficacy of our approach, underscoring its potential to significantly enhance diagnostic processes by providing accurate, automated tumor classification. The advancements detailed herein contribute to the broader application of machine learning in medical imaging, promising substantial impacts on patient care and treatment optimization.

Subtype classification of gastric spindle cell tumors in whole slide images.

Unraveling Round Cell Sarcomas: A Contemporary Diagnostic Guide Beyond Ewing Sarcoma.

Optimising Brain Tumour Segmentation and Classification with an Enhanced CNN Model on the BraTS-GOAT 2024 Dataset

Metabolic and epigenetic dysregulation in IDH1/2-mutant gliomas: A microglial-mediated mechanism of blood-brain barrier disruption.

Importance of hematological ratios in dogs with ovarian tumors.

Differences in advanced radiologic features of glioma subtypes under the 2021 WHO classification of tumors of the central Nervous system.

Comparative histologic survey and transcriptomic investigation into canine prostate carcinoma.

Vision differential Transformer for brain tumor classification

ShallowMRI: A novel lightweight CNN with novel attention mechanism for Multi brain tumor classification in MRI images

Research on brain cancer indicates that the severity of the disease varies according to tumor types and their specific characteristics. Accurate identification of tumor locations, extraction of distinctive features, and correct classification are of critical importance. In this study, brain tumors were detected using three different deep learning models developed on a dataset created within the scope of the TBP project and seven additional public datasets. All three models are based on Convolutional Neural Network (CNN) architectures for tumor detection. The first model is a baseline CNN; the second incorporates the Genetic Algorithm (GA), a traditional approach for hyperparameter optimization; and the third combines the CNN with the Slime Mold Algorithm (SMA), a recently proposed metaheuristic technique. Hybrid methods that achieve higher performance than baseline CNNs in binary tumor classification are presented and discussed. Experimental results were comparatively analyzed and visualized through graphs and tables. Compared to other CNN-based studies in the literature, the proposed approach improved accuracy by approximately 1–10%. Similarly, when compared with other machine learning (ML) and deep learning (DL) algorithms, excluding CNNs, performance gains ranged between 1% and 13%. The CNN+SMA model achieved the most consistent and notable improvements across all datasets. Although hybrid models generally require more computational resources due to their complex training structures, they tend to achieve higher accuracy and facilitate parameter optimization more effectively than single-model approaches.

MB-MSAT-Net: A Multi-Branch Multi-Scale Attention Framework with EFO and TabNet for Accurate and Interpretable Brain Tumor Classification

Accurate Brain Tumor Classification Using GoogLe Net and Extreme Learning Machine (ELM) With Multiple Features

Effective and efficient brain tumor classification from MRI scans is of critical importance as medical diagnostics in detecting early signs of the disease and treating the disease as early as possible. The focus of this paper is to propose a novel method to classify the brain tumors into 4 types of glioma, meningioma, notumor, and pituitary tumors using a combination of RNN based LSTM with PCA and SVM. To extract features from the MRI images, we use VGG19 a pre trained Convolutional Neural Network (CNN) and because the data is sequential, LSTM is utilized to process the sequential nature of the data so that the model learns the temporal relationship between multiple MRI slices. They are then applied to an SVM classifier with Principal Component Analysis (PCA) for dimensionality reduction and improved efficiency for classification. To further enhance model robustness, we combine three prominent brain MRI datasets, ensuring a diverse set of training examples. The experimental results show that the proposed LSTM-based SVM model gives 97% accuracy in all the tumor categories with high precision, recall and F1 scores. The model’s performance dominates the existing CNN based models especially in term of generalization where training and validation accuracy exhibit little change implying good overfitting prevention. Two main contributions are identified to address the problem with a hybrid approach consisting of both Deep Learning and traditional ML techniques: (a) both methods achieve high accuracy and (b) results are interpretable and scalable.

Background and objectives: The fifth edition of the WHO Classification of Tumors of the Central Nervous System divides grade 4 diffuse glioma based on IDH1 mutation in grade 4 astrocytoma, IDH-mutant and glioblastoma, IDH-wild type tumors. This study aimed to evaluate the IDH1 status in grade 4 diffuse glioma as well as its correlation with clinicopathological features and patient survival. To our knowledge, no Tunisian studies on the molecular profile of diffuse glioma have yet been published. Methods: This is a retrospective study including all cases of adult, grade 4 diffuse glioma collected in the pathology department of Habib Bourguiba hospital. Results: A total of 67 patients were included in the final analysis. The expression of IDH1 was positive in 22 cases (32%). IDH1-positive tumors were classified as grade 4 astrocytoma, IDH1-mutant while, 45 IDH1-negative tumors were classified as glioblastoma, IDH1-wild type tumors (68%). IDH1 expression was correlated with younger age (≤ 40 years old), frontal location, complete surgical resection and well-defined borders. IDH1-positive tumors were associated significantly with better prognosis. The 1-year overall survival (OS) for grade 4 astrocytoma, IDH1-mutant was 86% compared with 8% in glioblastoma, IDH1-wild type (p=0.008). Conclusion: Our study investigated IDH1 expression in grade 4 diffuse glioma and proved that grade 4 astrocytoma, IDH1 positive tumors displayed different characteristics with a more favorable outcome compared to glioblastoma, IDH1 negative. Thus, evaluation of IDH1 mutation should be standardized routinely not only as diagnostic marker but also to refine the prognostic classification of these tumors.

Abstract The term “atypical spindle cell/pleomorphic lipomatous tumor” was introduced in the WHO Classification of Soft Tissue Tumors in 2020. This tumor is an adipocytic neoplasm of benign or low-grade category, is clinically indolent, has poorly circumscribed margins, and composed of mature adipocytes, lipoblasts, atypical spindle-shaped cells, and multinucleated cells. A 75-year-old male presented with a paratesticular mass. On microscopic examination, the tumor showed a mixture of two components—adipose and fibrous tissue components—which blended with each other along with scattered atypical giant cells. Immunohistochemically, smooth muscle actin showed diffuse positivity in the spindle cells. S100 was negative in the spindle cells and giant cells but was positive in the nuclei of some adipocytes. The Ki-67 index was only 5%. CD34 and desmin were positive in the blood vessel walls—in endothelial cells and muscle layer respectively—and negative in the giant cells. Immunohistochemistry (IHC) with MDM2 (murine double minute 2) and Rb (retinoblastoma) was negative, while CDK4 (cyclin-dependent kinase 4) was variably positive in the nuclei of the spindle cells. The spectrum of adipocytic tumors that show overlapping morphologic features may pose diagnostic difficulty. Precise diagnosis of ASPLT is important, as it can be misdiagnosed as an intermediate grade or malignant lipomatous tumor. A tumor can be diagnosed as ASPLT when it is composed of a heterogeneous mixture of adipocytes, spindle cells with focal atypia, and multinucleated cells. Lipoblasts are not mandatory for diagnosis. IHC with MDM2, Rb1, Ki67, and molecular testing is helpful in differentiating benign ASPLT from other entities and in ensuring a better prognosis. CDK4 is not found to be useful.

Meningiomas are the most common primary brain tumors in the central nervous system. Although numerous studies in the literature have addressed multiclass brain tumor classification that includes the meningioma class, the method proposed in this study aims to improve meningioma detection performance by employing binary classification instead of multiclass classification. The proposed method enhances classification performance by implementing a three-step classification process. This study utilizes the Nickparvar dataset, which contains brain Magnetic Resonance (MR) images of meningioma, other tumor types, and tumor-free cases. We employ k-means clustering for tumor segmentation, GLCM and contour features for feature extraction, and CatBoost for classification (meningioma vs. non-meningioma). The performance of the proposed method is evaluated using accuracy, precision, recall, negative predictive value, F1-score, and specificity, achieving values of 0.96, 0.93, 0.89, 0.97, 0.91, and 0.98, respectively. Although deep learning methods demonstrate high performance, machine learning approaches require less training data and computational resources. Therefore, machine learning methods represent a more suitable choice for clinical environments with limited hardware capabilities. The results are comparable to those of recent deep learning studies, indicating that the proposed method achieves performance close to deep learning approaches while retaining the advantages of machine learning for meningioma detection.

Endometrial stromal tumors (ESTs) are the second most common type of uterine mesenchymal tumors and endometrial stromal nodule (ESN) is a benign neoplasm within this category. ESNs can exhibit smooth muscle differentiation, epithelial patterns, or fibromyxoid stroma, which can complicate differential diagnosis. In this report, we present a rare case of ESN with featuring extensive smooth muscle differentiation and focal myxoid areas. Grossly, the tumor was intramural, well-circumscribed, and cystic. Histologically, the tumor consisted of cellular areas, myxoid areas, and extensive collagen roset formation. Immunohistochemical analysis showed that, the tumor cells were diffusely positive for B-catenin and WT-1, focally positive for CD56, smooth muscle marker, CAM5.2, PanCK and CD10. ESN with smooth muscle differentiation and collagenous rosettes should be considered in the differential diagnosis of intracavitary and intramural uterine mesenchymal tumors. Both fibromyxoid stroma and extensive smooth muscle differentiation have been documented in ESNs. Recognizing this morphologic variant of ESN is crucial for accurate tumor classification.

DNA methylation and copy number variation (CNV) profiling are essential for diagnostic tumor classification. Current methods are complex and require considerable bioinformatics expertise, limiting clinical implementation. Mepylome ( https://mepylome.readthedocs.io ), an efficient open‐source Python‐based toolkit for microarray‐based DNA methylation and CNV analysis, resolves these challenges. It enables, through artificial intelligence, local tumor methylome comparison with customizable reference sets. Mepylome provides an intuitive graphical interface, supports supervised and unsupervised learning techniques, and processes various Illumina methylation array types. Users can examine their own data, add references from any source, perform analyses including dimension reduction, individual and multisample CNV plotting, and build supervised learning models to augment diagnostic classification. Tested on Ubuntu Linux and Windows with WSL, Mepylome runs on most modern hospital computers, including macOS. Performance is demonstrated on previously published datasets, including 363 salivary gland tumors, 1077 soft tissue tumor specimens, and a multisource collection of 1644 squamous cell carcinomas, reproducing classification accuracies and visualizations. The trained soft tissue classifier is validated on an independent in‐house set. Mepylome runs up to 65 times faster than comparable tools, enabling direct point‐of‐care application and substantially simplifying and accelerating DNA methylation and CNV analysis in clinical settings.