Artificial intelligence (AI) with deep learning models has been widely applied in numerous domains, including medical imaging and healthcare tasks. In the medical field, any judgment or decision is fraught with risk. A doctor will carefully judge whether a patient is sick before forming a reasonable explanation based on the patient’s symptoms and/or an examination. Therefore, to be a viable and accepted tool, AI needs to mimic human judgment and interpretation skills. Specifically, explainable AI (XAI) aims to explain the information behind the black-box model of deep learning that reveals how the decisions are made. This paper provides a survey of the most recent XAI techniques used in healthcare and related medical imaging applications. We summarize and categorize the XAI types, and highlight the algorithms used to increase interpretability in medical imaging topics. In addition, we focus on the challenging XAI problems in medical applications and provide guidelines to develop better interpretations of deep learning models using XAI concepts in medical image and text analysis. Furthermore, this survey provides future directions to guide developers and researchers for future prospective investigations on clinical topics, particularly on applications with medical imaging.

The electroencephalography (EEG) signal is a noninvasive and complex signal that has numerous applications in biomedical fields, including sleep and the brain–computer interface. Given its complexity, researchers have proposed several advanced preprocessing and feature extraction methods to analyze EEG signals. In this study, we analyze a comprehensive review of numerous articles related to EEG signal processing. We searched the major scientific and engineering databases and summarized the results of our findings. Our survey encompassed the entire process of EEG signal processing, from acquisition and pretreatment (denoising) to feature extraction, classification, and application. We present a detailed discussion and comparison of various methods and techniques used for EEG signal processing. Additionally, we identify the current limitations of these techniques and analyze their future development trends. We conclude by offering some suggestions for future research in the field of EEG signal processing.

Radiomics analysis has had remarkable progress along with advances in medical imaging, most notability in central nervous system malignancies. Radiomics refers to the extraction of a large number of quantitative features that describe the intensity, texture and geometrical characteristics attributed to the tumor radiographic data. These features have been used to build predictive models for diagnosis, prognosis, and therapeutic response. Such models are being combined with clinical, biological, genetics and proteomic features to enhance reproducibility. Broadly, the four steps necessary for radiomic analysis are: (1) image acquisition, (2) segmentation or labeling, (3) feature extraction, and (4) statistical analysis. Major methodological challenges remain prior to clinical implementation. Essential steps include: adoption of an optimized standard imaging process, establishing a common criterion for performing segmentation, fully automated extraction of radiomic features without redundancy, and robust statistical modeling validated in the prospective setting. This review walks through these steps in detail, as it pertains to high grade gliomas. The impact on precision medicine will be discussed, as well as the challenges facing clinical implementation of radiomic in the current management of glioblastoma.

Due to the fast advancement of artificial intelligence (AI), centralized-based models have become critical for healthcare tasks like in medical image analysis and human behavior recognition. Although these models exhibit suitable performance, they are frequently constrained by privacy concerns. To attenuate this, a centralized learning strategy cannot be used in cases where there is a risk of data privacy breach, particularly in healthcare centers. Federated learning (FL) is a technique that allows for training a global model without sharing data by training distributed local models and aggregating them. By implementing FL throughout the training process, we can obtain a model with comparable generalization abilities to centralized learning while maintaining data privacy. This survey provides an introduction to the fundamental concepts and categories of FL, highlights the limitations of the centralized healthcare model, and discusses how FL can address these constraints. We also provide a detailed overview of the healthcare applications using FL models, along with commonly used evaluation metrics and public data sets. In this context, we have implemented a case study to demonstrate how FL can be applied in the healthcare field. Furthermore, we outline the key challenges and future trends in FL.

Glioma are the most common type of malignant brain tumor, with glioblastoma (GBM) representing the most common and most lethal type of glioma. Surgical resection followed by radiotherapy and chemotherapy using the alkylating agent Temozolomide (TMZ) remain the mainstay of treatment for glioma. While this multimodal regimen is sufficient to temporarily eliminate the bulk of the tumor mass, recurrence is inevitable and often poses major challenges for clinical management due to treatment resistance and failure to respond to targeted therapies. Improved tumor profiling capacity has enabled characterization of the genomic landscape of gliomas with the overarching goal to identify clinically relevant subtypes and inform treatment decisions. Increased tumor mutational load has been shown to correlate with higher levels of neoantigens and is indicative of the potential to induce a durable response to immunotherapy. Following treatment with TMZ, a subset of glioma has been identified to recur with increased tumor mutational load. These hypermutant recurrent glioma represent a subtype of recurrence with unique molecular vulnerabilities. In this review, we will elaborate on the current knowledge regarding the evolution of hypermutation in gliomas and the potential therapeutic opportunities that arise with TMZ-induced hypermutation in gliomas.

Background: Novel radiomic features are enabling the extraction of biological data from routine sequences of MRI images. This study’s purpose was to establish a new model, based on the joint intensity matrix (JIM), to predict the Gleason score (GS) of prostate cancer (PCa) patients. Methods: A retrospective dataset comprised of the diagnostic imaging data of 99 PCa patients was used, extracted from The Cancer Imaging Archive’s (TCIA) T2-Weighted (T2-WI) and apparent diffusion coefficient (ADC) images. Radiomic features derived from JIM and the grey level co-occurrence matrix (GLCM) were extracted from the reported tumor locations. The Kruskal-Wallis test and Spearman’s rank correlation identified features related to the GS. The Random Forest classifier model was implemented to identify the best performing signature of JIM and GLCM radiomic features to predict for GS. Results: Five JIM-derived features: contrast, homogeneity, difference variance, dissimilarity, and inverse difference were independent predictors of GS (p < 0.05). Combined JIM and GLCM analysis provided the best performing area-under-the-curve, with values of 78.40% for GS ≤ 6, 82.35% for GS = 3 + 4, and 64.76% for GS ≥ 4 + 3. Conclusion: This retrospective study produced a novel predictive model for GS by the incorporation of JIM data from standard diagnostic MRI images.