The study by Mirzaei et al provides an overview of data fusion approaches for integrating information from various medical imaging modalities, such as MRI, CT, PET, SPECT, EEG, and MEG, with a specific emphasis on applications in neurological disorders. The research was performed as a systematic overview and review of data fusion approaches emphasizing techniques developed since 2016. Data fusion is important because no single imaging technique, such as structural MRI or EEG, is comprehensive enough to capture all necessary diagnostic information, due to inherent trade-offs between spatial and temporal resolution. Fusion strategies are categorized by the type of integration, leading to multi-view (same modality, different angles), multi-modal (different imaging techniques), and multi-temporal (longitudinal studies over time). Deep learning has also advanced this field, proving instrumental in combining inter-/intra-modal imaging data for applications such as segmentation and lesion detection. A major challenge facing the field is the need to develop algorithms that can easily integrate diverse data types while preserving key features and balancing image quality with computational efficiency. Future research prioritizes enhancing model interpretability through Explainable AI (XAI) techniques and developing real-time processing frameworks to facilitate clinical adoption.