Recent Advances in Deep Learning and Medical Imaging for Head and Neck Cancer Treatment: MRI, CT, and PET Scans.
Autor: | Illimoottil, Mathew, Ginat, Daniel |
---|---|
Předmět: |
HEAD & neck cancer diagnosis
HEAD & neck cancer treatment DEEP learning MEDICAL quality control MAGNETIC resonance imaging HEAD & neck cancer ARTIFICIAL intelligence DIAGNOSTIC imaging POSITRON emission tomography QUALITY assurance COMPUTED tomography DECISION making in clinical medicine ARTIFICIAL neural networks ALGORITHMS |
Zdroj: | Cancers; Jul2023, Vol. 15 Issue 13, p3267, 15p |
Abstrakt: | Simple Summary: Deep learning techniques have significant potential in head and neck cancer imaging, particularly in tumor detection, segmentation, and outcome prediction using magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET) scans. Advanced deep learning methods, such as convolutional autoencoders, generative adversarial networks (GANs), and transformer models, have further enhanced imaging capabilities. Comparing deep learning and traditional techniques and the advantages and limits of each reveals their complementary roles in cancer management. Integrating radiogenomics with deep learning models promises further advancements in personalized care. However, challenges such as standardization, data quality, model overfitting, and computational requirements persist. Addressing these issues, integrating multimodal and temporal information, enhancing explainability, and conducting clinical validation are crucial for implementing deep learning models in head and neck cancer diagnosis and treatment. Overcoming these obstacles will pave the way for improved patient outcomes and personalized treatment strategies in head and neck cancer management. Deep learning techniques have been developed for analyzing head and neck cancer imaging. This review covers deep learning applications in cancer imaging, emphasizing tumor detection, segmentation, classification, and response prediction. In particular, advanced deep learning techniques, such as convolutional autoencoders, generative adversarial networks (GANs), and transformer models, as well as the limitations of traditional imaging and the complementary roles of deep learning and traditional techniques in cancer management are discussed. Integration of radiomics, radiogenomics, and deep learning enables predictive models that aid in clinical decision-making. Challenges include standardization, algorithm interpretability, and clinical validation. Key gaps and controversies involve model generalizability across different imaging modalities and tumor types and the role of human expertise in the AI era. This review seeks to encourage advancements in deep learning applications for head and neck cancer management, ultimately enhancing patient care and outcomes. [ABSTRACT FROM AUTHOR] |
Databáze: | Complementary Index |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |