Akademik Veri Yönetim Sistemi
Digital Transformation in Healthcare 5.0, Prasenjit Chatterjee,Dilbagh Panchal,Dragan Pamucar,Sharfaraz Ashemkhani Zolfani, Editör, Walter de Gruyter, Inc. , Berlin, ss.307-331, 2024
The application of image processing tools to biomedical images has gained immense attention from researchers worldwide, as such technology can assist practitioners in various decision-making situations. Furthermore, with the increasing value of data in all sectors, including the biomedical healthcare industry, large datasets of biomedical images have become available to data scientists. As a result, successful data-driven artificial intelligence (AI) models have been developed, utilizing biomedical images as input and providing information about patients’ conditions as output, for various applications. These applications encompass diagnosis and disease detection, including cancer prognosis, monitoring, treatment, anatomy and physiology research, molecular imaging, drug development, and clinical trials, as well as biomedical research. As the knowledge base of AI algorithms continues to expand, the potential for groundbreaking advancements in biomedical imaging and its impact on healthcare will be significantly enhanced. In this regard, this chapter provides a review of the most recent literature, offering examples of AI applications in information retrieval from biomedical images. The algorithms used in each example are explicitly emphasized to facilitate the utilization of the most recent and best-performing AI algorithms. In conclusion, while machine learning (ML)-based AI models will remain valuable in most applications, deep learning (DL)-based AI models are expected to become even more prominent in the future, primarily due to the availability of large datasets of biomedical images. By presenting the importance of AI applications in obtaining information from biomedical images through the current literature, this section aims to shed light on researchers working in this dynamic field.