Lubomir M. Hadjiiski

Jun 29, 2024 | mdpi.com | Di Sun |Lubomir M. Hadjiiski |John Gormley |Heang-Ping Chan

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess.

Sep 1, 2023 | mdpi.com | Di Sun |Lubomir M. Hadjiiski |John Gormley |Heang-Ping Chan

4. DiscussionAll three descriptors—C, R, and D—showed strength in classifying the test dataset. However, the clinical descriptors demonstrated a higher performance compared to the deep-learning and radiomics descriptors. One of the main factors contributing to this result is that the nomogram model utilized in the clinical descriptors was developed using a larger training set, while the deep-learning and radiomics models used here were trained on a smaller dataset.