English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generalizability is a concern when applying a deep learning (DL) modeltrained on one dataset to other datasets. Training a universal model that worksanywhere, anytime, for anybody is unrealistic. In this work, we demonstrate thegeneralizability problem, then explore potential solutions based on transferlearning (TL) by using the cone-beam computed tomography (CBCT) to computedtomography (CT) image conversion task as the testbed. Previous works haveconverted CBCT to CT-like images. However, all of those works studied only oneor two anatomical sites and used images from the same vendor's scanners. Here,we investigated how a model trained for one machine and one anatomical siteworks on other machines and other sites. We trained a model on CBCT imagesacquired from one vendor's scanners for head and neck cancer patients andapplied it to images from another vendor's scanners and for other diseasesites. We found that generalizability could be a significant problem for thisparticular application when applying a trained DL model to datasets fromanother vendor's scanners. We then explored three practical solutions based onTL to solve this generalization problem: the target model, which is trained ona target domain from scratch; the combined model, which is trained on bothsource and target domain datasets from scratch; and the adapted model, whichfine-tunes the trained source model to a target domain. We found that whenthere are sufficient data in the target domain, all three models can achievegood performance. When the target dataset is limited, the adapted model worksthe best, which indicates that using the fine-tuning strategy to adapt thetrained model to an unseen target domain dataset is a viable and easy way toimplement DL models in the clinic.

Generalizability issues with deep learning models in medicine and their  potential solutions: illustrated with Cone-Beam Computed Tomography (CBCT) to  Computed Tomography (CT) image conversion