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

Acute appendicitis characterized by a painful inflammation of the vermiformappendix is one of the most common surgical emergencies. Localizing theappendix is challenging due to its unclear anatomy amidst the complexcolon-structure as observed in the conventional CT views, resulting in atime-consuming diagnosis. End-to-end learning of a convolutional neural network(CNN) is also not likely to be useful because of the negligible size of theappendix compared with the abdominal CT volume. With no prior computationalapproaches to the best of our knowledge, we propose the first computerizedautomation for acute appendicitis diagnosis. In our approach, we utilize areinforcement learning agent deployed in the lower abdominal region to obtainthe appendix location first to reduce the search space for diagnosis. Then, weobtain the classification scores (i.e., the likelihood of acute appendicitis)for the local neighborhood around the localized position, using a CNN trainedonly on a small appendix patch per volume. From the spatial representation ofthe resultant scores, we finally define a region of low-entropy (RLE) to choosethe optimal diagnosis score, which helps improve the classification accuracyshowing robustness even under high appendix localization error cases. In ourexperiment with 319 abdominal CT volumes, the proposed RLE-based decision withprior localization showed significant improvement over the standard CNN-baseddiagnosis approaches.

Reinforcement Learning-based Automatic Diagnosis of Acute Appendicitis in Abdominal CT