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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Paranasal anomalies are commonly discovered during routine radiologicalscreenings and can present with a wide range of morphological features. Thisdiversity can make it difficult for convolutional neural networks (CNNs) toaccurately classify these anomalies, especially when working with limiteddatasets. Additionally, current approaches to paranasal anomaly classificationare constrained to identifying a single anomaly at a time. These challengesnecessitate the need for further research and development in this area.  In this study, we investigate the feasibility of using a 3D convolutionalneural network (CNN) to classify healthy maxillary sinuses (MS) and MS withpolyps or cysts. The task of accurately identifying the relevant MS volumewithin larger head and neck Magnetic Resonance Imaging (MRI) scans can bedifficult, but we develop a straightforward strategy to tackle this challenge.Our end-to-end solution includes the use of a novel sampling technique that notonly effectively localizes the relevant MS volume, but also increases the sizeof the training dataset and improves classification results. Additionally, weemploy a multiple instance ensemble prediction method to further boostclassification performance. Finally, we identify the optimal size of MS volumesto achieve the highest possible classification performance on our dataset.  With our multiple instance ensemble prediction strategy and samplingstrategy, our 3D CNNs achieve an F1 of 0.85 whereas without it, they achieve anF1 of 0.70.  We demonstrate the feasibility of classifying anomalies in the MS. We proposea data enlarging strategy alongside a novel ensembling strategy that proves tobe beneficial for paranasal anomaly classification in the MS.

Multiple Instance Ensembling For Paranasal Anomaly Classification In The Maxillary Sinus