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/

Zendy Plus

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

Zendy Tools

Zendy Open

The rapid development in representation learning techniques such as deepneural networks and the availability of large-scale, well-annotated medicalimaging datasets have to a rapid increase in the use of supervised machinelearning in the 3D medical image analysis and diagnosis. In particular, deepconvolutional neural networks (D-CNNs) have been key players and were adoptedby the medical imaging community to assist clinicians and medical experts indisease diagnosis and treatment. However, training and inferencing deep neuralnetworks such as D-CNN on high-resolution 3D volumes of Computed Tomography(CT) scans for diagnostic tasks pose formidable computational challenges. Thischallenge raises the need of developing deep learning-based approaches that arerobust in learning representations in 2D images, instead 3D scans. In thiswork, we propose for the first time a new strategy to train \emph{slice-level}classifiers on CT scans based on the descriptors of the adjacent slices alongthe axis. In particular, each of which is extracted through a convolutionalneural network (CNN). This method is applicable to CT datasets with per-slicelabels such as the RSNA Intracranial Hemorrhage (ICH) dataset, which aims topredict the presence of ICH and classify it into 5 different sub-types. Weobtain a single model in the top 4% best-performing solutions of the RSNA ICHchallenge, where model ensembles are allowed. Experiments also show that theproposed method significantly outperforms the baseline model on CQ500. Theproposed method is general and can be applied to other 3D medical diagnosistasks such as MRI imaging. To encourage new advances in the field, we will makeour codes and pre-trained model available upon acceptance of the paper.

Slice-level Detection of Intracranial Hemorrhage on CT Using Deep Descriptors of Adjacent Slices