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

Recently deep learning has been witnessing widespread adoption in variousmedical image applications. However, training complex deep neural nets requireslarge-scale datasets labeled with ground truth, which are often unavailable inmany medical image domains. For instance, to train a deep neural net to detectpulmonary nodules in lung computed tomography (CT) images, current practice isto manually label nodule locations and sizes in many CT images to construct asufficiently large training dataset, which is costly and difficult to scale. Onthe other hand, electronic medical records (EMR) contain plenty of partialinformation on the content of each medical image. In this work, we explore howto tap this vast, but currently unexplored data source to improve pulmonarynodule detection. We propose DeepEM, a novel deep 3D ConvNet frameworkaugmented with expectation-maximization (EM), to mine weakly supervised labelsin EMRs for pulmonary nodule detection. Experimental results show that DeepEMcan lead to 1.5\% and 3.9\% average improvement in free-response receiveroperating characteristic (FROC) scores on LUNA16 and Tianchi datasets,respectively, demonstrating the utility of incomplete information in EMRs forimproving deep learningalgorithms.\footnote{https://github.com/uci-cbcl/DeepEM-for-Weakly-Supervised-Detection.git}

DeepEM: Deep 3D ConvNets With EM For Weakly Supervised Pulmonary Nodule Detection