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

The accurate diagnosis on pathological subtypes for lung cancer is ofsignificant importance for the follow-up treatments and prognosis managements.In this paper, we propose self-generating hybrid feature network (SGHF-Net) foraccurately classifying lung cancer subtypes on computed tomography (CT) images.Inspired by studies stating that cross-scale associations exist in the imagepatterns between the same case's CT images and its pathological images, weinnovatively developed a pathological feature synthetic module (PFSM), whichquantitatively maps cross-modality associations through deep neural networks,to derive the "gold standard" information contained in the correspondingpathological images from CT images. Additionally, we designed a radiologicalfeature extraction module (RFEM) to directly acquire CT image information andintegrated it with the pathological priors under an effective feature fusionframework, enabling the entire classification model to generate more indicativeand specific pathologically related features and eventually output moreaccurate predictions. The superiority of the proposed model lies in its abilityto self-generate hybrid features that contain multi-modality image informationbased on a single-modality input. To evaluate the effectiveness, adaptability,and generalization ability of our model, we performed extensive experiments ona large-scale multi-center dataset (i.e., 829 cases from three hospitals) tocompare our model and a series of state-of-the-art (SOTA) classificationmodels. The experimental results demonstrated the superiority of our model forlung cancer subtypes classification with significant accuracy improvements interms of accuracy (ACC), area under the curve (AUC), and F1 score.

Classification of lung cancer subtypes on CT images with synthetic pathological priors