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

Fluorodeoxyglucose (FDG) positron emission tomography (PET) combined withcomputed tomography (CT) is considered the primary solution for detecting somecancers, such as lung cancer and melanoma. Automatic segmentation of tumors inPET/CT images can help reduce doctors' workload, thereby improving diagnosticquality. However, precise tumor segmentation is challenging due to the smallsize of many tumors and the similarity of high-uptake normal areas to the tumorregions. To address these issues, this paper proposes alocalization-to-segmentation framework (L2SNet) for precise tumor segmentation.L2SNet first localizes the possible lesions in the lesion localization phaseand then uses the location cues to shape the segmentation results in the lesionsegmentation phase. To further improve the segmentation performance of L2SNet,we design an adaptive threshold scheme that takes the segmentation results ofthe two phases into consideration. The experiments with the MICCAI 2023Automated Lesion Segmentation in Whole-Body FDG-PET/CT challenge dataset showthat our method achieved a competitive result and was ranked in the top 7methods on the preliminary test set. Our work is available at:https://github.com/MedCAI/L2SNet.

A Localization-to-Segmentation Framework for Automatic Tumor Segmentation in Whole-Body PET/CT Images