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

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer withlimited treatment options. This research proposes a workflow and deeplearning-based segmentation models to automatically assess tumor-vesselinvolvement, a key factor in determining tumor resectability. Correctassessment of resectability is vital to determine treatment options. Theproposed workflow involves processing CT scans to segment the tumor andvascular structures, analyzing spatial relationships and the extent of vascularinvolvement, which follows a similar way of working as expert radiologists inPDAC assessment. Three segmentation architectures (nnU-Net, 3D U-Net, andProbabilistic 3D U-Net) achieve a high accuracy in segmenting veins, arteries,and the tumor. The segmentations enable automated detection of tumorinvolvement with high accuracy (0.88 sensitivity and 0.86 specificity) andautomated computation of the degree of tumor-vessel contact. Additionally, dueto significant inter-observer variability in these important structures, wepresent the uncertainty captured by each of the models to further increaseinsights into the predicted involvement. This result provides clinicians with aclear indication of tumor-vessel involvement and may be used to facilitate moreinformed decision-making for surgical interventions. The proposed method offersa valuable tool for improving patient outcomes, personalized treatmentstrategies and survival rates in pancreatic cancer.

Segmentation-based Assessment of Tumor-Vessel Involvement for Surgical Resectability Prediction of Pancreatic Ductal Adenocarcinoma