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 cancer is one of the leading causes of cancer-related death.Accurate detection, segmentation, and differential diagnosis of the fulltaxonomy of pancreatic lesions, i.e., normal, seven major types of lesions, andother lesions, is critical to aid the clinical decision-making of patientmanagement and treatment. However, existing works focus on segmentation andclassification for very specific lesion types (PDAC) or groups. Moreover, noneof the previous work considers using lesion prevalence-related non-imagingpatient information to assist the differential diagnosis. To this end, wedevelop a meta-information-aware dual-path transformer and exploit thefeasibility of classification and segmentation of the full taxonomy ofpancreatic lesions. Specifically, the proposed method consists of a CNN-basedsegmentation path (S-path) and a transformer-based classification path(C-path). The S-path focuses on initial feature extraction by semanticsegmentation using a UNet-based network. The C-path utilizes both the extractedfeatures and meta-information for patient-level classification based on stacksof dual-path transformer blocks that enhance the modeling of global contextualinformation. A large-scale multi-phase CT dataset of 3,096 patients withpathology-confirmed pancreatic lesion class labels, voxel-wise manualannotations of lesions from radiologists, and patient meta-information, wascollected for training and evaluations. Our results show that our method canenable accurate classification and segmentation of the full taxonomy ofpancreatic lesions, approaching the accuracy of the radiologist's report andsignificantly outperforming previous baselines. Results also show that addingthe common meta-information, i.e., gender and age, can boost the model'sperformance, thus demonstrating the importance of meta-information for aidingpancreatic disease diagnosis.

Meta-information-aware Dual-path Transformer for Differential Diagnosis of Multi-type Pancreatic Lesions in Multi-phase CT