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

Human readers or radiologists routinely perform full-body multi-organmulti-disease detection and diagnosis in clinical practice, while most medicalAI systems are built to focus on single organs with a narrow list of a fewdiseases. This might severely limit AI's clinical adoption. A certain number ofAI models need to be assembled non-trivially to match the diagnostic process ofa human reading a CT scan. In this paper, we construct a Unified TumorTransformer (CancerUniT) model to jointly detect tumor existence & location anddiagnose tumor characteristics for eight major cancers in CT scans. CancerUniTis a query-based Mask Transformer model with the output of multi-tumorprediction. We decouple the object queries into organ queries, tumor detectionqueries and tumor diagnosis queries, and further establish hierarchicalrelationships among the three groups. This clinically-inspired architectureeffectively assists inter- and intra-organ representation learning of tumorsand facilitates the resolution of these complex, anatomically relatedmulti-organ cancer image reading tasks. CancerUniT is trained end-to-end usinga curated large-scale CT images of 10,042 patients including eight major typesof cancers and occurring non-cancer tumors (all are pathology-confirmed with 3Dtumor masks annotated by radiologists). On the test set of 631 patients,CancerUniT has demonstrated strong performance under a set of clinicallyrelevant evaluation metrics, substantially outperforming both multi-diseasemethods and an assembly of eight single-organ expert models in tumor detection,segmentation, and diagnosis. This moves one step closer towards a universalhigh performance cancer screening tool.

CancerUniT: Towards a Single Unified Model for Effective Detection,  Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection  of CT Scans