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/

Zendy Plus

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

Zendy Tools

Zendy Open

Conventionally, the radiologist prepares the diagnosis notes and shares themwith the transcriptionist. Then the transcriptionist prepares a preliminaryformatted report referring to the notes, and finally, the radiologist reviewsthe report, corrects the errors, and signs off. This workflow causessignificant delays and errors in the report. In current research work, we focuson applications of NLP techniques like Information Extraction (IE) anddomain-specific Knowledge Graph (KG) to automatically generate radiologyreports from radiologist's dictation. This paper focuses on KG construction foreach organ by extracting information from an existing large corpus of free-textradiology reports. We develop an information extraction pipeline that combinesrule-based, pattern-based, and dictionary-based techniques withlexical-semantic features to extract entities and relations. Missinginformation in short dictation can be accessed from the KGs to generatepathological descriptions and hence the radiology report. Generatedpathological descriptions evaluated using semantic similarity metrics, whichshows 97% similarity with gold standard pathological descriptions. Also, ouranalysis shows that our IE module is performing better than the OpenIE tool forthe radiology domain. Furthermore, we include a manual qualitative analysisfrom radiologists, which shows that 80-85% of the generated reports arecorrectly written, and the remaining are partially correct.

Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictation