Papers by Kaveri Kale

3 papers
KGVL-BART: Knowledge Graph Augmented Visual Language BART for Radiology Report Generation (2023.eacl-main)

Copied to clipboard

Challenge: Timely generation of radiology reports and diagnoses is a challenge worldwide due to the enormous number of cases and shortage of radiologists.
Approach: They propose a Knowledge Graph Augmented Vision Language BART model that takes two chest X-ray images and outputs a report with patient-specific findings.
Outcome: The proposed model outperforms state-of-the-art transformer-based models on scoring metrics.
“Knowledge is Power”: Constructing Knowledge Graph of Abdominal Organs and Using Them for Automatic Radiology Report Generation (2023.acl-industry)

Copied to clipboard

Challenge: conventional radiology workflows involve dictating diagnosis to transcriptionists, which is prone to delay and error.
Approach: They propose to generate a set of knowledge graphs from a large collection of free-text radiology reports and use them to generate automatic radiology report generation.
Outcome: The proposed model improves the reported BLEU-3, ROUGE-L, METEOR, and CIDEr scores by 2%, 4%, 2% and 2% respectively.
Replace and Report: NLP Assisted Radiology Report Generation (2023.findings-acl)

Copied to clipboard

Challenge: Clinical practice frequently uses medical imaging for diagnosis and treatment.
Approach: They propose a template-based approach to generate radiology reports from radiographs . they use multilabel image classifiers to generate tags, pathological descriptions from tags .
Outcome: The proposed method improves on the most popular radiology report datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations