Challenge: Prior research on radiology report summarization has focused on single-step end-to-end models which subsume the task of salient content acquisition.
Approach: They propose a two-step extractive summarization followed by abstractive summaries and a new method that breaks down the extractive part into two independent tasks: extraction of salient (1) sentences and (2) keywords.
Outcome: The proposed model improves on English radiology reports with an overall improvement in F1 score of 3-4% compared to single-step and two-step-with-single-extractive-process baselines.

Similar Papers

The More, The Better? A Critical Study of Multimodal Context in Radiology Report Summarization (2025.findings-emnlp)

Copied to clipboard

Challenge: Current multimodal summarization models often fail to utilize radiology images in summarizing Findings section.
Approach: They conduct a thorough analysis to determine whether current multimodal summarization models can utilize radiology images in summarizing Findings section.
Outcome: The Impression section plays a crucial role in communication between radiologists and physicians.
Toward Expanding the Scope of Radiology Report Summarization to Multiple Anatomies and Modalities (2023.acl-short)

Copied to clipboard

Challenge: Existing studies are limited to a single modality and a chest X-ray, making it difficult to replicate results or compare approaches.
Approach: They propose a dataset to generate an impression section of a radiology report . they propose to use three new modalities and seven new anatomies to evaluate their models .
Outcome: The proposed model is based on the MIMIC-III and MIMIC CXR datasets and evaluates their clinical efficacy via RadGraph, a factual correctness metric.
Improving Radiology Summarization with Radiograph and Anatomy Prompts (2023.findings-acl)

Copied to clipboard

Challenge: Recent studies focus on automatic impression generation, but this task is time-consuming and in high demand.
Approach: They propose to use an anatomy-enhanced multimodal model to generate automatic impressions by combining radiology images with textual features.
Outcome: The proposed model achieves state-of-the-art on two benchmark datasets and compares with existing models.
Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-ray Reports (P19-1)

Copied to clipboard

Challenge: Existing studies do not consider the complex structure information between and within report sections.
Approach: They propose a framework which exploits the structure information between and within report sections for generating CXR imaging reports.
Outcome: The proposed framework achieves state-of-the-art performance on two CXR report datasets.
Word Graph Guided Summarization for Radiology Findings (2021.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings.
Approach: They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations.
Outcome: The proposed method is validated on two datasets, OPENI and MIMIC-CXR.
Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations (2022.aacl-main)

Copied to clipboard

Challenge: Existing approaches to generate text radiology reports are prone to errors and poor clinical accuracy.
Approach: They propose a two-step pipeline that subdivides the problem into factual triple extraction followed by free-text report generation.
Outcome: The proposed pipeline shows that the generated reports exhibit realistic style but lack clinical accuracy.
Graph Enhanced Contrastive Learning for Radiology Findings Summarization (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for automating impression generation have limited the relationship between extra knowledge and the original findings.
Approach: They propose a framework for automating impression generation that exploits extra knowledge and original findings . they propose combining key words and their relations to extract critical information .
Outcome: The proposed framework exploits extra knowledge and the original findings in an integrated way . the state-of-the-art results on two datasets confirm the effectiveness of the proposed method .
CSTRL: Context-Driven Sequential Transfer Learning for Abstractive Radiology Report Summarization (2025.findings-acl)

Copied to clipboard

Challenge: Pretrained models that excel in abstractive summarization problems face challenges when applied to specialized medical domains due to complex terminology and the necessity for accurate clinical context.
Approach: They propose a sequential transfer learning model that ensures key content extraction and coherent summarization.
Outcome: The proposed model shows 56.2% improvement in BLEU-1, 40.5% in ble-2, 84.3% in blu-3, 28.9% in ROUGE-1, 41.0% in Rough-2 and 26.5% of ROGUE-3 over benchmark studies.
Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports (2020.acl-main)

Copied to clipboard

Challenge: Existing abstractive summarization models do not guarantee factual correctness of summaries .
Approach: They propose a framework where models evaluate factual correctness by fact-checking it against its reference using an information extraction module.
Outcome: The proposed method significantly improves the factual correctness and overall quality of outputs over a competitive neural summarization system, producing radiology summaries that approach the quality of human-authored ones.
From Sights to Insights: Towards Summarization of Multimodal Clinical Documents (2024.acl-long)

Copied to clipboard

Challenge: a recent WHO report highlights a drastic doctor-to-patient ratio . telehealth is one of the most impactful sectors where AI advances can bring a significant revolution .
Approach: They propose an image-guided encoder-decoder model that uses contextual attention to create detailed visual-guides for multimodal documents.
Outcome: The proposed model outperforms state-of-the-art models on multimodal question and dialogue summarization tasks.

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