CSTRL: Context-Driven Sequential Transfer Learning for Abstractive Radiology Report Summarization

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.

Similar Papers

Overview

Challenge

Approach

Outcome

Multimodal Generation of Radiology Reports using Knowledge-Grounded Extraction of Entities and Relations (2022.aacl-main)

Copied to clipboard

Francesco Dalla Serra, William Clackett, Hamish MacKinnon, Chaoyang Wang, Fani Deligianni, Jeff Dalton, Alison Q. O’Neil

Information Extraction & Text Mining

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.

Controllable Chest X-Ray Report Generation from Longitudinal Representations (2023.findings-emnlp)

Copied to clipboard

Francesco Dalla Serra, Chaoyang Wang, Fani Deligianni, Jeff Dalton, Alison O’Neil

Explainability & Interpretability in NLP

Challenge:	Radiology reports are detailed text descriptions of the content of medical scans.
Approach:	They propose a method to align, concatenate and fuse the current and prior visual information into a joint longitudinal representation which can be provided to a multimodal report generation model.
Outcome:	The proposed method achieves state-of-the-art results while enabling anatomy-wise controllable report generation.

Graph Enhanced Contrastive Learning for Radiology Findings Summarization (2022.acl-long)

Copied to clipboard

Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan, Tsung-Hui Chang

Semantic Text Processing

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 .

Coherent and Concise Radiology Report Generation via Context Specific Image Representations and Orthogonal Sentence States (2021.naacl-industry)

Copied to clipboard

Litton J Kurisinkel, Ai Ti Aw, Nancy F Chen

Multimodality

Challenge:	Neural models for text generation are often designed in an end-to-end fashion, limiting their practical usability in downstream applications.
Approach:	They propose a method to compute image representations specific to each sentential context and exploiting diverse sentence states to ensure topical continuity and content diversity of generated radiology reports.
Outcome:	The proposed method outperforms baselines on objective metrics and human evaluations by 18% and 29% respectively in the evaluation for informativeness and content ordering respectively.

Differentiable Multi-Agent Actor-Critic for Multi-Step Radiology Report Summarization (2022.acl-long)

Copied to clipboard

Sanjeev Kumar Karn, Ning Liu, Hinrich Schuetze, Oladimeji Farri

Text Generation

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.

Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation (2023.emnlp-main)

Copied to clipboard

Siyuan Wang, Bo Peng, Yichao Liu, Qi Peng

Visual Data in NLP

Challenge:	Existing methods to learn medical vision-language representations by contrasting images with entire reports are not effective.
Approach:	They propose a phenotype-driven medical vision-language representation learning framework to bridge the gap between visual and textual modalities for improved text-oriented generation.
Outcome:	The proposed framework bridges the gap between visual and textual modalities for improved radiology report generation.

GECSum: Generative Evaluation-Driven Sequence Level Contrastive Learning for Abstractive Summarization (2024.lrec-main)

Copied to clipboard

Jiawen Xie, Shaoting Zhang, Xiaofan Zhang

Semantic Text Processing

Challenge:	Abstractive summarization is a technique in natural language processing that involves generating a summary of a source document by creating new sentences and phrases.
Approach:	They propose a sequence-level contrastive learning framework that leverages the semantic understanding capabilities of the abstractive model itself to evaluate summary in reference-based settings.
Outcome:	The proposed framework outperforms the state-of-the-art in four summarization datasets.

CPR-RAG: Clinical Prior-Regularized Retrieval for Anatomy-Aware 3D CT Report Generation (2026.acl-long)

Copied to clipboard

Sungkyu Yang, Kang-Min Kim, Mansu Kim

Multimodality

Challenge:	Existing approaches to grounding radiology reports from 3D volumetric data are limited due to visual-semantic ambiguity and lack of "normal" context.
Approach:	They propose a model-agnostic retrieval-augmented generation framework that integrates clinical priors into the retrieval process.
Outcome:	The proposed model improves clinical efficacy across state-of-the-art models.

Extracting and Encoding: Leveraging Large Language Models and Medical Knowledge to Enhance Radiological Text Representation (2024.findings-acl)

Copied to clipboard

Pablo Messina, Rene Vidal, Denis Parra, Alvaro Soto, Vladimir Araujo

Semantic Text Processing

Challenge:	Advancing representation learning in specialized fields like medicine remains challenging due to the scarcity of expert annotations for text and images.
Approach:	They propose a Fact Extractor that leverages large language models to extract factual statements from radiology reports.
Outcome:	The proposed framework outperforms current state-of-the-art methods in sentence ranking, natural language inference, and label extraction tasks.

CCD: Mitigating Hallucinations in Radiology MLLMs via Clinical Contrastive Decoding (2026.findings-acl)

Copied to clipboard

Xi Zhang, Zaiqiao Meng, Jake Lever, Edmond S. L. Ho

Reasoning

Challenge:	Multimodal large language models generate medical hallucinations due to over-sensitivity to clinical sections.
Approach:	They propose a framework that integrates structured clinical signals from task-specific radiology expert models.
Outcome:	The proposed framework improves overall performance on radiology report generation (RRG) on the MIMIC-CXR dataset, it yields up to 17% improvement in RadGraph-F1.