Structuring Radiology Reports: Challenging LLMs with Lightweight Models

• URL: http://arxiv.org/abs/2506.00200v2
• Date: Mon, 14 Jul 2025 09:19:59 GMT
• Title: Structuring Radiology Reports: Challenging LLMs with Lightweight Models
• Authors: Johannes Moll, Louisa Fay, Asfandyar Azhar, Sophie Ostmeier, Tim Lueth, Sergios Gatidis, Curtis Langlotz, Jean-Benoit Delbrouck,
• Abstract summary: Large language models (LLMs) have shown strong capabilities in reformatting clinical text, their high computational requirements, lack of transparency, and data privacy concerns hinder practical deployment.<n>We explore lightweight encoder-decoder models (300M parameters)-specifically T5 and BERT2BERT-for structuring radiology reports from the MIMIC-CXR and CheXpert Plus datasets.<n>Our best-performing lightweight model outperforms all LLMs adapted using prompt-based techniques on a human-annotated test set.
• Score: 5.01440254761063
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Radiology reports are critical for clinical decision-making but often lack a standardized format, limiting both human interpretability and machine learning (ML) applications. While large language models (LLMs) have shown strong capabilities in reformatting clinical text, their high computational requirements, lack of transparency, and data privacy concerns hinder practical deployment. To address these challenges, we explore lightweight encoder-decoder models (<300M parameters)-specifically T5 and BERT2BERT-for structuring radiology reports from the MIMIC-CXR and CheXpert Plus datasets. We benchmark these models against eight open-source LLMs (1B-70B), adapted using prefix prompting, in-context learning (ICL), and low-rank adaptation (LoRA) finetuning. Our best-performing lightweight model outperforms all LLMs adapted using prompt-based techniques on a human-annotated test set. While some LoRA-finetuned LLMs achieve modest gains over the lightweight model on the Findings section (BLEU 6.4%, ROUGE-L 4.8%, BERTScore 3.6%, F1-RadGraph 1.1%, GREEN 3.6%, and F1-SRR-BERT 4.3%), these improvements come at the cost of substantially greater computational resources. For example, LLaMA-3-70B incurred more than 400 times the inference time, cost, and carbon emissions compared to the lightweight model. These results underscore the potential of lightweight, task-specific models as sustainable and privacy-preserving solutions for structuring clinical text in resource-constrained healthcare settings.

Related papers

• Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study [64.26593350748401]
  Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities.<n>Current parameter reduction techniques primarily involve training MLLMs from Small Language Models (SLMs)<n>We propose to directly compress existing MLLMs through structural pruning combined with efficient recovery training.
  arXiv  Detail & Related papers  (2025-07-28T11:57:52Z)
• EfficientLLM: Efficiency in Large Language Models [64.3537131208038]
  Large Language Models (LLMs) have driven significant progress, yet their growing counts and context windows incur prohibitive compute, energy, and monetary costs.<n>We introduce EfficientLLM, a novel benchmark and the first comprehensive empirical study evaluating efficiency techniques for LLMs at scale.
  arXiv  Detail & Related papers  (2025-05-20T02:27:08Z)
• Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math [135.1260782461186]
  Chain-of-Thought (CoT) significantly enhances formal reasoning capabilities in Large Language Models (LLMs)<n>However, improving reasoning in Small Language Models (SLMs) remains challenging due to their limited model capacity.<n>We present a systematic training recipe for SLMs that consists of four steps: (1) large-scale mid-training on diverse distilled long-CoT data, (2) supervised fine-tuning on high-quality long-CoT data, (3) Rollout DPO leveraging a carefully curated preference dataset, and (4) Reinforcement Learning (RL) with Verifiable Reward.
  arXiv  Detail & Related papers  (2025-04-30T00:04:35Z)
• Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't [0.0]
  Our study investigates the potential of reinforcement learning to improve reasoning in small language models (LLMs)<n>Training on 4 NVIDIA A40 GPUs (48 GB VRAM each) within 24 hours resulted in rapid reasoning gains.<n>These findings highlight the efficacy of RL-based fine-tuning for small LLMs, offering a cost-effective alternative to large-scale approaches.
  arXiv  Detail & Related papers  (2025-03-20T15:13:23Z)
• Adaptive Pruning for Large Language Models with Structural Importance Awareness [66.2690963378878]
  Large language models (LLMs) have significantly improved language understanding and generation capabilities.<n>LLMs are difficult to deploy on resource-constrained edge devices due to their high computational and storage resource demands.<n>We propose structurally-aware adaptive pruning (SAAP) to significantly reduce the computational and memory costs while maintaining model performance.
  arXiv  Detail & Related papers  (2024-12-19T18:08:04Z)
• EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation [58.546205554954454]
  We propose Enhancing Alignment in MLLMs via Critical Observation (EACO)<n>EACO aligns MLLMs by self-generated preference data using only 5k images economically.<n>EACO reduces the overall hallucinations by 65.6% on HallusionBench and improves the reasoning ability by 21.8% on MME-Cognition.
  arXiv  Detail & Related papers  (2024-12-06T09:59:47Z)
• Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models? [16.312594953592665]
  Large language models (LLMs) excel on generative tasks, but their performance on extractive tasks remains debated.<n>This study is among the first to develop and evaluate a comprehensive clinical IE system using open-source LLMs.
  arXiv  Detail & Related papers  (2024-11-15T07:54:19Z)
• Large Language Models versus Classical Machine Learning: Performance in COVID-19 Mortality Prediction Using High-Dimensional Tabular Data [0.0]
  This study aimed to evaluate and compare the performance of classical machine learning models (CMLs) and large language models (LLMs) in predicting mortality associated with COVID-19. We analyzed data from 9,134 COVID-19 patients collected across four hospitals.
  arXiv  Detail & Related papers  (2024-09-02T14:51:12Z)
• The Impact of LoRA Adapters for LLMs on Clinical NLP Classification Under Data Limitations [32.23468444597675]
  Fine-tuning Large Language Models (LLMs) for clinical Natural Language Processing (NLP) poses significant challenges due to the domain gap and limited data availability.<n>This study investigates the effectiveness of various adapter techniques, equivalent to Low-Rank Adaptation (LoRA)<n>We fine-tuned biomedical pre-trained models, including CamemBERT-bio, AliBERT, and DrBERT, alongside two Transformer-based models.
  arXiv  Detail & Related papers  (2024-07-27T16:48:03Z)
• TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale [66.01943465390548]
  We introduce TriSum, a framework for distilling large language models' text summarization abilities into a compact, local model. Our method enhances local model performance on various benchmarks. It also improves interpretability by providing insights into the summarization rationale.
  arXiv  Detail & Related papers  (2024-03-15T14:36:38Z)
• A comparative study of zero-shot inference with large language models and supervised modeling in breast cancer pathology classification [1.4715634464004446]
  Large language models (LLMs) have demonstrated promising transfer learning capability. LLMs demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for curating large annotated datasets. This may result in an increase in the utilization of NLP-based variables and outcomes in observational clinical studies.
  arXiv  Detail & Related papers  (2024-01-25T02:05:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.