# Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models

arXiv: https://arxiv.org/abs/2608.30021 · HTML: https://mlsanity.com/paper/2608.30021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 30 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis](https://mlsanity.com/paper/2210.04714/) (2022)
- [MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes](https://mlsanity.com/paper/2412.19260/) (2024)
- [Generative Large Language Models Trained for Detecting Errors in Radiology Reports](https://mlsanity.com/paper/2504.04336/) (2025)
- [Specialised or Generic? Tokenization Choices for Radiology Language Models](https://mlsanity.com/paper/2508.09952/) (2025)

## Abstract (arXiv)

Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are often subtle and require domain expertise to detect. Although large language models (LLMs) have recently been proposed for radiology report verification, their ability to detect clinically meaningful errors beyond chest X-ray datasets remains under-explored. To this end, we present the first systematic evaluation of language models for PET/CT report error detection, comparing compact domain-specific models with SOTA open-weight LLMs. We collected 30,633 oncology FDG PET/CT reports from 23 radiologists over 10 years. We trained domain-specific BERT models to detect clinically motivated synthetic reporting errors and evaluated alongside zero-/few-shot Qwen3-32B, Gemma-3-27B and Llama-3.3-70B on a held-out benchmark of 11,500 reports. A 15M-parameter model achieved 94.4% balanced accuracy with a 5.8% false-positive rate, compared with 84.0% for the strongest prompted LLM. Task-specific adaptation of Llama-3.3-70B closed this performance gap (94.4%) but retained substantially greater computational requirements. Our results suggest that domain-specific training matters more than model scale for PET/CT report error detection, supporting compact models as an accurate and computationally efficient approach to automated radiology report quality assurance.