Scholarlink

Background/objective <p>Structured reporting improves the completeness and consistency of radiology documentation and may reduce error rates. This study evaluated a deep learning–based natural language processing (NLP) framework for the automatic conversion of free-text rectal MRI reports, acquired for local staging, into standardized structured reports.</p> Methods <p>Two expert radiologists authored 151 synthetic free-text rectal MRI reports and completed corresponding structured versions following the template of the Italian Society of Medical and Interventional Radiology (SIRM). These paired reports were used to fine-tune a large-scale pretrained text-to-text model (mT5) to extract 200 categorical variables corresponding to the fields of the structured report. Performance was assessed using accuracy, balanced accuracy, and F1-score. To mitigate class imbalance, a second training session was carried out after performing a targeted permutation of underrepresented variables.</p> Results <p>In the first training session, the model achieved an accuracy (mean ± SD) of 0.96 ± 0.08, a balanced accuracy of 0.93 ± 0.16, and an F1-score of 0.96 ± 0.09. In the second training session, after permutation, performance was an accuracy of 0.94 ± 0.09, a balanced accuracy of 0.85 ± 0.23, and an F1-score of 0.93 ± 0.10.</p> Conclusions <p>The mT5 model achieved high performance in the automatic structuring of rectal cancer staging MRI reports, without significant degradation after targeted permutation of variables in the second training session.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Automated population of structured magnetic resonance imaging staging reports for rectal cancer from free-text radiology reports using deep learning–based natural language processing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月6日

查看全文
  • Salvatore Claudio Fanni,
  • Simone Lossano,
  • Vincenzo Uggenti,
  • Francesca Lizzi,
  • Sara Saponaro,
  • Leonardo Ubaldi,
  • Maria Febi,
  • Claudio Bedini,
  • Irene Minetti,
  • Salvatore Valentino,
  • Sandro Ubbiali,
  • Giacomo Aringhieri,
  • Lorenzo Faggioni,
  • Riccardo Lencioni,
  • Emanuele Neri,
  • Dania Cioni

摘要

Background/objective

Structured reporting improves the completeness and consistency of radiology documentation and may reduce error rates. This study evaluated a deep learning–based natural language processing (NLP) framework for the automatic conversion of free-text rectal MRI reports, acquired for local staging, into standardized structured reports.

Methods

Two expert radiologists authored 151 synthetic free-text rectal MRI reports and completed corresponding structured versions following the template of the Italian Society of Medical and Interventional Radiology (SIRM). These paired reports were used to fine-tune a large-scale pretrained text-to-text model (mT5) to extract 200 categorical variables corresponding to the fields of the structured report. Performance was assessed using accuracy, balanced accuracy, and F1-score. To mitigate class imbalance, a second training session was carried out after performing a targeted permutation of underrepresented variables.

Results

In the first training session, the model achieved an accuracy (mean ± SD) of 0.96 ± 0.08, a balanced accuracy of 0.93 ± 0.16, and an F1-score of 0.96 ± 0.09. In the second training session, after permutation, performance was an accuracy of 0.94 ± 0.09, a balanced accuracy of 0.85 ± 0.23, and an F1-score of 0.93 ± 0.10.

Conclusions

The mT5 model achieved high performance in the automatic structuring of rectal cancer staging MRI reports, without significant degradation after targeted permutation of variables in the second training session.