Scholarlink

Purpose <p>To compare biparametric MRI (bpMRI) and multiparametric MRI (mpMRI) for detecting clinically significant prostate cancer (csPCa), and to assess the impact of artificial intelligence (AI)–assisted bpMRI on diagnostic performance and biopsy-related outcomes in readers with different expertise.</p> Material and methods <p>In this retrospective multi-reader study, 173 men referred for prostate mpMRI were evaluated by five radiologists (two experts, three basic readers) who scored bpMRI and mpMRI using PI-RADS v2.1. After a 45-day wash-out, the same readers reinterpreted bpMRI with concurrent AI decision support (available for 127 cases). Diagnostic performance for csPCa (ISUP ≥ 2) and benefit-to-harm ratios were compared across protocols and reader groups.</p> Results <p>Mean area under the receiver operating characteristic curve was 0.820 for bpMRI and 0.819 for mpMRI (difference 0.001), indicating comparable diagnostic performance. In the AI subset, AI increased mean specificity from 59.7% to 67.8% while reducing sensitivity from 90.2% to 84.5%. Biopsy selectivity and efficiency improved (3.9 to 4.6 and 1.7–1.9), particularly in basic readers. The effect was significant in basic readers (McNemar <i>p</i> = 0.012 for sensitivity, <i>p</i> &lt; 0.001 for specificity) but not in experts.</p> Conclusion <p>bpMRI showed comparable performance to mpMRI for csPCa detection in routine practice. AI-assisted bpMRI improved biopsy efficiency in less-experienced readers at the cost of reduced sensitivity, warranting careful consideration of the trade-off between missed cancers and avoided unproductive biopsies.</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

Diagnostic performance of bpMRI versus mpMRI and AI-assisted bpMRI in prostate cancer detection: a multi-reader study

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月29日

查看全文
  • Luca Russo,
  • Silvia Bottazzi,
  • Luca D’Erme,
  • Giacomo Avesani,
  • Valerio Di Paola,
  • Salvatore Persiani,
  • Alessandra Iacono,
  • Ina Isufi,
  • Lucy Davies,
  • Zobair Arya,
  • Matteo Mancino,
  • Francesca Lia,
  • Giuseppe Pallotta,
  • Maria Chiara Sighinolfi,
  • Francesco Pierconti,
  • Bernardo Rocco,
  • Evis Sala,
  • Benedetta Gui

摘要

Purpose

To compare biparametric MRI (bpMRI) and multiparametric MRI (mpMRI) for detecting clinically significant prostate cancer (csPCa), and to assess the impact of artificial intelligence (AI)–assisted bpMRI on diagnostic performance and biopsy-related outcomes in readers with different expertise.

Material and methods

In this retrospective multi-reader study, 173 men referred for prostate mpMRI were evaluated by five radiologists (two experts, three basic readers) who scored bpMRI and mpMRI using PI-RADS v2.1. After a 45-day wash-out, the same readers reinterpreted bpMRI with concurrent AI decision support (available for 127 cases). Diagnostic performance for csPCa (ISUP ≥ 2) and benefit-to-harm ratios were compared across protocols and reader groups.

Results

Mean area under the receiver operating characteristic curve was 0.820 for bpMRI and 0.819 for mpMRI (difference 0.001), indicating comparable diagnostic performance. In the AI subset, AI increased mean specificity from 59.7% to 67.8% while reducing sensitivity from 90.2% to 84.5%. Biopsy selectivity and efficiency improved (3.9 to 4.6 and 1.7–1.9), particularly in basic readers. The effect was significant in basic readers (McNemar p = 0.012 for sensitivity, p < 0.001 for specificity) but not in experts.

Conclusion

bpMRI showed comparable performance to mpMRI for csPCa detection in routine practice. AI-assisted bpMRI improved biopsy efficiency in less-experienced readers at the cost of reduced sensitivity, warranting careful consideration of the trade-off between missed cancers and avoided unproductive biopsies.