Scholarlink

Purpose <p>To investigate the effect of multiscale sampling artificial intelligence (msAI) software adapted to small hepatic lesions on the diagnostic performance of readers interpreting gadoxetic acid-enhanced hepatobiliary-phase (HBP) images.</p> Methods <p>HBP images of 30 patients harboring 186 hepatic lesions were included. Three board-certified radiologists, 9 radiology residents, and 2 general physicians interpreted HBP image data sets twice, once with and once without the msAI software at 2-week intervals. Jackknife free-response receiver-operating characteristic analysis was performed to calculate the figure of merit (FOM) for detecting hepatic lesions. The negative consultation ratio (NCR), percentage of correct diagnoses turning into incorrect by the AI software, was calculated. We defined readers whose NCR was lower than 10% as those correctly diagnosed the false findings presented by the software.</p> Results <p>The msAI software significantly improved the lesion localization fraction (LLF) for all readers (0.74 vs 0.82, <i>p</i> &lt; 0.01); the FOM did not (0.76 vs 0.78, <i>p</i> = 0.45). In lesion-size-based subgroup analysis, the LLF (0.40 vs 0.53, <i>p</i> &lt; 0.01) improved significantly with the AI software even for lesions smaller than 6&#xa0;mm, whereas the FOM (0.63 vs 0.66, <i>p</i> = 0.51) showed no significant difference. Among 10 readers with an NCR lower than 10%, not only the LLF but also the FOM were significantly better with the software (LLF 0.77 vs 0.82, FOM 0.79 vs 0.84, both <i>p</i> &lt; 0.01).</p> Conclusion <p>The detectability of small hepatic lesions on HBP images was improved with msAI software especially when its results were properly evaluated.</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

Artificial intelligence software to detect small hepatic lesions on hepatobiliary-phase images using multiscale sampling

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月29日

查看全文
  • Shogo Maeda,
  • Yuko Nakamura,
  • Toru Higaki,
  • Ayu Karasudani,
  • Tatsuya Yamaguchi,
  • Masaki Ishihara,
  • Takayuki Baba,
  • Shota Kondo,
  • Dara Fonseca,
  • Kazuo Awai

摘要

Purpose

To investigate the effect of multiscale sampling artificial intelligence (msAI) software adapted to small hepatic lesions on the diagnostic performance of readers interpreting gadoxetic acid-enhanced hepatobiliary-phase (HBP) images.

Methods

HBP images of 30 patients harboring 186 hepatic lesions were included. Three board-certified radiologists, 9 radiology residents, and 2 general physicians interpreted HBP image data sets twice, once with and once without the msAI software at 2-week intervals. Jackknife free-response receiver-operating characteristic analysis was performed to calculate the figure of merit (FOM) for detecting hepatic lesions. The negative consultation ratio (NCR), percentage of correct diagnoses turning into incorrect by the AI software, was calculated. We defined readers whose NCR was lower than 10% as those correctly diagnosed the false findings presented by the software.

Results

The msAI software significantly improved the lesion localization fraction (LLF) for all readers (0.74 vs 0.82, p < 0.01); the FOM did not (0.76 vs 0.78, p = 0.45). In lesion-size-based subgroup analysis, the LLF (0.40 vs 0.53, p < 0.01) improved significantly with the AI software even for lesions smaller than 6 mm, whereas the FOM (0.63 vs 0.66, p = 0.51) showed no significant difference. Among 10 readers with an NCR lower than 10%, not only the LLF but also the FOM were significantly better with the software (LLF 0.77 vs 0.82, FOM 0.79 vs 0.84, both p < 0.01).

Conclusion

The detectability of small hepatic lesions on HBP images was improved with msAI software especially when its results were properly evaluated.