Scholarlink

Purpose <p>To evaluate the utility of deep learning-based automated attenuation measurements on contrast-enhanced CT (CECT) for diagnosing moderate-to-severe hepatic steatosis (HS), using histology as reference standard.</p> Methods <p>This retrospective study included 3,620 liver donors (2,393 men and 1,227 women; mean age, 31.7 ± 9.4 years), divided into the development (<i>n</i> = 2,714) and test (<i>n</i> = 906) cohorts. Attenuation values of the liver and spleen on CECT were measured both manually and using a deep learning algorithm (before and after radiologists’ correction of segmentation errors). Performance of: (1) liver attenuation and (2) liver–spleen attenuation difference for diagnosing moderate-to-severe HS (&gt; 33%) was assessed using the area under the receiver operating characteristic curve (AUC). Three different criteria targeting 95% sensitivity, 95% specificity, and the maximum Youden’s index, respectively, for diagnosing moderate-to-severe HS, were developed and validated.</p> Results <p>The performance of deep learning-based measurements did not differ significantly, with or without radiologists’ corrections (<i>p</i> = 0.13). Liver–spleen attenuation difference outperformed liver attenuation alone in diagnosing moderate-to-severe HS in both deep learning-based (AUC, 0.868 vs. 0.821; <i>p</i> = 0.001) and manual (AUC, 0.871 vs. 0.823; <i>p</i> = 0.001) measurements. In the test cohort, the criterion targeting 95% sensitivity for diagnosing moderate-to-severe HS (liver–spleen attenuation difference ≤ 2.8 HU) yielded 92.0% (69/75) sensitivity and 48.5% (403/831) specificity. The criterion targeting 95% specificity (liver–spleen attenuation difference ≤ -18.8 HU) yielded 53.3% (40/75) sensitivity and 95.7% (795/831) specificity. The criterion targeting the maximum Youden’s index (liver–spleen attenuation difference ≤ -8.2 HU) yielded 82.7% (62/75) sensitivity and 80.7% (671/831) specificity.</p> Conclusion <p>Deep learning-based automated measurements of liver and spleen attenuation on CECT can be used reliably to detect moderate-to-severe HS.</p> Graphical Abstract <p></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

Diagnosis of moderate-to-severe hepatic steatosis using deep learning-based automated attenuation measurements on contrast-enhanced CT

  • 期刊论文

  • 发表日期：

    2025年3月17日

查看全文
  • Hae Young Kim,
  • Kyung Jin Lee,
  • Seung Soo Lee,
  • Se Jin Choi,
  • Dong Hwan Kim,
  • Subin Heo,
  • Hyeon Ji Jang,
  • Sang Hyun Choi

摘要

Purpose

To evaluate the utility of deep learning-based automated attenuation measurements on contrast-enhanced CT (CECT) for diagnosing moderate-to-severe hepatic steatosis (HS), using histology as reference standard.

Methods

This retrospective study included 3,620 liver donors (2,393 men and 1,227 women; mean age, 31.7 ± 9.4 years), divided into the development (n = 2,714) and test (n = 906) cohorts. Attenuation values of the liver and spleen on CECT were measured both manually and using a deep learning algorithm (before and after radiologists’ correction of segmentation errors). Performance of: (1) liver attenuation and (2) liver–spleen attenuation difference for diagnosing moderate-to-severe HS (> 33%) was assessed using the area under the receiver operating characteristic curve (AUC). Three different criteria targeting 95% sensitivity, 95% specificity, and the maximum Youden’s index, respectively, for diagnosing moderate-to-severe HS, were developed and validated.

Results

The performance of deep learning-based measurements did not differ significantly, with or without radiologists’ corrections (p = 0.13). Liver–spleen attenuation difference outperformed liver attenuation alone in diagnosing moderate-to-severe HS in both deep learning-based (AUC, 0.868 vs. 0.821; p = 0.001) and manual (AUC, 0.871 vs. 0.823; p = 0.001) measurements. In the test cohort, the criterion targeting 95% sensitivity for diagnosing moderate-to-severe HS (liver–spleen attenuation difference ≤ 2.8 HU) yielded 92.0% (69/75) sensitivity and 48.5% (403/831) specificity. The criterion targeting 95% specificity (liver–spleen attenuation difference ≤ -18.8 HU) yielded 53.3% (40/75) sensitivity and 95.7% (795/831) specificity. The criterion targeting the maximum Youden’s index (liver–spleen attenuation difference ≤ -8.2 HU) yielded 82.7% (62/75) sensitivity and 80.7% (671/831) specificity.

Conclusion

Deep learning-based automated measurements of liver and spleen attenuation on CECT can be used reliably to detect moderate-to-severe HS.

Graphical Abstract