文献速递腹部泌尿生殖CT

深度学习方法用于CT图像鉴别不确定肾上腺肿块

Deep learning approach for differentiating indeterminate adrenal masses using CT imaging.
PubMed 文献 · Abdom Radiol (NY) · 2023-06-27

该回顾性队列研究纳入48例病理证实的1-2期肾上腺皮质癌和43例>3 cm、中央平扫CT衰减>20 HU的乏脂性肾上腺腺瘤,用标注的单时相增强CT图像训练3D Densenet121模型进行分类。敏感度优先模型平均准确率87.2%、平均敏感度100%;准确率优先模型平均准确率91%、平均敏感度96%。结论认为深度学习在鉴别肾上腺皮质癌与大乏脂性腺瘤方面结果有前景,但广泛临床采用前需多中心及外部验证。

要点

  • 3D Densenet121模型用单时相增强CT鉴别1-2期肾上腺皮质癌与>3 cm乏脂性腺瘤,敏感度优先模型平均敏感度100%。
  • 准确率优先模型平均准确率91%、平均敏感度96%;敏感度优先模型平均准确率87.2%。
  • 作者结论认为结果有前景,但广泛临床采用前需多中心及外部验证。

核心结论

  • 深度学习在利用单时相CT图像区分1-2期肾上腺皮质癌与大乏脂性肾上腺腺瘤方面显示有前景的结果,但广泛临床采用前需多中心及外部验证。

研究设计与样本

  • 回顾性队列研究,1994年至2022年,纳入48例病理证实的1-2期肾上腺皮质癌和43例肾上腺腺瘤>3 cm且中央平扫CT衰减>20 HU的乏脂性腺瘤,参考标准为肾上腺活检和/或肾上腺切除术的组织学,另有4例乏脂性腺瘤由随访影像稳定或消退确定;使用标注的单时相增强CT图像输入3D Densenet121模型,五折交叉验证。

诊断标准与关键数值

  • 敏感度优先模型平均准确率87.2%、平均敏感度100%;准确率优先模型平均准确率91%、平均敏感度96%;乏脂性腺瘤定义为肾上腺腺瘤>3 cm且中央平扫CT衰减>20 HU。

局限性

  • 原文结论指出,在广泛临床采用前需要多中心及外部验证。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: Distinguishing stage 1-2 adrenocortical carcinoma (ACC) and large, lipid poor adrenal adenoma (LPAA) via imaging is challenging due to overlapping imaging characteristics. This study investigated the ability of deep learning to distinguish ACC and LPAA on single time-point CT images.

METHODS: Retrospective cohort study from 1994 to 2022. Imaging studies of patients with adrenal masses who had available adequate CT studies and histology as the reference standard by method of adrenal biopsy and/or adrenalectomy were included as well as four patients with LPAA determined by stability or regression on follow-up imaging. Forty-eight (48) subjects with pathology-proven, stage 1-2 ACC and 43 subjects with adrenal adenoma >3 cm in size demonstrating a mean non-contrast CT attenuation > 20 Hounsfield Units centrally were included. We used annotated single time-point contrast-enhanced CT images of these adrenal masses as input to a 3D Densenet121 model for classifying as ACC or LPAA with five-fold cross-validation. For each fold, two checkpoints were reported, highest accuracy with highest sensitivity (accuracy focused) and highest sensitivity with the highest accuracy (sensitivity focused).

RESULTS: We trained a deep learning model (3D Densenet121) to predict ACC versus LPAA. The sensitivity-focused model achieved mean accuracy: 87.2% and mean sensitivity: 100%. The accuracy-focused model achieved mean accuracy: 91% and mean sensitivity: 96%.

CONCLUSION: Deep learning demonstrates promising results distinguishing between ACC and large LPAA using single time-point CT images. Before being widely adopted in clinical practice, multicentric and external validation are needed.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Singh, Kelm, Faghani, et al. Deep learning approach for differentiating indeterminate adrenal masses using CT imaging. Abdom Radiol (NY). 2023. PMID: 37369921. doi:10.1007/s00261-023-03988-w

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。