一种辅助诊断儿童内侧颞叶硬化的图像处理算法:病例对照研究
回顾性病例对照研究评估相关图像增强(CIE)算法检测儿童内侧颞叶硬化(MTS)相关海马信号异常的性能,CIE 使 26/27 个病理确诊 MTS 海马对比噪声比升高,读者检出异常信号的敏感度由 83.3% 升至 94.8%,但 MTS 疾病状态检出敏感度仅由 79.6% 升至 80.7%。
要点
- CIE 处理冠状 FLAIR 图像后可选择性提高 MTS 侧海马信号强度与对比噪声比。
- 处理后读者检出海马信号异常的敏感度由 83.3% 升至 94.8%,特异度由 94.4% 升至 96.3%。
- 处理后 MTS 疾病状态检出敏感度仅由 79.6% 升至 80.7%,特异度由 95.7% 升至 96.3%。
核心结论
- CIE 图像处理算法选择性提高病理确诊 MTS 海马的对比噪声比,改善读者检出 MTS 相关海马信号异常的表现,可能对接受癫痫检查的儿童患者有较大影响。
研究设计与样本
- 回顾性病例对照研究,纳入 27 例经病理数据库确认的行杏仁核-海马切除术的儿童 MTS 病例(9 男 18 女,平均年龄 16±6.7 岁)和 27 例无癫痫史、脑 MRI 正常的儿童对照(9 男 18 女,平均年龄 13.8±2.8 岁)。
诊断标准与关键数值
- CIE 处理后 26/27 个病理确诊 MTS 海马(96.3%)信号强度和对比噪声比升高,病例组平均对比噪声比由 14.9(11.1)升至 77.7(58.7)(P<0.001)。
- CIE 处理后 1/54 个正常对照海马(1.9%)对比噪声比升高,对照组平均对比噪声比处理后无显著变化(P=0.57)。
- 读者检出异常信号强度的平均敏感度由 83.3%(14.2)升至 94.8%(3.3),平均特异度由 94.4%(7.3)升至 96.3%(0)。
- 6 名读者中 4 名在 CIE 处理后检出 MTS 疾病状态的敏感度提高,平均敏感度由 79.6% 升至 80.7%,平均特异度由 95.7% 升至 96.3%。
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
BACKGROUND: Mesial temporal sclerosis (MTS) is an important cause of intractable epilepsy. Early and accurate diagnosis of MTS is essential to providing curative and life-changing therapy but can be challenging in children in whom the impact of diagnosis is particularly high. Magnetic resonance imaging (MRI) plays an important role in the diagnosis of MTS, and image processing of MRI is a recently studied strategy to improve its accuracy.
OBJECTIVE: In a retrospective case-control study, we assessed the performance of an image processing algorithm (Correlative Image Enhancement [CIE]) for detecting MTS-related hippocampal signal abnormality in children.
MATERIALS AND METHODS: Twenty-seven pediatric MTS cases (9 males, 18 females; mean age: 16±standard deviation [SD] 6.7 years) were identified from a pathology database of amygdylo-hippocampectomies performed in children with epilepsy. Twenty-seven children with no seizure history (9 males, 18 females; mean age: 13.8±SD 2.8 years), and with normal brain MRI, were identified for the control group. Blinded investigators processed the MRI coronal FLAIR (fluid-attenuated inversion recovery) images with CIE, saved the processed images as a separate series, and made equivalent region of interest measurements on the processed and unprocessed series to calculate contrast-to-noise ratio. Six blinded reviewers then rated the randomized series for hippocampal signal abnormality and MTS disease status.
RESULTS: CIE increased signal intensity and contrast-to-noise ratio in 26/27 hippocampi with pathologically confirmed MTS (96.3%) with the mean (SD) contrast-to-noise ratio of cases increasing from 14.9 (11.1) to 77.7 (58.7) after processing (P<0.001). Contrast-to-noise ratio increased in 1/54 normal control hippocampi (1.9%), with no significant change in the mean contrast-to-noise ratio of the control group after processing (P=0.57). Mean (SD) reader sensitivity for detecting abnormal signal intensity increased from 83.3% (14.2) to 94.8% (3.3) after processing. Mean specificity for abnormal signal intensity increased from 94.4% (7.3) to 96.3% (0). While sensitivity improved after processing for detection of MTS disease status in 4/6 readers, the mean reader sensitivity and specificity for MTS detection increased only minimally after processing, from 79.6% to 80.7% and from 95.7% to 96.3%, respectively.
CONCLUSION: The CIE image processing algorithm selectively increased the contrast-to-noise ratio of hippocampi affected by MTS, improved reader performance in detecting MTS-related hippocampal signal abnormality and could have high impact on pediatric patients undergoing work-up for seizures.
引用
- Strnad BS, Orlowski HLP, Parsons MS, et al. An image processing algorithm to aid diagnosis of mesial temporal sclerosis in children: a case-control study. Pediatr Radiol. 2019. PMID: 31578627. doi:10.1007/s00247-019-04518-x
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。