深度学习在眼底照片上检测青光眼性视神经损害进展
该回顾性队列研究训练深度学习卷积神经网络从彩色眼底照片预测SD OCT测量的全局视网膜神经纤维层厚度,并在独立样本中测试其检测青光眼进展的能力。结果显示预测厚度变化与OCT观测变化显著相关(r=0.76),区分进展者与非进展者的ROC曲线下面积为0.86,检测快速进展者(斜率快于2 μm/年)的ROC曲线下面积为0.96。
要点
- 深度学习模型从眼底照片预测的RNFL厚度变化与SD OCT观测变化显著相关(r=0.76)。
- 预测RNFL厚度区分青光眼进展者与非进展者的ROC曲线下面积为0.86。
- 检测快速进展者(斜率快于2 μm/年)的ROC曲线下面积为0.96,80%特异度下敏感度97%。
核心结论
- 深度学习模型可从眼底照片获得客观定量的RNFL厚度估计,与SD OCT测量相关性好,有望用于监测青光眼随时间的变化。
主要发现
- 预测与观测的RNFL厚度随时间变化显著相关(r=0.76;95%CI 0.70-0.80;P<0.001)。
- 预测RNFL厚度区分进展者与非进展者的ROC曲线下面积为0.86(95%CI 0.83-0.88)。
- 检测快速进展者(斜率快于2 μm/年)的ROC曲线下面积为0.96(95%CI 0.94-0.98),80%特异度下敏感度97%,90%特异度下敏感度85%。
- 同一次随访获取的多张照片预测RNFL厚度的组内相关系数为0.946(95%CI 0.940-0.952),变异系数为3.2%(95%CI 3.1%-3.3%)。
临床怎么用
- 该模型可基于眼底照片提供客观定量的RNFL厚度估计,辅助监测青光眼进展,尤其有助于识别快速进展者。
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)。
原文
PURPOSE: To investigate whether predictions of retinal nerve fiber layer (RNFL) thickness obtained from a deep learning model applied to fundus photographs can detect progressive glaucomatous changes over time. DESIGN: Retrospective cohort study. PARTICIPANTS: Eighty-six thousand one hundred twenty-three pairs of color fundus photographs and spectral-domain (SD) OCT images collected during 21 232 visits from 8831 eyes of 5529 patients with glaucoma or glaucoma suspects. METHODS: A deep learning convolutional neural network was trained to assess fundus photographs and to predict SD OCT global RNFL thickness measurements. The model then was tested on an independent sample of eyes that had longitudinal follow-up with both fundus photography and SD OCT. The ability to detect eyes that had statistically significant slopes of SD OCT change was assessed by receiver operating characteristic (ROC) curves. The repeatability of RNFL thickness predictions was investigated by measurements obtained from multiple photographs that had been acquired during the same day. MAIN OUTCOME MEASURES: The relationship between change in predicted RNFL thickness from photographs and change in SD OCT RNFL thickness over time. RESULTS: The test sample consisted of 33 466 pairs of fundus photographs and SD OCT images collected during 7125 visits from 1147 eyes of 717 patients. Eyes in the test sample were followed up for an average of 5.3 ± 3.3 years, with an average of 6.2 ± 3.8 visits. A significant correlation was found between change over time in predicted and observed RNFL thickness (r = 0.76; 95% confidence interval [CI], 0.70-0.80; P < 0.001). Retinal nerve fiber layer predictions showed an ROC curve area of 0.86 (95% CI, 0.83-0.88) to discriminate progressors from nonprogressors. For detecting fast progressors (slope faster than 2 μm/year), the ROC curve area was 0.96 (95% CI, 0.94-0.98), with a sensitivity of 97% for 80% specificity and 85% for 90% specificity. For photographs obtained at the same visit, the intraclass correlation coefficient was 0.946 (95% CI, 0.940-0.952), with a coefficient of variation of 3.2% (95% CI, 3.1%-3.3%). CONCLUSIONS: A deep learning model was able to obtain objective and quantitative estimates of RNFL thickness that correlated well with SD OCT measurements and potentially could be used to monitor for glaucomatous changes over time.
引用
- Medeiros FA, Jammal AA, Mariottoni EB, et al. Detection of Progressive Glaucomatous Optic Nerve Damage on Fundus Photographs with Deep Learning. Ophthalmology. 2020. PMID: 32735906. doi:10.1016/j.ophtha.2020.07.045
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。