Univ Nord de France, UCLille, Faculté de Médecine et Maïeutique, Biomedical Signal Processing Unit (UTSB), F-59800, Lille, France.
Univ Nord de France, UCLille, Faculté de Médecine et Maïeutique, Biomedical Signal Processing Unit (UTSB), F-59800, Lille, France; Lille Catholic Hospital, Obstetrics Department, F-59020, Lille, France.
Comput Biol Med. 2019 Nov;114:103468. doi: 10.1016/j.compbiomed.2019.103468. Epub 2019 Sep 24.
Automated fetal heart rate (FHR) analysis removes inter- and intra-expert variability, and is a promising solution for reducing the occurrence of fetal acidosis and the implementation of unnecessary medical procedures. The first steps in automated FHR analysis are determination of the baseline, and detection of accelerations and decelerations (A/D). We describe a new method in which a weighted median filter baseline (WMFB) is computed and A/Ds are then detected.
The filter weightings are based on the prior probability that the sampled FHR is in the baseline state or in an A/D state. This probability is computed by estimating the signal's stability at low frequencies and by progressively trimming the signal. Using a competition dataset of 90 previously annotated FHR recordings, we evaluated the WMFB method and 11 recently published literature methods against the ground truth of an expert consensus. The level of agreement between the WMFB method and the expert consensus was estimated by calculating several indices (primarily the morphological analysis discordance index, MADI). The agreement indices were then compared with the values for eleven other methods. We also compared the level of method-expert agreement with the level of interrater agreement.
For the WMFB method, the MADI indicated a disagreement of 4.02% vs. the consensus; this value is significantly lower (p<10) than that calculated for the best of the 11 literature methods (7.27%, for Lu and Wei's empirical mode decomposition method). The level of inter-expert agreement (according to the MADI) and the level of WMFB-expert agreement did not differ significantly (p=0.22).
The WMFB method reproduced the expert consensus analysis better than 11 other methods. No differences in performance between the WMFB method and individual experts were observed. The method Matlab source code is available under General Public Licence at http://utsb.univ-catholille.fr/fhr-wmfb.
自动胎儿心率（FHR）分析消除了专家间和专家内的变异性，是减少胎儿酸中毒和不必要医疗程序的有希望的解决方案。自动 FHR 分析的第一步是确定基线，并检测加速和减速（A/D）。我们描述了一种新方法，其中计算加权中值滤波器基线（WMFB），然后检测 A/D。
滤波器权重基于采样 FHR 处于基线状态或 A/D 状态的先验概率。该概率通过估计信号在低频下的稳定性并逐步修剪信号来计算。使用 90 个先前注释的 FHR 记录的竞争数据集，我们评估了 WMFB 方法和 11 种最近发表的文献方法与专家共识的真实性。通过计算几个指标（主要是形态分析不一致指数，MADI）来估计 WMFB 方法与专家共识之间的一致性水平。然后将这些一致性指数与其他 11 种方法的值进行比较。我们还比较了方法与专家之间的一致性水平与评分者之间的一致性水平。
对于 WMFB 方法，MADI 表明与共识的不一致性为 4.02%；这一值明显低于（p<10）11 种文献方法中最佳方法（Lu 和 Wei 的经验模态分解方法，7.27%）。根据 MADI 计算的专家间一致性水平和 WMFB 与专家的一致性水平没有显著差异（p=0.22）。
WMFB 方法比其他 11 种方法更好地再现了专家共识分析。WMFB 方法与单个专家之间的性能没有差异。该方法的 Matlab 源代码可在 General Public Licence 下在 http://utsb.univ-catholille.fr/fhr-wmfb 获得。
