IEEE Trans Biomed Eng. 2023 Jun;70(6):1921-1930. doi: 10.1109/TBME.2022.3232068. Epub 2023 May 19.
Measuring the 3D morphology of spherical cell aggregates is required in both biology and medicine. Traditional methods either use fluorescent labeling, which cause cell toxicity and are unsuitable for clinical treatment, or use 2D images to roughly estimate 3D morphology. To overcome these limitations, this paper presents a quantitative label-free 3D morphology measurement technique using multi-view images. This technique, for the first time, enables the morphological evaluation of a blastocyst (Day 5 embryo) from "all angles" for IVF treatment. In this technique, a spherical rotation scale invariant feature transform (SR-SIFT) is proposed to address feature distortions for the rotation matrix calculation of the multi-view images. U-Net with generalized Dice loss is used to segment individual trophectoderm (TE) cells and the inner cell mass (ICM) of the blastocyst. Based on the rotation matrices and the segmentation results, the 3D morphological parameters of the entire blastocyst were quantified. Experimental results showed that the error of rotation angle was less than 1 , the Dice was 95.6% for TE segmentation and 92.3% for ICM segmentation, and the overall measurement error of clinically defined blastocyst parameters was less than 6.7%.
测量球形细胞聚集体的 3D 形态在生物学和医学中都很重要。传统的方法要么使用荧光标记，这会导致细胞毒性，不适合临床治疗，要么使用 2D 图像来粗略估计 3D 形态。为了克服这些限制，本文提出了一种使用多视图图像的定量无标记 3D 形态测量技术。该技术首次能够从“全方位”对 IVF 治疗中的囊胚（第 5 天胚胎）进行形态评估。在该技术中，提出了一种球形旋转不变特征变换 (SR-SIFT)，以解决多视图图像的旋转矩阵计算中的特征变形问题。使用具有广义 Dice 损失的 U-Net 来分割单个滋养外胚层 (TE) 细胞和囊胚的内细胞团 (ICM)。基于旋转矩阵和分割结果，对整个囊胚的 3D 形态参数进行了量化。实验结果表明，旋转角度的误差小于 1，TE 分割的 Dice 为 95.6%，ICM 分割的 Dice 为 92.3%，临床定义的囊胚参数的整体测量误差小于 6.7%。
