Texas A&M University, 3120 TAMU, College Station, 77840, United States.
Texas A&M University, 3120 TAMU, College Station, 77840, United States.
Comput Biol Med. 2024 Sep;179:108846. doi: 10.1016/j.compbiomed.2024.108846. Epub 2024 Jul 7.
Autofluorescence imaging of the coenzyme, reduced nicotinamide adenine dinucleotide (phosphate) (NAD(P)H), provides a label-free technique to assess cellular metabolism. Because NAD(P)H is localized in the cytosol and mitochondria, instance segmentation of cell cytoplasms from NAD(P)H images allows quantification of metabolism with cellular resolution. However, accurate cytoplasmic segmentation of autofluorescence images is difficult due to irregular cell shapes and cell clusters.
Here, a cytoplasm segmentation method is presented and tested. First, autofluorescence images are segmented into cells via either hand-segmentation or Cellpose, a deep learning-based segmentation method. Then, a cytoplasmic post-processing algorithm (CPPA) is applied for cytoplasmic segmentation. CPPA uses a binarized segmentation image to remove non-segmented pixels from the NAD(P)H image and then applies an intensity-based threshold to identify nuclei regions. Errors at cell edges are removed using a distance transform algorithm. The nucleus mask is then subtracted from the cell segmented image to yield the cytoplasm mask image. CPPA was tested on five NAD(P)H images of three different cell samples, quiescent T cells, activated T cells, and MCF7 cells.
Using POSEA, an evaluation method tailored for instance segmentation, the CPPA yielded F-measure values of 0.89, 0.87, and 0.94 for quiescent T cells, activated T cells, and MCF7 cells, respectively, for cytoplasm identification of hand-segmented cells. CPPA achieved F-measure values of 0.84, 0.74, and 0.72 for Cellpose segmented cells.
These results exceed the F-measure value of a comparative cell segmentation method (CellProfiler, ∼0.50-0.60) and support the use of artificial intelligence and post-processing techniques for accurate segmentation of autofluorescence images for single-cell metabolic analyses.
辅酶还原型烟酰胺腺嘌呤二核苷酸（磷酸）（NAD（P）H）的自发荧光成像是一种无标记技术，可用于评估细胞代谢。由于 NAD（P）H 定位于细胞质和线粒体中，因此从 NAD（P）H 图像中对细胞细胞质进行实例分割可以实现具有细胞分辨率的代谢量化。然而，由于细胞形状不规则和细胞簇，自发荧光图像的细胞质准确分割很困难。
本研究提出并测试了一种细胞质分割方法。首先，通过手动分割或基于深度学习的分割方法 Cellpose 将自发荧光图像分割成细胞。然后，应用细胞质后处理算法（CPPA）进行细胞质分割。CPPA 使用二值化分割图像从 NAD（P）H 图像中去除未分割的像素，然后应用基于强度的阈值识别核区域。使用距离变换算法去除细胞边缘的误差。然后，从分割的细胞掩模图像中减去细胞核掩模，得到细胞质掩模图像。CPPA 在来自三个不同细胞样本（静止 T 细胞、激活 T 细胞和 MCF7 细胞）的五个 NAD（P）H 图像上进行了测试。
使用 POSEA，一种专门用于实例分割的评估方法，CPPA 在手动分割细胞的细胞质识别方面，对静止 T 细胞、激活 T 细胞和 MCF7 细胞分别产生了 0.89、0.87 和 0.94 的 F-measure 值。对于 Cellpose 分割的细胞，CPPA 分别产生了 0.84、0.74 和 0.72 的 F-measure 值。
这些结果超过了比较细胞分割方法（CellProfiler，约 0.50-0.60）的 F-measure 值，并支持使用人工智能和后处理技术对单细胞代谢分析的自发荧光图像进行准确分割。
