Cameras and Algorithms Lab, Gdańsk University of Technology, Poland.
Cameras and Algorithms Lab, Gdańsk University of Technology, Poland; Multimedia Systems Department, Faculty of Electronics, Telecommunication, and Informatics, Gdańsk University of Technology, Poland.
Comput Biol Med. 2023 Nov;166:107520. doi: 10.1016/j.compbiomed.2023.107520. Epub 2023 Sep 22.
Sperm tail morphology and motility have been demonstrated to be important factors in determining sperm quality for in vitro fertilization. However, many existing computer-aided sperm analysis systems leave the sperm tail out of the analysis, as detecting a few tail pixels is challenging. Moreover, some publicly available datasets for classifying morphological defects contain images limited only to the sperm head. This study focuses on the segmentation of full sperm, which consists of the head and tail parts, and appear alone and in groups.
We re-purpose the Feature Pyramid Network to ensemble an input image with multiple masks from state-of-the-art segmentation algorithms using a scale-specific cross-attention module. We normalize homogeneous backgrounds for improved training. The low field depth of microscopes blurs the images, easily confusing human raters in discerning minuscule sperm from large backgrounds. We thus propose evaluation protocols for scoring segmentation models trained on imbalanced data and noisy ground truth.
The neural ensembling of noisy segmentation masks outperforms all single, state-of-the-art segmentation algorithms in full sperm segmentation. Human raters agree more on the head than tail masks. The algorithms also segment the head better than the tail.
The extensive evaluation of state-of-the-art segmentation algorithms shows that full sperm segmentation is challenging. We release the SegSperm dataset of images from Intracytoplasmic Sperm Injection procedures to spur further progress on full sperm segmentation with noisy and imbalanced ground truth. The dataset is publicly available at https://doi.org/10.34808/6wm7-1159.
精子尾部形态和运动能力已被证明是决定体外受精精子质量的重要因素。然而，许多现有的计算机辅助精子分析系统将精子尾部排除在分析之外，因为检测少数几个尾部像素具有挑战性。此外，一些现有的用于分类形态缺陷的公开数据集仅包含精子头部的图像。本研究专注于完整精子的分割，它由头部和尾部组成，单独出现或成群出现。
我们重新利用特征金字塔网络，使用特定于尺度的交叉注意模块，将输入图像与来自最先进分割算法的多个掩模集成在一起。我们对同质背景进行归一化，以提高训练效果。显微镜的低场深度会使图像模糊，容易混淆人类评分者，难以区分微小的精子和大背景。因此，我们提出了用于评估在不平衡数据和有噪声的真实数据上训练的分割模型的协议。
噪声分割掩模的神经集成在完整精子分割方面优于所有单一的、最先进的分割算法。人类评分者对头部掩模的一致性高于尾部掩模。算法对头部的分割也优于尾部。
对最先进的分割算法的广泛评估表明，完整精子的分割具有挑战性。我们发布了 Intracytoplasmic Sperm Injection 过程中的图像的 SegSperm 数据集，以激发在具有噪声和不平衡真实数据的情况下进一步推进完整精子分割的研究。该数据集可在 https://doi.org/10.34808/6wm7-1159 上获取。
