Human Blastocyst Components Detection Using Multiscale Aggregation Semantic Segmentation Network for Embryonic Analysis

Abstract

Infertility is one of the most important health concerns worldwide. It is characterized by not being successful of pregnancy after some periods of periodic unprotected sexual intercourse. In vitro fertilization (IVF) is an assisted reproduction technique that efficiently addresses infertility. IVF replaces the actual mode of reproduction through a manual procedure wherein embryos are cultivated in a controlled laboratory environment until they reach the blastocyst stage. The standard IVF procedure includes the transfer of one or two blastocysts from several blastocysts that are grown in a controlled environment. The morphometric properties of blastocysts with their compartments such as trophectoderm (TE), zona pellucida (ZP), inner cell mass (ICM), and blastocoel (BL), are analyzed through manual microscopic analysis to predict viability. Deep learning has been extensively used for medical diagnosis and analysis and can be a powerful tool to automate the morphological analysis of human blastocysts. However, the existing approaches are inaccurate and require extensive preprocessing and expensive architectures. Thus, to cope with the automatic detection of blastocyst components, this study proposed a novel multiscale aggregation semantic segmentation network (MASS-Net) that combined four different scales via depth-wise concatenation. The extensive use of depthwise separable convolutions resulted in a decrease in the number of trainable parameters. Further, the innovative multiscale design provided rich spatial information of different resolutions, thereby achieving good segmentation performance without a very deep architecture. MASS-Net utilized 2.06 million trainable parameters and accurately detects TE, ZP, ICM, and BL without using preprocessing stages. Moreover, it can provide a separate binary mask for each blastocyst component simultaneously, and these masks provide the structure of each component for embryonic analysis. Further, the proposed MASS-Net was evaluated using publicly available human blastocyst (microscopic) imaging data. The experimental results revealed that it can effectively detect TE, ZP, ICM, and BL with mean Jaccard indices of 79.08, 84.69, 85.88%, and 89.28%, respectively, for embryological analysis, which was higher than those of the state-of-the-art methods.

Deep Learning-Based Detection of Human Blastocyst Compartments with Fractal Dimension Estimation

“…PSF-Net provides a multiclass binary mask with zeros and ones, and JI is computed by comparing the pixels of the binary mask with the corresponding pixels in the ground truth image. Many recent studies [38,39] used JI for the pixel-level evaluation of the predicted mask for the blastocyst image. Where TP is the pixel that belongs to the blastocyst class in both the predicted mask and expert label mask, FP is the pixel that belongs to the blastocyst class in the predicted mask image, but it is a non-blastocyst pixel in the expert label mask image; FN is the pixel that belongs to the non-embryo class in the predicted mask image and, actually, it is an embryo pixel in the expert label mask image.…”

Microscopic Video-Based Grouped Embryo Segmentation: A Deep Learning Approach

“…This research predominantly focuses on segmenting the complete embryo, which is why the segmentation of specific embryo components falls beyond the scope of this study. Furthermore, individuals interested in exploring intricate segmentation of embryo components are recommended to consult relevant literature concerning day 1 [7][8][9] and day 5 [10][11][12].…”

Exploring the Role of Explainability in AI-Assisted Embryo Selection

“…Blastocyst Segmentation: four crucial morphological regions to segment: TE, ZP, ICM and BL (see §1). A multiscaling architecture that outputs segmentation masks for the four regions is introduced in [4], where authors apply Grad-CAM to different layers to show the evolution of activations. A U-Net has also been used to separate the background from the blastocyst [21], using an ellipse on top of the segmentation mask to separate inner cell mass from trophectoderm.…”

“…A representative list can be found in Table 1. In many cases XAI is only considered through the illustration and minor discussion of a few saliency maps [4,21,41,43]. Others take one more step and analyze the map activations in order to correlate them to morphological features [39,42] or to the objective [12].…”

“…Another limitation in the field is privacy. None of the previous works makes the code (except for [4]) or the data (except for [17]) publicly available, making reproducibility impossible and replicability impractical. These flaws, in a task with a high degree of subjectivity (inter and intra-observer variability) induce a high risk of confirmation bias.…”