Gold-standard and improved framework for sperm head segmentation

[Application of Artificial Intelligence in Sperm Quality Analysis and Sperm Screening]

Infertility is a global health issue, and more and more people are hoping to have babies by means of assisted reproductive technology. However, there are still many challenges in fertilization and pregnancy outcomes. Sperm quality is a key factor affecting the success rate of assisted reproduction. Therefore, sperm quality screening is crucial for achieving breakthroughs in assisted reproduction technology. At present, with its capabilities in the field of image recognition, artificial intelligence (AI) is providing new ideas and methods for sperm screening. Various attempts have been made with AI-based models to evaluate indicators such as sperm morphology, DNA quality, and motility level, and some results have been achieved. Herein, we reviewed the application of AI in sperm quality analysis and selection, providing support for the future development of AI and the improvement in the fertilization rate and outcomes of assisted reproductive technology.

Evolution of intracytoplasmic sperm injection: From initial challenges to wider applications

Background

In vitro fertilization (IVF) has revolutionized infertility treatment. Nevertheless, male infertility requires more effective solutions. In 1992, the first-ever case of human birth via intracytoplasmic sperm injection (ICSI) was reported. ICSI involves microscopically injecting a sperm into an ovum. Successful ICSI has become a reliable therapy for couples facing infertility, a significant milestone. However, it has also introduced various challenges. This study also delves into ethical dilemmas arising from widespread ICSI use.

Methods

This review traces the history of ICSI, presenting pioneering attempts, first successful attempts, and critical reports on account of the initial skepticism toward the technology. The review also focuses on chronological progress until ICSI was recognized as effective and became widely applied.

Main findings

The review reveals that ICSI, although transformative, presents challenges. Successes include addressing male infertility and aiding fertilization. However, concerns arise regarding optimal sperm and embryo selection, genetic mutations, and long-term health implications. Ethical considerations surrounding ICSI's broad applications also surface.

Conclusions

Despite its success and effectiveness, ICSI is still evolving as a therapeutic method. By comprehensively evaluating the historical progress and the current status of ICSI and exploring its future prospects, this study highlights the importance of ICSI in infertility treatment.

Ensembling noisy segmentation masks of blurred sperm images

BACKGROUND

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.

METHODS

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.

RESULTS

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.

CONCLUSIONS

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.

Study on Sperm-Cell Detection Using YOLOv5 Architecture with Labaled Dataset

Infertility has recently emerged as a severe medical problem. The essential elements in male infertility are sperm morphology, sperm motility, and sperm density. In order to analyze sperm motility, density, and morphology, laboratory experts do a semen analysis. However, it is simple to err when using a subjective interpretation based on laboratory observation. In this work, a computer-aided sperm count estimation approach is suggested to lessen the impact of experts in semen analysis. Object detection techniques concentrating on sperm motility estimate the number of active sperm in the semen. This study provides an overview of other techniques that we can compare. The Visem dataset from the Association for Computing Machinery was used to test the proposed strategy. We created a labelled dataset to prove that our network can detect sperms in images. The best not-super tuned result is mAP 72.15.

Automated rare sperm identification from low-magnification microscopy images of dissociated microsurgical testicular sperm extraction samples using deep learning

OBJECTIVE

To develop a machine learning algorithm to detect rare human sperm in semen and microsurgical testicular sperm extraction (microTESE) samples using bright-field (BF) microscopy for nonobstructive azoospermia patients.

DESIGN

Spermatozoa were collected from fertile men. Testis biopsies were collected from microTESE samples determined to be clinically negative for sperm. A convolutional neural network based on the U-Net architecture was trained using 35,761 BF image patches with fluorescent ground truth image pairs to segment sperm. The algorithm was validated using 7,663 image patches. The algorithm was tested using 7,663 image patches containing abundant sperm, as well as 7,985 image patches containing rare sperm.

SETTING

In vitro fertilization center and university laboratories.

PATIENT(S)

Normospermic and nonobstructive azoospermia patients.

INTERVENTION(S)

None.

MAIN OUTCOME MEASURE(S)

Precision (positive predictive value [PPV]), recall (sensitivity), and F1-score of detected sperm locations.

RESULT(S)

For sperm-only samples, our algorithm achieved 91% PPV, 95.8% sensitivity, and 93.3% F1-score at ×10 magnification. For dissociated microTESE samples doped with an abundant quantity of sperm, our algorithm achieved 84.0% PPV, 72.7% sensitivity, and 77.9% F1-score. For dissociated microTESE samples doped with rare sperm, our algorithm achieved 84.4% PPV, 86.1% sensitivity, and 85.2% F1-score.

CONCLUSION(S)

Rare sperm can be detected in patients' testis biopsy samples for potential subsequent use in in vitro fertilization-intracytoplasmic sperm injection. A machine learning algorithm can use BF images at ×10 magnification to accurately detect sperm locations using automated imaging.

Segmentation of human spermatozoa using improved Havrda-Chavrat entropy-based thresholding method

The assisted method of fertilization has required an identification of sperm cells with normal morphological structure. The abnormal sperm cells cannot provide successful result in artificial fertilization. Nowadays the assessment of morphology of sperm cells is subjective and error prone hence creating automatic evaluation method for morphology assessment, it will improve the success ratio in infertility treatment. The first step in our proposed system is pre-processing where noise removal process is applied on microscopic medical images. In second step, adaptive alpha valued Havrda-Chavrat entropy-based threshold technique is proposed where the maximum probability distribution of foreground pixels or background pixels is assigned to alpha value. Further, existing state-of-art threshold-based segmentation methods are implemented and obtained results on the input images. These segmentation results are compared with the proposed method in terms of supervised and unsupervised evaluation metrics, in which our proposed thresholding method has given optimum threshold value for the segmentation of spermatozoa cells. The outcome of the segmented images and their metric values are indicating better segmentation by our proposed method. Furthermore, this proposed method can be implemented in the mobile applications for diagnosis with artificial intelligence techniques.

Prolificacy Assessment of Spermatozoan via State-of-the-Art Deep Learning Frameworks

Childlessness or infertility among couples has become a global health concern. Due to the rise in infertility, couples are looking for medical supports to attain reproduction. This paper deals with diagnosing infertility among men and the major factor in diagnosing infertility among men is the Sperm Morphology Analysis (SMA). In this manuscript, we explore establishing deep learning frameworks to automate the classification problem in the fertilization of sperm cells. We investigate the performance of multiple state-of-the-art deep neural networks on the MHSMA dataset. The experimental results demonstrate that the deep learning-based framework outperforms human experts on sperm classification in terms of accuracy, throughput and reliability. We further analyse the sperm cell data by visualizing the feature activations of the deep learning models, providing a new perspective to understand the data. Finally, a comprehensive analysis is also demonstrated on the experimental results obtained and attributing them to pertinent reasons.

Multi-model CNN fusion for sperm morphology analysis

Infertility is a common disorder affecting 20% of couples worldwide. Furthermore, 40% of all cases are related to male infertility. The first step in the determination of male infertility is semen analysis. The morphology, concentration, and motility of sperm are important characteristics evaluated by experts during semen analysis. Most laboratories perform the tests manually. However, manual semen analysis requires much time and is subject to observer variability during the evaluation. Therefore, computer-assisted systems are required. Additionally, to obtain more objective results, a large amount of data is necessary. Deep learning networks, which have become popular in recent years, are used for processing and analysing such quantities of data. Convolutional neural networks (CNNs) are a class of deep learning algorithm that are used extensively for processing and analysing images. In this study, six different CNN models were created for completely automating the morphological classification of sperm images. Additionally, two decision-level fusion techniques namely hard-voting and soft-voting were applied over these CNNs. To evaluate the performance of the proposed approach, three publicly available sperm morphology data sets were used in the experimental tests. For an objective analysis, a cross-validation technique was applied by dividing the data sets into five sub-sets. In addition, various data augmentation scales and mini-batch analysis were employed to obtain the highest classification accuracies. Finally, in the classification, accuracies 90.73%, 85.18% and 71.91% were obtained for the SMIDS, HuSHeM and SCIAN-Morpho data sets, respectively, using the soft-voting based fusion approach over the six created CNN models. The results suggested that the proposed approach could automatically classify as well as achieve high success in three different data sets.

Impact of transfer learning for human sperm segmentation using deep learning

BACKGROUND AND OBJECTIVE

Infertility affects approximately one in ten couples, and almost half of the infertility cases are due to the malefactor. To diagnose infertility and determine future treatment, a semen analysis is performed. Evaluation of sperm morphology is one of several steps in semen analysis, in which the shape and size of sperm parts are examined. The laboratories dedicated to this use traditional methods susceptible to errors. An alternative to replace the poor visual ability to assess sperm size and shape is to analyze sperm morphology with a computer's help. However, since the automatic sperm classification rates do not show an acceptable precision rate for use in the clinical setting, it is considered an exciting approach to focus efforts on improving the precision in sperm segmentation to extract the contour sperm before classification. This work aims to assess the utility of two image segmentation deep learning models for segmenting human sperm heads, acrosome, and nucleus.

METHODS

In this work, we evaluate the use of two well-known deep learning architectures (U-Net and Mask-RCNN) to segment parts of human sperm cells using data augmentation, cross-validation, hyperparameter tuning, and transfer learning. The experimental results are carried out using SCIAN-SpermSegGS, a public dataset with more than two hundred manually segmented sperm cells and widely used to validate segmentation methods of human sperm parts.

RESULTS

Experimental evaluation shows that U-net with transfer learning achieves up to 95% overlapping against hand-segmented masks for sperm head (0.96), acrosome (0.94), and nucleus (0.95), using Dice coefficient as the evaluation metric. These results outperform state-of-the-art sperm parts segmentation methods.

CONCLUSIONS

The impact of transfer learning is substantial, significantly improving the results of state-of-the-art methods with a higher Dice coefficient, less dispersion, and fewer cases where the model failed to segment sperm parts. These results represent a promising advance in the ultimate goal of performing computer-assisted morphological sperm analysis.

Artificial intelligence in the fertility clinic: status, pitfalls and possibilities

In recent years, the amount of data produced in the field of ART has increased exponentially. The diversity of data is large, ranging from videos to tabular data. At the same time, artificial intelligence (AI) is progressively used in medical practice and may become a promising tool to improve success rates with ART. AI models may compensate for the lack of objectivity in several critical procedures in fertility clinics, especially embryo and sperm assessments. Various models have been developed, and even though several of them show promising performance, there are still many challenges to overcome. In this review, we present recent research on AI in the context of ART. We discuss the strengths and weaknesses of the presented methods, especially regarding clinical relevance. We also address the pitfalls hampering successful use of AI in the clinic and discuss future possibilities and important aspects to make AI truly useful for ART.

Optimising adjacent membrane segmentation and parameterisation in multicellular aggregates by piecewise active contours

In fluorescence microscopy imaging, the segmentation of adjacent cell membranes within cell aggregates, multicellular samples, tissue, organs, or whole organisms remains a challenging task. The lipid bilayer is a very thin membrane when compared to the wavelength of photons in the visual spectra. Fluorescent molecules or proteins used for labelling membranes provide a limited signal intensity, and light scattering in combination with sample dynamics during in vivo imaging lead to poor or ambivalent signal patterns that hinder precise localisation of the membrane sheets. In the proximity of cells, membranes approach and distance each other. Here, the presence of membrane protrusions such as blebs; filopodia and lamellipodia; microvilli; or membrane vesicle trafficking, lead to a plurality of signal patterns, and the accurate localisation of two adjacent membranes becomes difficult. Several computational methods for membrane segmentation have been introduced. However, few of them specifically consider the accurate detection of adjacent membranes. In this article we present ALPACA (ALgorithm for Piecewise Adjacent Contour Adjustment), a novel method based on 2D piecewise parametric active contours that allows: (i) a definition of proximity for adjacent contours, (ii) a precise detection of adjacent, nonadjacent, and overlapping contour sections, (iii) the definition of a polyline for an optimised shared contour within adjacent sections and (iv) a solution for connecting adjacent and nonadjacent sections under the constraint of preserving the inherent cell morphology. We show that ALPACA leads to a precise quantification of adjacent and nonadjacent membrane zones in regular hexagons and live image sequences of cells of the parapineal organ during zebrafish embryo development. The algorithm detects and corrects adjacent, nonadjacent, and overlapping contour sections within a selected adjacency distance d, calculates shared contour sections for neighbouring cells with minimum alterations of the contour characteristics, and presents piecewise active contour solutions, preserving the contour shape and the overall cell morphology. ALPACA quantifies adjacent contours and can improve the meshing of 3D surfaces, the determination of forces, or tracking of contours in combination with previously published algorithms. We discuss pitfalls, strengths, and limits of our approach, and present a guideline to take the best decision for varying experimental conditions for in vivo microscopy.

Deep learning-based selection of human sperm with high DNA integrity

Despite the importance of sperm DNA to human reproduction, currently no method exists to assess individual sperm DNA quality prior to clinical selection. Traditionally, skilled clinicians select sperm based on a variety of morphological and motility criteria, but without direct knowledge of their DNA cargo. Here, we show how a deep convolutional neural network can be trained on a collection of ~1000 sperm cells of known DNA quality, to predict DNA quality from brightfield images alone. Our results demonstrate moderate correlation (bivariate correlation ~0.43) between a sperm cell image and DNA quality and the ability to identify higher DNA integrity cells relative to the median. This deep learning selection process is directly compatible with current, manual microscopy-based sperm selection and could assist clinicians, by providing rapid DNA quality predictions (under 10 ms per cell) and sperm selection within the 86th percentile from a given sample.

Automated Non-Invasive Measurement of Single Sperm's Motility and Morphology

Measuring cell motility and morphology is important for revealing their functional characteristics. This paper presents automation techniques that enable automated, non-invasive measurement of motility and morphology parameters of single sperm. Compared to the status quo of qualitative estimation of single sperm's motility and morphology manually, the automation techniques provide quantitative data for embryologists to select a single sperm for intracytoplasmic sperm injection. An adapted joint probabilistic data association filter was used for multi-sperm tracking and tackled challenges of identifying sperms that intersect or have small spatial distances. Since the standard differential interference contrast (DIC) imaging method has side illumination effect which causes inherent inhomogeneous image intensity and poses difficulties for accurate sperm morphology measurement, we integrated total variation norm into the quadratic cost function method, which together effectively removed inhomogeneous image intensity and retained sperm's subcellular structures after DIC image reconstruction. In order to relocate the same sperm of interest identified under low magnification after switching to high magnification, coordinate transformation was conducted to handle the changes in the field of view caused by magnification switch. The sperm's position after magnification switch was accurately predicted by accounting for the sperm's swimming motion during magnification switch. Experimental results demonstrated an accuracy of 95.6% in sperm motility measurement and an error <10% in morphology measurement.

Automatic classification of human sperm head morphology

BACKGROUND AND OBJECTIVE

Infertility is a problem that affects up to 15% of couples worldwide with emotional and physiological implications and semen analysis is the first step in the evaluation of an infertile couple. Indeed the morphology of human sperm cells is considered to be a clinical tool dedicated to the fertility prognosis and serves, mainly, for making decisions regarding the options of assisted reproduction technologies. Therefore, a complete analysis of not only normal sperm but also abnormal sperm turns out to be critical in this context. This paper sets out to develop, implement and calibrate a novel methodology to characterize and classify sperm heads towards morphological sperm analysis. Our work is aimed at focusing on a depth analysis of abnormal sperm heads for fertility diagnosis, prognosis, reproductive toxicology, basic research or public health studies.

METHODS

We introduce a morphological characterization for human sperm heads based on shape measures. We also present a pipeline for sperm head classification, according to the last Laboratory Manual for the Examination and Processing of Human Semen of the World Health Organization (WHO). In this sense, we propose a two-stage classification scheme that permits to classify sperm heads among five different classes (one class for normal sperm heads and four classes for abnormal sperm heads) combining an ensemble strategy for feature selection and a cascade approach with several support vector machines dedicated to the verification of each class. We use Fisher's exact test to demonstrate that there is no statistically significant differences between our results and those achieved by domain experts.

RESULTS

Experimental evaluation shows that our two-stage classification scheme outperforms some state-of-the-art monolithic classifiers, exhibiting 58% of average accuracy. More interestingly, on the subset of data for which there is a total agreement between experts for the label of the samples, our system is able to provide 73% of average classification accuracy.

CONCLUSIONS

We show that our system behaves like a human expert; therefore it can be used as a supplementary source for labeling new unknown data. However, as sperm head classification is still a challenging issue due to the uncertainty on the class label of each sperm head, with the consequent high degree of variability among domain experts, we conclude that there are still opportunities for further improvement in designing a more accurate system by investigating other feature extraction methods and classification schemes.

Automated Sperm Head Detection Using Intersecting Cortical Model Optimised by Particle Swarm Optimization

In human sperm motility analysis, sperm segmentation plays an important role to determine the location of multiple sperms. To ensure an improved segmentation result, the Laplacian of Gaussian filter is implemented as a kernel in a pre-processing step before applying the image segmentation process to automatically segment and detect human spermatozoa. This study proposes an intersecting cortical model (ICM), which was derived from several visual cortex models, to segment the sperm head region. However, the proposed method suffered from parameter selection; thus, the ICM network is optimised using particle swarm optimization where feature mutual information is introduced as the new fitness function. The final results showed that the proposed method is more accurate and robust than four state-of-the-art segmentation methods. The proposed method resulted in rates of 98.14%, 98.82%, 86.46% and 99.81% in accuracy, sensitivity, specificity and precision, respectively, after testing with 1200 sperms. The proposed algorithm is expected to be implemented in analysing sperm motility because of the robustness and capability of this algorithm.

Automatic detection and segmentation of sperm head, acrosome and nucleus in microscopic images of human semen smears

BACKGROUND AND OBJECTIVE

Manual assessment of sperm morphology is subjective and error prone so developing automatic methods is vital for a more accurate assessment. The first step in automatic evaluation of sperm morphology is sperm head detection and segmentation. In this paper a complete framework for automatic sperm head detection and segmentation is presented.

METHODS

After an initial thresholding step, the histogram of the Hue channel of HSV color space is used, in addition to size criterion, to discriminate sperm heads in microscopic images. To achieve an improved segmentation of sperm heads, an edge-based active contour method is used. Also a novel tail point detection method is proposed to refine the segmentation by locating and removing the midpiece from the segmented head. An algorithm is also proposed to separate the acrosome and nucleus using morphological operations. Dice coefficient is used to evaluate the segmentation performance. The proposed methods are evaluated using a publicly available dataset.

RESULTS

The proposed method has achieved segmentation accuracy of 0.92 for sperm heads, 0.84 for acrosomes and 0.87 for nuclei, with the standard deviation of 0.05, which significantly outperforms the current state-of-the-art. Also our tail detection method achieved true detection rate of 96%.

CONCLUSIONS

In this paper we presented a complete framework for sperm detection and segmentation which is totally automatic. It is shown that using active contours can improve the segmentation results of sperm heads. Our proposed algorithms for tail detection and midpiece removal further improved the segmentation results. The results indicate that our method achieved higher Dice coefficients with less dispersion compared to the existing solutions.

An efficient method for automatic morphological abnormality detection from human sperm images

BACKGROUND AND OBJECTIVE

Sperm morphology analysis (SMA) is an important factor in the diagnosis of human male infertility. This study presents an automatic algorithm for sperm morphology analysis (to detect malformation) using images of human sperm cells.

METHODS

The SMA method was used to detect and analyze different parts of the human sperm. First of all, SMA removes the image noises and enhances the contrast of the image to a great extent. Then it recognizes the different parts of sperm (e.g., head, tail) and analyzes the size and shape of each part. Finally, the algorithm classifies each sperm as normal or abnormal. Malformations in the head, midpiece, and tail of a sperm, can be detected by the SMA method. In contrast to other similar methods, the SMA method can work with low resolution and non-stained images. Furthermore, an image collection created for the SMA, has also been described in this study. This benchmark consists of 1457 sperm images from 235 patients, and is known as human sperm morphology analysis dataset (HSMA-DS).

RESULTS

The proposed algorithm was tested on HSMA-DS. The experimental results show the high ability of SMA to detect morphological deformities from sperm images. In this study, the SMA algorithm produced above 90% accuracy in sperm abnormality detection task. Another advantage of the proposed method is its low computation time (that is, less than 9s), as such, the expert can quickly decide to choose the analyzed sperm or select another one.

CONCLUSIONS

Automatic and fast analysis of human sperm morphology can be useful during intracytoplasmic sperm injection for helping embryologists to select the best sperm in real time.