Zhuoran Zhang’s research while affiliated with Dalian University of Technology and other places

STUDY QUESTION Can a quantitative method be developed to differentiate between blastocysts with similar or same inner cell mass (ICM) and trophectoderm (TE) grades, while also reflecting their potential for live birth? SUMMARY ANSWER We developed BlastScoringNet, an interpretable deep-learning model that quantifies blastocyst ICM and TE morphology with continuous scores, enabling finer differentiation between blastocysts with similar or same grades, with higher scores significantly correlating with higher live birth rates. WHAT IS KNOWN ALREADY While the Gardner grading system is widely used by embryologists worldwide, blastocysts having similar or same ICM and TE grades cause challenges for embryologists in decision-making. Furthermore, human assessment is subjective and inconsistent in predicting which blastocysts have higher potential to result in live birth. STUDY DESIGN, SIZE, DURATION The study design consists of three main steps. First, BlastScoringNet was developed using a grading dataset of 2760 blastocysts with majority-voted Gardner grades. Second, the model was applied to a live birth dataset of 15 228 blastocysts with known live birth outcomes to generate blastocyst scores. Finally, the correlation between these scores and live birth outcomes was assessed. The blastocysts were collected from patients who underwent IVF treatments between 2016 and 2018. For external application study, an additional grading dataset of 1455 blastocysts and a live birth dataset of 476 blastocysts were collected from patients who underwent IVF treatments between 2021 and 2023 at an external IVF institution. PARTICIPANTS/MATERIALS, SETTING, METHODS In this retrospective study, we developed BlastScoringNet, an interpretable deep-learning model which outputs expansion degree grade and continuous scores quantifying a blastocyst’s ICM morphology and TE morphology, based on the Gardner grading system. The continuous ICM and TE scores were calculated by weighting each base grade’s predicted probability and summing the predicted probabilities. To represent each blastocyst’s overall potential for live birth, we combined the ICM and TE scores using their odds ratios (ORs) for live birth. We further assessed the correlation between live birth rates and the ICM score, TE score, and the OR-combined score (adjusted for expansion degree) by applying BlastScoringNet to blastocysts with known live birth outcomes. To test its generalizability, we also applied BlastScoringNet to an external IVF institution, accounting for variations in imaging conditions, live birth rates, and embryologists’ experience levels. MAIN RESULTS AND THE ROLE OF CHANCE BlastScoringNet was developed using data from 2760 blastocysts with majority-voted grades for expansion degree, ICM, and TE. The model achieved mean area under the receiver operating characteristic curve values of 0.997 (SD 0.004) for expansion degree, 0.903 (SD 0.031) for ICM, and 0.943 (SD 0.040) for TE, based on predicted probabilities for each base grade. From these predicted probabilities, BlastScoringNet generated continuous ICM and TE scores, as well as expansion degree grades, for an additional 15 228 blastocysts with known live birth outcomes. Higher ICM and TE scores, along with their OR-combined scores, were significantly correlated with increased live birth rates (P < 0.0001). By fine-tuning, BlastScoringNet was applied to an external IVF institution, where higher OR-combined ICM and TE scores also significantly correlated with increased live birth rates (P = 0.00078), demonstrating consistent results across both institutions. LIMITATIONS, REASONS FOR CAUTION This study is limited by its retrospective nature. Further prospective randomized trials are required to confirm the clinical impact of BlastScoringNet in assisting embryologists in blastocyst selection. WIDER IMPLICATIONS OF THE FINDINGS BlastScoringNet provides an interpretable and quantitative method for evaluating blastocysts, aligned with the widely used Gardner grading system. Higher OR-combined ICM and TE scores, representing each blastocyst’s overall potential for live birth, were significantly correlated with increased live birth rates. The model’s demonstrated generalizability across two institutions further supports its clinical utility. These findings suggest that BlastScoringNet is a valuable tool for assisting embryologists in selecting blastocysts with the highest potential for live birth. The code and pre-trained models are publicly available to facilitate further research and widespread implementation. STUDY FUNDING/COMPETING INTEREST(S) This work was supported by the Vector Institute and the Temerty Faculty of Medicine at the University of Toronto, Toronto, Ontario, Canada, via a Clinical AI Integration Grant, and the Natural Science Foundation of Hunan Province of China (2023JJ30714). The authors declare no competing interests. TRIAL REGISTRATION NUMBER N/A.

Automated positioning systems play a pivotal role in micro-scale cell manipulation. In clinical intracytoplasmic sperm injection (ICSI) for infertility treatment, a motile sperm needs to be immobilized by glass micropipette tapping for subsequent surgical steps. The process requires accurate tracking of the target sperm and precise alignment between the sperm tail and the micropipette. Manual sperm immobilization suffers from inconsistent success rates, and current robotic systems developed for the task fail to comply with the standard clinical setup. Instead of using a motorized micromanipulator as in existing robotic systems, this paper presents an automated and compact three-dimensional (3-D) positioning stage for sperm immobilization that can be seamlessly integrated into standard clinical platforms. To tackle the challenge of accurately tracking the target sperm with degraded detection quality due to the complex 3-D motion of the positioning stage, a multi-stage sperm tracking scheme is designed for detection-to-tracklet association. To prevent physical contact between the sperm head and the micropipette, an adaptive tail-tapping planning strategy based on the sperm head orientation analysis is established. A visual servo controller equipped with a dynamic sperm motion observer is further employed to achieve precise positioning of the target sperm during the immobilization process. Experimental results demonstrated that the proposed system achieved a sperm tracking accuracy of 88.12%, and a sperm positioning accuracy of 2.3 ± 1.2 μm. Further experiments revealed the system achieved a success rate of 93.5% and a time cost of 5.5 s for automated sperm immobilization.

Sperm morphology measurement is vital for diagnosing male infertility, which involves quantification of multiple subcellular parts for each sperm. Instance-aware part segmentation networks have been introduced to address this task by automatically identifying individual sperm and segmenting their subcellular parts. However, major limitations of state-of-the-art instance-aware part segmentation networks include: 1) they are time-consuming and computational expensive due to sequential processing and multi-stage frameworks; 2) they perform poorly for densely packed sperm that overlap or cross over one another. To overcome these challenges, this paper proposes 1) integrating instance identification and subcellular part segmentation within a single-stage framework to save inference time and memory usage; 2) dividing a sperm target into simpler components (head and tail) to improve prediction accuracy, followed by a contrastive learning-based matching method to pair the head and tail. Experimental results on our clinically collected human sperm dataset demonstrated that the proposed network not only outperformed state-of-the-art CP-Net (by 3.5% APp vol) but also achieved realtime inference (48.0 frames per second), effectively meeting the clinical requirements for automated parts segmentation of sperm. final part segmentation results. 2) Since the sperm head and tail have simpler shapes, they are detected separately to improve segmentation accuracy. A contrastive learning-based method is then designed to pair head and tail based on similarity of feature embeddings extracted from the proposed instance prediction branch. The proposed method significantly outperformed existing networks, particularly in handling densely packed sperm. The presented method has applicability to analyzing sperm and more broadly other cell types.

Background Blastocyst morphology has been demonstrated to be associated with ploidy status. Existing artificial intelligence models use manual grading or 2D images as the input for euploidy prediction, which suffer from subjectivity from observers and information loss due to incomplete features from 2D images. Here we aim to predict euploidy in human blastocysts using quantitative morphological parameters obtained by 3D morphology measurement. Methods Multi-view images of 226 blastocysts on Day 6 were captured by manually rotating blastocysts during the preparation stage of trophectoderm biopsy. Quantitative morphological parameters were obtained by 3D morphology measurement. Six machine learning models were trained using 3D morphological parameters as the input and PGT-A results as the ground truth outcome. Model performance, including sensitivity, specificity, precision, accuracy and AUC, was evaluated on an additional test dataset. Model interpretation was conducted on the best-performing model. Results All the 3D morphological parameters were significantly different between euploid and non-euploid blastocysts. Multivariate analysis revealed that three of the five parameters including trophectoderm cell number, trophectoderm cell size variance and inner cell mass area maintained statistical significance (P < 0.001, aOR = 1.054, 95% CI 1.034–1.073; P = 0.003, aOR = 0.994, 95% CI 0.991–0.998; P = 0.010, aOR = 1.003, 95% CI 1.001–1.006). The accuracy of euploidy prediction by the six machine learning models ranged from 80 to 95.6%, and the AUCs ranged from 0.881 to 0.984. Particularly, the decision tree model achieved the highest accuracy of 95.6% (95% CI 84.9-99.5%) with the AUC of 0.978 (95% CI 0.882–0.999), and the extreme gradient boosting model achieved the highest AUC of 0.984 (95% CI 0.892-1.000) with the accuracy of 93.3% (95% CI 81.7-98.6%). No significant difference was found between different age groups using either decision tree or extreme gradient boosting to predict euploid blastocysts. The quantitative criteria extracted from the decision tree imply that euploid blastocysts have a higher number of trophectoderm cells, larger inner cell mass area, and smaller trophectoderm cell size variance compared to non-euploid blastocysts. Conclusions Using quantitative morphological parameters obtained by 3D morphology measurement, the decision tree-based machine learning model achieved an accuracy of 95.6% and AUC of 0.978 for predicting euploidy in Day 6 human blastocysts. Trial registration N/A.

Arrhythmogenic cardiomyopathy (ACM) is a leading cause of sudden cardiac death among young adults. Aberrant gap junction remodeling has been linked to disease-causative mutations in plakophilin-2 ( PKP2 ). Although gap junctions are a key therapeutic target, measurement of gap junction function in preclinical disease models is technically challenging. To quantify gap junction function with high precision and high consistency, we developed a robotic cell manipulation system with visual feedback from digital holographic microscopy for three-dimensional and label-free imaging of human induced pluripotent stem cell–derived cardiomyocytes (iPSC-CMs). The robotic system can accurately determine the dynamic height changes in the cells’ contraction and resting phases, microinject drug-treated healthy and diseased iPSC-CMs in their resting phase with constant injection depth across all cells, and deposit a membrane-impermeable dye that solely diffuses between cells through gap junctions for measuring the gap junction diffusion function. The robotic system was applied toward a targeted drug screen to identify gap junction modulators and potential therapeutics for ACM. Five compounds were found to dose-dependently enhance gap junction permeability in cardiomyocytes with PKP2 knockdown. In addition, PCO 400 (pinacidil) reduced beating irregularity in a mouse model of ACM expressing mutant PKP2 (R735X). These results highlight the utility of the robotic cell manipulation system to efficiently assess gap junction function in a relevant preclinical disease model, thus providing a technique to advance drug discovery for ACM and other gap junction–mediated diseases.

Traditional sperm morphology analysis is based on tedious manual annotation. Automated morphology analysis of a high number of sperm requires accurate segmentation of each sperm part and quantitative morphology evaluation. State-of-the-art instance-aware part segmentation networks follow a "detect-then-segment" paradigm. However, due to sperm's slim shape, their segmentation suffers from large context loss and feature distortion due to bounding box cropping and resizing during ROI Align. Moreover, morphology measurement of sperm tail is demanding because of the long and curved shape and its uneven width. This paper presents automated techniques to measure sperm morphology parameters automatically and quantitatively. A novel attention-based instance-aware part segmentation network is designed to reconstruct lost contexts outside bounding boxes and to fix distorted features, by refining preliminary segmented masks through merging features extracted by feature pyramid network. An automated centerline-based tail morphology measurement method is also proposed, in which an outlier filtering method and endpoint detection algorithm are designed to accurately reconstruct tail endpoints. Experimental results demonstrate that the proposed network outperformed the state-of-the-art top-down RP-R-CNN by 9.2% [AP]_vol^p, and the proposed automated tail morphology measurement method achieved high measurement accuracies of 95.34%,96.39%,91.2% for length, width and curvature, respectively.

Background Deep learning has been increasingly investigated for assisting clinical in vitro fertilization (IVF). The first technical step in many tasks is to visually detect and locate sperm, oocytes, and embryos in images. For clinical deployment of such deep learning models, different clinics use different image acquisition hardware and different sample preprocessing protocols, raising the concern over whether the reported accuracy of a deep learning model by one clinic could be reproduced in another clinic. Here we aim to investigate the effect of each imaging factor on the generalizability of object detection models, using sperm analysis as a pilot example. Methods Ablation studies were performed using state-of-the-art models for detecting human sperm to quantitatively assess how model precision (false-positive detection) and recall (missed detection) were affected by imaging magnification, imaging mode, and sample preprocessing protocols. The results led to the hypothesis that the richness of image acquisition conditions in a training dataset deterministically affects model generalizability. The hypothesis was tested by first enriching the training dataset with a wide range of imaging conditions, then validated through internal blind tests on new samples and external multi-center clinical validations. Results Ablation experiments revealed that removing subsets of data from the training dataset significantly reduced model precision. Removing raw sample images from the training dataset caused the largest drop in model precision, whereas removing 20x images caused the largest drop in model recall. by incorporating different imaging and sample preprocessing conditions into a rich training dataset, the model achieved an intraclass correlation coefficient (ICC) of 0.97 (95% CI: 0.94-0.99) for precision, and an ICC of 0.97 (95% CI: 0.93-0.99) for recall. Multi-center clinical validation showed no significant differences in model precision or recall across different clinics and applications. Conclusions The results validated the hypothesis that the richness of data in the training dataset is a key factor impacting model generalizability. These findings highlight the importance of diversity in a training dataset for model evaluation and suggest that future deep learning models in andrology and reproductive medicine should incorporate comprehensive feature sets for enhanced generalizability across clinics.