Department of Mechanical Engineering, University of British Columbia, Vancouver, British Columbia, Canada; Centre for Blood Research, University of British Columbia, Vancouver, British Columbia, Canada; Department of Urologic Sciences, University of British Columbia, Vancouver, British Columbia, Canada.
Department of Urologic Sciences, University of British Columbia, Vancouver, British Columbia, Canada; Vancouver Prostate Centre, Vancouver General Hospital, Vancouver, British Columbia, Canada; Department of Urology, The Ottawa Hospital, Ottawa, Ontario, Canada.
Fertil Steril. 2022 Jul;118(1):90-99. doi: 10.1016/j.fertnstert.2022.03.011. Epub 2022 May 10.
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.
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.
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.
开发一种机器学习算法，使用明场（BF）显微镜检测非梗阻性无精子症患者精液和显微睾丸精子提取（microTESE）样本中的稀有人类精子。
从正常生育男性中收集精子。从microTESE 样本中收集睾丸活检样本，这些样本在临床上被确定为无精子。使用基于 U-Net 架构的卷积神经网络，通过 35761 个 BF 图像补丁和荧光地面实况图像对进行训练，以分割精子。使用 7663 个图像补丁对算法进行验证。该算法使用包含丰富精子的 7663 个图像补丁以及包含稀有精子的 7985 个图像补丁进行测试。
体外受精中心和大学实验室。
正常生育和非梗阻性无精子症患者。
无。
检测到的精子位置的精度（阳性预测值[PPV]）、召回率（灵敏度）和 F1 评分。
对于仅精子样本，我们的算法在 ×10 放大倍数下达到 91%的 PPV、95.8%的灵敏度和 93.3%的 F1 评分。对于用大量精子稀释的分离 microTESE 样本，我们的算法达到 84.0%的 PPV、72.7%的灵敏度和 77.9%的 F1 评分。对于用稀有精子稀释的分离 microTESE 样本，我们的算法达到 84.4%的 PPV、86.1%的灵敏度和 85.2%的 F1 评分。
可以在患者的睾丸活检样本中检测到稀有精子，以备随后用于体外受精-胞浆内精子注射。机器学习算法可以使用 ×10 放大倍数的 BF 图像，通过自动成像准确检测精子位置。
