基于深度学习从显微取精样本低倍显微图像中自动识别稀有精子
本研究开发基于U-Net的卷积神经网络,用35,761个明场图像块训练,检测非梗阻性无精子症患者精液和显微取精样本中的稀有精子;在含稀有精子的样本中达到84.4%阳性预测值、86.1%灵敏度和85.2% F1分数,作者认为该算法可自动识别精子位置。
要点
- 算法在仅含精子的样本中×10放大下达91%阳性预测值、95.8%灵敏度和93.3% F1分数。
- 在掺入大量精子的显微取精样本中达84.0%阳性预测值、72.7%灵敏度和77.9% F1分数。
- 在掺入稀有精子的显微取精样本中达84.4%阳性预测值、86.1%灵敏度和85.2% F1分数。
核心结论
- 作者认为,在非梗阻性无精子症患者睾丸活检样本中可检测到稀有精子,可能用于后续体外受精-卵胞浆内单精子注射。
- 作者认为,机器学习算法可利用×10放大明场图像通过自动成像准确检测精子位置。
研究设计与样本
- 研究从生育力正常男性收集精子,从临床判定为无精子的显微取精样本收集睾丸活检组织。
- 基于U-Net架构的卷积神经网络使用35,761个明场图像块及荧光基准图像对训练,用于分割精子。
- 算法使用7,663个图像块验证,并使用7,663个含大量精子的图像块和7,985个含稀有精子的图像块测试。
- 研究场所为体外受精中心和大学实验室,患者为精子正常男性及非梗阻性无精子症患者,无干预措施。
主要发现
- 仅含精子的样本在×10放大下,算法达到91%阳性预测值、95.8%灵敏度和93.3% F1分数。
- 掺入大量精子的解离显微取精样本,算法达到84.0%阳性预测值、72.7%灵敏度和77.9% F1分数。
- 掺入稀有精子的解离显微取精样本,算法达到84.4%阳性预测值、86.1%灵敏度和85.2% F1分数。
临床怎么用
- 作者认为,机器学习算法可利用×10放大明场图像通过自动成像准确检测精子位置。
- 作者认为,非梗阻性无精子症患者睾丸活检样本中检测到的稀有精子可能用于后续体外受精-卵胞浆内单精子注射。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
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.
引用
- Lee R, Witherspoon L, Robinson M, et al. Automated rare sperm identification from low-magnification microscopy images of dissociated microsurgical testicular sperm extraction samples using deep learning. Fertil Steril. 2022. PMID: 35562203. doi:10.1016/j.fertnstert.2022.03.011
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。