PDF(Pubmed)
Abstract：
UNASSIGNED: This study aimed to develop a deep learning system to identify and differentiate the metastatic cervical lymph nodes (CLNs) of thyroid cancer.
UNASSIGNED: From January 2014 to December 2020, 3059 consecutive patients with suspected with metastatic CLNs of thyroid cancer were retrospectively enrolled in this study. All CLNs were confirmed by fine needle aspiration. The patients were randomly divided into the training (1228 benign and 1284 metastatic CLNs) and test (307 benign and 240 metastatic CLNs) groups. Grayscale ultrasonic images were used to develop and test the performance of the Y-Net deep learning model. We used the Y-Net network model to segment and differentiate the lymph nodes. The Dice coefficient was used to evaluate the segmentation efficiency. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the classification efficiency.
UNASSIGNED: In the test set, the median Dice coefficient was 0.832. The sensitivity, specificity, accuracy, PPV, and NPV were 57.25%, 87.08%, 72.03%, 81.87%, and 66.67%, respectively. We also used the Y-Net classified branch to evaluate the classification efficiency of the LNs ultrasonic images. The classification branch model had sensitivity, specificity, accuracy, PPV, and NPV of 84.78%, 80.23%, 82.45%, 79.35%, and 85.61%, respectively. For the original ultrasonic reports, the sensitivity, specificity, accuracy, PPV, and NPV were 95.14%, 34.3%, 64.66%, 59.02%, 87.71%, respectively. The Y-Net model yielded better accuracy than the original ultrasonic reports.
UNASSIGNED: The Y-Net model can be useful in assisting sonographers to improve the accuracy of the classification of ultrasound images of metastatic CLNs.
UNASSIGNED: From January 2014 to December 2020, 3059 consecutive patients with suspected with metastatic CLNs of thyroid cancer were retrospectively enrolled in this study. All CLNs were confirmed by fine needle aspiration. The patients were randomly divided into the training (1228 benign and 1284 metastatic CLNs) and test (307 benign and 240 metastatic CLNs) groups. Grayscale ultrasonic images were used to develop and test the performance of the Y-Net deep learning model. We used the Y-Net network model to segment and differentiate the lymph nodes. The Dice coefficient was used to evaluate the segmentation efficiency. Sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the classification efficiency.
UNASSIGNED: In the test set, the median Dice coefficient was 0.832. The sensitivity, specificity, accuracy, PPV, and NPV were 57.25%, 87.08%, 72.03%, 81.87%, and 66.67%, respectively. We also used the Y-Net classified branch to evaluate the classification efficiency of the LNs ultrasonic images. The classification branch model had sensitivity, specificity, accuracy, PPV, and NPV of 84.78%, 80.23%, 82.45%, 79.35%, and 85.61%, respectively. For the original ultrasonic reports, the sensitivity, specificity, accuracy, PPV, and NPV were 95.14%, 34.3%, 64.66%, 59.02%, 87.71%, respectively. The Y-Net model yielded better accuracy than the original ultrasonic reports.
UNASSIGNED: The Y-Net model can be useful in assisting sonographers to improve the accuracy of the classification of ultrasound images of metastatic CLNs.
摘要：
■本研究旨在开发一种深度学习系统，以识别和区分甲状腺癌的转移性颈淋巴结（CLN）。
■从2014年1月至2020年12月，回顾性纳入3059例疑似甲状腺癌转移性CLN的连续患者。通过细针抽吸确认所有CLN。将患者随机分为训练组（1228个良性CLN和1284个转移性CLN）和测试组（307个良性CLN和240个转移性CLN）。使用灰度超声图像来开发和测试Y-Net深度学习模型的性能。我们使用Y-Net网络模型来分割和区分淋巴结。使用Dice系数来评估分割效率。灵敏度,特异性，准确度,阳性预测值(PPV)，和阴性预测值(NPV)用于评估分类效率。
■在测试集中，Dice系数中位数为0.832。敏感性,特异性，准确度,PPV,净现值为57.25%，87.08%,72.03%,81.87%,和66.67%，分别。我们还使用Y-Net分类分支来评估LNs超声图像的分类效率。分类分支模型具有敏感性，特异性，准确度,PPV,净现值为84.78%，80.23%，82.45%,79.35%,和85.61%，分别。对于原始超声报告，灵敏度,特异性，准确度,PPV,净现值为95.14%，34.3%,64.66%,59.02%,87.71%,分别。Y-Net模型比原始超声报告具有更好的准确性。
■Y-Net模型可用于协助超声检查者提高转移性CLNs超声图像分类的准确性。
■从2014年1月至2020年12月，回顾性纳入3059例疑似甲状腺癌转移性CLN的连续患者。通过细针抽吸确认所有CLN。将患者随机分为训练组（1228个良性CLN和1284个转移性CLN）和测试组（307个良性CLN和240个转移性CLN）。使用灰度超声图像来开发和测试Y-Net深度学习模型的性能。我们使用Y-Net网络模型来分割和区分淋巴结。使用Dice系数来评估分割效率。灵敏度,特异性，准确度,阳性预测值(PPV)，和阴性预测值(NPV)用于评估分类效率。
■在测试集中，Dice系数中位数为0.832。敏感性,特异性，准确度,PPV,净现值为57.25%，87.08%,72.03%,81.87%,和66.67%，分别。我们还使用Y-Net分类分支来评估LNs超声图像的分类效率。分类分支模型具有敏感性，特异性，准确度,PPV,净现值为84.78%，80.23%，82.45%,79.35%,和85.61%，分别。对于原始超声报告，灵敏度,特异性，准确度,PPV,净现值为95.14%，34.3%,64.66%,59.02%,87.71%,分别。Y-Net模型比原始超声报告具有更好的准确性。
■Y-Net模型可用于协助超声检查者提高转移性CLNs超声图像分类的准确性。
