School of Engineering Sciences, KTH Royal Institute of Technology, Stockholm, Sweden.
Department of Clinical Science and Education, Karolinska Institutet, and Department of Obstetrics and Gynecology, Södersjukhuset, Stockholm, Sweden.
Ultrasound Obstet Gynecol. 2021 Jan;57(1):155-163. doi: 10.1002/uog.23530.
OBJECTIVES: To develop and test the performance of computerized ultrasound image analysis using deep neural networks (DNNs) in discriminating between benign and malignant ovarian tumors and to compare its diagnostic accuracy with that of subjective assessment (SA) by an ultrasound expert. METHODS: We included 3077 (grayscale, n = 1927; power Doppler, n = 1150) ultrasound images from 758 women with ovarian tumors, who were classified prospectively by expert ultrasound examiners according to IOTA (International Ovarian Tumor Analysis) terms and definitions. Histological outcome from surgery (n = 634) or long-term (≥ 3 years) follow-up (n = 124) served as the gold standard. The dataset was split into a training set (n = 508; 314 benign and 194 malignant), a validation set (n = 100; 60 benign and 40 malignant) and a test set (n = 150; 75 benign and 75 malignant). We used transfer learning on three pre-trained DNNs: VGG16, ResNet50 and MobileNet. Each model was trained, and the outputs calibrated, using temperature scaling. An ensemble of the three models was then used to estimate the probability of malignancy based on all images from a given case. The DNN ensemble classified the tumors as benign or malignant (Ovry-Dx1 model); or as benign, inconclusive or malignant (Ovry-Dx2 model). The diagnostic performance of the DNN models, in terms of sensitivity and specificity, was compared to that of SA for classifying ovarian tumors in the test set. RESULTS: At a sensitivity of 96.0%, Ovry-Dx1 had a specificity similar to that of SA (86.7% vs 88.0%; P = 1.0). Ovry-Dx2 had a sensitivity of 97.1% and a specificity of 93.7%, when designating 12.7% of the lesions as inconclusive. By complimenting Ovry-Dx2 with SA in inconclusive cases, the overall sensitivity (96.0%) and specificity (89.3%) were not significantly different from using SA in all cases (P = 1.0). CONCLUSION: Ultrasound image analysis using DNNs can predict ovarian malignancy with a diagnostic accuracy comparable to that of human expert examiners, indicating that these models may have a role in the triage of women with an ovarian tumor. © 2020 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.
目的：开发并测试基于深度神经网络（DNN）的计算机化超声图像分析在鉴别良恶性卵巢肿瘤方面的性能，并与超声专家的主观评估（SA）的诊断准确性进行比较。
方法：我们纳入了 758 名患有卵巢肿瘤的女性的 3077 个（灰度，n=1927；功率多普勒，n=1150）超声图像。这些图像由超声专家根据 IOTA（国际卵巢肿瘤分析）术语和定义进行前瞻性分类。手术（n=634）或长期（≥3 年）随访（n=124）的组织学结果作为金标准。数据集分为训练集（n=508；314 个良性和 194 个恶性）、验证集（n=100；60 个良性和 40 个恶性）和测试集（n=150；75 个良性和 75 个恶性）。我们使用三种预训练的 DNN 进行迁移学习：VGG16、ResNet50 和 MobileNet。每个模型都使用温度缩放进行训练和输出校准。然后，使用三个模型的集合来估计给定病例中所有图像的恶性概率。DNN 集合将肿瘤分类为良性或恶性（Ovry-Dx1 模型）；或分类为良性、不确定或恶性（Ovry-Dx2 模型）。比较了 DNN 模型在测试集中分类卵巢肿瘤的灵敏度和特异性，与 SA 的诊断性能。
结果：当敏感性为 96.0%时，Ovry-Dx1 的特异性与 SA 相似（86.7%比 88.0%；P=1.0）。当将 12.7%的病变指定为不确定时，Ovry-Dx2 的敏感性为 97.1%，特异性为 93.7%。通过在不确定病例中补充 Ovry-Dx2 和 SA，整体敏感性（96.0%）和特异性（89.3%）与在所有病例中使用 SA 无显著差异（P=1.0）。
结论：基于 DNN 的超声图像分析可以预测卵巢恶性肿瘤，其诊断准确性可与人类专家检查者相媲美，表明这些模型可能在卵巢肿瘤患者的分诊中发挥作用。© 2020 作者。约翰威立父子公司出版由国际妇产科超声学会代表超声在妇产科。
Ultrasound Obstet Gynecol. 2017-11
Ultrasound Obstet Gynecol. 2023-10
Sci Rep. 2025-4-21
Bioengineering (Basel). 2025-3-13
Abdom Radiol (NY). 2018-4
Zotero 插件
