Zhao Tingting, Zeng Zhiyong, Li Tong, Tao Wenjing, Yu Xing, Feng Tao, Bu Rui
School of Statistics and Mathematics, Yunnan University of Finance and Economics, Longquan Road, Kunming, 650221 Yunnan China.
Department of Medical Ultrasound, The Second Affiliated Hospital of Kunming Medical University, Dianmian Road, Kunming, 650101 Yunnan China.
Health Inf Sci Syst. 2023 Mar 19;11(1):15. doi: 10.1007/s13755-023-00217-y. eCollection 2023 Dec.
Ultrasound image acquisition has the advantages of being low cost, rapid, and non-invasive, and it does not produce radiation. Currently, ultrasound is widely used in the diagnosis of liver tumors. However, owing to the complex presentation and diverse features of benign and malignant liver tumors, accurate diagnosis of liver tumors using ultrasound is difficult even for experienced radiologists. In recent years, artificial intelligence-assisted diagnosis has proven to provide effective support to radiologists. However, there is room for further improvement in the existing ultrasound artificial intelligence diagnostic model of liver tumor. First, the image diagnostic model may not fully consider relevant clinical data in the decision-making process. Second, owing to the difficulty in collecting biopsy pathology and physician-labeled ultrasound data of liver tumors, training datasets are usually small, and commonly used large neural networks tend to overfit on small datasets, which seriously affects the generalization of the model.
In this study, we propose a deep learning-assisted diagnosis model called USC-ENet, which integrates B-mode ultrasound features of liver tumors and clinical data of patients, and we design a small neural network specifically for small-scale medical images combined with an attention mechanism.
Real data from 542 patients with liver tumors (N = 2168 images) are used during model training and validation. Experiments show that USC-ENet can achieve a good classification effect (area under the curve = 0.956, sensitivity = 0.915, and specificity = 0.880) after small-scale data training, and it has certain interpretability, showing good potential for clinical adoption. In conclusion, our model provides not only a reliable second opinion for radiologists but also a reference for junior radiologists who lack clinical experience.
超声图像采集具有成本低、速度快、无创且不产生辐射的优点。目前，超声广泛应用于肝脏肿瘤的诊断。然而，由于良性和恶性肝脏肿瘤的表现复杂且特征多样，即使是经验丰富的放射科医生，使用超声准确诊断肝脏肿瘤也很困难。近年来，人工智能辅助诊断已被证明能为放射科医生提供有效支持。然而，现有的肝脏肿瘤超声人工智能诊断模型仍有进一步改进的空间。首先，图像诊断模型在决策过程中可能没有充分考虑相关临床数据。其次，由于肝脏肿瘤活检病理和医生标注的超声数据收集困难，训练数据集通常较小，常用的大型神经网络在小数据集上容易过拟合，这严重影响了模型的泛化能力。
在本研究中，我们提出了一种名为USC-ENet的深度学习辅助诊断模型，该模型整合了肝脏肿瘤的B超特征和患者的临床数据，并结合注意力机制设计了一个专门用于小规模医学图像的小型神经网络。
在模型训练和验证过程中使用了542例肝脏肿瘤患者的真实数据（N = 2168张图像）。实验表明，USC-ENet在小规模数据训练后能取得良好的分类效果（曲线下面积 = 0.956，灵敏度 = 0.915，特异性 = 0.880），并且具有一定的可解释性，显示出良好的临床应用潜力。总之，我们的模型不仅为放射科医生提供了可靠的第二意见，也为缺乏临床经验的初级放射科医生提供了参考。
