Faculty of Automation, Computers and Electronics, University of Craiova, Craiova, Romania.
Research Center of Gastroenterology and Hepatology Craiova, University of Medicine and Pharmacy Craiova, Craiova, Romania.
PLoS One. 2021 Jun 28;16(6):e0251701. doi: 10.1371/journal.pone.0251701. eCollection 2021.
Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.
胰腺局灶性肿块的鉴别诊断基于内镜超声（EUS）引导下的细针抽吸活检（EUS-FNA/FNB）。有几种影像学技术（即灰阶、彩色多普勒、增强对比和弹性成像）用于鉴别诊断。然而，诊断仍然高度依赖于操作者。为了解决这个问题，机器学习算法（MLA）可以通过实时分析大量临床图像来生成自动计算机辅助诊断（CAD）。我们旨在开发一种 MLA 来描述 EUS 过程中的胰腺局灶性肿块。该研究纳入了 65 例胰腺局灶性肿块患者，每位患者选择 20 个 EUS 图像（灰阶、彩色多普勒、动脉期和静脉期增强以及弹性成像）。根据细胞学检查将图像分类为：慢性假性肿瘤性胰腺炎（CPP）、神经内分泌肿瘤（PNET）和导管腺癌（PDAC）。MLA 基于一种深度学习方法，该方法结合了卷积神经网络（CNN）和长短期记忆神经网络（LSTM）。2688 张图像用于训练，672 张图像用于测试深度学习模型。CNN 用于识别图像的鉴别特征，而 LSTM 神经网络用于提取图像之间的依赖关系。该模型预测的临床诊断曲线下面积指数为 0.98，总体准确率为 98.26%。PDAC 的阴性预测值（NPV）和阳性预测值（PPV）及相应的 95%置信区间（CI）分别为 96.7%、[94.5，98.9]和 98.1%、[96.81，99.4]，CPP 的 NPV 和 PPV 及相应的 95%CI 分别为 96.5%、[94.1，98.8]和 99.7%、[99.3，100]，PNET 的 NPV 和 PPV 及相应的 95%CI 分别为 98.9%、[97.5，100]和 98.3%、[97.1，99.4]。在对独立测试队列进行进一步验证后，该方法有望成为一种实时区分胰腺局灶性肿块的有效 CAD 工具。
