Automatic Classification of Hepatic Cystic Echinococcosis Using Ultrasound Images and Deep Learning

Abstract

Background Hepatic cystic echinococcosis is the main form of hepatic echinococcosis, which is a life‐threatening liver disease caused by parasites that requires a precise diagnosis and proper treatment. Objective This study focuses on the automatic classification system of five different subtypes of hepatic cystic echinococcosis based on ultrasound images and deep learning algorithms. Methods Three popular deep convolutional neural networks (VGG19, Inception‐v3, and ResNet18) with and without pretrained weights were selected to test their performance on the classification task, and the experiments were followed by a 5‐fold cross‐validation process. Results A total of 1820 abdominal ultrasound images covering five subtypes of hepatic cystic echinococcosis from 967 patients were used in the study. The classification accuracy for the models with pretrained weights (fine‐tuning) ranged from 88.2 to 90.6%. The best accuracy of 90.6% was obtained by VGG19. For comparison, the models without pretrained weights (from scratch) achieved a lower accuracy, ranging from 69.4 to 75.1%. Conclusion Deep convolutional neural networks with pretrained weights are capable of recognizing different subtypes of hepatic cystic echinococcosis from ultrasound images, which are expected to be applied in the computer‐aided diagnosis systems in future work.

A two‐stage multiresolution neural network for automatic diagnosis of hepatic echinococcosis from ultrasound images: A multicenter study

“…They collected CT scans from 160 patients (CE 103 and AE 57) and achieved a precision and recall of 80.45% and 83.72% (F1 score = 82.05%) for the CE vs. AE classification. Due to the similar reason that they used a segmentation network to detect lesions automatically instead of using manual annotation, the performance is much lower than that in the study by Wu et al 27 …”

“…Two recent studies have documented the effectiveness of deep CNN‐based methods in the classification of HE from either ultrasound 27 or CT 28 images. Table 6 describes the differences in detail between our study and the two studies.…”

“…27,28 Xin et al 28 proposed an automatic method to segment and classify HE lesions based on a CNN and CT images. Wu et al 27 proposed a semiautomatic method to classify hepatic CE using transfer learning and ultrasound images. However, the two studies focused on either a coarse classification (e.g., CE vs. AE) or the classification of a subset of HE (e.g., CE), instead of a more complete classification.…”

“…In the context of ultrasound image analysis, deep learning has been used to segment ovaries and follicles from 3D ultrasound, 21 localize standard planes, 22,23 assess the severity of COVID‐19 from lung ultrasound images, 24 predict axillary lymph node status in breast cancer, 25 and predict lymph node metastasis of papillary thyroid carcinoma 26 . For the classification of HE, we found the two most relevant studies 27,28 . Xin et al 28 …”

A systematic review on application of deep learning in digestive system image processing

“…Wu et al used three types of CNNs for DL, and because the architecture and features extraction was different, the final result was not wholly consistent. The three systems complement each other further to improve the accuracy of the model's accuracy and ultimately enable the exact classification of hepatic cystic echinococcosis under ultrasound [70]. Ultrasonography(US) has crucial diagnostic value for benign and malignant lesions of the liver.…”