Gallbladder Polyp Classification in Ultrasound Images Using an Ensemble Convolutional Neural Network Model

Abstract

Differential diagnosis of true gallbladder polyps remains a challenging task. This study aimed to differentiate true polyps in ultrasound images using deep learning, especially gallbladder polyps less than 20 mm in size, where clinical distinction is necessary. A total of 501 patients with gallbladder polyp pathology confirmed through cholecystectomy were enrolled from two tertiary hospitals. Abdominal ultrasound images of gallbladder polyps from these patients were analyzed using an ensemble model combining three convolutional neural network (CNN) models and a 5-fold cross-validation. True polyp diagnosis with the ensemble model that learned only using ultrasonography images achieved an area under receiver operating characteristic curve (AUC) of 0.8960 and accuracy of 83.63%. After adding patient age and polyp size information, the diagnostic performance of the ensemble model improved, with a high specificity of 88.35%, AUC of 0.9082, and accuracy of 87.61%, outperforming the individual CNN models constituting the ensemble model. In the subgroup analysis, the ensemble model showed the best performance with AUC of 0.9131 for polyps larger than 10 mm. Our proposed ensemble model that combines three CNN models classifies gallbladder polyps of less than 20 mm in ultrasonography images with high accuracy and can be useful for avoiding unnecessary cholecystectomy with high specificity.

Diagnosing gangrenous cholecystitis on computed tomography using deep learning: A preliminary study

“…In recent years, numerous applications of deep learning have been proposed in the medical field, several which have been reported in the gallbladder. Kim et al 15 ,. Jeong et al 16 ,.…”

“…In recent years, numerous applications of deep learning have been proposed in the medical field, several which have been reported in the gallbladder. Kim et al 15 , Jeong et al 16 , and Jang et al 17 evaluated the diagnostic performance of deep learning in differentiating polypoid lesions using US images. Loukas et al 18 proposed a deep learning approach for the assessment of gallbladder wall vascularity from images of laparoscopic cholecystectomy.…”

Contemporary diagnosis and management of gallbladder polyps

“…The most widely used diagnostic tool as a first step in day practice is abdominal US, [25,[46][47][48][49] followed by CT [50][51][52] and MRI, [3,10,20,53,54] to evaluate GB pathology, particularly for differentiating benign from malignant lesions. CT or better MRI can overcome any misdiagnosis of conventional US incidental findings alone that may lead to potentially unnecessary operations.…”

“…CT or better MRI can overcome any misdiagnosis of conventional US incidental findings alone that may lead to potentially unnecessary operations. [25,55] In challenging cases high-resolution US, novel three-dimensional US, endoscopic US or contrast-enhanced endoscopic US could be helpful. [4,10,23] The used diagnostic tools for gallbladder polyps are shown in Table 2.…”

“…[3,4,10,20,23] The US accuracy is important and may be increased by the above current modalities. [25] On US, the differential diagnosis of true or neoplastic polyps is challenging. [26][27][28] The prediction of malignant polyps is valuable, [10,[29][30][31] and relevant scoring systems have been developed.…”