A Deep Residual U-Net Algorithm for Automatic Detection and Quantification of Ascites on Abdominopelvic Computed Tomography Images Acquired in the Emergency Department: Model Development and Validation.

Hoon Ko,Jei Hee Lee,Jimi Huh,Heewon Chung,Yousun Ko,Kyung Won Kim,Jinseok Lee,Jai Keun Kim

doi:10.2196/34415

Abstract

BackgroundDetection and quantification of intra-abdominal free fluid (ie, ascites) on computed tomography (CT) images are essential processes for finding emergent or urgent conditions in patients. In an emergency department, automatic detection and quantification of ascites will be beneficial.ObjectiveWe aimed to develop an artificial intelligence (AI) algorithm for the automatic detection and quantification of ascites simultaneously using a single deep learning model (DLM).MethodsWe developed 2D DLMs based on deep residual U-Net, U-Net, bidirectional U-Net, and recurrent residual U-Net (R2U-Net) algorithms to segment areas of ascites on abdominopelvic CT images. Based on segmentation results, the DLMs detected ascites by classifying CT images into ascites images and nonascites images. The AI algorithms were trained using 6337 CT images from 160 subjects (80 with ascites and 80 without ascites) and tested using 1635 CT images from 40 subjects (20 with ascites and 20 without ascites). The performance of the AI algorithms was evaluated for diagnostic accuracy of ascites detection and for segmentation accuracy of ascites areas. Of these DLMs, we proposed an AI algorithm with the best performance.ResultsThe segmentation accuracy was the highest for the deep residual U-Net model with a mean intersection over union (mIoU) value of 0.87, followed by U-Net, bidirectional U-Net, and R2U-Net models (mIoU values of 0.80, 0.77, and 0.67, respectively). The detection accuracy was the highest for the deep residual U-Net model (0.96), followed by U-Net, bidirectional U-Net, and R2U-Net models (0.90, 0.88, and 0.82, respectively). The deep residual U-Net model also achieved high sensitivity (0.96) and high specificity (0.96).ConclusionsWe propose a deep residual U-Net–based AI algorithm for automatic detection and quantification of ascites on abdominopelvic CT scans, which provides excellent performance.

Highlights

Computed tomography (CT) of the abdomen and pelvis continues to be the primary modality for patients who visit an emergency department for abdominal pain or trauma, especially in time-critical situations [1]
We proposed the model for ascites region segmentation based on a single abdomen computed tomography (CT) image using a deep residual U-Net algorithm
Similar to the cross-validation results, these results show that the deep residual U-Net model with four residual blocks including two convolutional layers provided the highest mean intersection over union (mIoU) (0.87) and area under the ROC curve (AUROC) (0.96) with the isolated testing data set (n=1635)

Summary

Introduction

Immediate assessment of CT is required, but limited radiologic resources may hamper or delay the recognition of patients who need urgent intervention or surgery [2]. To overcome these challenges, the development of artificial intelligence (AI) techniques using a deep learning model (DLM) to detect critical findings on CT images might be a possible solution [3]. Detection and quantification of intra-abdominal free fluid (ie, ascites) on computed tomography (CT) images are essential processes for finding emergent or urgent conditions in patients. Automatic detection and quantification of ascites will be beneficial

Methods

Results

Discussion

Conclusion