Analysis of neural networks for routine classification of sixteen ultrasound upper abdominal cross sections

Lawley, Alistair and Hampson, Rory and Worrall, Kevin and Dobie, Gordon (2024) Analysis of neural networks for routine classification of sixteen ultrasound upper abdominal cross sections. Abdominal Radiology, 49 (2). pp. 651-661. ISSN 2366-0058 (https://doi.org/10.1007/s00261-023-04147-x)

Full text not available in this repository.Request a copy

Abstract

Purpose: Abdominal ultrasound screening requires the capture of multiple standardized plane views as per clinical guidelines. Currently, the extent of adherence to such guidelines is dependent entirely on the skills of the sonographer. The use of neural network classification has the potential to better standardize captured plane views and streamline plane capture reducing the time burden on operators by combatting operator variability. Methods: A dataset consisting of 16 routine upper abdominal ultrasound scans from 64 patients was used to test the classification accuracy of 9 neural networks. These networks were tested on both a small, idealised subset of 800 samples as well as full video sweeps of the region of interest using stratified sampling and transfer learning. Results: The highest validation accuracy attained by both GoogLeNet and InceptionV3 is 83.9% using transfer learning and the large sample set of 26,294 images. A top-2 accuracy of 95.1% was achieved using InceptionV3. Alexnet attained the highest accuracy of 79.5% (top-2 of 91.5%) for the smaller sample set of 800 images. The neural networks evaluated during this study were also successfully able to identify problematic individual cross sections such as between kidneys, with right and left kidney being accurately identified 78.6% and 89.7% respectively. Conclusion: Dataset size proved a more important factor in determining accuracy than network selection with more complex neural networks providing higher accuracy as dataset size increases and simpler linear neural networks providing better results where the dataset is small.

CORE (COnnecting REpositories)