Evaluation of a hybrid pipeline for automated segmentation of solid lesions based on mathematical algorithms and deep learning

Abstract

We evaluate the accuracy of an original hybrid segmentation pipeline, combining variational and deep learning methods, in the segmentation of CT scans of stented aortic aneurysms, abdominal organs and brain lesions. The hybrid pipeline is trained on 50 aortic CT scans and tested on 10. Additionally, we trained and tested the hybrid pipeline on publicly available datasets of CT scans of abdominal organs and MR scans of brain tumours. We tested the accuracy of the hybrid pipeline against a gold standard (manual segmentation) and compared its performance to that of a standard automated segmentation method with commonly used metrics, including the DICE and JACCARD and volumetric similarity (VS) coefficients, and the Hausdorff Distance (HD). Results. The hybrid pipeline produced very accurate segmentations of the aorta, with mean DICE, JACCARD and VS coefficients of: 0.909, 0.837 and 0.972 in thrombus segmentation and 0.937, 0.884 and 0.970 for stent and lumen segmentation. It consistently outperformed the standard automated method. Similar results were observed when the hybrid pipeline was trained and tested on publicly available datasets, with mean DICE scores of: 0.832 on brain tumour segmentation, and 0.894/0.841/0.853/0.847/0.941 on left kidney/right kidney/spleen/aorta/liver organ segmentation.

A semi-automatic segmentation method for meningioma developed using a variational approach model

“…The segmentation results were compared using standard metrics including the Sørensen–Dice coefficient (DICE), JACCARD index, volumetric similarity (VS) coefficient and Haussdorff distance (HD). 19 Both DICE and JACCARD scores range between 0 (where no overlap between compared segmentation results occurs) and 1 (where the two segmentation results are an exact match). VS represents how similar the volumes of the segmented outputs are, not influenced by the overlap.…”