Automatic segmentation of paravertebral muscles in abdominal CT scan by U-Net

Abstract

Sarcopenia, characterized by a decline of skeletal muscle mass, has emerged as an important prognostic factor for cancer patients. Trunk computed tomography (CT) is a commonly used modality for assessment of cancer disease extent and treatment outcome. CT images can also be used to analyze the skeletal muscle mass filtered by the appropriate range of Hounsfield scale. However, a manual depiction of skeletal muscle in CT scan images for assessing skeletal muscle mass is labor-intensive and unrealistic in clinical practice. In this paper, we propose a novel U-Net based segmentation system for CT scan of paravertebral muscles in the third and fourth lumbar spines. Since the number of training samples is limited (i.e., 1024 CT images only), it is well-known that the performance of the deep learning approach is restricted due to overfitting. A data augmentation strategy to enlarge the diversity of the training set to boost the performance further is employed. On the other hand, we also discuss how the number of features in our U-Net affects the performance of the semantic segmentation. The efficacies of the proposed methodology based on w/ and w/o data augmentation and different feature maps are compared in the experiments. We show that the Jaccard score is approximately 95.0% based on the proposed data augmentation method with only 16 feature maps used in U-Net. The stability and efficiency of the proposed U-Net are verified in the experiments in a cross-validation manner.

Automated classification of intravenous contrast enhancement phase of CT scans using residual networks

“…Our model could be used in conjunction with GAN's to create synthetic dataset augmentations reflecting a diverse distribution of contrast medium that may not otherwise be captured in small datasets. 1,2,13 In addition to fine-tuned dataset curation and augmentation, phase information from a CT scan could be used as an input feature when training models on diverse, multiphase CT datasets. This extra information could enhance model performance by lending inherently useful information about the CT scan to the model.…”

“…Data augmentation has been widely applied to improve the robustness and accuracy in training a deep learning model. 1,2 It is particularly important for medical images, such as CT scans, since dataset size is limited by costly acquisition and annotations. The existing literature often classifies CT scans as contrast and non-contrast, yet within the contrast-enhanced category there is significant variation.…”

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

“…U-Net MRI [5,7,11,19,25,27,[31][32][33][34][35][36][37][38][39][40][41][42]44,46,55,57,64,65,89,107] US [49,100,101] CT [4,9,13,15,16,59,69,[71][72][73][76][77][78][79][80][81]83,90,91,[93][94][95]99,[103]…”