Deep generative models for automated muscle segmentation in computed tomography scanning

Abstract

Accurate gluteus medius (GMd) volume evaluation may aid in the analysis of muscular atrophy states and help gain an improved understanding of patient recovery via rehabilitation. However, the segmentation of muscle regions in GMd images for cubic muscle volume assessment is time-consuming and labor-intensive. This study automated GMd-region segmentation from the computed tomography (CT) images of patients diagnosed with hip osteoarthritis using deep learning and evaluated the segmentation accuracy. To this end, 5250 augmented pairs of training data were obtained from five participants, and a conditional generative adversarial network was used to identify the relationships between the image pairs. Using the preserved test datasets, the results of automatic segmentation with the trained deep learning model were compared to those of manual segmentation in terms of the dice similarity coefficient (DSC), volume similarity (VS), and shape similarity (MS). As observed, the average DSC values for automatic and manual segmentations were 0.748 and 0.812, respectively, with a significant difference (p < 0.0001); the average VS values were 0.247 and 0.203, respectively, with no significant difference (p = 0.069); and the average MS values were 1.394 and 1.156, respectively, with no significant difference (p = 0.308). The GMd volumes obtained by automatic and manual segmentation were 246.2 cm3 and 282.9 cm3, respectively. The noninferiority of the DSC obtained by automatic segmentation was verified against that obtained by manual segmentation. Accordingly, the proposed GAN-based automatic GMd-segmentation technique is confirmed to be noninferior to manual segmentation. Therefore, the findings of this research confirm that the proposed method not only reduces time and effort but also facilitates accurate assessment of the cubic muscle volume.

Artificial Intelligence and Its Potential Application in Advancing Hip Osteoarthritis Care

“…A joint loading device developed using an iterative design process, has been deemed to have favorable impacts in the realm of efforts to develop a personalized joint loading predictive device. Using this along with imaging, improved network performance, and cartilage cellular and muscle structural and functional measures may add considerably to its clinical utility [30][31][32][33].…”

UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation

“…Robotic surgery, computer aided diagnosis, targeted radiation therapy require meticulous segmentation of affected organ from adjacent organs [1][2][3][4][5]. The authors of [6] examined the evolution of automatic multi-organ segmentation techniques, comparing traditional methods with deep learning approaches and found that deep learning methods consistently outperformed traditional approaches, indicating their superior efficiency in segmentation tasks.…”

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

“…In this regard, artificial intelligence (AI) approaches, such as deep learning (DL) have become increasingly popular methods for solving various automated computer vision tasks, such as the abovementioned segmentation. The advantage of DL algorithms is their ability to "learn" complex relationships from large datasets in a self-taught way, with minimal operator-imposed assumptions and without explicit knowledge of the data in terms of features to identify objects [4,[19][20][21]. Prior to the recent advances in DL solutions, intensity-based approaches were a common choice; however, they have limitations due to the strong influence of imaging artifacts and variations in the intensity of different organs, which leads to inconsistent and misleading interpretations of the results [22].…”