Semantic Segmentation of Extraocular Muscles on Computed Tomography Images Using Convolutional Neural Networks

Normal Diameters of Extraocular Muscles: A Nigerian Retrospective Study

BACKGROUND

The thickness of extraocular muscles (EOMs) is important in the management of several conditions associated with EOM enlargement. This study determined the normative values of EOM diameters in adult patients seen at a teaching hospital in Nigeria.

MATERIALS AND METHODS

The study measured the thickness of the EOMs and the interzygomatic line (IZL) on brain images of 300 patients with non-orbital conditions (150 computed tomography [CT] and 150 magnetic resonance imaging [MRI]) archived in the radiological database of Delta State University Hospital, Nigeria, after ethical clearance. The Statistical Package for the Social Sciences (version 23) was used to obtain descriptive statistics and further compare the variables based on gender, age groups and laterality. The association between parameters was tested using Pearson's correlation test. A probability value of <5% was considered significant.

RESULTS

The thickest muscles were the medial rectus (0.42 ± 0.08 cm) and superior muscle group (0.42 ± 0.33 cm) on CT and the inferior rectus (0.40 ± 0.08 cm) on MRI. The diameters were symmetrical with sexual dimorphism in the superior muscle group on CT, medial and lateral recti on MRI and sum of all EOMs on both imaging groups (P < 0.05). The superior muscle group and the sum of all EOMs showed significant age group variations and a positive correlation with age. We noted a positive correlation between each EOM diameter and the sum of all EOMs besides the IZL (P < 0.05).

CONCLUSION

This study offers normative data regarding EOMs that radiologists and ophthalmologists can use to diagnose disease conditions that cause EOM enlargement and further assess their response to treatment.

Generative adversarial networks for spine imaging: A critical review of current applications

PURPOSE

In recent years, the field of medical imaging has witnessed remarkable advancements, with innovative technologies which revolutionized the visualization and analysis of the human spine. Among the groundbreaking developments in medical imaging, Generative Adversarial Networks (GANs) have emerged as a transformative tool, offering unprecedented possibilities in enhancing spinal imaging techniques and diagnostic outcomes. This review paper aims to provide a comprehensive overview of the use of GANs in spinal imaging, and to emphasize their potential to improve the diagnosis and treatment of spine-related disorders. A specific review focusing on Generative Adversarial Networks (GANs) in the context of medical spine imaging is needed to provide a comprehensive and specialized analysis of the unique challenges, applications, and advancements within this specific domain, which might not be fully addressed in broader reviews covering GANs in general medical imaging. Such a review can offer insights into the tailored solutions and innovations that GANs bring to the field of spinal medical imaging.

METHODS

An extensive literature search from 2017 until July 2023, was conducted using the most important search engines and identified studies that used GANs in spinal imaging.

RESULTS

The implementations include generating fat suppressed T2-weighted (fsT2W) images from T1 and T2-weighted sequences, to reduce scan time. The generated images had a significantly better image quality than true fsT2W images and could improve diagnostic accuracy for certain pathologies. GANs were also utilized in generating virtual thin-slice images of intervertebral spaces, creating digital twins of human vertebrae, and predicting fracture response. Lastly, they could be applied to convert CT to MRI images, with the potential to generate near-MR images from CT without MRI.

CONCLUSIONS

GANs have promising applications in personalized medicine, image augmentation, and improved diagnostic accuracy. However, limitations such as small databases and misalignment in CT-MRI pairs, must be considered.

Deep-Learning-Based Segmentation of Extraocular Muscles from Magnetic Resonance Images

In this study, we investigated the performance of four deep learning frameworks of U-Net, U-NeXt, DeepLabV3+, and ConResNet in multi-class pixel-based segmentation of the extraocular muscles (EOMs) from coronal MRI. Performances of the four models were evaluated and compared with the standard F-measure-based metrics of intersection over union (IoU) and Dice, where the U-Net achieved the highest overall IoU and Dice scores of 0.77 and 0.85, respectively. Centroid distance offset between identified and ground truth EOM centroids was measured where U-Net and DeepLabV3+ achieved low offsets (p > 0.05) of 0.33 mm and 0.35 mm, respectively. Our results also demonstrated that segmentation accuracy varies in spatially different image planes. This study systematically compared factors that impact the variability of segmentation and morphometric accuracy of the deep learning models when applied to segmenting EOMs from MRI.