Diagnostic Ultrasound in Ophthalmology

Automated classification of multiple ophthalmic diseases using ultrasound images by deep learning

BACKGROUND

Ultrasound imaging is suitable for detecting and diagnosing ophthalmic abnormalities. However, a shortage of experienced sonographers and ophthalmologists remains a problem. This study aims to develop a multibranch transformer network (MBT-Net) for the automated classification of multiple ophthalmic diseases using B-mode ultrasound images.

METHODS

Ultrasound images with six clinically confirmed categories, including normal, retinal detachment, vitreous haemorrhage, intraocular tumour, posterior scleral staphyloma and other abnormalities, were used to develop and evaluate the MBT-Net. Images were derived from five different ultrasonic devices operated by different sonographers and divided into training set, validation set, internal testing set and temporal external testing set. Two senior ophthalmologists and two junior ophthalmologists were recruited to compare the model's performance.

RESULTS

A total of 10 184 ultrasound images were collected. The MBT-Net got an accuracy of 87.80% (95% CI 86.26% to 89.18%) in the internal testing set, which was significantly higher than junior ophthalmologists (95% CI 67.37% to 79.16%; both p<0.05) and lower than senior ophthalmologists (95% CI 89.45% to 92.61%; both p<0.05). The micro-average area under the curve of the six-category classification was 0.98. With reference to comprehensive clinical diagnosis, the measurements of agreement were almost perfect in the MBT-Net (kappa=0.85, p<0.05). There was no significant difference in the accuracy of the MBT-Net across five ultrasonic devices (p=0.27). The MBT-Net got an accuracy of 82.21% (95% CI 78.45% to 85.44%) in the temporal external testing set.

CONCLUSIONS

The MBT-Net showed high accuracy for screening and diagnosing multiple ophthalmic diseases using only ultrasound images across mutioperators and mutidevices.

The utility of bedside ultrasound in the detection of a ruptured globe in a porcine model

BACKGROUND

Recent case reports have shown that ultrasonography can be used to diagnose ocular pathology in an emergency setting. Ultrasound may be especially useful when periorbital edema and pain interfere with the examination of the post-traumatic eye.

OBJECTIVE

This study evaluated the ability of emergency physicians to detect a ruptured globe in an ex-vivo porcine model.

METHODS

Following a brief training lecture, 15 emergency medicine residents and 4 emergency medicine attending physicians used ultrasonography to evaluate 18 porcine eyes, randomized as normal, ruptured, or completely devoid of vitreous humor. The consequences of ultrasound applanation with this method were evaluated by measuring intraocular pressure changes with and without a 1mm clear plastic shield.

RESULTS

Our study participants were able to identify abnormal eyes with a sensitivity of 79% (95% CI 73% to 84%) and a specificity of 51% (95% CI 41% to 61%). Intraocular pressure increased 5% with ultrasound applanation, though with a 1mm thick plastic shield there was no measurable change.

CONCLUSIONS

Ultrasound imaging may be a future modality to be used by trained emergency physicians to expedite the identification of a rupture globe, but it is unlikely to replace more definitive imaging techniques. The use of a clear plastic barrier in this porcine model prevents an increase in intra-ocular pressure without affecting image quality, and should be used in any future studies on this method.