Due to lack of the practical technique to measure the biomechanical properties of the ocular cornea in vivo, clinical ophthalmologists have some difficulties in understanding the deformation mechanism of the cornea under the action of physiological intraocular pressures. Using Young's theory analysis of the corneal deformation during applanation tonometry, the relation between the elasticity moduli of the cornea and the applanated corneal area and the measured and true intraocular pressures can be obtained. A new applanation technique has been developed for measuring the biomechanical properties of the ocular cornea tissue in vivo, which can simultaneously acquire the data of the applanation area and displacement of the corneal deformation as well as the exerted applanation force on the cornea. Experimental results on a rabbit's eyeball demonstrated that the present technique could be used to measure the elasticity moduli and creep properties of the ocular cornea nondestructively in vivo.
Accurate reconstruction of tissue elasticity modulus distribution has always been an important challenge in ultrasound elastography. Considering that existing deep learning-based supervised reconstruction methods only use simulated displacement data with random noise in training, which cannot fully provide the complexity and diversity brought by in-vivo ultrasound data, this study introduces the use of displacement data obtained by tracking in-vivo ultrasound radio frequency signals (i.e., real displacement data) during training, employing a semi-supervised approach to enhance the prediction accuracy of the model. Experimental results indicate that in phantom experiments, the semi-supervised model augmented with real displacement data provides more accurate predictions, with mean absolute errors and mean relative errors both around 3%, while the corresponding data for the fully supervised model are around 5%. When processing real displacement data, the area of prediction error of semi-supervised model was less than that of fully supervised model. The findings of this study confirm the effectiveness and practicality of the proposed approach, providing new insights for the application of deep learning methods in the reconstruction of elastic distribution from in-vivo ultrasound data.