Tomey (Japan)

To predict multiple postoperative parameters following implantable collamer lens (ICL) surgery with generative artificial intelligence, using preoperative anterior segment optical coherence tomography (AS-OCT) images as the input. Daikanyama Eye Clinic, Tokyo, Japan; Miyata Eye Hospital, Miyazaki, Japan; Nagoya Eye Clinic, Nagoya, Japan; Yokohama Sky Eye Clinic, Kanagawa, Japan. Retrospective Study. Our research involved paired preoperative and postoperative AS-OCT images from 1010 patients (1585 eyes) who underwent horizontal ICL implantation, and 86 patients (86 eyes) who received vertical implantation from four clinical centers. A Generative Adversarial Network, ICL-GAN, was employed to predict postoperative structures based on preoperative AS-OCT slice from each eye. Postoperative parameters, including vault, AOD500, and TIA500, were measured from the predicted postoperative structures. The prediction error was evaluated using the mean absolute error (MAE) and root mean square error (RMSE). The correlation and agreement between the prediction and the achieved values were also analyzed. The vaults measured from the predictions of postoperative anatomical structure have a strong correlation with the achieved values on horizontal data (r=0.659, p<0.01 for ICL size of 12.1mm, r=0.799, p<0.01 for 12.6mm, and r=0.737, p<0.01 for 13.2mm) and when compared with the NK-formula and KS-formula achieved the minimum prediction errors (MAE are 105 μm, 114 μm, and 111 μm). ICL-GAN also performed best on the vertical implantation data. The AOD500 and TIA500 also showed good correlation and agreement with the achieved values. The generative artificial intelligence demonstrates the capability to predict multiple postoperative parameters following ICL surgery.

Abstract PurposeTo determine the structural characteristics of the peripapillary sclera in myopic eyes using polarization-sensitive optical coherence tomography (PS-OCT).MethodsPatients with myopia who underwent PS-OCT imaging between April and June 2023 were studied. The intensity, optic axis, and birefringence of PS-OCT images were analyzed to determine the surface of the lamina cribrosa (LC). The direction and arrangement of the scleral collagen fibers in the peripapillary region and scleral ridge were determined.ResultsOne hundred and ten eyes of 59 patients with myopia (mean axial length, 30.00 ± 1.98 mm) were studied. The scleral fibers around the optic nerve were arranged circularly in all eyes regardless of the presence or size of the peripapillary atrophy. Inner scleral fibers that penetrated beneath this circular arrangement were detected in 98 eyes (89.1%). There was a Y-shaped split at the point of penetration in 77 eyes (70.0%). The integrity of the circular arrangement and penetrating scleral fiber complexes remained intact even in cases of severe peripapillary scleral deformation. A scleral ridge was identified in 27 eyes (24.5%), and it appeared as a full-thickness protrusion composed primarily of outer scleral fibers. The ridge was consistently located outside the circular arrangement.ConclusionsThe penetration of the radial inner scleral fibers into the circular arrangement and extension to the LC suggest that they act as stabilizing anchors for the circular structure. The differences of the scleral ridges from those in eyes with dome-shaped macula suggest that unique mechanisms cause the scleral differences.

Bu araştırmanın amacı, Kutadgu Bilig’in eğitsel değerine yönelik çalışmaları bir araya getirmek, ilgili araştırmaları birtakım özelliklerine göre inceleyip değerlendirmektir. Araştırma “Doküman İncelemesi” yöntemiyle yürütülmüş ve verilerin çözümlenmesi için “İçerik Analizi” tekniği kullanılmıştır. Tr Dizin ve Ulusal Tez Merkezi veri tabanları incelenerek yapılan alan yazını taraması sonucunda Kutadgu Bilig üzerine yayımlanmış olan çalışmalar içerisinden eserin eğitsel değerine yönelik yürütülmüş olan 21 makale, 8 yüksek lisans tezi, 2 doktora tezi tespit edilmiştir. Elde edilen veriler 5 farklı başlık altında tablolaştırılarak aktarılmıştır. Araştırma sonucunda Kutadgu Bilig’in eğitsel değeri üzerine yapılan çalışmaların çoğunlukla 2017-2021 yılları arasında yoğunlaştığı, birçoğunda araştırma ve analiz yöntemlerinin belirtilmediği, belirtilenlerin ise nitel şekilde desenlendiği ve bu araştırmalarda toplanan verilerin içerik analiziyle analiz edildiği tespit edilmiştir.

Abstract The OA-2000 is an optical biometer that automatically measures all parameters needed for IOL power calculation. Axial measurements are obtained by means of swept-source optical coherence tomography and corneal measurements by means of a Placido ring corneal topographer. Long coherence length allows high penetration and high success rate on long axial length myopic eyes. Different technical features provide a high success rate in measuring dense cataract eyes. Corneal keratometry and astigmatism are measured with accuracy and precision. The device includes different kinds of IOL formulae: standard, toric, and post-Lasik. In addition, software for optimization of IOL constants is included in OA-2000.

Cataracts are the leading cause of visual impairment and blindness globally attracting abroad attention from society. Over the years researchers have developed many state-of-the-art convolutional neural networks (CNNs) to recognize cataract severity levels based on different ophthalmic images. However most current works focus on improving cataract recognition performance by designing complex CNNs often ignoring resource-constrained medical device limitations. To this problem this paper proposes a novel dual-mixed channel-independent convolution (DMIConv) method which takes advantage of the multiscale convolution kernels by combining a depthwise convolution with a depthwise dilated convolution sequentially. Moreover we build a lightweight dual-mixed channel-independent network (DMINet) to recognize cataracts. To verify the effectiveness and efficiency of DMINet we conduct extensive experiments on a clinical anterior segment optical coherence tomography (AS-OCT) dataset of nuclear cataract (NC) and a publicly available OCT dataset. The results show that our proposed DMINet keeps a better tradeoff between the model complexity and the classification performance than efficient CNNs e.g DMINet outperforms MixNet by 3.34% of accuracy by using 4.58 % fewer parameters

The intra-class imbalance usually occurs in medical images due to external influences, such as noise interference and changes in camera angle. It leads to complex textures and varied appearances within the target object region and makes segmentation task challenging. To deal with this kind of problem, we proposed a dual-path framework in this paper. Considering that the object consists of two subclasses (majority- and minority-subclass), a deep learning model is adopted to separate them. We constructed two weighted maps for the dual paths, related to majority- and minority-subclass respectively. A fusion module was designed to generate the final output according to the results from the dual paths. The experimental results on two datasets shew our approach's validity and superiority for medical image segmentation compared with other competing methods.

The quality of the cornea endothelial microscopy image is critical for clinical analysis. Although the noncontact specular microscope is more user-friendly than the contact confocal microscope, the imaging quality of the specular microscope is lower. The modality transfer is a promising solution for image quality enhancement. This paper proposes a Structure Consistent Generative Adversarial Network (SC-GAN) to transfer the imaging style from the specular microscope to the confocal microscope. Specifically, we use the Fourier frequency domain consistency to preserve cell structure and propose a multi-scale perception discriminator to improve model robustness under cell size variation. Experiment results prove the effectiveness of our method.