Vitreous hyper-reflective dots and the macular thickness after cataract surgery.

PURPOSE: To assess the association between vitreous hyper-reflective dots (VHD) and the macular thickness changes following uneventful phacoemulsification. METHODS: In this prospective cohort study optical coherence tomography (OCT) examinations were performed preoperatively and 1 week, 1 month and 3 months postoperatively in patients undergoing cataract surgery. OCT images were analyzed for retinal central subfield thickness (CST) and preretinal VHDs. Surgeries were recorded for the assessment of lens fragments in the space of Berger. RESULTS: 111 eyes of 97 patient were enrolled of whom 69 (62.2%) were female. VHDs were seen in 25 eyes (22.5%) at week 1; in 21 eyes (18.9%) at month 1 and in 3 eyes (2.7%) at month 3. In all eyes with VHDs retro-capsular lens fragments were visible immediately after phacoemulsification. The number of VHDs significantly decreased over the postoperative period. There was a moderate correlation between the number of VHDs and CST at 1 month (r = 0.426, p<0.001). In eyes with VHD the CST averaged 238.8±17.6 µm (214-266) at 1 week; 276.1±63.5 µm (231-481) at 1 month and 285.1±122.3 µm (227-785) at 3 months. In eyes with no detectable VHDs CST averaged 235.9±23.3 µm (192-311) at 1 week; 240.1±21.6 µm (200-288) at 1 month and 242.2±21.3 µm (205-289) at 3 months. Although the differences among the assessment points were relatively low, there was a significant difference in general (p<0.001, Friedman test). CONCLUSION: In conclusion, VHDs seem to cause macular thickening throughout the postoperative course. The origin of VHDs is still unknown; however, they presumably represent lens fragments that provoke subclinical inflammation.

Exceeding radiation thresholds for cataract induction in diagnostic imaging: a paediatric case report.

This case report investigates the radiation dose received by a paediatric patient with a ventricular assist device who underwent four non-contrast brain computed tomography (CT) scans, two brain perfusion CT scans and two head angiographic CT scans. The total estimated absorbed dose to the lens of the eye is above the 500 mGy radiation-induced cataract threshold. It is recommended that this patient and those with similar imaging histories have routine follow-up with an ophthalmologist. It is also recommended that radiation dose tracking and an electronic medical alert program be implemented to allow the identification of patients who may exceed tissue reaction thresholds.

In utero ultrasound diagnosis of bilateral cataract and hydrops in a mule pregnancy: Case report.

Once diagnosed pregnant with ultrasound at an early stage of gestation, mares are usually not examined before foaling. The objective of this case report was to highlight the importance of transrectal ultrasound screening examination and to report a unique case of fetal congenital cataracts associated with other feto-placental abnormalities in a mule pregnancy, its in utero ultrasound diagnosis and outcome. A 17-year-old Thoroughbred research mare carrying a mule fetus was examined by transrectal ultrasonography at 186 days of gestation for a routine pregnancy examination. Ultrasonography allowed in utero diagnosis of fetal congenital cataracts, hyperechogenic bowels, intrauterine growth restriction (IUGR), hydramnios and placental abnormalities. The mare was monitored bi-monthly to observe the progress of the pregnancy. At 258 days of gestation, the abnormal chorioallantois detached at the cervical star and at 272 days, fetal asystole was diagnosed. Abortion was induced and the fetus was delivered uneventfully. Post-mortem gross and histologic findings confirmed the prenatal ultrasonographic diagnosis. This case highlights the diagnostic value of a complete fetal ultrasound examination to detect equine fetal abnormalities.

A Transformer-Based Knowledge Distillation Network for Cortical Cataract Grading.

Cortical cataract, a common type of cataract, is particularly difficult to be diagnosed automatically due to the complex features of the lesions. Recently, many methods based on edge detection or deep learning were proposed for automatic cataract grading. However, these methods suffer a large performance drop in cortical cataract grading due to the more complex cortical opacities and uncertain data. In this paper, we propose a novel Transformer-based Knowledge Distillation Network, called TKD-Net, for cortical cataract grading. To tackle the complex opacity problem, we first devise a zone decomposition strategy to extract more refined features and introduce special sub-scores to consider critical factors of clinical cortical opacity assessment (location, area, density) for comprehensive quantification. Next, we develop a multi-modal mix-attention Transformer to efficiently fuse sub-scores and image modality for complex feature learning. However, obtaining the sub-score modality is a challenge in the clinic, which could cause the modality missing problem instead. To simultaneously alleviate the issues of modality missing and uncertain data, we further design a Transformer-based knowledge distillation method, which uses a teacher model with perfect data to guide a student model with modality-missing and uncertain data. We conduct extensive experiments on a dataset of commonly-used slit-lamp images annotated by the LOCS III grading system to demonstrate that our TKD-Net outperforms state-of-the-art methods, as well as the effectiveness of its key components. Codes are available at https://github.com/wjh892521292/Cataract_TKD-Net.

Adaptive enhancement of cataractous retinal images for contrast standardization.

Cataract affects the quality of fundus images, especially the contrast, due to lens opacity. In this paper, we propose a scheme to enhance different cataractous retinal images to the same contrast as normal images, which can automatically choose the suitable enhancement model based on cataract grading. A multi-level cataract dataset is constructed via the degradation model with quantified contrast. Then, an adaptive enhancement strategy is introduced to choose among three enhancement networks based on a blurriness classifier. The blurriness grading loss is proposed in the enhancement models to further constrain the contrast of the enhanced images. During test, the well-trained blurriness classifier can assist in the selection of enhancement networks with specific enhancement ability. Our method performs the best on the synthetic paired data on PSNR, SSIM, and FSIM and has the best PIQE and FID on 406 clinical fundus images. There is a 7.78% improvement for our method compared with the second on the introduced [Formula: see text] score without over-enhancement according to [Formula: see text], which demonstrates that the proper enhancement by our method is close to the high-quality images. The visual evaluation on multiple clinical datasets also shows the applicability of our method for different blurriness. The proposed method can benefit clinical diagnosis and improve the performance of computer-aided algorithms such as vessel tracking and vessel segmentation.

Multi-style spatial attention module for cortical cataract classification in AS-OCT image with supervised contrastive learning.

BACKGROUND AND OBJECTIVE: Precise cortical cataract (CC) classification plays a significant role in early cataract intervention and surgery. Anterior segment optical coherence tomography (AS-OCT) images have shown excellent potential in cataract diagnosis. However, due to the complex opacity distributions of CC, automatic AS-OCT-based CC classification has been rarely studied. In this paper, we aim to explore the opacity distribution characteristics of CC as clinical priori to enhance the representational capability of deep convolutional neural networks (CNNs) in CC classification tasks. METHODS: We propose a novel architectural unit, Multi-style Spatial Attention module (MSSA), which recalibrates intermediate feature maps by exploiting diverse clinical contexts. MSSA first extracts the clinical style context features with Group-wise Style Pooling (GSP), then refines the clinical style context features with Local Transform (LT), and finally executes group-wise feature map recalibration via Style Feature Recalibration (SFR). MSSA can be easily integrated into modern CNNs with negligible overhead. RESULTS: The extensive experiments on a CASIA2 AS-OCT dataset and two public ophthalmic datasets demonstrate the superiority of MSSA over state-of-the-art attention methods. The visualization analysis and ablation study are conducted to improve the explainability of MSSA in the decision-making process. CONCLUSIONS: Our proposed MSSANet utilized the opacity distribution characteristics of CC to enhance the representational power and explainability of deep convolutional neural network (CNN) and improve the CC classification performance. Our proposed method has the potential in the early clinical CC diagnosis.

Adaptive Tensor-Based Feature Extraction for Pupil Segmentation in Cataract Surgery.

Cataract surgery remains the only definitive treatment for visually significant cataracts, which are a major cause of preventable blindness worldwide. Successful performance of cataract surgery relies on stable dilation of the pupil. Automated pupil segmentation from surgical videos can assist surgeons in detecting risk factors for pupillary instability prior to the development of surgical complications. However, surgical illumination variations, surgical instrument obstruction, and lens material hydration during cataract surgery can limit pupil segmentation accuracy. To address these problems, we propose a novel method named adaptive wavelet tensor feature extraction (AWTFE). AWTFE is designed to enhance the accuracy of deep learning-powered pupil recognition systems. First, we represent the correlations among spatial information, color channels, and wavelet subbands by constructing a third-order tensor. We then utilize higher-order singular value decomposition to eliminate redundant information adaptively and estimate pupil feature information. We evaluated the proposed method by conducting experiments with state-of-the-art deep learning segmentation models on our BigCat dataset consisting of 5,700 annotated intraoperative images from 190 cataract surgeries and a public CaDIS dataset. The experimental results reveal that the AWTFE method effectively identifies features relevant to the pupil region and improved the overall performance of segmentation models by up to 2.26% (BigCat) and 3.31% (CaDIS). Incorporation of the AWTFE method led to statistically significant improvements in segmentation performance (P < 1.29 × 10-10 for each model) and yielded the highest-performing model overall (Dice coefficients of 94.74% and 96.71% for the BigCat and CaDIS datasets, respectively). In performance comparisons, the AWTFE consistently outperformed other feature extraction methods in enhancing model performance. In addition, the proposed AWTFE method significantly improved pupil recognition performance by up to 2.87% in particularly challenging phases of cataract surgery.

Change in Subfoveal Choroidal Thickness following Cataract Surgery Imaged with Enhanced Depth Imaging Optical Coherence Tomography.

BACKGROUND: Due to its invasive nature, cataract surgery can lead to inflammatory processes in the posterior segment, which can result in prolonged recovery times, reduced functional outcomes, and late-onset complications. The aim of the current study was to identify wherever phacoemulsification parameters play a role in choroidal thickness change following cataract surgery. METHODS: This prospective single-center study enrolled 31 patients (31 eyes) scheduled to undergo routine cataract surgery. Patients with previous ocular surgeries, pathologies or general disorders affecting vision were excluded. Patients were examined preoperatively, as well as 1, 4, and 12 weeks after surgery. Corrected distance visual acuity (CDVA), intraocular pressure (IOP) as well as cumulative dissipated energy (CDE), ultrasound time (UT), and fluids used during surgery were recorded. Subfoveal choroidal thickness was measured manually by two masked independent experts using enhanced depth imaging (EDI) optical coherence tomography (OCT). Furthermore, cataract density was automatically calculated using a custom MATLAB script and an anterior segment OCT. RESULTS: Subfoveal choroidal thickness increased significantly (p < 0.001, Student's paired sample t-test) and continuously during the 12-week-long follow-up period. Both the nuclear lens density and the improvement in CDVA correlated significantly with this increase (r = 0.413, p = 0.021 and r = 0.421, p = 0.018, respectively). Neither the CDE (r = 0.334, p = 0.071), the UT (r = 0.102, p = 0.629), the amount of fluid used (r = 0.237, p = 0.27) nor the decrease in IOP (r = - 0.197, p = 0.288) showed any significant correlation with the choroidal swelling. CONCLUSION: Cataract surgery leads to an increase in subfoveal choroidal thickness. While no statistically significant correlation to the phacoemulsification parameters could be established, this might be because of a selection bias due to the technological constraints of the OCT. Nevertheless, the choroid might play a central role in early- and late-onset complications.

MUTE: A multilevel-stimulated denoising strategy for single cataractous retinal image dehazing.

In this research, we studied the duality between cataractous retinal image dehazing and image denoising and proposed that the dehazing task for cataractous retinal images can be achieved with the combination of image denoising and sigmoid function. To do so, we introduce the double-pass fundus reflection model in the YPbPr color space and developed a multilevel stimulated denoising strategy termed MUTE. The transmission matrix of the cataract layer is expressed as the superposition of denoised raw images of different levels weighted by pixel-wise sigmoid functions. We further designed an intensity-based cost function that can guide the updating of the model parameters. They are updated by gradient descent with adaptive momentum estimation, which gives us the final refined transmission matrix of the cataract layer. We tested our methods on cataract retinal images from both public and proprietary databases, and we compared the performance of our method with other state-of-the-art enhancement methods. Both visual assessments and objective assessments show the superiority of the proposed method. We further demonstrated three potential applications including blood vessel segmentation, retinal image registrations, and diagnosing with enhanced images that may largely benefit from our proposed methods.

Differences Between Angle Configurations in Different Body Positions by Ultrasound Biomicroscopy in Patients with Cortical Age-Related Cataract.

Purpose: To investigate the differences in parameters related to angle configuration and lens position in patients with cortical age-related cataract by ultrasound biomicroscopy (UBM) in different body positions. Methods: Prospective study with 55 patients with cortical age-related cataract proposed for phacoemulsification, examined using a Compact Touch STS UBM (Quantel Medical, France). UBM bag/balloon technology was applied to measure the central anterior chamber depth (ACD) and lens vault (LV) in horizontal and vertical orientation in sitting and supine positions, angle opening distance (AOD500), trabecular iris angle (TIA) and iris lens angle (ILA) in four quadrants: superior, inferior, nasal, and temporal. Results: We found no significant difference in ACD between sitting and supine positions (p = 0.053); LV was significantly greater in the supine position (p < 0.001); AOD500 in superior and inferior quadrants were significantly longer in the sitting position (p = 0.001; p < 0.001); TIA in superior and inferior quadrants was significantly greater in the sitting position (p < 0.001; p < 0.001), and TIAmax-min was significantly smaller in the sitting position (p = 0.001); ILA in temporal quadrant was significantly larger in the sitting position (p = 0.015) and ILAmax-min was significantly smaller in the sitting position (p < 0.001). Conclusion: The anterior chamber angle was narrower and the lens was positioned more anteriorly in the supine than in the sitting position in cortical age-related cataract. Different positions may affect the angle configuration and the relative space of lens through different directions of mechanics and modes of action.

Exome sequencing identifies a novel pathogenic variant in RAB3GAP1 causing Warburg Micro syndrome in a Pakistani family.

BACKGROUND: Warburg Micro (WARBM) syndrome is a rare heterogeneous recessive genetic disorder characterized by ocular, neurological, and endocrine problems. To date, disease-causing variants in four genes have been identified to cause this syndrome; of these, RAB3GAP1 variants are the most frequent. Very little is known about WARBM syndrome in rural populations. OBJECTIVES: This study aims to investigate the genetics underpinnings of WARBM syndrome in a Pashtun family with two patients from Pakistan. The patients presented with spastic diplegia, severe intellectual disability, microphthalmia, microcornea, congenital cataracts, optic atrophy, and hypogonadism. METHODS: Magnetic resonance imaging (MRI) analysis revealed pronounced cerebral atrophy including corpus callosum hypoplasia and polymicrogyria. Exome sequencing and subsequent filtering identified a novel homozygous missense variant NM_001172435: c.2891A>G, p.Gln964Arg in the RAB3GAP1 gene. The variant was validated, and its segregation confirmed, by Sanger sequencing. RESULTS: Multiple prediction tools assess this variant to be damaging, and structural analysis of the protein shows that the mutant amino acid residue affects polar contact with the neighboring atoms. It is extremely rare and is absent in all the public databases. Taken together, these observations suggest that this variant underlies Micro syndrome in our family and is extremely important for management and family planning. CONCLUSIONS: Identification of this extremely rare variant extends the mutations spectrum of Micro syndrome. Screening more families, especially in underrepresented populations, will help unveil the mutation spectrum underlying this syndrome.

Distribution and associated factors of crystalline lens volume in noncataract adolescents and adults and patients with cataract in a Chinese population.

PURPOSE: To explore the distribution of lens volume (VOL) and its associated factors in noncataract adolescents and adults and patients with cataract in a Chinese population. SETTING: Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China. DESIGN: Cross-sectional study. METHODS: 1674 eyes from 1674 Chinese participants (690 adolescents and 363 adults without cataract, and 621 patients with cataract) aged from 7 to 90 years were included. Lens thickness (LT) and lens diameter (LD) were measured using swept-source anterior segment optical coherence tomography (SS-AS OCT) to calculate VOL. Axial length (AL) was measured by IOL-Master 700. Pearson correlation analysis and multivariate linear regression models were used to evaluate the potential associated factors of lens dimensions. RESULTS: The mean VOL was 167.74 ± 12.18 mm 3 in noncataract adolescents, 185.20 ± 14.95 mm 3 in noncataract adults, and 226.10 ± 49.25 mm 3 in patients with cataract. VOL had no significant correlation with AL in patients with cataract ( P > .05), neither in noncataract adolescents nor noncataract adults, when adjusted with LT, LD, age, and sex ( P > .05). On the other hand, eyes with longer ALs tended to have smaller LTs and larger LDs in all groups (all P -trend < .05). Larger VOL was associated with older age in all groups (all P < .001). CONCLUSIONS: A data set of VOLs in Chinese eyes over a wide age range was presented. It is inaccurate to predict VOL, LT, and LD solely according to AL. The direct measurement and calculation of VOL in vivo and the establishment of the normal range of VOL could help predict the size of lens capsular bag and plan cataract surgery.

Development and validation of a pixel wise deep learning model to detect cataract on swept-source optical coherence tomography images.

PURPOSE: The diagnosis of cataract is mostly clinical and there is a lack of objective and specific tool to detect and grade it automatically. The goal of this study was to develop and validate a deep learning model to detect and localize cataract on Swept Source Optical Coherance Tomography (SS-OCT) images. METHODS: We trained a convolutional network to detect cataract at the pixel level from 504 SS-OCT images of clear lens and cataract patients. The model was then validated on 1326 different images of 114 patients. The output of the model is a map repreenting the probability of cataract for each pixel of the image. We calculated the Cataract Fraction (CF), defined as the number of pixel classified as "cataract" divided by the number of pixel representing the lens for each image. Receiver Operating Characteristic Curves were plotted. Area Under the Curve (ROC AUC) sensitivity and specitivity to detect cataract were calculated. RESULTS: In the validsation set, mean CF was 0.024 ± 0.077 and 0.479 ± 0.230 (p < 0.001). ROC AUC was 0.98 with an optimal CF threshold of 0.14. Using that threshold, sensitivity and specificity to detect cataract were 94.4% and 94.7%, respectively. CONCLUSION: We developed an automatic detection tool for cataract on SS-OCT images. Probability maps of cataract on the images provide an additional tool to help the physician in its diagnosis and surgical planning.

Axial length measurement failure rates using optical biometry based on swept-source OCT in cataractous eyes.

INTRODUCTION: Ocular dimensions measurement is extremely important in cataract procedures and refractive surgery. The use of optical techniques for axial measurements has been developed in recent years. AREAS COVERED: The purpose was to summarize the outcomes reported when swept-source optical coherence tomography (SS-OCT) optical biometry failed during axial length measurement. A peer-reviewed literature search was carried out to identify publications reporting clinical outcomes for cataractous eyes measured with SS-OCT optical biometers available on the market. A comprehensive analysis of the available data was performed, focusing on parameters such as the sample of eyes evaluated, failure rates, and specifically, the cataract type when the measurement was not possible. 27 studies were included in this review. In general, SS-OCT biometers lead to only small failure rates when measuring axial length (but in some cases up to 38.49%). In the few cases where the measurement was not possible, the cataract type of the eyes was mainly mature white or grade ≥ IV. SS-OCT optical biometers show good outcomes when measuring axial length in eyes with advanced cataracts. EXPERT OPINION: We believe that the use of SS-OCT technology may be considered the gold standard for measuring axial length in any type of cataract.

Attention to region: Region-based integration-and-recalibration networks for nuclear cataract classification using AS-OCT images.

Nuclear cataract (NC) is a leading eye disease for blindness and vision impairment globally. Accurate and objective NC grading/classification is essential for clinically early intervention and cataract surgery planning. Anterior segment optical coherence tomography (AS-OCT) images are capable of capturing the nucleus region clearly and measuring the opacity of NC quantitatively. Recently, clinical research has suggested that the opacity correlation and repeatability between NC severity levels and the average nucleus density on AS-OCT images is high with the interclass and intraclass analysis. Moreover, clinical research has suggested that opacity distribution is uneven on the nucleus region, indicating that the opacities from different nucleus regions may play different roles in NC diagnosis. Motivated by the clinical priors, this paper proposes a simple yet effective region-based integration-and-recalibration attention (RIR), which integrates multiple feature map region representations and recalibrates the weights of each region via softmax attention adaptively. This region recalibration strategy enables the network to focus on high contribution region representations and suppress less useful ones. We combine the RIR block with the residual block to form a Residual-RIR module, and then a sequence of Residual-RIR modules are stacked to a deep network named region-based integration-and-recalibration network (RIR-Net), to predict NC severity levels automatically. The experiments on a clinical AS-OCT image dataset and two OCT datasets demonstrate that our method outperforms strong baselines and previous state-of-the-art methods. Furthermore, attention weight visualization analysis and ablation studies verify the capability of our RIR-Net for adjusting the relative importance of different regions in feature maps dynamically, agreeing with the clinical research.

Clinical Analysis of Color Doppler Ultrasound Diagnosis of Senile Cataract Based on Intelligent Processor.

In order to improve the effect of on-the-spot diagnosis of senile cataract, this paper combines the intelligent processor to explore the application of color Doppler ultrasound in the clinical analysis of senile cataract. Moreover, this paper measures and calculates the diameter, perimeter, area, volume, or velocity of blood flow reflected by color Doppler ultrasound images. In addition, this paper adopts the measurement method provided by composite measurement to design the intelligent processor. Each measurement analysis package is defined as an independent class, and the data, properties, and methods are encapsulated in a class, which is beneficial to the modular design of the program and the overall management of the system. The experimental results verify that the intelligent processor proposed in this paper has a certain effect in the clinical analysis of color Doppler ultrasound diagnosis of senile cataract.

End-to-end residual attention mechanism for cataractous retinal image dehazing.

BACKGROUND AND OBJECTIVE: Cataract is one of the most common causes of vision loss. Light scattering due to clouding of the lens in cataract patients makes it extremely difficult to image the retina of cataract patients with fundus cameras, resulting in a serious decrease in the quality of the retinal images taken. Furthermore, the age of cataract patients is generally too old, in addition to cataracts, the patients often have other retinal diseases, which brings great challenges to experts in the clinical diagnosis of cataract patients using retinal imaging. METHODS: In this paper, we present the End-to-End Residual Attention Mechanism (ERAN) for Cataractous Retinal Image Dehazing, which it includes four modules: encoding module, multi-scale feature extraction module, feature fusion module, and decoding module. The encoding module encodes the input cataract haze image into an image, facilitating subsequent feature extraction and reducing memory usage. The multi-scale feature extraction module includes a hole convolution module, a residual block, and an adaptive skip connection, which can expand the receptive field and extract features of different scales through weighted screening for fusion. The feature fusion module uses adaptive skip connections to enhance the network's ability to extract haze density images to make haze removal more thorough. Furthermore, the decoding module performs non-linear mapping on the fused features to obtain the haze density image, and then restores the haze-free image. RESULTS: The experimental results show that the proposed method has achieved better objective and subjective evaluation results, and has a better dehazing effect. CONCLUSION: We proposed ERAN method not only provides visually better images, but also helps experts better diagnose other retinal diseases in cataract patients, leading to better care and treatment.

Correlation Between Degree of Lens Opacity and the Phacoemulsification Energy Parameters Using Different Imaging Methods in Age-Related Cataract.

Purpose: To compare the correlation between degree of lens opacity and the phacoemulsification energy parameter in patients with age-related cataract as determined by slit lamp, 25-MHz ultrasound biomicroscopy (UBM), and Scheimpflug imaging (Pentacam) and to evaluate the application of these three methods to measuring lens opacification. Methods: This observational study was conducted in 319 patients (381 eyes) with different types of age-related cataract. The average age of patients was 67.3 ± 11.4 years. The degree of lens opacity acquired by slit lamp, 25-MHz UBM, and Pentacam was determined by the Lens Opacity Classification System III (LOCSIII), pixel units calculated by ImageJ, and lens density, respectively. We primarily analyzed and compared the correlation between lens opacity and the cumulative dissipated energy (CDE) values of phacoemulsification. Results: Cortical, nuclear, and posterior subcapsular (PSC) cataracts were evaluated as follows: LOCSIII grades 3.31 ± 1.42, 3.29 ± 1.49, and 0.91 ± 0.83; pixel units 120.91 ± 22.8, 93.2 ± 15.9, and 99.7 ± 13.0; and lens density 51.8 ± 31.2, 21.2 ± 6.10, and 53.3 ± 35.3, respectively. The CDE values were 12.1 ± 12.4, 13.5 ± 9.11, and 3.93 ± 1.96. In cortical cataract, there was a linear correlation among LOCSIII, pixel units, and CDE value (r = 0.560, r = 0.832, and r = 0.582, respectively; both P < 0.05), but lens density had no correlation with other parameters. In nuclear cataract, there was a linear correlation among LOCSIII, lens density, and CDE value (r = 0.747, r = 0.865, and r = 0.906, respectively; both P < 0.05), but pixel units had no correlation with other parameters. In PSC, only pixel units and LOCSIII showed a correlation. Conclusions: The various imaging methods offered different advantages in terms of determining lens opacity, a feature related to types of age-related cataracts. Choosing the most suitable imaging method to evaluate lens opacification based on the type of age-related cataract is important for accurately predicting the phacoemulsification parameters for cataract surgery. Translational Relevance: Determining the appropriate phacoemulsification strategy depends on quantitative analysis of the degree of lens opacity to reduce intraoperative and postoperative complications and to obtain the optimal postoperative visual outcome.

Adaptive feature squeeze network for nuclear cataract classification in AS-OCT image.

Nuclear cataract (NC) is an age-related cataract disease. Cataract surgery is an effective method to improve the vision and life quality of NC patients. Anterior segment optical coherence tomography (AS-OCT) images are noninvasive, reproductive, and easy-measured, which can capture opacity clearly on the lens nucleus region. However, automatic AS-OCT-based NC classification research has not been extensively studied. This paper proposes a novel convolutional neural network (CNN) framework named Adaptive Feature Squeeze Network (AFSNet) to classify NC severity levels automatically. In the AFSNet, we construct an adaptive feature squeeze module to dynamically squeeze local feature representations and update the relative importance of global feature representations, which is comprised of a squeeze block and a global adaptive pooling operation. We conduct comprehensive experiments on a clinical AS-OCT image dataset and a public OCT images dataset, and results demonstrate our method's effectiveness and superiority over strong baselines and previous state-of-the-art methods. Furthermore, this paper also demonstrates that CNNs achieve better NC classification results on the nucleus region than the lens region. We also adopt the class activation mapping (CAM) technique to localize the discriminative regions that CNN models learned, which enhances the interpretability of classification results.