Animal model for in-vivo Nuclear Cataract. Lens hardness and elasticity assessment

Age-related cataract is the most frequent cause of blindness in the world being responsible for 48% of blindness and affecting more than 10% of the working population. Currently there is no objective data of the lens biomechanical properties so the process by which the cataract affects the lens's properties (e.g. hardness and elasticity) is still unclear. A modified animal model was produced to create different severities of nuclear cataract. Different doses of sodium selenite were injected in two different moments of the rat' eyes maturation resulting in 12, 13 and 11 rats with incipient, moderate and severe cataract, respectively. The nucleus and cortex's hardness and the stiffness were measured using NanoTest™. Statistically significant differences were found between healthy and cataractous lenses. Statistically significant differences were also found between the different nuclear cataract degrees (p = 0.016), showing that the lens' hardness increases with cataract formation. The nucleus shows a higher hardness increase with cataract formation (p = 0.049). The animal model used in this study allowed for the first time the characterization of the lens's hardness and elasticity in two regions of the lens, in healthy and cataractous lenses.

Lumpy skin disease diagnosis in cattle: A deep learning approach optimized with RMSProp and MobileNetV2

Lumpy skin disease (LSD) is a critical problem for cattle populations, affecting both individual cows and the entire herd. Given cattle's critical role in meeting human needs, effective management of this disease is essential to prevent significant losses. The study proposes a deep learning approach using the MobileNetV2 model and the RMSprop optimizer to address this challenge. Tests on a dataset of healthy and lumpy cattle images show an impressive accuracy of 95%, outperforming existing benchmarks by 4-10%. These results underline the potential of the proposed methodology to revolutionize the diagnosis and management of skin diseases in cattle farming. Researchers and graduate students are the audience for our paper.

DenseHillNet: a lightweight CNN for accurate classification of natural images

The detection of natural images, such as glaciers and mountains, holds practical applications in transportation automation and outdoor activities. Convolutional neural networks (CNNs) have been widely employed for image recognition and classification tasks. While previous studies have focused on fruits, land sliding, and medical images, there is a need for further research on the detection of natural images, particularly glaciers and mountains. To address the limitations of traditional CNNs, such as vanishing gradients and the need for many layers, the proposed work introduces a novel model called DenseHillNet. The model utilizes a DenseHillNet architecture, a type of CNN with densely connected layers, to accurately classify images as glaciers or mountains. The model contributes to the development of automation technologies in transportation and outdoor activities. The dataset used in this study comprises 3,096 images of each of the "glacier" and "mountain" categories. Rigorous methodology was employed for dataset preparation and model training, ensuring the validity of the results. A comparison with a previous work revealed that the proposed DenseHillNet model, trained on both glacier and mountain images, achieved higher accuracy (86%) compared to a CNN model that only utilized glacier images (72%). Researchers and graduate students are the audience of our article.

Advancements in Cataract Detection: The Systematic Development of LeNet-Convolutional Neural Network Models

Regular screening and timely treatment play a crucial role in addressing the progression and visual impairment caused by cataracts, the leading cause of blindness in Thailand and many other countries. Despite the potential for prevention and successful treatment, patients often delay seeking medical attention due to the gradual and relatively asymptomatic nature of cataracts. To address this challenge, this research focuses on the identification of cataract abnormalities using image processing techniques and machine learning for preliminary assessment. The LeNet-convolutional neural network (LeNet-CNN) model is employed to train a dataset of digital camera images, and its performance is compared to the support vector machine (SVM) model in categorizing cataract abnormalities. The evaluation demonstrates that the LeNet-CNN model achieves impressive results in the testing phase. It attains an accuracy rate of 96%, exhibiting a sensitivity of 95% for detecting positive cases and a specificity of 96% for accurately identifying negative cases. These outcomes surpass the performance of previous studies in this field. This highlights the accuracy and effectiveness of the proposed approach, particularly the superior performance of LeNet-CNN. By utilizing image processing technology and convolutional neural networks, this research provides an effective tool for initial cataract screening. Patients can independently assess their eye health by capturing self-images, facilitating early intervention and medical consultations. The proposed method holds promise in enhancing the preliminary assessment of cataracts, enabling early detection and timely access to appropriate care.

Feasibility assessment of the Eye Scan Ultrasound System for cataract characterization and optimal phacoemulsification energy estimation: protocol for a pilot, nonblinded and monocentre study

Background

Cataracts are lens opacifications that are responsible for more than half of blindness cases worldwide, and the only treatment is surgical intervention. Phacoemulsification surgery, the most frequently performed cataract surgery in developed countries, has associated risks, some of which are related to excessive phacoemulsification energy levels and times. The protocol proposed in herein will be used to evaluate the feasibility of a new experimental medical device, the Eye Scan Ultrasound System (ESUS), for the automatic classification of cataract type and severity and quantitative estimation of the optimal phacoemulsification energy.

Methods

The pilot study protocol will be used to evaluate the feasibility and safety of the ESUS in clinical practice. The study will be conducted in subjects with age-related cataracts and on healthy subjects as controls. The procedures include data acquisition with the experimental ESUS, classification based on the Lens Opacity Classification System III (LOCS III, comparator) using a slit lamp, contrast sensitivity test, optical coherence tomography, specular microscopy and surgical parameters.

ESUS works in A-scan pulse-echo mode, with a central frequency of 20 MHz. From the collected signals, acoustic parameters will be extracted and used for automatic cataract characterization and optimal phacoemulsification energy estimation.

The study includes two phases. The data collected in the first phase (40 patients, 2 eyes per patient) will be used to train the ESUS algorithms, while the data collected in the second phase (10 patients, 2 eyes per patient) will be used to assess the classification performance. System safety will be monitored during the study.

Discussion

The present pilot study protocol will evaluate the feasibility and safety of the ESUS for use in clinical practice, and the results will support a larger clinical study for the efficacy assessment of the ESUS as a diagnostic tool. Ultimately, the ESUS is expected to represent a valuable tool for surgical planning by reducing complications associated with excessive levels of phacoemulsification energy and surgical times, which will have a positive impact on healthcare systems and society. The study is not yet recruiting.

Trial registration

ClinicalTrials.gov identifier NCT04461912, registered on July 8, 2020.

The Use of Convolutional Neural Networks and Digital Camera Images in Cataract Detection

Cataract is one of the major causes of blindness in the world. Its early detection and treatment could greatly reduce the risk of deterioration and blindness. Instruments commonly used to detect cataracts are slit lamps and fundus cameras, which are highly expensive and require domain knowledge. Thus, the problem is that the lack of professional ophthalmologists could result in the delay of cataract detection, where medical treatment is inevitable. Therefore, this study aimed to design a convolutional neural network (CNN) with digital camera images (CNNDCI) system to detect cataracts efficiently and effectively. The designed CNNDCI system can perform the cataract identification process accurately in a user-friendly manner using smartphones to collect digital images. In addition, the existing numerical results provided by the literature were used to demonstrate the performance of the proposed CNNDCI system for cataract detection. Numerical results revealed that the designed CNNDCI system could identify cataracts effectively with satisfying accuracy. Thus, this study concluded that the presented CNNDCI architecture is a feasible and promising alternative for cataract detection.

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.

A-scan ultrasound in ophthalmology: A simulation tool

In the present study, we developed a computational tool for simulating the ophthalmological applications of A-scan ultrasound, including cataract characterisation and biometry. A-scan biometry is used to measure the axial length (AL) of the eye before cataract surgery to calculate the refractive power of the intraocular lens to be implanted. Errors in the measurement of the AL lead to post-surgical refractive errors. The simulation tool was developed using the k-Wave Matlab toolbox, together with a user-friendly interface developed in Matlab. Diverse error sources were evaluated. Constant ultrasound speed assumptions may introduce refractive errors of up to 0.6 D; by contrast, probe positioning errors had a lower impact, of up to 0.11 D. The correct identification of the Bruch's membrane is limited not only by axial resolution constraints but also by the low reflection coefficient at the retina/choroid interface. Regarding cataract characterisation, the amplitudes of the echoes reflected at the lens interfaces are sensitive to diverse cataract types and severities, and a more realistic representation could be obtained by using a higher resolution in the eye grid; however, the required computational times would make simulations impracticable when using personal computers. The simulation tool shows good versatility for evaluating diverse aspects of A-scan biometry.

Development and evaluation of a deep learning model for the detection of multiple fundus diseases based on colour fundus photography

AIM

To explore and evaluate an appropriate deep learning system (DLS) for the detection of 12 major fundus diseases using colour fundus photography.

METHODS

Diagnostic performance of a DLS was tested on the detection of normal fundus and 12 major fundus diseases including referable diabetic retinopathy, pathologic myopic retinal degeneration, retinal vein occlusion, retinitis pigmentosa, retinal detachment, wet and dry age-related macular degeneration, epiretinal membrane, macula hole, possible glaucomatous optic neuropathy, papilledema and optic nerve atrophy. The DLS was developed with 56 738 images and tested with 8176 images from one internal test set and two external test sets. The comparison with human doctors was also conducted.

RESULTS

The area under the receiver operating characteristic curves of the DLS on the internal test set and the two external test sets were 0.950 (95% CI 0.942 to 0.957) to 0.996 (95% CI 0.994 to 0.998), 0.931 (95% CI 0.923 to 0.939) to 1.000 (95% CI 0.999 to 1.000) and 0.934 (95% CI 0.929 to 0.938) to 1.000 (95% CI 0.999 to 1.000), with sensitivities of 80.4% (95% CI 79.1% to 81.6%) to 97.3% (95% CI 96.7% to 97.8%), 64.6% (95% CI 63.0% to 66.1%) to 100% (95% CI 100% to 100%) and 68.0% (95% CI 67.1% to 68.9%) to 100% (95% CI 100% to 100%), respectively, and specificities of 89.7% (95% CI 88.8% to 90.7%) to 98.1% (95%CI 97.7% to 98.6%), 78.7% (95% CI 77.4% to 80.0%) to 99.6% (95% CI 99.4% to 99.8%) and 88.1% (95% CI 87.4% to 88.7%) to 98.7% (95% CI 98.5% to 99.0%), respectively. When compared with human doctors, the DLS obtained a higher diagnostic sensitivity but lower specificity.

CONCLUSION

The proposed DLS is effective in diagnosing normal fundus and 12 major fundus diseases, and thus has much potential for fundus diseases screening in the real world.

Safety Assessment of an A-Scan Ultrasonic System for Ophthalmic Use

OBJECTIVES

This study describes the safety assessment of an A-scan ultrasonic system for ophthalmic use. The system is an investigational medical device for automatic cataract detection and classification.

METHODS

The risk management was based on the International Organization for Standardization (ISO) standard DIN EN ISO 14971:2009-10 and International Electrotechnical Commission (IEC) standard IEC 60601-2-37. The calibration of the ultrasonic field was conducted according to the standards IEC 62127-1:2007 and IEC 62359:2010. The uncertainty on measurements was delineated in agreement with the guide JCGM 100:2008.

RESULTS

After risk management, all risks were qualitatively classified as acceptable. The mechanical index (0.08 ± 0.05), soft tissue thermal index (0.08 ± 0.08) and spatial-peak temporal-average intensity (0.56 ± 0.59 mW/cm² ) were under the maximum index values indicated by the US Food and Drug Administration guidance, Marketing Clearance of Diagnostic Ultrasound Systems and Transducers (0.23, 1, and 17 mW/cm² , respectively).

CONCLUSIONS

This study presents a practical approach for the safety assessment of A-scan ultrasonic systems for ophthalmic use. The safety evaluation of a medical device is mandatory before its use in clinical practice. However, the safety monitoring throughout its life cycle should also be considered, since many device components may deteriorate over time and use.

Introduction to Machine Learning, Neural Networks, and Deep Learning

Purpose

To present an overview of current machine learning methods and their use in medical research, focusing on select machine learning techniques, best practices, and deep learning.

Methods

A systematic literature search in PubMed was performed for articles pertinent to the topic of artificial intelligence methods used in medicine with an emphasis on ophthalmology.

Results

A review of machine learning and deep learning methodology for the audience without an extensive technical computer programming background.

Conclusions

Artificial intelligence has a promising future in medicine; however, many challenges remain.

Translational Relevance

The aim of this review article is to provide the nontechnical readers a layman's explanation of the machine learning methods being used in medicine today. The goal is to provide the reader a better understanding of the potential and challenges of artificial intelligence within the field of medicine.

In Vivo Characterization of Corneal Changes in a Type 1 Diabetic Animal Model

Diabetes mellitus (DM) is a metabolic disease that affects 9% of the adult population, promoting an increase in glucose concentration that affects the corneal structure, namely, its thickness, as well as the constituents and flow of the aqueous humor. In this study, high-frequency transducers (20-MHz and 50-MHz) were used to measure and characterize changes in the corneal and aqueous humor in streptozotocin-induced type 1 diabetic rats followed over 8 weeks. Increases of 24.6 and 15.4 μm in central corneal thickness were measured with the 20-MHz and 50-MHz probes, respectively, in DM rats (p < 0.001). The increases in thickness of the different corneal layers ranged from 7% to 17%. Structural alterations of the aqueous humor were also studied by relating the amplitudes of the anterior lens and posterior cornea boundary signals, the result of which was denominated by pseudo-attenuation. The results revealed an increase of 49% at week 8 compared with the baseline values (p < 0.020, with the 50-MHz probe). This study illustrated that high-frequency ultrasound can be used to measure corneal layer thickness and study the alterations promoted by diabetes in the eye's anterior segment. Those assessments may allow early detection of DM, improving the monitoring of diabetic patients.

Applications of Artificial Intelligence in Ophthalmology: General Overview

With the emergence of unmanned plane, autonomous vehicles, face recognition, and language processing, the artificial intelligence (AI) has remarkably revolutionized our lifestyle. Recent studies indicate that AI has astounding potential to perform much better than human beings in some tasks, especially in the image recognition field. As the amount of image data in imaging center of ophthalmology is increasing dramatically, analyzing and processing these data is in urgent need. AI has been tried to apply to decipher medical data and has made extraordinary progress in intelligent diagnosis. In this paper, we presented the basic workflow for building an AI model and systematically reviewed applications of AI in the diagnosis of eye diseases. Future work should focus on setting up systematic AI platforms to diagnose general eye diseases based on multimodal data in the real world.

Modeling analysis of the relationship between atherosclerosis and related inflammatory factors

Objective: To establish early diagnosis model of inflammatory factors for atherosclerosis (AS), providing theoretical evidence for early detection of AS and development of plaques. Methods: Serum samples were collected to detect the inflammatory factors including CysC, Hcy, hs-CRP, UA, FIB, D-D, LP (a), IL-6, SAA, sCD40L and MDA. Using Logistic regression analysis, the inflammatory factors used for modeling were screened out, and then the AS early diagnosis models were established based on receiver operating characteristic (ROC) curve, support vector machine and BP neural network respectively. Results: No significant difference exists between the general materials of two groups. All 11 inflammatory factors had higher level in AS group than in control group. As shown in ROC curve, all inflammatory factors were helpful in AS diagnosis. In terms of sensitivity, UA ranked first (98) and FIB ranked last (55.5); in terms of specificity, UA ranked first (99) and FIB ranked last (78); in terms of area under the curve, UA and SAA ranked first (both were 0.995) and FIB ranked last (0.721). Based on Logistic regression equation, six factors were screened out, including Hcy, Hs-CRP, IL-6, D-D, CysC and MDA. According to classification, the final sixth steps had a prediction accuracy of 99%. When six inflammatory factors included in Logistic regression equation were detected jointly, the sensitivity, specificity and area under the curve were 57%, 97% and 0.821 respectively, while those of the model excluding D-D were 64%, 90% and 0.828, generally superior to results of joint detection including six factors. The ROC curve based on Hcy, Hs-CRP and MDA had a sensitivity of 87%, a specificity of 94% and an area under the curve of 0.869, being inferior to those of the ROC curve based on IL-6, D-D and Cys C, which were 87%, 92% and 0.936 respectively. The accuracy of SVM-AS diagnosis model and BP neural network model were 82.5% and 77.5% respectively. Conclusion: All 11 inflammatory factors are valuable in AS diagnosis. AS early diagnosis models based on Logistic regression analysis, ROC curve, support vector machine and BP neural network possess diagnostic value and can provide reference for clinical diagnosis.