Adopting low-shot deep learning for the detection of conjunctival melanoma using ocular surface images

Detection of Ocular Surface Squamous Neoplasia Using Artificial Intelligence With Anterior Segment Optical Coherence Tomography

PURPOSE

To develop and validate a deep learning (DL) model to differentiate ocular surface squamous neoplasia (OSSN) from pterygium and pinguecula using high-resolution anterior segment optical coherence tomography (AS-OCT).

DESIGN

Retrospective Diagnostic Accuracy Study.

METHODS

Setting: Single-center.

STUDY POPULATION

All eyes with a clinical or biopsy-proven diagnosis of OSSN, pterygium, or pinguecula that received AS-OCT imaging.

PROCEDURES

Imaging data was extracted from Optovue AS-OCT (Fremont, CA) and patients' clinical or biopsy-proven diagnoses were collected from electronic medical records. A DL classification model was developed using two methodologies: (1) a masked autoencoder was trained with unlabeled data from 105,859 AS-OCT images of 5746 eyes and (2) a Vision Transformer supervised model coupled to the autoencoder used labeled data for fine-tuning a binary classifier (OSSN vs non-OSSN lesions). A sample of 2022 AS-OCT images from 523 eyes (427 patients) were classified by expert graders into "OSSN or suspicious for OSSN" and "pterygium or pinguecula." The algorithm's diagnostic performance was evaluated in a separate test sample using 566 scans (62 eyes, 48 patients) with biopsy-proven OSSN and compared with expert clinicians who were masked to the diagnosis. Analysis was conducted at the scan-level for both the DL model and expert clinicians, who were not provided with clinical images or supporting clinical data.

MAIN OUTCOME

Diagnostic performance of expert clinicians and the DL model in identifying OSSN on AS-OCT scans.

RESULTS

The DL model had an accuracy of 90.3% (95% confidence intervals [CI]: 87.5%-92.6%), with sensitivity of 86.4% (95% CI: 81.4%-90.4%) and specificity of 93.2% (95% CI: 89.9%-95.7%) compared to the biopsy-proven diagnosis. Expert graders had a lower sensitivity 69.8% (95% CI: 63.6%-75.5%) and slightly higher specificity 98.5% (95% CI: 96.4%-99.5%) than the DL model. The area under the receiver operating characteristic curve for the DL model was 0.945 (95% CI: 0.918-0.972) and significantly greater than expert graders (area under the receiver operating characteristic curve = 0.688, P < .001).

CONCLUSIONS

A DL model applied to AS-OCT scans demonstrated high accuracy, sensitivity, and specificity in differentiating OSSN from pterygium and pinguecula. Interestingly, the model had comparable diagnostic performance to expert clinicians in this study and shows promise for enhancing clinical decision-making. Further research is warranted to explore the integration of this artificial intelligence-driven approach in routine screening and diagnostic protocols for OSSN.

AI image generation technology in ophthalmology: Use, misuse and future applications

BACKGROUND

AI-powered image generation technology holds the potential to reshape medical practice, yet it remains an unfamiliar technology for both medical researchers and clinicians alike. Given the adoption of this technology relies on clinician understanding and acceptance, we sought to demystify its use in ophthalmology. To this end, we present a literature review on image generation technology in ophthalmology, examining both its theoretical applications and future role in clinical practice.

METHODS

First, we consider the key model designs used for image synthesis, including generative adversarial networks, autoencoders, and diffusion models. We then perform a survey of the literature for image generation technology in ophthalmology prior to September 2024, presenting both the type of model used and its clinical application. Finally, we discuss the limitations of this technology, the risks of its misuse and the future directions of research in this field.

RESULTS

Applications of this technology include improving AI diagnostic models, inter-modality image transformation, more accurate treatment and disease prognostication, image denoising, and individualised education. Key barriers to its adoption include bias in generative models, risks to patient data security, computational and logistical barriers to development, challenges with model explainability, inconsistent use of validation metrics between studies and misuse of synthetic images. Looking forward, researchers are placing a further emphasis on clinically grounded metrics, the development of image generation foundation models and the implementation of methods to ensure data provenance.

CONCLUSION

Compared to other medical applications of AI, image generation is still in its infancy. Yet, it holds the potential to revolutionise ophthalmology across research, education and clinical practice. This review aims to guide ophthalmic researchers wanting to leverage this technology, while also providing an insight for clinicians on how it may change ophthalmic practice in the future.

Assessment of perceived realism in AI-generated synthetic spine fracture CT images

BackgroundDeep learning-based decision support systems require synthetic images generated by adversarial networks, which require clinical evaluation to ensure their quality.ObjectiveThe study evaluates perceived realism of high-dimension synthetic spine fracture CT images generated Progressive Growing Generative Adversarial Networks (PGGANs).Method: The study used 2820 spine fracture CT images from 456 patients to train an PGGAN model. The model synthesized images up to 512 × 512 pixels, and the realism of the generated images was assessed using Visual Turing Tests and Fracture Identification Test. Three spine surgeons evaluated the images, and clinical evaluation results were statistically analysed.Result: Spine surgeons have an average prediction accuracy of nearly 50% during clinical evaluations, indicating difficulty in distinguishing between real and generated images. The accuracy varies for different dimensions, with synthetic images being more realistic, especially in 512 × 512-dimension images. During FIT, among 16 generated images of each fracture type, 13-15 images were correctly identified, indicating images are more realistic and clearly depict fracture lines in 512 × 512 dimensions.ConclusionThe study reveals that AI-based PGGAN can generate realistic synthetic spine fracture CT images up to 512 × 512 pixels, making them difficult to distinguish from real images, and improving the automatic spine fracture type detection system.

AI in dermatology: a comprehensive review into skin cancer detection

Background

Artificial Intelligence (AI) is significantly transforming dermatology, particularly in early skin cancer detection and diagnosis. This technological advancement addresses a crucial public health issue by enhancing diagnostic accuracy, efficiency, and accessibility. AI integration in medical imaging and diagnostic procedures offers promising solutions to the limitations of traditional methods, which often rely on subjective clinical evaluations and histopathological analyses. This study systematically reviews current AI applications in skin cancer classification, providing a comprehensive overview of their advantages, challenges, methodologies, and functionalities.

Methodology

In this study, we conducted a comprehensive analysis of artificial intelligence (AI) applications in the classification of skin cancer. We evaluated publications from three prominent journal databases: Scopus, IEEE, and MDPI. We conducted a thorough selection process using the PRISMA guidelines, collecting 1,156 scientific articles. Our methodology included evaluating the titles and abstracts and thoroughly examining the full text to determine their relevance and quality. Consequently, we included a total of 95 publications in the final study. We analyzed and categorized the articles based on four key dimensions: advantages, difficulties, methodologies, and functionalities.

Results

AI-based models exhibit remarkable performance in skin cancer detection by leveraging advanced deep learning algorithms, image processing techniques, and feature extraction methods. The advantages of AI integration include significantly improved diagnostic accuracy, faster turnaround times, and increased accessibility to dermatological expertise, particularly benefiting underserved areas. However, several challenges remain, such as concerns over data privacy, complexities in integrating AI systems into existing workflows, and the need for large, high-quality datasets. AI-based methods for skin cancer detection, including CNNs, SVMs, and ensemble learning techniques, aim to improve lesion classification accuracy and increase early detection. AI systems enhance healthcare by enabling remote consultations, continuous patient monitoring, and supporting clinical decision-making, leading to more efficient care and better patient outcomes.

Conclusions

This comprehensive review highlights the transformative potential of AI in dermatology, particularly in skin cancer detection and diagnosis. While AI technologies have significantly improved diagnostic accuracy, efficiency, and accessibility, several challenges remain. Future research should focus on ensuring data privacy, developing robust AI systems that can generalize across diverse populations, and creating large, high-quality datasets. Integrating AI tools into clinical workflows is critical to maximizing their utility and effectiveness. Continuous innovation and interdisciplinary collaboration will be essential for fully realizing the benefits of AI in skin cancer detection and diagnosis.

Generative artificial intelligence in ophthalmology: current innovations, future applications and challenges

The rapid advancements in generative artificial intelligence are set to significantly influence the medical sector, particularly ophthalmology. Generative adversarial networks and diffusion models enable the creation of synthetic images, aiding the development of deep learning models tailored for specific imaging tasks. Additionally, the advent of multimodal foundational models, capable of generating images, text and videos, presents a broad spectrum of applications within ophthalmology. These range from enhancing diagnostic accuracy to improving patient education and training healthcare professionals. Despite the promising potential, this area of technology is still in its infancy, and there are several challenges to be addressed, including data bias, safety concerns and the practical implementation of these technologies in clinical settings.

DeepMonitoring: a deep learning-based monitoring system for assessing the quality of cornea images captured by smartphones

Smartphone-based artificial intelligence (AI) diagnostic systems could assist high-risk patients to self-screen for corneal diseases (e.g., keratitis) instead of detecting them in traditional face-to-face medical practices, enabling the patients to proactively identify their own corneal diseases at an early stage. However, AI diagnostic systems have significantly diminished performance in low-quality images which are unavoidable in real-world environments (especially common in patient-recorded images) due to various factors, hindering the implementation of these systems in clinical practice. Here, we construct a deep learning-based image quality monitoring system (DeepMonitoring) not only to discern low-quality cornea images created by smartphones but also to identify the underlying factors contributing to the generation of such low-quality images, which can guide operators to acquire high-quality images in a timely manner. This system performs well across validation, internal, and external testing sets, with AUCs ranging from 0.984 to 0.999. DeepMonitoring holds the potential to filter out low-quality cornea images produced by smartphones, facilitating the application of smartphone-based AI diagnostic systems in real-world clinical settings, especially in the context of self-screening for corneal diseases.

Artificial intelligence and machine learning a new frontier in the diagnosis of ocular adnexal tumors: A review

In our article, we explore the transformative potential of Artificial Intelligence and Machine Learning in oculo-oncology, focusing on the diagnosis and management of ocular adnexal tumors. Delving into the intricacies of adnexal conditions such as conjunctival melanoma and squamous conjunctival carcinoma, the study emphasizes recent breakthroughs, such as Artificial Intelligence-driven early detection methods. While acknowledging challenges like the scarcity of specialized datasets and issues in standardizing image capture, the research underscores encouraging patient acceptance, as demonstrated in melanoma diagnosis studies. The abstract calls for overcoming obstacles, conducting clinical trials, establishing global regulatory norms and fostering collaboration between ophthalmologists and Artificial Intelligence experts. Overall, the article envisions Artificial Intelligence's imminent transformative impact on ocular and periocular cancer diagnosis.

Latest developments of generative artificial intelligence and applications in ophthalmology

The emergence of generative artificial intelligence (AI) has revolutionized various fields. In ophthalmology, generative AI has the potential to enhance efficiency, accuracy, personalization and innovation in clinical practice and medical research, through processing data, streamlining medical documentation, facilitating patient-doctor communication, aiding in clinical decision-making, and simulating clinical trials. This review focuses on the development and integration of generative AI models into clinical workflows and scientific research of ophthalmology. It outlines the need for development of a standard framework for comprehensive assessments, robust evidence, and exploration of the potential of multimodal capabilities and intelligent agents. Additionally, the review addresses the risks in AI model development and application in clinical service and research of ophthalmology, including data privacy, data bias, adaptation friction, over interdependence, and job replacement, based on which we summarized a risk management framework to mitigate these concerns. This review highlights the transformative potential of generative AI in enhancing patient care, improving operational efficiency in the clinical service and research in ophthalmology. It also advocates for a balanced approach to its adoption.

Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening

Age-related macular degeneration (AMD) is the leading cause of central vision impairment among the elderly. Effective and accurate AMD screening tools are urgently needed. Indocyanine green angiography (ICGA) is a well-established technique for detecting chorioretinal diseases, but its invasive nature and potential risks impede its routine clinical application. Here, we innovatively developed a deep-learning model capable of generating realistic ICGA images from color fundus photography (CF) using generative adversarial networks (GANs) and evaluated its performance in AMD classification. The model was developed with 99,002 CF-ICGA pairs from a tertiary center. The quality of the generated ICGA images underwent objective evaluation using mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structural similarity measures (SSIM), etc., and subjective evaluation by two experienced ophthalmologists. The model generated realistic early, mid and late-phase ICGA images, with SSIM spanned from 0.57 to 0.65. The subjective quality scores ranged from 1.46 to 2.74 on the five-point scale (1 refers to the real ICGA image quality, Kappa 0.79-0.84). Moreover, we assessed the application of translated ICGA images in AMD screening on an external dataset (n = 13887) by calculating area under the ROC curve (AUC) in classifying AMD. Combining generated ICGA with real CF images improved the accuracy of AMD classification with AUC increased from 0.93 to 0.97 (P < 0.001). These results suggested that CF-to-ICGA translation can serve as a cross-modal data augmentation method to address the data hunger often encountered in deep-learning research, and as a promising add-on for population-based AMD screening. Real-world validation is warranted before clinical usage.

Deep learning prediction of steep and flat corneal curvature using fundus photography in post-COVID telemedicine era

Recently, fundus photography (FP) is being increasingly used. Corneal curvature is an essential factor in refractive errors and is associated with several pathological corneal conditions. As FP-based examination systems have already been widely distributed, it would be helpful for telemedicine to extract information such as corneal curvature using FP. This study aims to develop a deep learning model based on FP for corneal curvature prediction by categorizing corneas into steep, regular, and flat groups. The EfficientNetB0 architecture with transfer learning was used to learn FP patterns to predict flat, regular, and steep corneas. In validation, the model achieved a multiclass accuracy of 0.727, a Matthews correlation coefficient of 0.519, and an unweighted Cohen's κ of 0.590. The areas under the receiver operating characteristic curves for binary prediction of flat and steep corneas were 0.863 and 0.848, respectively. The optic nerve and its peripheral areas were the main focus of the model. The developed algorithm shows that FP can potentially be used as an imaging modality to estimate corneal curvature in the post-COVID-19 era, whereby patients may benefit from the detection of abnormal corneal curvatures using FP in the telemedicine setting.

Comparison of machine learning methods in the early identification of vasculitides, myositides and glomerulonephritides

BACKGROUND

Rare disease diagnoses are often delayed by years, including multiple doctor visits, and potential imprecise or incorrect diagnoses before receiving the correct one. Machine learning could solve this problem by flagging potential patients that doctors should examine more closely.

METHODS

Making the prediction situation as close as possible to real situation, we tested different masking sizes. In the masking phase, data was removed, and it was applied to all data points following the first rare disease diagnosis, including the day when the diagnosis was received, and in addition applied to selected number of days before initial diagnosis. Performance of machine learning models were compared with positive predictive value (PPV), negative predictive value (NPV), prevalence PPV (pPPV), prevalence NPV (pNPV), accuracy (ACC) and area under the receiver operation characteristics curve (AUC).

RESULTS

XGBoost had PPVs over 90 % in all masking settings, and InceptionVasGloMyotides had most of the PPVs over 90 %, but not as consistently. When the prevalence of the diseases was considered XGBoost achieved highest value of 8.8 % in binary classification with 30 days masking and InceptionVasGloMyotides achieved the best value of 6 % in the binary classification as well, but with 2160 days and 4320 days masking. ACC were varying between 89 % and 98 % with XGBoost and InceptionVasGloMyotides having variation between 79 % and 94 %. AUC on the other hand varied between 72.6 % and 94.5 % with InceptionVasGloMyotides and for XGBoost it varied between 69.9 % and 96.4 %.

CONCLUSIONS

XGBoost and InceptionVasGloMyotides could successfully predict rare diseases for patients at least 30 days prior to initial rare disease diagnose. In addition, we managed to build performative custom deep learning model.

Deep Transfer Learning for Ethnically Distinct Populations: Prediction of Refractive Error Using Optical Coherence Tomography

INTRODUCTION

The mismatch between training and testing data distribution causes significant degradation in the deep learning model performance in multi-ethnic scenarios. To reduce the performance differences between ethnic groups and image domains, we built a deep transfer learning model with adaptation training to predict uncorrected refractive errors using posterior segment optical coherence tomography (OCT) images of the macula and optic nerve.

METHODS

Observational, cross-sectional, multicenter study design. We pre-trained a deep learning model on OCT images from the B&VIIT Eye Center (Seoul, South Korea) (N = 2602 eyes of 1301 patients). OCT images from Poona Eye Care (Pune, India) were chronologically sorted into adaptation training data (N = 60 eyes of 30 patients) for transfer learning and test data (N = 142 eyes of 71 patients) for validation. Deep learning models were trained to predict spherical equivalent (SE) and mean keratometry (K) values via transfer learning for domain adaptation.

RESULTS

Both adaptation models for SE and K were significantly better than those without adaptation (P < 0.001). In myopia/hyperopia classification, the model trained on circular optic disc OCT images yielded the best performance (accuracy = 74.7%). It also performed best in estimating SE with the lowest mean absolute error (MAE) of 1.58 D. For classifying the degree of corneal curvature, the optic nerve vertical algorithm performed best (accuracy = 65.7%). The optic nerve horizontal model achieved the lowest MAE (1.85 D) when predicting the K value. Saliency maps frequently highlighted the retinal nerve fiber layers.

CONCLUSIONS

Adaptation training via transfer learning is an effective technique for estimating refractive errors and K values using macular and optic nerve OCT images from ethnically heterogeneous populations. Further studies with larger sample sizes and various data sources are needed to confirm the feasibility of the proposed algorithm.

Unsupervised synthesis of realistic coronary artery X-ray angiogram

PURPOSE

Medical image analysis suffers from a sparsity of annotated data necessary in learning-based models. Cardiorespiratory simulators have been developed to counter the lack of data. However, the resulting data often lack realism. Hence, the proposed method aims to synthesize realistic and fully customizable angiograms of coronary arteries for the training of learning-based biomedical tasks, for cardiologists performing interventions, and for cardiologist trainees.

METHODS

3D models of coronary arteries are generated with a fully customizable realistic cardiorespiratory simulator. The transfer of X-ray angiography style to simulator-generated images is performed using a new vessel-specific adaptation of the CycleGAN model. The CycleGAN model is paired with a vesselness-based loss function that is designed as a vessel-specific structural integrity constraint.

RESULTS

Validation is performed both on the style and on the preservation of the shape of the arteries of the images. The results show a PSNR of 14.125, an SSIM of 0.898, and an overlapping of 89.5% using the Dice coefficient.

CONCLUSION

We proposed a novel fluoroscopy-based style transfer method for the enhancement of the realism of simulated coronary artery angiograms. The results show that the proposed model is capable of accurately transferring the style of X-ray angiograms to the simulations while keeping the integrity of the structures of interest (i.e., the topology of the coronary arteries).

Computer-aided diagnosis of keratoconus through VAE-augmented images using deep learning

Detecting clinical keratoconus (KCN) poses a challenging and time-consuming task. During the diagnostic process, ophthalmologists are required to review demographic and clinical ophthalmic examinations in order to make an accurate diagnosis. This study aims to develop and evaluate the accuracy of deep convolutional neural network (CNN) models for the detection of keratoconus (KCN) using corneal topographic maps. We retrospectively collected 1758 corneal images (978 normal and 780 keratoconus) from 1010 subjects of the KCN group with clinically evident keratoconus and the normal group with regular astigmatism. To expand the dataset, we developed a model using Variational Auto Encoder (VAE) to generate and augment images, resulting in a dataset of 4000 samples. Four deep learning models were used to extract and identify deep corneal features of original and synthesized images. We demonstrated that the utilization of synthesized images during training process increased classification performance. The overall average accuracy of the deep learning models ranged from 99% for VGG16 to 95% for EfficientNet-B0. All CNN models exhibited sensitivity and specificity above 0.94, with the VGG16 model achieving an AUC of 0.99. The customized CNN model achieved satisfactory results with an accuracy and AUC of 0.97 at a much faster processing speed compared to other models. In conclusion, the DL models showed high accuracy in screening for keratoconus based on corneal topography images. This is a development toward the potential clinical implementation of a more enhanced computer-aided diagnosis (CAD) system for KCN detection, which would aid ophthalmologists in validating the clinical decision and carrying out prompt and precise KCN treatment.

Updates in Diagnostic Imaging for Infectious Keratitis: A Review

Infectious keratitis (IK) is among the top five leading causes of blindness globally. Early diagnosis is needed to guide appropriate therapy to avoid complications such as vision impairment and blindness. Slit lamp microscopy and culture of corneal scrapes are key to diagnosing IK. Slit lamp photography was transformed when digital cameras and smartphones were invented. The digital camera or smartphone camera sensor's resolution, the resolution of the slit lamp and the focal length of the smartphone camera system are key to a high-quality slit lamp image. Alternative diagnostic tools include imaging, such as optical coherence tomography (OCT) and in vivo confocal microscopy (IVCM). OCT's advantage is its ability to accurately determine the depth and extent of the corneal ulceration, infiltrates and haze, therefore characterizing the severity and progression of the infection. However, OCT is not a preferred choice in the diagnostic tool package for infectious keratitis. Rather, IVCM is a great aid in the diagnosis of fungal and Acanthamoeba keratitis with overall sensitivities of 66-74% and 80-100% and specificity of 78-100% and 84-100%, respectively. Recently, deep learning (DL) models have been shown to be promising aids for the diagnosis of IK via image recognition. Most of the studies that have developed DL models to diagnose the different types of IK have utilised slit lamp photographs. Some studies have used extremely efficient single convolutional neural network algorithms to train their models, and others used ensemble approaches with variable results. Limitations of DL models include the need for large image datasets to train the models, the difficulty in finding special features of the different types of IK, the imbalance of training models, the lack of image protocols and misclassification bias, which need to be overcome to apply these models into real-world settings. Newer artificial intelligence technology that generates synthetic data, such as generative adversarial networks, may assist in overcoming some of these limitations of CNN models.

Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma

PURPOSE

Primary central nervous system lymphoma (PCNSL) is a rare, aggressive form of extranodal non-Hodgkin lymphoma. To predict the overall survival (OS) in advance is of utmost importance as it has the potential to aid clinical decision-making. Though radiomics-based machine learning (ML) has demonstrated the promising performance in PCNSL, it demands large amounts of manual feature extraction efforts from magnetic resonance images beforehand. deep learning (DL) overcomes this limitation.

METHODS

In this paper, we tailored the 3D ResNet to predict the OS of patients with PCNSL. To overcome the limitation of data sparsity, we introduced data augmentation and transfer learning, and we evaluated the results using r stratified k-fold cross-validation. To explain the results of our model, gradient-weighted class activation mapping was applied.

RESULTS

We obtained the best performance (the standard error) on post-contrast T1-weighted (T1Gd)-area under curve [Formula: see text], accuracy [Formula: see text], precision [Formula: see text], recall [Formula: see text] and F1-score [Formula: see text], while compared with ML-based models on clinical data and radiomics data, respectively, further confirming the stability of our model. Also, we observed that PCNSL is a whole-brain disease and in the cases where the OS is less than 1 year, it is more difficult to distinguish the tumor boundary from the normal part of the brain, which is consistent with the clinical outcome.

CONCLUSIONS

All these findings indicate that T1Gd can improve prognosis predictions of patients with PCNSL. To the best of our knowledge, this is the first time to use DL to explain model patterns in OS classification of patients with PCNSL. Future work would involve collecting more data of patients with PCNSL, or additional retrospective studies on different patient populations with rare diseases, to further promote the clinical role of our model.

Generative Adversarial Networks in Medicine: Important Considerations for this Emerging Innovation in Artificial Intelligence

The advent of artificial intelligence (AI) and machine learning (ML) has revolutionized the field of medicine. Although highly effective, the rapid expansion of this technology has created some anticipated and unanticipated bioethical considerations. With these powerful applications, there is a necessity for framework regulations to ensure equitable and safe deployment of technology. Generative Adversarial Networks (GANs) are emerging ML techniques that have immense applications in medical imaging due to their ability to produce synthetic medical images and aid in medical AI training. Producing accurate synthetic images with GANs can address current limitations in AI development for medical imaging and overcome current dataset type and size constraints. Offsetting these constraints can dramatically improve the development and implementation of AI medical imaging and restructure the practice of medicine. As observed with its other AI predecessors, considerations must be taken into place to help regulate its development for clinical use. In this paper, we discuss the legal, ethical, and technical challenges for future safe integration of this technology in the healthcare sector.

Artificial intelligence for ocular oncology

PURPOSE OF REVIEW

The aim of this article is to provide an update on the latest applications of deep learning (DL) and classical machine learning (ML) techniques to the detection and prognostication of intraocular and ocular surface malignancies.

RECENT FINDINGS

Most recent studies focused on using DL and classical ML techniques for prognostication purposes in patients with uveal melanoma (UM).

SUMMARY

DL has emerged as the leading ML technique for prognostication in ocular oncological conditions, particularly in UM. However, the application of DL may be limited by the relatively rarity of these conditions.

Addressing inter-device variations in optical coherence tomography angiography: will image-to-image translation systems help?

BACKGROUND

Optical coherence tomography angiography (OCTA) is an innovative technology providing visual and quantitative data on retinal microvasculature in a non-invasive manner.

MAIN BODY

Due to variations in the technical specifications of different OCTA devices, there are significant inter-device differences in OCTA data, which can limit their comparability and generalizability. These variations can also result in a domain shift problem that may interfere with applicability of machine learning models on data obtained from different OCTA machines. One possible approach to address this issue may be unsupervised deep image-to-image translation leveraging systems such as Cycle-Consistent Generative Adversarial Networks (Cycle-GANs) and Denoising Diffusion Probabilistic Models (DDPMs). Through training on unpaired images from different device domains, Cycle-GANs and DDPMs may enable cross-domain translation of images. They have been successfully applied in various medical imaging tasks, including segmentation, denoising, and cross-modality image-to-image translation. In this commentary, we briefly describe how Cycle-GANs and DDPMs operate, and review the recent experiments with these models on medical and ocular imaging data. We then discuss the benefits of applying such techniques for inter-device translation of OCTA data and the potential challenges ahead.

CONCLUSION

Retinal imaging technologies and deep learning-based domain adaptation techniques are rapidly evolving. We suggest exploring the potential of image-to-image translation methods in improving the comparability of OCTA data from different centers or devices. This may facilitate more efficient analysis of heterogeneous data and broader applicability of machine learning models trained on limited datasets in this field.

Machine-Learning-Enabled Framework in Engineering Plastics Discovery: A Case Study of Designing Polyimides with Desired Glass-Transition Temperature

Great and continuous efforts have been made to discover high-performance engineering plastics with specific properties to replace traditional engineering materials in many fields. The utilization of machine learning (ML) has brought more opportunities for the discovery of high-performing engineering plastics. However, hindered by either the relatively small database or a lack of accurate structure descriptors with clear physical and chemical meanings relating to polymer properties, the current ML studies show some flaws in the accuracy and efficiency in polymer development. Herein, we collected a dataset of 878 polyimides (PI), one of the best engineering plastics, with experimentally measured glass-transition temperature (Tg) values, and developed a rapid and accurate ML approach to design PI candidates with the desired Tg value. After the conversion from PI structures into "mechanically identifiable" SMILES (Simplified molecular input line entry system) language, the eight most critical descriptors were ultimately obtained by multiple analysis methods. The physiochemical meaning of the key descriptors was further analyzed carefully to translate the implicit "machine language" to chemical knowledge. The artificial neural network (ANN)-based model gave the most accurate results with a root-mean-square error of ∼11 K among the studied ML methods. More importantly, three potential PI candidates with desired Tg (DPIs) were designed according to the chemical insight of the key descriptors, which were then verified by experiments. The experimental and predicted Tg values of DPIs have an acceptable average deviation of ca. 3.66%. This accuracy has reached the level of the traditional molecular simulation, but the time consumption and hold-up computing resource are tremendously reduced. Furthermore, the current ML approach could offer a scalable and adaptable framework in future engineer plastics innovation.

Artificial intelligence-assisted diagnosis of ocular surface diseases

With the rapid development of computer technology, the application of artificial intelligence (AI) in ophthalmology research has gained prominence in modern medicine. Artificial intelligence-related research in ophthalmology previously focused on the screening and diagnosis of fundus diseases, particularly diabetic retinopathy, age-related macular degeneration, and glaucoma. Since fundus images are relatively fixed, their standards are easy to unify. Artificial intelligence research related to ocular surface diseases has also increased. The main issue with research on ocular surface diseases is that the images involved are complex, with many modalities. Therefore, this review aims to summarize current artificial intelligence research and technologies used to diagnose ocular surface diseases such as pterygium, keratoconus, infectious keratitis, and dry eye to identify mature artificial intelligence models that are suitable for research of ocular surface diseases and potential algorithms that may be used in the future.

Prediction of corneal astigmatism based on corneal tomography after femtosecond laser arcuate keratotomy using a pix2pix conditional generative adversarial network

Purpose

This study aimed to develop a deep learning model to generate a postoperative corneal axial curvature map of femtosecond laser arcuate keratotomy (FLAK) based on corneal tomography using a pix2pix conditional generative adversarial network (pix2pix cGAN) for surgical planning.

Methods

A total of 451 eyes of 318 nonconsecutive patients were subjected to FLAK for corneal astigmatism correction during cataract surgery. Paired or single anterior penetrating FLAKs were performed at an 8.0-mm optical zone with a depth of 90% using a femtosecond laser (LenSx laser, Alcon Laboratories, Inc.). Corneal tomography images were acquired from Oculus Pentacam HR (Optikgeräte GmbH, Wetzlar, Germany) before and 3 months after the surgery. The raw data required for analysis consisted of the anterior corneal curvature for a range of ± 3.5 mm around the corneal apex in 0.1-mm steps, which the pseudo-color corneal curvature map synthesized was based on. The deep learning model used was a pix2pix conditional generative adversarial network. The prediction accuracy of synthetic postoperative corneal astigmatism in zones of different diameters centered on the corneal apex was assessed using vector analysis. The synthetic postoperative corneal axial curvature maps were compared with the real postoperative corneal axial curvature maps using the structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR).

Results

A total of 386 pairs of preoperative and postoperative corneal tomography data were included in the training set, whereas 65 preoperative data were retrospectively included in the test set. The correlation coefficient between synthetic and real postoperative astigmatism (difference vector) in the 3-mm zone was 0.89, and that between surgically induced astigmatism (SIA) was 0.93. The mean absolute errors of SIA for real and synthetic postoperative corneal axial curvature maps in the 1-, 3-, and 5-mm zone were 0.20 ± 0.25, 0.12 ± 0.17, and 0.09 ± 0.13 diopters, respectively. The average SSIM and PSNR of the 3-mm zone were 0.86 ± 0.04 and 18.24 ± 5.78, respectively.

Conclusion

Our results showed that the application of pix2pix cGAN can synthesize plausible postoperative corneal tomography for FLAK, showing the possibility of using GAN to predict corneal tomography, with the potential of applying artificial intelligence to construct surgical planning models.

A deep learning approach for detection of shallow anterior chamber depth based on the hidden features of fundus photographs

BACKGROUND AND OBJECTIVES

Patients with angle-closure glaucoma (ACG) are asymptomatic until they experience a painful attack. Shallow anterior chamber depth (ACD) is considered a significant risk factor for ACG. We propose a deep learning approach to detect shallow ACD using fundus photographs and to identify the hidden features of shallow ACD.

METHODS

This retrospective study assigned healthy subjects to the training (n = 1188 eyes) and test (n = 594) datasets (prospective validation design). We used a deep learning approach to estimate ACD and build a classification model to identify eyes with a shallow ACD. The proposed method, including subtraction of the input and output images of CycleGAN and a thresholding algorithm, was adopted to visualize the characteristic features of fundus photographs with a shallow ACD.

RESULTS

The deep learning model integrating fundus photographs and clinical variables achieved areas under the receiver operating characteristic curve of 0.978 (95% confidence interval [CI], 0.963-0.988) for an ACD ≤ 2.60 mm and 0.895 (95% CI, 0.868-0.919) for an ACD ≤ 2.80 mm, and outperformed the regression model using only clinical variables. However, the difference between shallow and deep ACD classes on fundus photographs was difficult to be detected with the naked eye. We were unable to identify the features of shallow ACD using the Grad-CAM. The CycleGAN-based feature images showed that area around the macula and optic disk significantly contributed to the classification of fundus photographs with a shallow ACD.

CONCLUSIONS

We demonstrated the feasibility of a novel deep learning model to detect a shallow ACD as a screening tool for ACG using fundus photographs. The CycleGAN-based feature map showed the hidden characteristic features of shallow ACD that were previously undetectable by conventional techniques and ophthalmologists. This framework will facilitate the early detection of shallow ACD to prevent overlooking the risks associated with ACG.

SMD-YOLO: An efficient and lightweight detection method for mask wearing status during the COVID-19 pandemic

BACKGROUND AND OBJECTIVE

At present, the COVID-19 epidemic is still spreading worldwide and wearing a mask in public areas is an effective way to prevent the spread of the respiratory virus. Although there are many deep learning methods used for detecting the face masks, there are few lightweight detectors having a good effect on small or medium-size face masks detection in the complicated environments.

METHODS

In this work we propose an efficient and lightweight detection method based on YOLOv4-tiny, and a face mask detection and monitoring system for mask wearing status. Two feasible improvement strategies, network structure optimization and K-means++ clustering algorithm, are utilized for improving the detection accuracy on the premise of ensuring the real-time face masks recognition. Particularly, the improved residual module and cross fusion module are designed to aim at extracting the features of small or medium-size targets effectively. Moreover, the enhanced dual attention mechanism and the improved spatial pyramid pooling module are employed for merging sufficiently the deep and shallow semantic information and expanding the receptive field. Afterwards, the detection accuracy is compensated through the combination of activation functions. Finally, the depthwise separable convolution module is used to reduce the quantity of parameters and improve the detection efficiency. Our proposed detector is evaluated on a public face mask dataset, and an ablation experiment is also provided to verify the effectiveness of our proposed model, which is compared with the state-of-the-art (SOTA) models as well.

RESULTS

Our proposed detector increases the AP (average precision) values in each category of the public face mask dataset compared with the original YOLOv4-tiny. The mAP (mean average precision) is improved by 4.56% and the speed reaches 92.81 FPS. Meanwhile, the quantity of parameters and the FLOPs (floating-point operations) are reduced by 1/3, 16.48%, respectively.

CONCLUSIONS

The proposed detector achieves better overall detection performance compared with other SOTA detectors for real-time mask detection, demonstrated the superiority with both theoretical value and practical significance. The developed system also brings greater flexibility to the application of face mask detection in hospitals, campuses, communities, etc.

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

BACKGROUND

Recent advances in deep learning techniques have led to improved diagnostic abilities in ophthalmology. A generative adversarial network (GAN), which consists of two competing types of deep neural networks, including a generator and a discriminator, has demonstrated remarkable performance in image synthesis and image-to-image translation. The adoption of GAN for medical imaging is increasing for image generation and translation, but it is not familiar to researchers in the field of ophthalmology. In this work, we present a literature review on the application of GAN in ophthalmology image domains to discuss important contributions and to identify potential future research directions.

METHODS

We performed a survey on studies using GAN published before June 2021 only, and we introduced various applications of GAN in ophthalmology image domains. The search identified 48 peer-reviewed papers in the final review. The type of GAN used in the analysis, task, imaging domain, and the outcome were collected to verify the usefulness of the GAN.

RESULTS

In ophthalmology image domains, GAN can perform segmentation, data augmentation, denoising, domain transfer, super-resolution, post-intervention prediction, and feature extraction. GAN techniques have established an extension of datasets and modalities in ophthalmology. GAN has several limitations, such as mode collapse, spatial deformities, unintended changes, and the generation of high-frequency noises and artifacts of checkerboard patterns.

CONCLUSIONS

The use of GAN has benefited the various tasks in ophthalmology image domains. Based on our observations, the adoption of GAN in ophthalmology is still in a very early stage of clinical validation compared with deep learning classification techniques because several problems need to be overcome for practical use. However, the proper selection of the GAN technique and statistical modeling of ocular imaging will greatly improve the performance of each image analysis. Finally, this survey would enable researchers to access the appropriate GAN technique to maximize the potential of ophthalmology datasets for deep learning research.