Corneal biopsy with tissue micro-homogenisation for isolation of organisms in bacterial keratitis

Diagnosis of Acanthamoeba Keratitis: Past, Present and Future

Acanthamoeba keratitis (AK) is a painful and sight-threatening parasitic corneal infection. In recent years, the incidence of AK has increased. Timely and accurate diagnosis is crucial during the management of AK, as delayed diagnosis often results in poor clinical outcomes. Currently, AK diagnosis is primarily achieved through a combination of clinical suspicion, microbiological investigations and corneal imaging. Historically, corneal scraping for microbiological culture has been considered to be the gold standard. Despite its technical ease, accessibility and cost-effectiveness, the long diagnostic turnaround time and variably low sensitivity of microbiological culture limit its use as a sole diagnostic test for AK in clinical practice. In this review, we aim to provide a comprehensive overview of the diagnostic modalities that are currently used to diagnose AK, including microscopy with staining, culture, corneal biopsy, in vivo confocal microscopy, polymerase chain reaction and anterior segment optical coherence tomography. We also highlight emerging techniques, such as next-generation sequencing and artificial intelligence-assisted models, which have the potential to transform the diagnostic landscape of AK.

Detection of Corneal Ulcer Using a Genetic Algorithm-Based Image Selection and Residual Neural Network

Corneal ulcer is one of the most devastating eye diseases causing permanent damage. There exist limited soft techniques available for detecting this disease. In recent years, deep neural networks (DNN) have significantly solved numerous classification problems. However, many samples are needed to obtain reasonable classification performance using a DNN with a huge amount of layers and weights. Since collecting a data set with a large number of samples is usually a difficult and time-consuming process, very large-scale pre-trained DNNs, such as the AlexNet, the ResNet and the DenseNet, can be adapted to classify a dataset with a small number of samples, through the utility of transfer learning techniques. Although such pre-trained DNNs produce successful results in some cases, their classification performances can be low due to many parameters, weights and the emergence of redundancy features that repeat themselves in many layers in som cases. The proposed technique removes these unnecessary features by systematically selecting images in the layers using a genetic algorithm (GA). The proposed method has been tested on ResNet on a small-scale dataset which classifies corneal ulcers. According to the results, the proposed method significantly increased the classification performance compared to the classical approaches.

Comparison of Culture Results between Specimens from Corneal Scraping with Microhomogenization and Corneal Swab in Moderate and Severe Bacterial Corneal Ulcers

The purpose of this study was to compare the bacterial culture results from corneal infiltrate specimens collected using two different methods, corneal scraping followed by microhomogenization and corneal swab. This is a comparative crosssectional study, with 18 participants undergoing corneal specimen collection using each of the 2 sampling techniques. The results from the scraping and swab methods were separated and then compared using data analysis. The proportion of Gram stain results that matched the culture results for the scraping-microhomogenization technique was 6/13 (46.2%), and the proportion of Gram stain results that matched the culture results for the swab technique was 5/13 (38.5%) (McNemar test P value, 1.000; P > 0.05). The proportion of positive cultures obtained using the scraping-microhomogenization technique was 13/18 (72.2%), and the proportion of positive cultures obtained using the swab technique was 9/18 (50%) (McNemar test P value, 0.219; P > 0.05). The Kappa suitability test value for comparison of the scraping-microhomogenization technique to the corneal swab was 0.333. The specimens collected by corneal scraping followed by microhomogenization had a higher positive bacterial culture rate than those collected by corneal swab, but the results were not statistically significant. IMPORTANCE This study aimed to compare the culture results between scraping specimens with microhomogenization and corneal smears in patients with moderate to severe bacterial corneal ulcers. This study could be a guideline for treating bacterial corneal ulcers.

Multi-scale information fusion network with label smoothing strategy for corneal ulcer classification in slit lamp images

Corneal ulcer is the most common symptom of corneal disease, which is one of the main causes of corneal blindness. The accurate classification of corneal ulcer has important clinical importance for the diagnosis and treatment of the disease. To achieve this, we propose a deep learning method based on multi-scale information fusion and label smoothing strategy. Firstly, the proposed method utilizes the densely connected network (DenseNet121) as backbone for feature extraction. Secondly, to fully integrate the shallow local information and the deep global information and improve the classification accuracy, we develop a multi-scale information fusion network (MIF-Net), which uses multi-scale information for joint learning. Finally, to reduce the influence of the inter-class similarity and intra-class diversity on the feature representation, the learning strategy of label smoothing is introduced. Compared with other state-of-the-art classification networks, the proposed MIF-Net with label smoothing achieves high classification performance, which reaches 87.07 and 83.84% for weighted-average recall (W_R) on the general ulcer pattern and specific ulcer pattern, respectively. The proposed method holds promise for corneal ulcer classification in fluorescein staining slit lamp images, which can assist ophthalmologists in the objective and accurate diagnosis of corneal ulcer.

Role of corneal biopsy in the management of infectious keratitis

PURPOSE OF REVIEW

The aim of this study was to review the existing literature and investigate the role of microbiologic culture and histopathologic examination of corneal biopsies in the management of infectious keratitis.

RECENT FINDINGS

Corneal biopsy continues to be a significantly useful tool in the diagnosis and tailored management of infectious keratitis. Several techniques can be employed for tissue collection, handling and processing to optimize diagnostic yield and maximize safety, including emerging femtosecond laser-assisted biopsy.

SUMMARY

Corneal opacities represent a significant cause of global blindness, and infectious keratitis is the most common cause. Organism identification in progressive infectious keratitis is essential for proper management. However, microbiological culture alone has a high rate of false-negative results. Records from the Bascom Palmer Eye Institute were retrospectively searched for patients between 1 January 2015, and 31 December 2019, who underwent corneal biopsy, therapeutic keratoplasty or endothelial graft removal for infectious keratitis and had specimens bisected and submitted for evaluation with both microbiologic culture and histopathologic examination. Detection of bacteria, fungus and mycobacteria was not statistically different between culture and histopathology. Microbiology and histopathology are complementary methods for the identification of causative microorganisms in corneal specimens with presumed infectious keratitis.

Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images

Corneal ulcer is a common leading cause of corneal blindness. It is difficult to accurately segment corneal ulcers due to the following problems: large differences in the pathological shapes between point-flaky and flaky corneal ulcers, blurred boundary, noise interference, and the lack of sufficient slit-lamp images with ground truth. To address these problems, in this paper, we proposed a novel semi-supervised multi-scale self-transformer generative adversarial network (Semi-MsST-GAN) that can leverage unlabeled images to improve the performance of corneal ulcer segmentation in fluorescein staining of slit-lamp images. Firstly, to improve the performance of segmenting the corneal ulcer regions with complex pathological features, we proposed a novel multi-scale self-transformer network (MsSTNet) as the MsST-GAN generator, which can guide the model to aggregate the low-level weak semantic features with the high-level strong semantic information and adaptively learn the spatial correlation in feature maps. Then, to further improve the segmentation performance by leveraging unlabeled data, the semi-supervised approach based on the proposed MsST-GAN was explored to solve the problem of the lack of slit-lamp images with corresponding ground truth. The proposed Semi-MsST-GAN was comprehensively evaluated on the public SUSTech-SYSU dataset, which contains 354 labeled and 358 unlabeled fluorescein staining slit-lamp images. The results showed that, compared with other state-of-the-art methods, our proposed method achieves better performance with comparable efficiency.

Diagnostic methods for the etiological assessment of infectious corneal pathology (Review)

Infectious keratitis is a leading cause of visual morbidity, including blindness, all across the globe, especially in developing countries. Prompt and adequate treatment is mandatory to maintain corneal integrity and to recover the best possible final visual acuity. Although in most of the cases practitioners chose to employ empirical broad-spectrum antimicrobial medication that is usually effective, in some instances, they face the need to identify the causative agent to establish the appropriate therapy. An extensive search was conducted on published literature before December 2020 concerning the main laboratory investigations used to identify the microbial agents found in infectious keratitis, their indications, advantages, and disadvantages, as well as the results reported by other studies concerning different diagnostic tools. At present, the gold standard for diagnosis is still considered to be the isolation of microorganisms in cultures, along with the examination of smears, but other newer techniques, such as polymerase chain reaction (PCR), next-generation sequencing (NGS), and in vivo confocal microscopy (IVCM) have gained popularity in the last decades. Currently, these newer methods have proved to be valuable adjuvants in making the diagnosis, but technological advances hold promise that, in the future, these methods will have increased performance and availability, and may become the new gold standard, replacing the classic cultures and smears.

The SUSTech-SYSU dataset for automatically segmenting and classifying corneal ulcers

Corneal ulcer is a common ophthalmic symptom. Segmentation algorithms are needed to identify and quantify corneal ulcers from ocular staining images. Developments of such algorithms have been obstructed by a lack of high quality datasets (the ocular staining images and the corresponding gold-standard ulcer segmentation labels), especially for supervised learning based segmentation algorithms. In such context, we prepare a dataset containing 712 ocular staining images and the associated segmentation labels of flaky corneal ulcers. In addition to segmentation labels for flaky corneal ulcers, we also provide each image with three-fold class labels: firstly, each image has a label in terms of its general ulcer pattern; secondly, each image has a label in terms of its specific ulcer pattern; thirdly, each image has a label indicating its ulcer severity degree. This dataset not only provides an excellent opportunity for investigating the accuracy and reliability of different segmentation and classification algorithms for corneal ulcers, but also advances the development of new supervised learning based algorithms especially those in the deep learning framework.

Spectrum of bacterial keratitis at a tertiary eye care centre in India

Aim. To report the aetiological spectrum and susceptibility patterns of bacteria isolated from patients with corneal ulceration. Method. The microbiological data of all patients with suspected infectious corneal ulceration who presented to the ocular microbiology service at this centre between 2005 and 2012 were reviewed retrospectively. Result. Microorganisms were recovered from 1665 (77%) of the 2170 ulcers. Bacterial isolates accounted for 1205 of the organisms isolated. The most common bacterial pathogens isolated were various species of Staphylococcus, representing 777 (64.5%), followed by Staphylococcus spp. (148; 12.3%) and Pseudomonas aeruginosa (117; 9.7%). High percentages of Gram-positive bacteria were susceptible to gatifloxacin (>94%), followed by ofloxacin and moxifloxacin. Almost 90% of Pseudomonas aeruginosa isolates were susceptible to ciprofloxacin and moxifloxacin. Sixty-two (44%) of 140 isolates of Streptococcus pneumoniae, 79 (14.8%) of 534 isolates of Staphylococcus epidermidis, and 33 (14%) of 234 isolates of Staphylococcus aureus were resistant to three or more antibiotics. Conclusion. Staphylococcus spp. were the most common bacterial pathogens isolated from patients with keratitis in this setting. High percentages of Gram-positive and Gram-negative bacteria were susceptible to gatifloxacin and moxifloxacin, respectively. Interestingly, a high percentage of Streptococcus pneumoniae isolates were found to be resistant to three or more antibiotics.

Bacterial keratitis: a prospective clinical and microbiological study

AIM

To define the clinical and microbiological profile of bacterial keratitis at the Jules Gonin Eye Hospital and to test the in vitro bacterial resistance.

METHODS

Patients presenting with bacterial keratitis were prospectively followed; clinical features (age, risk factors, visual acuity) and response to therapy were analysed. Bacteriological profile was determined and the sensitivity/resistance of isolated strains were tested towards 12 ocular antibiotics (NCCLS disc diffusion test).

RESULTS

85 consecutive patients (mean age 44.3 (SD 20.7) years) were prospectively enrolled from 1 March 1997 to 30 November 1998. The following risk factors were identified: contact lens wear, 36%; blepharitis, 21%; trauma, 20%; xerophthalmia, 15%; keratopathies, 8%; and eyelid abnormalities, 6%. The most commonly isolated bacteria were Staphylococcus epidermidis, 40%; Staphylococcus aureus, 22%; Streptococcus pneumoniae, 8%; others Streptococcus species, 5%; Pseudomonas, 9%; Moraxella and Serratia marcescens, 5% each; Bacillus, Corynebacterium, Alcaligenes xyloxidans, Morganella morganii, and Haemophilus influenza, 1% each. 1-15% of strains were resistant to fluoroquinolones, 13-22% to aminoglycosides, 37% to cefazolin, 18% to chloramphenicol, 54% to polymyxin B, 51% to fusidic acid, and 45% to bacitracin. Five of the 85 patients (5.8%) had a poor clinical outcome with a visual loss of one or more lines of visual acuity.

CONCLUSION

Fluoroquinolones appear to be the therapy of choice for bacterial keratitis, but, based upon these in vitro studies, some strains may be resistant.