Fundus image classification using Inception V3 and ResNet-50 for the early diagnostics of fundus diseases.

Purpose: We aim to present effective and computer aided diagnostics in the field of ophthalmology and improve eye health. This study aims to create an automated deep learning based system for categorizing fundus images into three classes: normal, macular degeneration and tessellated fundus for the timely recognition and treatment of diabetic retinopathy and other diseases. Methods: A total of 1,032 fundus images were collected from 516 patients using fundus camera from Health Management Center, Shenzhen University General Hospital Shenzhen University, Shenzhen 518055, Guangdong, China. Then, Inception V3 and ResNet-50 deep learning models are used to classify fundus images into three classes, Normal, Macular degeneration and tessellated fundus for the timely recognition and treatment of fundus diseases. Results: The experimental results show that the effect of model recognition is the best when the Adam is used as optimizer method, the number of iterations is 150, and 0.00 as the learning rate. According to our proposed approach we, achieved the highest accuracy of 93.81% and 91.76% by using ResNet-50 and Inception V3 after fine-tuned and adjusted hyper parameters according to our classification problem. Conclusion: Our research provides a reference to the clinical diagnosis or screening for diabetic retinopathy and other eye diseases. Our suggested computer aided diagnostics framework will prevent incorrect diagnoses caused by the low image quality and individual experience, and other factors. In future implementations, the ophthalmologists can implement more advanced learning algorithms to improve the accuracy of diagnosis.

A deep learning based framework for the classification of multi- class capsule gastroscope image in gastroenterologic diagnosis.

Purpose: The purpose of this paper is to develop a method to automatic classify capsule gastroscope image into three categories to prevent high-risk factors for carcinogenesis, such as atrophic gastritis (AG). The purpose of this research work is to develop a deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. Method: In this research work, we proposed deep learning framework based on transfer learning to classify capsule gastroscope image into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. We used VGG- 16, ResNet-50, and Inception V3 pre-trained models, fine-tuned them and adjust hyperparameters according to our classification problem. Results: A dataset containing 380 images was collected for each capsule gastroscope image category, and divided into training set and test set in a ratio of 70%, and 30% respectively, and then based on the dataset, three methods, including as VGG- 16, ResNet-50, and Inception v3 are used. We achieved highest accuracy of 94.80% by using VGG- 16 to diagnose and classify capsule gastroscopic images into three categories: normal gastroscopic image, chronic erosive gastritis images, and ulcer gastric image. Our proposed approach classified capsule gastroscope image with respectable specificity and accuracy. Conclusion: The primary technique and industry standard for diagnosing and treating numerous stomach problems is gastroscopy. Capsule gastroscope is a new screening tool for gastric diseases. However, a number of elements, including image quality of capsule endoscopy, the doctors' experience and fatigue, limit its effectiveness. Early identification is necessary for high-risk factors for carcinogenesis, such as atrophic gastritis (AG). Our suggested framework will help prevent incorrect diagnoses brought on by low image quality, individual experience, and inadequate gastroscopy inspection coverage, among other factors. As a result, the suggested approach will raise the standard of gastroscopy. Deep learning has great potential in gastritis image classification for assisting with achieving accurate diagnoses after endoscopic procedures.

Evaluation of Meibomian Gland Function after Therapy of Eyelid Tumors at Palpebral Margin with Super Pulse CO2 Laser.

PURPOSE: To investigate the effect on meibomian gland function of super pulse carbon dioxide (CO2) laser excision in the treatment of eyelid tumors at palpebral margin. METHODS: 36 patients with 36 eyelid tumor size ≤ 1 cm and within 1 mm to palpebral margin were recruited in this study. Of which, 16 cases with tumors in the upper eyelid and 20 cases in the lower eyelid were involved. The eyelid tumors of all the patients were treated by super pulse CO2 laser with its power density varied between 0.6 and 21.1 W/mm2 and in repeat mode. The laser spot size ranged from 120 to 200 µm. Ocular surface parameters including tear film break-up time (BUT) and meibograde, meibum expressibility, and meibum quality were evaluated at pretherapy, 1 week, 1 month, and 3 months posttherapy in all 36 patients. RESULT: All the patients were satisfied with the therapy. No infective complications and recurrence occurred in any of the 36 patients at the following period. The eyelid wound recovered well with nearly normal appearing after 2 to 3 weeks. The morphology of limbi palpebralis, BUT, meibograde, meibum expressibility, and meibum quality of all the 36 patients showed no significant difference before and after the therapy. CONCLUSIONS: Super pulse CO2 laser had no effect on meibomian gland function and morphology in the excision of tumors at palpebral margins, which was an efficacy and well-tolerated therapy with lower complications and recurrence.

Super pulse CO2 laser therapy for benign eyelid tumors.

BACKGROUND: Benign eyelid tumors occur commonly in daily outpatient services. OBJECTIVES: The aim of this study was to evaluate the treatment of benign eyelid lesions with a super pulse CO2 laser as an alternative to surgical excision. METHODS: This retrospective clinical study included 80 patients with 99 benign eyelid lesions treated with super pulse CO2 laser photocoagulation. The following areas were involved: the upper eyelid in 38 cases, the lower eyelid in 39 cases, and the angulus oculi in seven cases (the eyelid margin was included in 18 cases). The laser spot size ranged from 120 to 200 µm and the super pulse CO2 laser power density varied between 0.6 and 21.1 W/mm2 . The mean follow-up period was 14.0±7.1 months (range five to 30). Histological diagnoses were obtained in 62 of the 80 patients. RESULTS: The cosmetic outcomes of all of the patients were satisfactory after treatment, and the wounds formed dry scabs, with no infections. They were epithelialized within 2-4 weeks with normal-appearing epithelium. Temporarily, the treated area had less hyperpigmentation than the surrounding normal skin, showing no obvious scars or notches. No complications were observed, with no relapses during the follow-up. CONCLUSIONS: The super pulse CO2 laser therapy of the benign eyelid tumors provided satisfactory cosmetic results in this study. It is a convenient, cheap, accessible, and well-tolerated alternative to traditional surgery, especially for diffuse tumors, or those positioned close to the lacrimal papillae.