iris nevus
Recently Published Documents


TOTAL DOCUMENTS

31
(FIVE YEARS 1)

H-INDEX

8
(FIVE YEARS 0)

2021 ◽  
Author(s):  
Abdulkader Helwan

Recently, Convolutional neural networks (CNN) have shown a growth due to their ability of learning different level image representations that helps in image classification in different fields. These networks have been trained on millions of images, so they gained a powerful ability of extracting the rightful features from input images, which results in accurate classification. In this research, we investigate the effects of transfer learning based convolutional neural networks for the iris tumor malignancy identification as it is notoriously hard to distinguish an iris nevus from an iris tumor. Features are transferred from a CNN trained on a source task, i.e. ImageNet, to a target task, i.e. iris tumor datasets. We transfer features learned from AlexNet and VGG-16 that are trained on ImageNet, to classify three different iris images types which are: iris nevus unaffected, iris cysts, and iris melanocytic tumors. The employed pre-trained models are modified by replacing their feedforward neural network classifier, Softmax, by a support vector machine (SVM) that is expected to slightly boost their performance (AlexNet-SVM and VGG16-SVM). All employed models are trained (fine-tuned) on a 60% of the available large dataset of iris images in order to investigate their power of generalization when trained using large amount of data. The networks are also tested on 40% of the data. The best performance was achieved by the VGG16-SVM which scored a high accuracy of 96.27% and strong features extraction capability as compared to the other models. Experimentally, it was seen that adding SVM contributed in improving the network performance compared to original models which use a feedforward neural network classifier.


2020 ◽  
Vol 10 (24) ◽  
pp. 8766
Author(s):  
Andrea Russo ◽  
Teresio Avitabile ◽  
Michele Reibaldi ◽  
Vincenza Bonfiglio ◽  
Francesco Pignatelli ◽  
...  

Iris melanomas represent 2–5% of uveal melanomas. Iris melanomas vary in their size, shape, degree of pigmentation and clinical behavior. The main local clinical complications of iris melanomas are tumor vascularization, ectropion uvea, pupillary distortion, pigment dispersion, sector cataract, chronic uveitis, hyphema and glaucoma with irreversible optic nerve damage. The most effective treatment for iris nevus and melanoma remains debatable; treatment modalities have been proposed depending on the local status as well as the age and general condition of the patient. A melanocytic iris nevus is usually observed until documented progression is identified. In this case, radiotherapy or surgical resection is generally performed. Cataract, glaucoma and limbal stem cell deficiency are usually secondary to radiotherapy, while incomplete tumor excisions, which could lead to recurrence, hemorrhage, vitreous loss, dislocated lens, iridocyclitis, macular edema, retinal detachment, glaucoma and cataract, are related to surgical resection. In some cases, a combination of radiotherapy and surgery is used. Conservative treatment is an efficient alternative to enucleation and allows good local tumor control.


2020 ◽  
Vol 13 (12) ◽  
pp. e237269
Author(s):  
Catarina Xavier ◽  
Diogo Hipolito-Fernandes ◽  
Joana Cardigos ◽  
Ana Magriço

Iris melanocytoma (IM) is a rare variant of iris nevus with distinctive clinical and histopathological features. A 66-year-old woman, with a history of right eye pigmented iris nevus, presented to us with a recent onset of visual acuity decrease in that eye. She had a melanocytic iris lesion with iridocorneal angle invasion, peripheral corneal adhesion, pupil corectopia, sectorial cataract and high intraocular pressure. Ultrasound biomicroscopy did not exclude malignant transformation, so excisional biopsy was performed revealing the presence of IM without signs of atypia. Subsequently, the patient underwent cataract surgery combined with iridoplasty and later an ab externo trabeculectomy. Most cases of IM remain stable and require no intervention, but in cases of unusual clinical course, with rapid growth or secondary glaucoma, surgical treatment is indicated as a diagnostic and therapeutic measure. This case report highlights the importance of a timely and multidisciplinary ophthalmological approach for a better visual outcome.


2020 ◽  
Author(s):  
Keyword(s):  

Author(s):  
Maxwell R. Harley ◽  
Raksha Rao ◽  
Sara E. Lally ◽  
Carol L. Shields

2016 ◽  
Vol 7 (3) ◽  
pp. 450-456 ◽  
Author(s):  
Davide Allegrini ◽  
Giovanni Montesano ◽  
Alfredo Pece

Iris nevus is common: 6% of patients with suspected iris melanoma have lesions other than melanoma, and 36% of them are nevi. Iris nevus turns into melanoma in approximately 8% of cases at a mean of 15 years. This case report provides the first description of an iris tumor examined with iris optical coherence tomography angiography (OCTA) compared to iris fluorescein angiography (IFA). A 60-year-old man with a diagnosis of iris nevus in the left eye was referred to our department for IFA and iris OCTA. The iris vasculature in IFA was visible only in the early phases, but not clearly. OCTA, however, gave visualization of the vascular network and very precisely defined the vessels of the whole lesion, except for the pupillary portion, which was masked by superficial pigment accumulations. IFA and iris OCTA can add information about the vascular architecture compared to slit-lamp biomicroscopy, ultrasound biomicroscopy, and anterior-segment OCT. However, IFA is time-consuming and invasive and can – very occasionally – cause serious adverse reactions. In contrast, OCTA defines the texture of the iris vasculature better. In conclusion, OCTA is a new method, easy to execute, needing no dye injection, and provides useful information on the vascular network of iris lesions. It could therefore be helpful in the diagnosis and follow-up of these lesions.


QJM ◽  
2015 ◽  
Vol 109 (2) ◽  
pp. 137-137
Author(s):  
A. Mahdavi Fard ◽  
L. Pourafkari ◽  
N.D. Nader
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document