Explore the vast range of titles available.

Retinitis Pigmentosa (RP) is a rare genetic retinal disorder characterized by the progressive degeneration of rod and cone photoreceptors, leading to vision impairment and eventual blindness. This study investigates the application of state-of-the-art convolutional neural networks (CNNs) and aggregation methods related to Ordered Weighted Averaging Operators (OWA) to classify RP with enhanced accuracy. Using pre-trained CNN architectures such as EfficientNet, ResNet, and DenseNet, individual classifiers were evaluated, among which EfficientNet achieved the highest performance. To improve these results, aggregation methods, including classic Ordered Weighted Averaging (OWA) operators and the novel Smooth OWA operators, were employed. The aggregation process significantly boosted classification accuracy, with the OWA operator variants achieving approximately 25 percentage point improvement over the best-performing individual classifier. The best results were obtained using Smooth OWA operators inspired by Newton-Cotes quadratures, achieving a consistent additional improvement over the base OWA operator. This study demonstrates the effectiveness of combining advanced CNN models with aggregation techniques for improving classification accuracy on small and imbalanced datasets. The results highlight the potential of Smooth OWA operators in enhancing the robustness and performance of machine learning models in medical diagnosis tasks.

AimTo develop a simple and easily applicable classification of disease severity in retinitis pigmentosa (RP).MethodsThis is a retrospective cross-sectional study. Visual acuity (VA), visual field width (VF) and ellipsoid zone width (EZ) were obtained from medical records of patients with RP. A scoring criterion was developed wherein each variable was assigned a score from 0 to 5 depending on its distribution. The cumulative score (from 0 to 15) was used to classify disease severity from grade 0 to 5. The scores were correlated with each other and the final grade. The grades were then correlated with age and disease duration.ResultsThe median age (range) of patients (n=93) was 55 (12–87) years, 51% were female, 70% had been diagnosed within 10 years, and 50% had autosomal recessive disease. Most eyes (n=181) at least had a VA of 20/40 (67%), a VF of 20° (75%) and an EZ of 5° (76%). All scores were correlated with each other (r=0.509–0.613; p<0.001 for all) and with the final grade (r=0.790–0.869; p<0.001 for all). Except for grade 0 (5%), all grades were evenly distributed: 21% for grade 1, 23% for grade 2, 22% for grade 3, 17% for grade 4 and 12% for grade 5. Grades were correlated with both age (r=0.252; p<0.001) and disease duration (r=0.383; p<0.001).ConclusionsWe present a simple, objective and easy to use disease severity classification for RP which can be used to categorise and compare patients.

Purpose To determine whether convolutional neural networks (CNN) can classify the severity of central vision loss using fundus autofluorescence (FAF) images and color fundus images of retinitis pigmentosa (RP), and to evaluate the utility of those images for severity classification. Study design Retrospective observational study. Methods Medical charts of patients with RP who visited Nagoya University Hospital were reviewed. Eyes with atypical RP or previous surgery were excluded. The mild group was comprised of patients with a mean deviation value of > − 10 decibels, and the severe group of < − 20 decibels, in the Humphrey field analyzer 10-2 program. CNN models were created by transfer learning of VGG16 pretrained with ImageNet to classify patients as either mild or severe, using FAF images or color fundus images. Results Overall, 165 patients were included in this study; 80 patients were classified into the severe and 85 into the mild group. The test data comprised 40 patients in each group, and the images of the remaining patients were used as training data, with data augmentation by rotation and flipping. The highest accuracies of the CNN models when using color fundus and FAF images were 63.75% and 87.50%, respectively. Conclusion Using FAF images may enable the accurate assessment of central vision function in RP. FAF images may include more parameters than color fundus images that can evaluate central visual function.

Background To investigate the association between fundus autofluorescence (FAF) and retinal structure and function in retinitis pigmentosa (RP). Methods For image acquisition, HRA2 (Heidelberg Engineering) and 3D-OCT1000 (Topcon Corp.) were used. Based on FAF examination, 88 eyes of 44 RP patients were categorized into three types. The area within the hyperautofluorescent ring and the area of preserved retinal autofluorescence with FAF was calculated. The association between the pattern of FAF and the residual area of the junction between the inner and outer segments of the photoreceptors (IS/OS line), and the relationship between the area within hyperautofluorescent ring, the area of preserved retinal autofluorescence and the mean deviation (MD) of static perimetry were assessed. Results Twenty-four eyes were with preserved retinal autofluorescence without hyperautofluorescent ring, 54 eyes were with hyperautofluorescent ring and ten eyes were with abnormal foveal autofluorescence both in the fovea and the periphery of the 30° scan. In the first type, the IS/OS line was clearly detected. In the second type, the residual area of the partially distinct IS/OS line corresponded with the area within hyperautofluorescent ring with significant correlation between the area within hyperautofluorescent ring and the MD (R 2  = 0.705, p  < 0.001); however, there was no correlation between the area of preserved retinal autofluorescence and the MD, or between the area of preserved retinal autofluorescence and the area within hyperautofluorescent ring. In the third type, the IS/OS line was completely absent. Conclusions The residual IS/OS line can be found in the area inside the hyperautofluorescent ring and correlates with residual visual function.

Retinitis pigmentosa is the most common form of retinal degeneration and is heterogeneous both clinically and genetically. The autosomal dominant forms (ADRP) can be caused by mutations in 12 different genes. This report describes the first simultaneous mutation analysis of all the known ADRP genes in the same population, represented by 43 Italian families. This analysis allowed the identification of causative mutations in 12 of the families (28% of the total). Seven different mutations were identified, two of which are novel (458delC and 6901C→T (P2301S), in the CRX and PRPF8 genes, respectively). Several novel polymorphisms leading to amino acid changes in the FSCN2, NRL, IMPDH1, and RP1 genes were also identified. Analysis of gene prevalences indicates that the relative involvement of the RHO and the RDS genes in the pathogenesis of ADRP is less in Italy than in US and UK populations. As causative mutations were not found in over 70% of the families analysed, this study suggests the presence of further novel genes or sequence elements involved in the pathogenesis of ADRP.

To see if any a-wave measure segregated normal cats from those affected by a recessively inherited Abyssinian rod/cone dystrophy more efficiently than a(max) to scotopic I(max). A-waves to electroretinograms (ERGs) evoked by a 4 cd x s/m(2) scotopic flash were extracted from 241 ERG sessions using 108 cats. They were either wild type or from an affected Abyssinian stock. Fourty four were bred by back-crossing to have a 50% probability of being affected. Most were diagnosed by retinal appearance or by the pattern of loss in a long protocol ERG. Eight were still unclassified. The diagnostic efficiency of amplitudes at 7, 8, 9, and 10 ms and a(max), of a(max) peak time, age at testing, and the main components of principal components factor analysis were compared by scaling their ability to segregate affected and normal cats. Variance and overlap between the groups both decreased as time along the a-wave increased. The loading of each animal on the largest factor also gave considerable overlap. There was a small absolute separation between groups when a(max) itself was used. Age and peak time were uncorrelated with disease. The light intensity used could be calculated to be equivalent to one sufficient for about 75% of full saturation in man. A(max) is a simple measure that is already in routine clinical use. When the flash is very bright and the animal fully dark adapted, this single measure is the most efficient sign of this rod/cone degeneration and possibly of all degenerations involving rods.

Retinitis pigmentosa (RP) is an inherited retinal disorder clinically characterized by a pale, waxy optic nerve head, attenuated retinal blood vessels and bone spicule pigment in the retina. Hemodynamic studies have demonstrated that RP is associated with a reduction in the retinal and choroidal blood flow. Retinal hemodynamic impairment is also present in the early stages of RP and various hypotheses have been advanced as to its cause. The authors studied 20 patients, 12 males and 8 females, aged between 26 and 42 years (mean 34.6 years) affected by simplex RP. The twenty patients were divided in two groups according to the degree of sight impairment: group A consisted of 10 patients with a visual acuity of 0.3 ± 0.1, visual field mean defect 18.988 ± 3.419 dB and b-wave electroretinogram amplitude of 13.14 ± 0.308 µV. Group B consisted of 10 patients with a visual acuity of 0.8 ± 0.2, visual field MD 10.523 ± 3.582 dB and b-wave electroretinogram amplitude of 26.000 ± 0.757 µV. An increase in plasma levels of endothelin-1 (ET-1) was found as compared with healthy controls: 1.910 ± 0.617 pg/ml vs. 1.180 ± 0.210 pg/ml (p < 0.021), but there was no statistical difference between group A and B (p < 0.163). It is thought that an increase in ET-1 and retinal oxygen levels in RP could lead to vasoconstriction and a decrease in the retinal blood flow worsening the abiotrophic process.

Although many genes have been linked to inherited retinal disorders, it is difficult to explain how specific mutations can cause such a wide variety of phenotypes.

Retinitis pigmentosa (RP) is a group of inherited retinal diseases that are caused by genetic defects that lead to progressive photoreceptor loss and eventual blindness. Early diagnosis would be helpful for effective management of the disease; however, many patients stay unaware of early symptoms. Meanwhile, fundus images are widely obtained during routine medical checkups but are underused for detecting RP. This study explores the effectiveness of finetuning deep learning models, pre-trained for general visual tasks, to identify RP from color fundus images. The dataset comprised 321 color fundus images from 201 Japanese subjects at Keio University Hospital, including 200 images from 107 patients with retinitis pigmentosa and 121 images from 94 non-retinitis pigmentosa subjects. Multiple images were available for some subjects. Using transfer learning, pretrained convolutional neural network models -VGG16, Resnet50, and InceptionV3- were finetuned to detect RP. As a result, Inception V3 achieved the best accuracy of 96.97%, which matches the average diagnostic accuracy of ophthalmologists. Gradient-weighted Class Activation Mapping (Grad-CAM) suggested that the model attended to clinically relevant fundus regions, including the peripheral retina and posterior pole, which may reflect features such as peripheral degenerative changes and retinal vascular attenuation. These findings support the potential interpretability of the finetuned model and suggest that deep learning may assist ophthalmologists in RP screening as a supportive tool.

Classification of inheritance patterns is important for clinical characterization and genetic counseling in inherited retinal diseases (IRDs). In practice, inheritance assessment integrates pedigree information, clinical evaluation, and genetic testing. However, a definitive molecular diagnosis is not achievable in a subset of patients, even with contemporary sequencing approaches, and family history may be incomplete or ambiguous. These limitations motivate investigation of complementary phenotype-based approaches that may provide additional contextual information, while not replacing molecular diagnosis when available. Deep learning (DL) applied to fundus imaging presents a promising approach for automated inference of inheritance modes, as recent advances in oculomics have demonstrated applications of DL in uncovering subtle phenotypic patterns associated with retinal conditions. However, development has been hindered by the low prevalence of IRDs and the scarcity of annotated datasets in individual clinical settings. In this study, we focus on retinitis pigmentosa (RP), a highly heterogeneous disorder in both clinical presentation and genetic etiology. We present a first-in-class deep learning approach that leverages Vision Transformer (ViT) models to distinguish autosomal from X-linked RP using color fundus photography. To overcome challenges posed by limited data, we introduce an innovative variational autoencoder–based data expansion strategy, which improves inheritance pattern classification based on color fundus photos from 0.67 AUC to 0.79 AUC. Our findings demonstrate the potential of deep learning to uncover subtle phenotypic differences linked to genetic inheritance, complementing existing genetic testing approaches, and introduce a novel training data augmentation method to render deep learning accessible to rare diseases.