Eye2Gene: prediction of causal inherited retinal disease gene from multimodal imaging using deep-learning

Pontikos, Nikolas; Woof, William; Veturi, Advaith; Ibarra-Arellano, Miguel; Hustinx, Alexander; Moghul, Ismail; Liu, Yichen; Hess, Kristina; Georgiou, Michalis; Pfau, Maximilian; Shah, Mital; Yu, Jing; Al‐Khuzaei, Saoud; Wagner, Siegfried; Varela, Malena Daich; Guimarães, Thales Antonio Cabral de; Sen, Sagnik; Kabiri, Nathaniel; Nguyen, Quang Uy; Furman, Jennifer; Liefers, Bart; Lee, Aaron; Silva, Samantha De; Texeira, Caio Henrique Marques; Motta, Fabiana Louise; Fujinami‐Yokokawa, Yu; Arno, Gavin; Fujinami, Kaoru; Sallum, Juliana Maria Ferraz; Madhusudhan, Savita; Downes, Susan M.; Holz, Frank G.; Balaskas, Konstantinos; Webster, Andrew R.; Mahroo, Omar Abdul Rahman; Krawitz, Peter; Michaelides, Michel

doi:10.21203/rs.3.rs-2110140/v1

Cited by 9 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, deep learning AI models to analyse FAF images from IRD patients have been limited. There have been studies developing classification models of FAF images based on IRD phenotypes [44][45][46][47] . But as to segmentation approaches, areas of hypo-AF have been measured either manually or semi-automatically using RegionFinder on HEYEX2 software to study the progression rate of the area of atrophy in STGD1 disease [48][49][50][51] .…”

Section: D)mentioning

confidence: 99%

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom

Woof,

de Guimarães,

Al-Khuzaei

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Purpose: To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients. Design: Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients. Participants: Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019. Methods: Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire imaging dataset. Main Outcome Measures: Quantitative FAF imaging features including area in mm2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively. Results: A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM, ABCC6, ABCA4, RDH12, and RPE65, with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm2. The five genes with the largest hyper-AF areas were BEST1, CDH23, RDH12, MYO7A, and NR2E3, with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm2 respectively. The five genes with largest ring areas were CDH23, NR2E3, CRX, EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm2. Vessel density was found to be highest in EFEMP1, BEST1, TIMP3, RS1, and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes (RPGR, USH2A, RHO, EYS) found EYS to be the fastest progressor at -0.18 mm2/year. Conclusions: We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.

show abstract

Section: D)mentioning

confidence: 99%

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom

Woof,

de Guimarães,

Al-Khuzaei

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…While there have been some studies employing DL-based techniques on medical images of patients with rare genetic diseases (e.g. Gurovich et al, 2019; Hsieh et al, 2022; Pontikos et al, 2022), this field is still understudied perhaps mainly due to the inherently small amount of available data from such diseases. The current study is limited to only seven different genetic bone diseases.…”

Section: Discussionmentioning

confidence: 99%

“…DL model ensembles often show higher performances compared to single models (see e.g. [50, 43]), however, usually multiple experimentations are required to reach a suitable set of models. We took the following steps for investigating the optimum model configurations:…”

Section: Appendicesmentioning

confidence: 99%

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

Rassmann

Keller

Skaf

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Skeletal dysplasias collectively affect a large number of patients worldwide. The majority of these disorders cause growth anomalies. Hence, assessing skeletal maturity via determining the bone age (BA) is one of the most valuable tools for their diagnoses. Moreover, consecutive BA assessments are crucial for monitoring the pediatric growth of patients with such disorders, especially for timing hormone treatments or orthopedic interventions. However, manual BA assessment is time-consuming and suffers from high intra-and inter-rater variability. This is further exacerbated by genetic disorders causing severe skeletal malformations. While numerous approaches to automatize BA assessment were proposed, few were validated for BA assessment on children with abnormal development. In this work, we present Deeplasia, an open-source prior-free deep-learning ensemble approach. After training on the public RSNA BA dataset, we achieve state-of-the-art performance with a mean absolute difference (MAD) of 3.87 months based on the average of six different reference ratings. Next, we demonstrate that Deeplasia generalizes to an unseen dataset of 568 X-ray images from 189 patients with molecularly confirmed diagnoses of seven different genetic bone disorders (including Achondroplasia and Hypochondroplasia) achieving a MAD of 5.84 months w.r.t. to the average of two references. Further, using longitudinal data from a subset of the cohort (149 images), we estimate the test-retest precision of our model ensemble to be at least at the human expert level (2.74 months). We conclude that Deeplasia suits assessing and monitoring the BA in patients with skeletal dysplasias.

show abstract

“…6 In ophthalmology, leveraging synthetic images not only improves the training of deep learning (DL) models but also facilitates the development of innovative solutions for rare diseases such as inherited retinal disease (IRD). 7 Concurrently, the advent of visionlanguage models (VLMs) has propelled significant advancements in natural language processing. 8 These models, trained on extensive datasets of images paired with textual captions, show promising capabilities in generating visual content from text descriptions.…”

Section: Introductionmentioning

confidence: 99%

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

Sonmez,

Sevgi,

Antaki

et al. 2024

Br J Ophthalmol

View full text Add to dashboard Cite

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.

show abstract

Eye2Gene: prediction of causal inherited retinal disease gene from multimodal imaging using deep-learning

Cited by 9 publications

References 31 publications

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom

Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3500 Inherited Retinal Disease Patients from the United Kingdom

Deeplasia: prior-free deep learning for pediatric bone age assessment robust to skeletal dysplasias

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

Contact Info

Product

Resources

About