Progression of Geographic Atrophy: Epistemic Uncertainties Affecting Mathematical Models and Machine Learning

Arslan, Janan; Benke, Kurt K.

doi:10.1167/tvst.10.13.3

Cited by 9 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A recent systematic review revealed that the primary focus of Artificial Intelligence (AI) in GA applications has been the extraction of lesions, with a minor focus on GA progression [8,9]. In the case of GA lesions, deep learning has been investigated for lesion segmentation, while information in hyperfluorescent regions appears to have been neglected [10].…”

Section: Artificial Intelligencementioning

confidence: 99%

Automation of Cluster Extraction in Fundus Autofluorescence Images of Geographic Atrophy

Arslan

Benke

2023

Applied Biosciences

Self Cite

View full text Add to dashboard Cite

The build-up of lipofuscin—an age-associated biomarker referred to as hyperfluorescence—is considered a precursor in the progression of geographic atrophy (GA). Prior studies have attempted to classify hyperfluorescent regions to explain varying rates of GA progression. In this study, digital image processing and unsupervised learning were used to (1) completely automate the extraction of hyperfluorescent regions from images, and (2) evaluate prospective patterns and groupings of hyperfluorescent areas associated with varying levels of GA progression. Patterns were determined by clustering methods, such as k-Means, and performance was evaluated using metrics such as the Silhouette Coefficient (SC), the Davies–Bouldin Index (DBI), and the Calinski–Harabasz Index (CHI). Automated extraction of hyperfluorescent regions was carried out using pseudocoloring techniques. The approach revealed three distinct types of hyperfluorescence based on color intensity changes: early-stage hyperfluorescence, intermediate-stage hyperfluorescence, and late-stage hyperfluorescence, with the early and late stages having three additional subclassifications that could explain varying levels of GA progression. The performance metrics for early-stage hyperfluorescence were SC = 0.597, DBI = 0.915, and CHI = 186.989. For late-stage hyperfluorescence, SC = 0.593, DBI = 1.013, and CHI = 217.325. No meaningful subclusters were identified for the intermediate-stage hyperfluorescence, possibly because it is a transitional phase of hyperfluorescence progression.

show abstract

Section: Artificial Intelligencementioning

confidence: 99%

Automation of Cluster Extraction in Fundus Autofluorescence Images of Geographic Atrophy

Arslan

Benke

2023

Applied Biosciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…WSI acquisition is littered with epistemic uncertainty (i.e., uncertainty due to incomplete knowledge of a disease or process, or reducible errors, such as subjective, measurement, or human-related errors). 13 This is mostly due to the process being heavily reliant on humans manually carrying out each task of WSI acquisition (i.e., the slicing of the tissue, its addition to a glass slide, etc). To minimize tissue shift, images were crop-centered.…”

Section: Image Pre-processingmentioning

confidence: 99%

Efficient 3D reconstruction of whole slide images in melanoma

Arslan

Ounissi

Luo

et al. 2023

Medical Imaging 2023: Digital and Computational Pathology

View full text Add to dashboard Cite

Cutaneous melanoma is an invasive cancer with a worldwide annual death toll of 57,000 (Arnold et al., JAMA Dermatol 2022). In a metastatic state, surgical interventions are not curative and must be coupled with targeted therapy, or immunotherapy. However, resistance appears almost systematically and late-stage prognosis can remain poor. The complexity to eradicate melanoma stems from its plasticity; these cancer cells continually adapt to the tumor microenvironment, which leads to treatment resistance. Our primary assumption is that therapeutic resistance relies in part on a series of non-genetic transitions including changes in the metabolic states of these cancer cells. The 3D spatial distribution of blood vessels that are sources of nutrition and oxygen that drive this metabolic status is an important variable for understanding zoning aspects of this adaptation process. Using Whole Slide Images (WSI) of melanoma tumors from Patient-Derived Xenograft (PDX) mouse models, we build 3D vascular models to help predict and understand the metabolic states of cancer cells within the tumor. Our 3D reconstruction pipeline was based on PDX tumor samples sectioned over 2mm depth and stained with Hematoxylin and Eosin (H&E). The pipeline involves three primary steps, including 2D vessel segmentation using Deep Learning, intensity-and affine-based image registration, and 3D reconstruction using interpolation and 3D rendering (allowing for better interaction with biologists, pathologists, and clinicians). The originality of our computer-assisted pipeline is its capability to (a) deal with sparse data (i.e., not all tissue sections were readily available), and (b) adapt to a multitude of WSI-related challenges (e.g., epistemic uncertainty, extended processing times due to WSI scale, etc.). We posit both our 3D reconstruction pipeline, quantitative results of the major stages of the process, and a detailed illustration of the challenges faced, presenting resolutions to improve the pipeline's efficiency.

show abstract

“…45 Moving beyond neovascular complications, AI has also been employed in the setting of geographic atrophy, based on the high reliability of AI-based algorithms to detect atrophic margins and to follow the expansion over time. [46][47][48][49][50][51] Recently, AI has been tested alongside a novel treatment for geographic atrophy, namely pegcetacoplan. AI-based models were useful in calculating the topography and progression rate of geographic atrophy, 52 as well as in quantifying photoreceptor thinning and loss over time.…”

Section: Artificial Intelligence Models In Age-related Macular Degene...mentioning

confidence: 99%

Artificial Intelligence for the Diagnosis and Screening of Retinal Diseases

Arrigo¹,

Aragona²,

Bandello³

2023

US Ophthalmic Review

View full text Add to dashboard Cite

Artificial intelligence (AI) is becoming established as a new method for analysing ophthalmological data, and unveiling new clinical and pathogenic insights into retinal diseases. AI-based algorithms are largely employed in the field of the most prevalent retinal diseases, including diabetic retinopathy, age-related macular degeneration and myopia. Several research groups are also testing AI in other retinal diseases, including inherited retinal dystrophies, retinopathy of prematurity, central serous chorioretinopathy and retinal vein occlusion. AI models are mainly used in screening of the fundus and structural optical coherence tomography images. However, more advanced methodologies are under investigation to extract clinically relevant information regarding the biomarkers of disease activity and outcome measures. AI is a powerful tool for increasing the amount of information obtained in clinical and research contexts. However, many issues still need addressing, including the resulting high demand for technology and resources, and the need for very large databases. Moreover, several ethical issues require debate, and specific rules are needed to govern the use of AI algorithms and check the quality of the analysed data. This article reviews the current use of AI in retinal diseases, unmet needs and future perspectives.

show abstract

Progression of Geographic Atrophy: Epistemic Uncertainties Affecting Mathematical Models and Machine Learning

Cited by 9 publications

References 25 publications

Automation of Cluster Extraction in Fundus Autofluorescence Images of Geographic Atrophy

Automation of Cluster Extraction in Fundus Autofluorescence Images of Geographic Atrophy

Efficient 3D reconstruction of whole slide images in melanoma

Artificial Intelligence for the Diagnosis and Screening of Retinal Diseases

Contact Info

Product

Resources

About