Pterygium and Ocular Surface Squamous Neoplasia: Optical Biopsy Using a Novel Autofluorescence Multispectral Imaging Technique

Abstract

In this study, differentiation of pterygium vs. ocular surface squamous neoplasia based on multispectral autofluorescence imaging technique was investigated. Fifty (N = 50) patients with histopathological diagnosis of pterygium (PTG) and/or ocular surface squamous neoplasia (OSSN) were recruited. Fixed unstained biopsy specimens were imaged by multispectral microscopy. Tissue autofluorescence images were obtained with a custom-built fluorescent microscope with 59 spectral channels, each with specific excitation and emission wavelength ranges, suitable for the most abundant tissue fluorophores such as elastin, flavins, porphyrin, and lipofuscin. Images were analyzed using a new classification framework called fused-classification, designed to minimize interpatient variability, as an established support vector machine learning method. Normal, PTG, and OSSN regions were automatically detected and delineated, with accuracy evaluated against expert assessment by a specialist in OSSN pathology. Signals from spectral channels yielding signals from elastin, flavins, porphyrin, and lipofuscin were significantly different between regions classified as normal, PTG, and OSSN (p < 0.01). Differential diagnosis of PTG/OSSN and normal tissue had accuracy, sensitivity, and specificity of 88 ± 6%, 84 ± 10% and 91 ± 6%, respectively. Our automated diagnostic method generated maps of the reasonably well circumscribed normal/PTG and OSSN interface. PTG and OSSN margins identified by our automated analysis were in close agreement with the margins found in the H&E sections. Such a map can be rapidly generated on a real time basis and potentially used for intraoperative assessment.

Automated identification of aneuploid cells within the inner cell mass of an embryo using a numerical extraction of morphological signatures

“…First, to facilitate external cross validation, we divided data into training (75%) and testing (25%) data sets(Habibalahi and Safizadeh, 2014). We then applied image augmentation (see section 2.3.1) and a deep convolutional learning approach (LeCun, et al, 2015) where several (N=3) architecturally different deep learning nets(Habibalahi, et al, 2021, Habibalahi, et al, 2022) each of which with specific resolutions were employed to generate precise and data-driven image information (details of the nets are given in section 2.3.2). The DMS was discovered through iterative use of swarm intelligence (Kennedy, 2006) which utilizes cooperative behavior of a number of self-organizing, decentralized, naïve agents to efficiently achieve optimum results (Blum and Li, 2008, Garnier, et al, 2007).…”

“…The DMS was discovered through iterative use of swarm intelligence (Kennedy, 2006) which utilizes cooperative behavior of a number of self-organizing, decentralized, naïve agents to efficiently achieve optimum results (Blum and Li, 2008, Garnier, et al, 2007). In this part (see section 2.3.3) we employed a Fisher distance gauge function to assess feature subsets quality offered by swarm intelligence in an iterative manner (Beni, 2009, Habibalahi, et al, 2022, Hu, et al, 2004, Panigrahi, et al, 2011) that eventually converge to select an optimised set of features. The final DMS employed to train a classifier which is support vector machine (SVM) as our preferred classifier (Furey, et al, 2000) in this study.…”

“…SVM is a powerful supervised technique capable of dealing with biological data with sparse condition and. SVM has limited overfitting risk since it uses linear predictor function to distinguish the label of data(Habibalahi, et al, 2022). The SVM was cross validated internally using standard k-fold cross validation (k=10) and the classification performance was assessed by receiver operating characteristic (ROC) curve and associated area under the curve (AUC)(Habibalahi, 2019, Habibalahi, et al, 2019).…”

Emerging clinical applications in oncology for non‐invasive multi‐ and hyperspectral imaging of cell and tissue autofluorescence

“…This was reinforced in a related work where the application of 10 or 5 select channels from their set could detect OSSN with 1% and 14% misclassification errors, decreasing imaging times by 75% and 80%, respectively [20]. In an additional work published since this review's primary search, the same group used a similar technology with 59 channels to automatically discriminate pterygium and/or OSSN from 50 patients from normal tissue with an accuracy of 88%, and also defined boundaries in close agreement with hematoxylin and eosin stained sections [66].…”

Unique Deep Radiomic Signature Shows NMN Treatment Reverses Morphology of Oocytes from Aged Mice

“…Recently, artificial intelligence (AI) has been widely applied to objective biomedical image assessment for disease diagnosis and monitoring to enable the precise customization of treatment plans [ 5 , 6 , 7 , 8 , 9 ]. Deep learning strategies (machine learning algorithms that use multiple layers to progressively extract higher-level features from data) have been used to interpret electroencephalogram (EEG), electrocardiogram (ECG), magnetoencephalography (MEG), and magnetic resonance imaging (MRI) data, to improve reliability and precision [ 10 ].…”