Automated In Vivo High-Resolution Imaging to Detect Human Papillomavirus-Associated Anal Precancer in Persons Living With HIV

Abstract

Introduction: In the United States, the effectiveness of anal cancer screening programs has been limited by a lack of trained professionals proficient in high-resolution anoscopy (HRA) and a high patient lost-to-follow-up rate between diagnosis and treatment. Simplifying anal intraepithelial neoplasia grade 2 or more severe (AIN 2+) detection could radically improve the access and efficiency of anal cancer prevention. Novel optical imaging providing point-of-care diagnoses could substantially improve existing HRA and histology-based diagnosis. This work aims to demonstrate the potential of high-resolution microendoscopy (HRME) coupled with a novel machine learning algorithm for the automated, in vivo diagnosis of anal precancer.

Methods: The HRME, a fiber-optic fluorescence microscope, was used to capture real-time images of anal squamous epithelial nuclei. Nuclear staining is achieved using 0.01% wt/vol proflavine, a topical contrast agent. HRME images were analyzed by a multitask deep learning network (MTN) that computed the probability of AIN 2+ for each HRME image.

Results: The study accrued data from 77 people living with HIV. The MTN achieved an area under the receiver operating curve of 0.84 for detection of AIN 2+. At the AIN 2+ probability cutoff of 0.212, the MTN achieved comparable performance to expert HRA impression with a sensitivity of 0.92 ( P = 0.68) and specificity of 0.60 ( P = 0.48) when using histopathology as the gold standard.

Discussion: When used in combination with HRA, this system could facilitate more selective biopsies and promote same-day AIN2+ treatment options by enabling real-time diagnosis.

Trial registration: ClinicalTrials.gov NCT04563754.

Figure 1.

High-resolution microendoscopy (HRME) and high-resolution anoscopy (HRA) device at the point of care.

Figure 2.

(a) Clinical high-resolution anoscopy (HRA) image of the right lateral squamocolumnar junction in the anal canal with (1) normal-appearing anal mucosa and (2) a distinct posterior anal canal lesion. Outlines indicate lesion boundaries and arrows denote the sites imaged with high-resolution microendoscopy (HRME) and biopsied. (b) HRME image of site 1, which was classified as negative by the multitask deep learning network (MTN) and HRA impression, and was determined to be anal intraepithelial neoplasia grade 1 (AIN 1) by histopathology. (c) HRME image of site 2, which was classified as positive by the MTN and HRA impression, and was determined to be anal intraepithelial neoplasia grade 2 (AIN 2) by histopathology. The contrast of the HRA image was improved through dynamic range adjustment.

Figure 3.

Diagnostic performance of multitask deep learning network (MTN) and high-resolution anoscopy (HRA) impression using histopathology as the gold standard. (a) Per site anal intraepithelial neoplasia grade 2 or more severe (AIN 2+) probability stratified by histopathologic diagnosis. Histopathologic diagnosis of AIN 2+ was considered positive. Error bars indicate the mean and 95% confidence intervals (CIs), while the solid line across all classes denotes a retrospective cutoff to discriminate AIN 2+ lesions. (b) Receiver operating characteristic curve for MTN; operating points for MTN and HRA impression are indicated with symbols. (c) Sensitivity and specificity of MTN and HRA impression at corresponding operating points. Error bars indicate 95% CI.