Core Needle Biopsy Guidance Based on Tissue Morphology Assessment with AI-OCT Imaging.

This paper presents a combined optical imaging/artificial intelligence (OI/AI) technique for the real-time analysis of tissue morphology at the tip of the biopsy needle, prior to collecting a biopsy specimen. This is an important clinical problem as up to 40% of collected biopsy cores provide low diagnostic value due to high adipose or necrotic content. Micron-scale-resolution optical coherence tomography (OCT) images can be collected with a minimally invasive needle probe and automatically analyzed using a computer neural network (CNN)-based AI software. The results can be conveyed to the clinician in real time and used to select the biopsy location more adequately. This technology was evaluated on a rabbit model of cancer. OCT images were collected with a hand-held custom-made OCT probe. Annotated OCT images were used as ground truth for AI algorithm training. The overall performance of the AI model was very close to that of the humans performing the same classification tasks. Specifically, tissue segmentation was excellent (~99% accuracy) and provided segmentation that closely mimicked the ground truth provided by the human annotations, while over 84% correlation accuracy was obtained for tumor and non-tumor classification.

Fiber-based hand-held RCM-OCT probe for noninvasive assessment of skin lesions and therapy guidance.

Noninvasive assessment of skin lesions, especially of basal cell carcinoma (BCC), has benefited more recently from the use of optical imaging techniques such as optical coherence tomography (OCT) and reflectance confocal microscopy (RCM). While RCM provides submicron scale resolution and thus enables identification of skin morphological changes of the skin, with the downside of limited penetration depth, OCT imaging of the same lesion brings the benefit of better resolving its depth of invasion. OCT and RCM can be used either individually or combined within the same instrument for the noninvasive diagnosis of nonmelanoma skin cancers (NMSCs). Their combined use has shown to provide certain benefits such as better characterization of the lesion's margins, both in depth and laterally, as well as improved sensitivity and specificity, as previously demonstrated by our team. In this paper we report a new "fiber-based" implementation of the second-generation RCM-OCT hand-held probe. The fiber-based implementation of both imaging modalities enabled the construction of a smaller footprint/lower weight hand-held probe. Its preliminary evaluation on the skin of healthy volunteers is reported here, demonstrating improved capabilities for resolving sub-cellular structures and image skin morphology with micron-scale resolution to a higher depth than in the previous implementation, while also enabling the construction of angiography maps showing vascular remodeling.