Utilizing Machine Learning for Image Quality Assessment for Reflectance Confocal Microscopy

Abstract

In vivo reflectance confocal microscopy (RCM) enables clinicians to examine lesions' morphological and cytological information in epidermal and dermal layers while reducing the need for biopsies. As RCM is being adopted more widely, the workflow is expanding from real-time diagnosis at the bedside to include a capture, store, and forward model with image interpretation and diagnosis occurring offsite, similar to radiology. As the patient may no longer be present at the time of image interpretation, quality assurance is key during image acquisition. Herein, we introduce a quality assurance process by means of automatically quantifying diagnostically uninformative areas within the lesional area by using RCM and coregistered dermoscopy images together. We trained and validated a pixel-level segmentation model on 117 RCM mosaics collected by international collaborators. The model delineates diagnostically uninformative areas with 82% sensitivity and 93% specificity. We further tested the model on a separate set of 372 coregistered RCM-dermoscopic image pairs and illustrate how the results of the RCM-only model can be improved via a multimodal (RCM þ dermoscopy) approach, which can help quantify the uninformative regions within the lesional area. Our data suggest that machine learningebased automatic quantification offers a feasible objective quality control measure for RCM imaging.

A Texture Selection Approach for Cultural Artifact 3D Reconstruction Considering Both Geometry and Radiation Quality

“…Thus, how to determine and evaluate the threshold automatically needs further study. In order to improve the automation and robustness of radiation quality evaluation, the introduction of machine learning training under the participation of expert visual evaluation will further improve the intelligence of texture selection of radiation quality along with an increasing number of digital 3D reconstruction projects of cultural artifacts [49,50]. As Figure 10 shows, all multi-view images were directly used for 3D reconstruction.…”

Deep Learning in Biomedical Optics

“…A remaining limitation of many studies was some level of manual or semi‐automated pre‐processing of pCLE and RCM images/videos to exclude low‐quality and/or non‐diagnostic image data. Building on the aforementioned reports for diagnostic classification, additional work utilized similar techniques for automated image quality assessment using transfer learning [123,124] as well as MED‐Net [125].…”

Clinical noninvasive imaging and spectroscopic tools for dermatological applications: Review of recent progress

“…AI models using deep learning frameworks are able to recognize patterns and features after being trained using huge numbers of images and data, from which the characterization of atypical findings are identified. PAI [151], RCM [152], MPM [153] and OCT [154] combined with deep learning based image analysis methods in dermatological applications have been reported for automatic classification of skin conditions (healthy vs disease) or automatic segmentation of morphological structures such as skin layers or vascular networks. This can aid in the automatic quantification of morphological skin parameters which are used as surrogate biomarkers of skin conditions.…”