Automated analysis of scattering-based light sheet microscopy images of anal squamous intraepithelial lesions.

We developed an algorithm for automatically analyzing scattering-based light sheet microscopy (sLSM) images of anal squamous intraepithelial lesions. We developed a method for automatically segmenting sLSM images for nuclei and calculating seven features: nuclear intensity, intensity slope as a function of depth, nuclear-to-nuclear distance, nuclear-to-cytoplasm ratio, cell density, nuclear area, and proportion of pixels corresponding to nuclei. 187 images from 80 anal biopsies were used for feature analysis and classifier development. The automated nuclear segmentation method provided reliable performance with the precision of 0.97 and recall of 0.91 when compared with the manual segmentation. Among the seven features, six showed statistically significant differences between high-grade squamous intraepithelial lesion (HSIL) and non-HSIL (non-dysplastic or low-grade squamous intraepithelial lesion, LSIL). A classifier using linear support vector machine (SVM) achieved promising performance in diagnosing HSIL versus non-HSIL: sensitivity of 90%, specificity of 70%, and area under the curve (AUC) of 0.89 for per-image diagnosis, and sensitivity of 90%, specificity of 80%, and AUC of 0.92 for per-biopsy diagnosis.

Handheld cross-polarised microscope for imaging individual pigmented cells in human skin in vivo.

We present the development of a simple, handheld cross-polarised microscope (CPM) and demonstration of imaging individual pigmented cells in human skin in vivo. In the CPM device, the cross-polarised detection approach is used to reduce the specular reflection from the skin surface and preferentially detect multiply-scattered light. The multiply-scattered light works as back illumination from within the tissue towards the skin surface, and superficial pigment such as intraepidermal melanin absorbs some spectral bands of the multiply-scattered light and cast coloured shadows. Since the light that interacted with the superficial pigment only needs to travel a short distance before it exits the skin surface, microscopic details of the pigment can be preserved. The CPM device uses a water-immersion objective lens with a high numerical aperture to image the microscopic details with minimal spherical aberrations and a small depth of focus. Preliminary results from a pilot study of imaging skin lesions in vivo showed that the CPM device could reveal three-dimensional distribution of pigmented cells and intracellular distribution of pigment. Co-registered CPM and reflectance confocal microscopy images showed good correspondence between dark, brown cells in CPM images and bright, melanin-containing cells in reflectance confocal microscopy images.