Software tools and platforms in Digital Pathology: a review for clinicians and computer scientists

Abstract

At the end of the twentieth century, a new technology was developed that allowed an entire tissue section to be scanned on an objective slide. Originally called virtual microscopy, this technology is now known as Whole Slide Imaging (WSI). WSI presents new challenges for reading, visualization, storage, and analysis. For this reason, several technologies have been developed to facilitate the handling of these images. In this paper, we analyze the most widely used technologies in the field of digital pathology, ranging from specialized libraries for the reading of these images to complete platforms that allow reading, visualization, and analysis. Our aim is to provide the reader, whether a pathologist or a computational scientist, with the knowledge to choose the technologies to use for new studies, development, or research.

Keywords: Computational pathology; Digital Pathology; Image analysis; Pathomics; Whole Slide Imaging.

Fig. 1

Examples of WSI modalities. (a) Brightfield image, (b) Fluorescence image, and (c) Fluorescence multispectral, planes, and RGB representation cube. These images were provided by the Leibniz-Institutfür Photonische Technologien, and correspond to different hard bone and bone marrow tissues of a mouse.

Fig. 2

Pyramid organization used to store and visualize WSIs. This illustration shows a pyramid representation of a whole slide image with 4 levels. The top-level of the pyramid has the lowest resolution, the bottom level has the highest resolution, and the middle levels have intermediate resolutions. Each level is divided into two-dimensional blocks called tiles (unfilled squares). This image also shows the tiles that will be loaded in memory (Gray squares) to display a region of interest (Green squares). The resolution used (pyramid level) will depend on the zoom that is requested.

Fig. 3

Categorizing of image analysis levels according to magnification. The identification and extraction of the features in the tissue are carried out at different levels of magnification (pixel, object, and tissue levels). At the pixel-level, it is possible to analyze changes in intensity, edge discontinuities, frequency in the histogram, or saturation values. At object-level, objects can be categorized by their morphological characteristics or by their topology. And at the tissue-level, the entire tissue structure is analyzed.

Fig. 4

Examples of different types of variation in tissue images. On the left of the image, different sections of the same tissue sample are shown, and one can see variations in the structure and the elements of the same sample. In the middle box, there are shown variations caused by different staining techniques using the same type of tissue (breast). Moreover, a fold in the tissue which makes distortions in shape and color is shown. On the right side, a tissue with healthy areas and areas with pathological alterations is shown.