Emerging Themes in Image Informatics and Molecular Analysis for Digital Pathology

Abstract

Pathology is essential for research in disease and development, as well as for clinical decision making. For more than 100 years, pathology practice has involved analyzing images of stained, thin tissue sections by a trained human using an optical microscope. Technological advances are now driving major changes in this paradigm toward digital pathology (DP). The digital transformation of pathology goes beyond recording, archiving, and retrieving images, providing new computational tools to inform better decision making for precision medicine. First, we discuss some emerging innovations in both computational image analytics and imaging instrumentation in DP. Second, we discuss molecular contrast in pathology. Molecular DP has traditionally been an extension of pathology with molecularly specific dyes. Label-free, spectroscopic images are rapidly emerging as another important information source, and we describe the benefits and potential of this evolution. Third, we describe multimodal DP, which is enabled by computational algorithms and combines the best characteristics of structural and molecular pathology. Finally, we provide examples of application areas in telepathology, education, and precision medicine. We conclude by discussing challenges and emerging opportunities in this area.

Automated tubule nuclei quantification and correlation with oncotype DX risk categories in ER+ breast cancer whole slide images

“…Some applications of the DNNs in histological image analysis include the mitosis identification task 13 and the localization of regions of interest in histological images 14 . With the recent emergence of whole slide tissue scanning and digital pathology [15][16][17] there has been substantial interest in developing automated computerized histologic predictors of tumor grade and outcome for several diseases including oropharyngeal squamous cell carcinoma 18 , prostate cancer 19,20 and glioblastoma 21 . The correlation of computerized extracted features with breast cancer survival has also been explored.…”

Digital pathology in nephrology clinical trials, research, and pathology practice

“…Concurrently to the emerging precision medicine approach, seeking to comprehensively integrate large multiscale datasets at the patient level, powerful new computational disease approaches are being developed for analyzing large digital pathology datasets using mathematical models and algorithms [53–55]. However, the intelligent combination of divergent large-scale datasets for patient profiles with predictive power must be able to withstand disparate dimensionalities of the data [53]. One successful approach has employed machine learning and data fusion methods to computationally combine computer-derived morphometric features and protein expression data from prostate specimens that more accurately predict risk of biochemical recurrence than with either feature alone.…”

Identifying the morphologic basis for radiomic features in distinguishing different Gleason grades of prostate cancer on MRI: Preliminary findings

“…[36] Indeed, there have been a number of recent approaches involving QH features for characterizing aggressiveness of PCa on digitized tissue slides. [37–41] For example, Lee et.…”