Journal of Pathology Informatics 2017

3 papers
In 2017, the Journal of Pathology Informatics featured research centered on digital image analysis, quality control, and the integration of machine learning into histopathology. A primary focus involved the technical factors influencing data reliability, such as the impact of altering image parameters on Human Epidermal Growth Factor Receptor 2 (HER2) analysis and the development of texture-based quality assessment for nucleus segmentation. These studies addressed the necessity of standardized imaging protocols to ensure the accuracy of automated diagnostic tools. The year’s contributions also highlighted the application of deep learning architectures in oncology. Specifically, research explored the use of convolutional neural networks (CNNs) for the classification of multispectral colorectal cancer tissues. Prolific authors contributing to these developments included Joel Saltz, Tahsin Kurç, and Ahmad Chaddad. Together, these works reflect a trend toward utilizing advanced computational models to improve the precision of tissue-based diagnostics and the overall robustness of digital pathology workflows.

Top Authors

AuthorPapers
tianhao zhao1

Papers

Title
A Methodology for Texture Feature-based Quality Assessment in Nucleus Segmentation of Histopathology Image
Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network
Impact of Altering Various Image Parameters on Human Epidermal Growth Factor Receptor 2 Image Analysis Data Quality