Computational pathology: A survey review and the way forward

Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.

Standardizing HER2 immunohistochemistry assessment: calibration of color and intensity variation in whole slide imaging caused by staining and scanning

In the evaluation of human epidermal growth factor receptor 2 (HER2) immunohistochemistry (IHC) - one of the standard biomarkers for breast cancer- visual assessment is laborious and subjective. Image analysis using whole slide image (WSI) could produce more consistent results; however, color variability in WSIs due to the choice of stain and scanning processes may impact image analysis. We therefore developed a calibration protocol to diminish the staining and scanning variations of WSI using two calibrator slides. The IHC calibrator slide (IHC-CS) contains peptide-coated microbeads with different concentrations. The color distribution obtained from the WSI of stained IHC-CS reflects the staining process and scanner characteristics. A color chart slide (CCS) is also useful for calibrating the color variation due to the scanner. The results of the automated HER2 assessment were compared to confirm the effectiveness of two calibration slides. The IHC-CS and HER2 breast cancer cases were stained on different days. All stained slides and CCS were digitized by two different WSI scanners. Results revealed 100% concordance between automated evaluation and the pathologist's assessment with both the scanner and staining calibration. The proposed method may enable consistent evaluation of HER2.

A machine learning model for detecting invasive ductal carcinoma with Google Cloud AutoML Vision

OBJECTIVES

This study is aimed to assess the feasibility of AutoML technology for the identification of invasive ductal carcinoma (IDC) in whole slide images (WSI).

METHODS

The study presents an experimental machine learning (ML) model based on Google Cloud AutoML Vision instead of a handcrafted neural network. A public dataset of 278,124 labeled histopathology images is used as the original dataset for the model creation. In order to balance the number of positive and negative IDC samples, this study also augments the original public dataset by rotating a large portion of positive image samples. As a result, a total number of 378,215 labeled images are applied.

RESULTS

A score of 91.6% average accuracy is achieved during the model evaluation as measured by the area under precision-recall curve (AuPRC). A subsequent test on a held-out test dataset (unseen by the model) yields a balanced accuracy of 84.6%. These results outperform the ones reported in the earlier studies. Similar performance is observed from a generalization test with new breast tissue samples we collected from the hospital.

CONCLUSIONS

The results obtained from this study demonstrate the maturity and feasibility of an AutoML approach for IDC identification. The study also shows the advantage of AutoML approach when combined at scale with cloud computing.