piNET: An Automated Proliferation Index Calculator Framework for Ki67 Breast Cancer Images

In this work, a novel proliferation index (PI) calculator for Ki67 images called piNET is proposed. It is successfully tested on four datasets, from three scanners comprised of patches, tissue microarrays (TMAs) and wholeslide images (WSI), representing a diverse multicentre dataset for evaluating Ki67 quantification. Compared to state of the art methods, piNET consistently performs the best over all datasets with an average PI difference of 5.603%, PI accuracy rate of 86% and correlation coefficient R = 0.927. The success of the system can be attributed to a number of innovations. Firstly, this tool is built based on deep learning, which can adapt to wide variability of medical images and it was posed as a detection problem to mimic pathologists workflow which improves accuracy and efficiency. Secondly, the system is trained purely on tumour cells, which reduces false positives from non-tumour cells without needing the usual pre-requisite tumour segmentation step for Ki67 quantification. Thirdly, the concept of learning background regions through weak supervision is introduced, by providing the system with ideal and non-ideal (artifact) patches that further reduces false positives. Lastly, a novel hotspot analysis is proposed to allow automated methods to score patches from WSI that contain significant activity.