Automated and Manual Quantification of Tumour Cellularity in Digital Slides for Tumour Burden Assessment

Abstract

The residual cancer burden index is an important quantitative measure used for assessing treatment response following neoadjuvant therapy for breast cancer. It has shown to be predictive of overall survival and is composed of two key metrics: qualitative assessment of lymph nodes and the percentage of invasive or in situ tumour cellularity (TC) in the tumour bed (TB). Currently, TC is assessed through eye-balling of routine histopathology slides estimating the proportion of tumour cells within the TB. With the advances in production of digitized slides and increasing availability of slide scanners in pathology laboratories, there is potential to measure TC using automated algorithms with greater precision and accuracy. We describe two methods for automated TC scoring: 1) a traditional approach to image analysis development whereby we mimic the pathologists’ workflow, and 2) a recent development in artificial intelligence in which features are learned automatically in deep neural networks using image data alone. We show strong agreements between automated and manual analysis of digital slides. Agreements between our trained deep neural networks and experts in this study (0.82) approach the inter-rater agreements between pathologists (0.89). We also reveal properties that are captured when we apply deep neural network to whole slide images, and discuss the potential of using such visualisations to improve upon TC assessment in the future.

Breast Tumor Cellularity Assessment using Deep Neural Networks

“…Our second method that leverages feature extraction from the weakly-supervised segmentation mask yields the highest score among the all previously published feature extraction-based methods [24,19].…”

“…Recent works by Akbar et al [24,25] have compared the conventional approach based on segmentation and feature extraction and direct applications of deep CNNs to image patches in both regression and classification settings. Overall, they showed that the DL-based approach outperformed hand-crafted features in both accuracy and intraclass correlation (ICC) with expert pathologist annotations.…”

Breast Tumor Cellularity Assessment Using Deep Neural Networks

“…Recent works by Akbar et al [3,2] have compared the conventional approach based on segmentation and feature extraction and direct applications of deep CNNs to image patches in both regression and classification settings. Overall, they showed that the DL-based approach outperformed hand-crafted features in both accuracy and intra- Figure 2: Encoder-decoder segmentation network architecture with Resnet-34 encoder and feature pyramid network decoder.…”

Estimation of cellularity in tumours treated with Neoadjuvant therapy: A comparison of Machine Learning algorithms

“…Breast cancer NAT therapy has been used as a locally treatment for breastconserving surgery [1], it provides prognostic and survival information [2] and is also used to determine a rate of local recurrence [3]. Efficacy of NAT is determined by means of the pathological complete response (pCR) but an accurate assessment of pCR is needed.…”

“…TC estimation problem was addressed by Peikari [10] who proposed a method based on nuclei segmentation and morphological parameters extraction used to train machine learning algorithms to classify cells as benign or malign. Akbar [1] compares this technique with deep learning and evaluates performance and also Pei [11] implemented a direct method based on transfer learning approach. Also during the 2019 SPIE Breast Path Q Challenge called for development of automated TC algorithms.…”