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.

Figure 1

TB outlined in black in a digital slide scanned at 20X magnification (displayed at lower resolution). Regions of interest are shown in a higher magnification on the right alongside TC scores provided by an expert pathologist.

Figure 2

Overview of two methods for generating automated TC score. Hand-engineered feature approach is shown above and a cascade approach using two deep convolutional neural networks below.

Figure 3

TC scores between 0% and 100% predicted by a hand-engineered approach (top) and deep neural networks (bottom) against scores provided by both expert pathologists (Pathologist A, Pathologist B).

Figure 4

Boxplot of distribution of scores within low (0-30%), medium (30-70%) and high (>70%) ranges of TC.

Figure 5

Subset of results from TC test dataset for healthy tissue, and low/medium/high TC categories (top to bottom). Scores are given for both automated systems (H = hand-engineered features, D = deep convolutional neural networks) and Pathologist A (P).

Figure 6

TC scores produced by a trained deep neural network overlaid on whole slide images. Scores are provided on a patch-by-patch level, where blue denotes healthy (0% TC) and red denotes 100% TC. Some close-up results of cellularity scores are provided to the right of each whole slide image.