Automatic cellularity assessment from post‐treated breast surgical specimens

Abstract

Neoadjuvant treatment (NAT) of breast cancer (BCa) is an option for patients with the locally advanced disease. It has been compared with standard adjuvant therapy with the aim of improving prognosis and surgical outcome. Moreover, the response of the tumor to the therapy provides useful information for patient management. The pathological examination of the tissue sections after surgery is the gold-standard to estimate the residual tumor and the assessment of cellularity is an important component of tumor burden assessment. In the current clinical practice, tumor cellularity is manually estimated by pathologists on hematoxylin and eosin (H&E) stained slides, the quality, and reliability of which might be impaired by inter-observer variability which potentially affects prognostic power assessment in NAT trials. This procedure is also qualitative and time-consuming. In this paper, we describe a method of automatically assessing cellularity. A pipeline to automatically segment nuclei figures and estimate residual cancer cellularity from within patches and whole slide images (WSIs) of BCa was developed. We have compared the performance of our proposed pipeline in estimating residual cancer cellularity with that of two expert pathologists. We found an intra-class agreement coefficient (ICC) of 0.89 (95% CI of [0.70, 0.95]) between pathologists, 0.74 (95% CI of [0.70, 0.77]) between pathologist #1 and proposed method, and 0.75 (95% CI of [0.71, 0.79]) between pathologist #2 and proposed method. We have also successfully applied our proposed technique on a WSI to locate areas with high concentration of residual cancer. The main advantage of our approach is that it is fully automatic and can be used to find areas with high cellularity in WSIs. This provides a first step in developing an automatic technique for post-NAT tumor response assessment from pathology slides.

Breast Tumor Cellularity Assessment using Deep Neural Networks

“…In order to make our results comparable with previous work, we also report Cohen's kappa coefficient agreement and the intra-class correlation coefficient (ICC) between expert and automated methods, similar to [19]. In all experiments, we find our results superior to our predecessors; however, the cellularity score itself in [19] is evaluated based on binning it into four categories of 0-25%, 26-50%, 51-75%, and 76-100%. Such 4-class categorization is relatively coarse and, in our opinion, does not represent a suitable evaluation metric for continuous cellularity estimation that is our goal in this work.…”

“…Although there are not many studies focusing directly on automated quantitative cellularity assessment, it has been shown that this task can be solved by first segmenting malignant cells and then computing the tumor's area [19]. Many efforts have been devoted to developing supervised and unsupervised methods for automated cell and nuclear segmentation and detection [20,21].…”

“…In these approaches, segmented nuclear bodies are used to extract features that are typically inspired by visual markers recognized by pathologists. Commonly used features describe morphology, texture, and spatial relationships among cell nuclei in tissue [19,22].…”

“…The conventional approach most relevant to our work is by Peikari et al [19] who proposed an automated cellularity assesement protocol. First, they used smaller patches, or regions of interest (RoI), extracted from whole slide images to segment all present cell nuclei.…”

“…The data used in this study had been acquired from the Sunnybrook Health Sciences Centre with funding from the Canadian Cancer Society and was made available for the BreastPathQ challenge sponsored by the SPIE, NCI/NIH, AAPM, and the Sunnybrook Research Institute [19].…”