Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer

Abstract

Histological Grade is a well-known prognostic factor that is routinely assessed in breast tumours. However, manual assessment of Nottingham Histological Grade (NHG) has high inter-assessor and inter-lab variability, causing uncertainty in grade assignments. To address this challenge, we developed and validated a three-level NHG-like deep learning-based histological grade model. The primary performance evaluation focuses on prognostic performance. This observational study is based on two patient cohorts (SöS-BC-4, N=2421 (training and internal test); SCAN-B-Lund, N=1262 (test)) that include routine histological whole slide images together with patient outcomes. A Deep Convolutional Neural Network (CNN) model with an attention mechanism was optimised for the classification of the three-level histological grading (NHG) from hematoxylin and eosin-stained WSIs. The prognostic performance was evaluated by time-to-event analysis of Recurrence-free survival (RFS) and compared to clinical NHG grade assignments in the internal test set as well as in the fully independent external test cohort. We observed effect sizes (Hazard Ratio) for grade 3 vs 1, for the conventional NHG method (HR=2.60 (1.18-5.70 95%CI, p-value = 0.017)) and the deep learning model (HR = 2.27, 95%CI: 1.07-4.82, p-value = 0.033) on the internal test set after adjusting for established clinicopathological risk factors. In the external test set, the unadjusted HR for NHG 1 vs 2 was estimated to be 2.59 (p-value = 0.004) and NHG 1 vs 3 was estimated to be 3.58 (p-value < 0.001). For predGrade, the unadjusted HR for grade 1 vs 2 HR=2.52 (p-value = 0.030), and 4.07 (p-value = 0.001) for grade 1 vs 3. In multivariable analysis, HR estimates for neither NHG nor predGrade were found to be significant (p-value > 0.05). We tested for differences in HR estimates between NHG and predGrade in the independent test set, and found no significant difference between the two classification models (p-value > 0.05), confirming similar prognostic performance between conventional NHG and predGrade. Routine histopathology assessment of NHG has a high degree of inter-assessor variability, motivating the development of model-based decision support to improve reproducibility in histological grading. We found that the proposed model provides similar prognostic performance as NHG. The results indicate that deep CNN-based models can be applied for breast cancer histological grading.