- Keywords: Deep learning, Digital pathology, Multiplex immunohistochemistry
- TL;DR: A novel deep learning model combining stop-gradient and class-weighted loss function to parallelly detect and classify cells in mIHC images and achieve better performance than models trained separately on individual tasks.
- Abstract: Deep-learning-based automatic analysis of the multiplex immunohistochemistry (mIHC) enables distinct cell populations to be localized on a large scale, providing insights into disease biology and therapeutic targets. However, standard deep-learning pipelines performed cell detection and classification as two-stage tasks, which is computationally inefficient and faces challenges to incorporate neighbouring tissue context for determining the cell identity. To overcome these limitations and to obtain a more accurate mapping of cell phenotypes, we presented a symmetric dense inception neural network for detecting and classifying cells in mIHC slides simultaneously. The model was applied with a novel stop-gradient strategy and a loss function accounted for class imbalance. When evaluated on an ovarian cancer dataset containing 6 cell types, the model achieved an F1 score of 0.835 in cell detection, and a weighted F1-score of 0.867 in cell classification, which outperformed separate models trained on individual tasks by 1.9% and 3.8% respectively. Taken together, the proposed method boosts the learning efficiency and prediction accuracy of cell detection and classification by jointly learning from both tasks.