Cell abundance aware deep learning for cell detection on highly imbalanced pathological data
This work addresses the challenge of detecting rare but biologically significant cells in pathological data, which is incremental as it adapts existing methods to handle class imbalance.
The authors tackled the problem of biased cell detection in digital pathology due to class imbalance by proposing a deep learning pipeline that weights less abundant cells during training, achieving a 2% increase in F1-score to 0.78 and better detection of rare cell types.
Automated analysis of tissue sections allows a better understanding of disease biology and may reveal biomarkers that could guide prognosis or treatment selection. In digital pathology, less abundant cell types can be of biological significance, but their scarcity can result in biased and sub-optimal cell detection model. To minimize the effect of cell imbalance on cell detection, we proposed a deep learning pipeline that considers the abundance of cell types during model training. Cell weight images were generated, which assign larger weights to less abundant cells and used the weights to regularize Dice overlap loss function. The model was trained and evaluated on myeloma bone marrow trephine samples. Our model obtained a cell detection F1-score of 0.78, a 2% increase compared to baseline models, and it outperformed baseline models at detecting rare cell types. We found that scaling deep learning loss function by the abundance of cells improves cell detection performance. Our results demonstrate the importance of incorporating domain knowledge on deep learning methods for pathological data with class imbalance.