Comparing Mask R-CNN and U-Net architectures for robust automatic segmentation of immune cells in immunofluorescence images of Lupus Nephritis biopsies

Systemic lupus erythematosus (SLE) is a complex, systemic autoimmune disease with many clinical presentations including lupus nephritis (LuN), or chronic inflammation of the kidneys. Current therapies for SLE are only modestly effective, highlighting the need to better understand networks of immune cells in SLE and LuN. In this work, we assess the performance of two convolutional neural network (CNN) architectures –Mask R-CNN and U-Net— in the task of instance segmentation of 5 immune-cell classes in 31 LuN biopsies. Each biopsy was stained for myeloid dendritic cells (mDCs), plasmacytoid dendritic cells (pDCs), B cells, and two populations of T cells, then imaged on a Leica SP8 fluorescence confocal microscope. Two instances of Mask R-CNN were trained on manually segmented images—one on lymphocytes (T cells and B cells), and one on DCs (pDCs and mDCs)—resulting in an average network sensitivities of 0.88 ± 0.04 and 0.82 ± 0.03, respectively. Five U-Nets, one for each of the five individual cell classes, were trained resulting in an average sensitivity of 0.85 ± 0.09 across all cell classes. Mask R-CNN yielded fewer false positives for all cell classes, with an average precision of 0.76 ± 0.03 compared to the U-Net object-level average precision of 0.43 ± 0.12. Overall, Mask R-CNN was more robust than the U-Net for segmenting cells in immunofluorescence images of kidney biopsies from lupus nephritis patients.