A Mask R-CNN approach to counting bacterial colony forming units in\n pharmaceutical development

Abstract

We present an application of the well-known Mask R-CNN approach to the\ncounting of different types of bacterial colony forming units that were\ncultured in Petri dishes. Our model was made available to lab technicians in a\nmodern SPA (Single-Page Application). Users can upload images of dishes, after\nwhich the Mask R-CNN model that was trained and tuned specifically for this\ntask detects the number of BVG- and BVG+ colonies and displays these in an\ninteractive interface for the user to verify. Users can then check the model's\npredictions, correct them if deemed necessary, and finally validate them. Our\nadapted Mask R-CNN model achieves a mean average precision (mAP) of 94\\% at an\nintersection-over-union (IoU) threshold of 50\\%. With these encouraging\nresults, we see opportunities to bring the benefits of improved accuracy and\ntime saved to related problems, such as generalising to other bacteria types\nand viral foci counting.\n