Counting dead cells is a key step in evaluating the performance of chemotherapy treatment and drug screening. Deep convolutional neural networks (CNNs) can learn complex visual features, but require massive ground truth annotations which is expensive in biomedical experiments. Counting cells, especially dead cells, with very few ground truth annotations remains unexplored. In this paper, we automate dead cell counting using a weakly supervised strategy. We took advantage of the fact that cell death is low before chemotherapy treatment and increases after treatment. Motivated by the contrast, we first design image level supervised only classification neural networks to detect dead cells. Based on the class response map in classification networks, we calculate a Dead Confidence Map (DCM) to specify confidence of each dead cell. Associated with peak clustering, local maximums in the DCM are used to count the number of dead cells. In addition, a biological experiment based weakly supervised data preparation strategy is proposed to minimize human intervention. We show classification performance compared to general purpose and cell classification networks, and report results for the image-level supervised counting task.

Current technologies for assessing the microbial load in food and water require cellular outgrowth to increase the cell count to a detectable level. This step therefore makes real-time assessment of microbial loads impossible. To circumvent this problem, we have developed a high-sensitivity, multiwavelength fluorescence detector and signal- collection and processing software. This detection system enables one to distinguish between abiotic matter, sporulated bacteria, vegetative bacteria, dead bacteria, and other biomaterials containing aromatic amino acids. Our detection limit is in the 10-100 cell/cm2range (or per cm3if bulk aqueous samples are used), and there is no sample contact. To supplement this detection system, we have developed a variety of ligands, including hemin derivatives, peptides, glycoconjugates, and siderophores, for cell capture to circumvent problems associated with antibodies. These materials are tethered to disposable surfaces (glass, plastics) in arrays for use in capturing biomaterials (e.g., live bacterial cells, dead cells, spores, and toxins); identification is based on which sector of an array it binds to. The detection system can serve as a reader for these coated materials, and variants have been tested for use in scanning food surfaces and food wash water.