Can we read the pathologist mind and understand which are the visual cues tracked during cell screening? In a synergistic collaboration among cytopathologists, doctors, engineers and psychologists, we are formulating models that truly mimic human behavior and deliver recognition algorithms with potential to revolutionize cell analysis.

Center for Recognition and Inspection of Cells (CRIC) Searchable Image Database is a public cell image database. We have collected hundreds cell images and hand labeled classify thousands of cells, visit our Classification page to see the images and their classifications [here].

pyCBIR is a new python tool for content-based image retrieval (CBIR) capable of searching for relevant items in large databases given unseen samples. pyCBIR allows general purpose investigation across image domains and experiments. Also, pyCBIR contains different distance metrics and several feature extraction techniques, including two convolutional neural network (CNN) for automated featurization using GPU and TensorFlow. [MORE]

SPVD stands for super pixel Voronoi diagrams, and it is the algorithm that won the IEEE International Symposium on Biomedical Imaging Cervical Cell Detection challenge in 2014. We went further on extending the algorithm to neuron detection and counting, and the results are impressive. Check the application of SPVD for both cervical cell and neuron detection.