Iterative Deep Learning Based Unbiased Stereology With Human-in-the-Loop
This work addresses the challenge of accurate cell counting in biomedical imaging for researchers, though it is incremental as it builds on existing adaptive segmentation algorithms.
The paper tackles the problem of error-prone and time-consuming manual annotation for cell segmentation and counting in extended depth of field images by introducing an iterative deep learning method with human verification, reducing the error rate from about 3% to less than 1% after five iterations.
Lack of enough labeled data is a major problem in building machine learning based models when the manual annotation (labeling) is error-prone, expensive, tedious, and time-consuming. In this paper, we introduce an iterative deep learning based method to improve segmentation and counting of cells based on unbiased stereology applied to regions of interest of extended depth of field (EDF) images. This method uses an existing machine learning algorithm called the adaptive segmentation algorithm (ASA) to generate masks (verified by a user) for EDF images to train deep learning models. Then an iterative deep learning approach is used to feed newly predicted and accepted deep learning masks/images (verified by a user) to the training set of the deep learning model. The error rate in unbiased stereology count of cells on an unseen test set reduced from about 3 % to less than 1 % after 5 iterations of the iterative deep learning based unbiased stereology process.