Computer Aided Antibody Screening for IHC Assay Development

摘要

Antibody development is crucial for immunohistochemistry (IHC) applications. To improve the efficiency of primaryantibody screening processes, we developed a computer aided detection scheme to automatically identify the non-negativetissue slides which indicate reactive antibodies. A dataset with 564 digital IHC whole slide images were used for algorithmtraining and testing, each of which was labeled by pathologist as a negative (i.e., no staining) or non-negative (i.e., purebackground or partial staining) slide. To avoid unnecessary computations, color deconvolution was first applied to lowresolution whole slide images and histogram based image features were extracted from each unmixed single stain image.Then, different classifiers were built using the low resolution image features computed from the training dataset throughten-fold cross validation. The trained model was tested over the testing dataset. Results indicated that linear supportedvector machine (LSVM) method yielded the highest area under ROC curve. To further improve the accuracy, our schemeutilized the LSVM classifier score to identify the slides for which additional analysis was needed. The additional analysiswas performed through dividing the original whole slide image into non-overlapping tiles and extracting high resolutionimage features from each tile. The tile-based features are then used to form a bag-of-words (BoW) representation of thecorresponding whole slide image, based on which a second classifier was built to perform the predictions. The resultsshowed that the proposed scheme can effectively perform negative versus non-negative classification with high accuracyand thus reduce pathologists’ manual reviewing time for antibody screening.