Assessing the Impact of Stain Normalization on a Cell Classification Model in Digital Histopathology

Sammanfattning: In the field of digital histopathology, computeraideddiagnosis of digitized tissue samples with computationalalgorithms is a rising research field. The tissue samples in thisstudy are stained using chemicals that enhance the recognizabilityof different tissue structures. This staining can be highly variable,which has an impact on the performance of the computationalalgorithms. The aim of this project is to assess the use of threecolor normalization algorithms as a pre-processing step on the KIdataset from a collaborative research project between KarolinskaInstitutet and KTH Royal Institute of Technology. The colornormalization algorithms aim to reduce the color variability ofthe data. The basis of the study is an implementation of theEfficentNet Convolutional Neural Network classification model,that was adapted for the specific needs of the study. Performancewas assessed by firstly applying the color normalization filters tothe dataset and training multiple models on each of the filtereddatasets. The results from the individually trained models andthe combined results with ensemble learning techniques werethen analyzed. Our conclusions are clear, stain normalizationfilters significantly impacts classification performance metrics.The impact depends on the staining qualities of the filters.Ensemble learning techniques present a more robust performancethan the individual filters with a performance comparable to thebest performing filter.