Stain normalization gives greater generalizability than stain jittering in neural network training for the classification of coeliac disease in duodenal biopsy whole slide images

Abstract

Around 1% of the population of the UK and North America have a diagnosis of coeliac disease (CD), due to a damaging immune response to the small intestine. Assessing whether a patient has CD relies primarily on the examination of a duodenal biopsy, an unavoidably subjective process with poor inter-observer concordance. Wei et al. [11] developed a neural network-based method for diagnosing CD using a dataset of duodenal biopsy whole slide images (WSIs). As all training and validation data came from one source, there was no guarantee that their results would generalize to WSIs obtained from different scanners and laboratories. In this study, the effects of applying stain normalization and jittering to the training data were compared. We trained a deep neural network on 331 WSIs obtained with a Ventana scanner (WSIs; CD: $n=190$; normal: $n=141$) to classify presence of CD. In order to test the effects of stain processing when validating on WSIs scanned on varying scanners and from varying laboratories, the neural network was validated on 4 datasets: WSIs of slides scanned on a Ventana scanner (WSIs; CD: $n=48$; normal: $n=35$), WSIs of the same slides rescanned on a Hamamatsu scanner (WSIs; CD: $n=48$; normal: $n=35$), WSIs of the same slides rescanned on an Aperio scanner (WSIs; CD: $n=48$; normal: $n=35$), and WSIs of different slides scanned on an Aperio scanner (WSIs; CD: $n=38$; normal: $n=37$). Without stain processing, the F1 scores of the neural network were $0.947$, $0.619$, $0.746$_, and $0.727$ when validating on the Ventana validation WSIs, Hamamatsu and Aperio rescans of the Ventana validation WSIs, and Aperio WSIs from a different source respectively. With stain normalization, the performance of the neural network improved significantly with respective F1 scores $0.982$, $0.943$, $0.903$, and $0.847$. Stain jittering resulted in a better performance than stain normalization when validating on data from the same source F1 score $1.000$, but resulted in poorer performance than stain normalization when validating on WSIs from different scanners (F1 scores $0.939$, $0.814$_, and $0.747$). This study shows the importance of stain processing, in particular stain normalization, when training machine learning models on duodenal biopsy WSIs to ensure generalizability between different scanners and laboratories.

Keywords: Coeliac; Neural network; Stain jittering; Stain normalization; Supervised learning.

Fig. 1

Examples from the 4 datasets. An example patch at $\times 20$ magnification is shown in a blue square for each example. (i) An example from the Ventana validation dataset. Each WSI in the Ventana dataset contains 2–6 pieces of tissue. (ii, iii) The WSI in the Hamamatsu and Aperio 1 datasets, respectively, which are rescans of example (i). While the morphology of the biopsies remain the same, the stain absorption vectors and background colour do not. (iv) An example from the Aperio 2 dataset. The Aperio 2 dataset contains WSIs of different biopsies stained in a different laboratory. The stain absorption vectors and background colour are similar to (iii).

Fig. 2

Tile selection and preprocessing steps: (i) Experiment 1 where the model is trained with no stain processing (NP model). (ii) Experiment 2 where the model trains on stain normalized data (SN model). (iii) Experiment 3 where the model trains on stain jittered data (SJ model). In all experiments, tissue was segmented using Otsu thresholding and only tiles for which at least 10% was tissue were included in training. These tiles were then randomly rotated and reflected as data augmentation.

Fig. 3

The WSI-level ROC curves of each model on each dataset. Left to right: The ROC curves of the models trained with no stain processing (NP model), trained with stain normalization (SN model), and trained with stain jittering (SJ model). Top to bottom: The ROC curves when validating on the Ventana dataset, Hamamatsu dataset, Aperio 1 dataset, and the Aperio 2 dataset.