Integrated spatial and multimodal single-cell transcriptomics reveal patient-dependent cell heterogeneity in splenic marginal zone lymphoma.

Biological hallmarks of splenic marginal zone lymphoma (SMZL) remain poorly described. Herein, we performed in-depth SMZL characterization through multimodal single-cell analyses of paired blood/spleen samples. The 3'-single-cell RNA-sequencing, Cellular Indexing of Transcriptomes and Epitopes by sequencing, and 5'-V(D)J single-cell RNA-sequencing datasets were integrated to characterize SMZL transcriptome profiles, including B-cell receptor and T-cell receptor repertoires. Hyperexpanded B-cell clones in the spleen were at a memory-like stage, whereas recirculating tumor B-cells in blood encompassed multiple differentiation stages, indicating an unexpected desynchronization of the B-cell maturation program in SMZL cells. Spatial transcriptomics showed the enrichment of T-effector and T-follicular helper (TFH) signatures in the nodular subtype of SMZL. This latter also exhibited gene-based cell-cell interactions suggestive of dynamic crosstalk between TFH and cancer cells in transcriptomics, further substantiated by using imaging mass cytometry. Our findings provide a comprehensive high-resolution description of SMZL biological hallmarks and characterize, for the first time in situ, inter- and intra-patient heterogeneity at both transcriptomic and protein levels. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

Bias reduction using combined stain normalization and augmentation for AI-based classification of histological images.

Artificial intelligence (AI)-assisted diagnosis is an ongoing revolution in pathology. However, a frequent drawback of AI models is their propension to make decisions based rather on bias in training dataset than on concrete biological features, thus weakening pathologists' trust in these tools. Technically, it is well known that microscopic images are altered by tissue processing and staining procedures, being one of the main sources of bias in machine learning for digital pathology. So as to deal with it, many teams have written about color normalization and augmentation methods. However, only a few of them have monitored their effects on bias reduction and model generalizability. In our study, two methods for stain augmentation (AugmentHE) and fast normalization (HEnorm) have been created and their effect on bias reduction has been monitored. Actually, they have also been compared to previously described strategies. To that end, a multicenter dataset created for breast cancer histological grading has been used. Thanks to it, classification models have been trained in a single center before assessing its performance in other centers images. This setting led to extensively monitor bias reduction while providing accurate insight of both augmentation and normalization methods. AugmentHE provided an 81% increase in color dispersion compared to geometric augmentations only. In addition, every classification model that involved AugmentHE presented a significant increase in the area under receiving operator characteristic curve (AUC) over the widely used RGB shift. More precisely, AugmentHE-based models showed at least 0.14 AUC increase over RGB shift-based models. Regarding normalization, HEnorm appeared to be up to 78x faster than conventional methods. It also provided satisfying results in terms of bias reduction. Altogether, our pipeline composed of AugmentHE and HEnorm improved AUC on biased data by up to 21.7% compared to usual augmentations. Conventional normalization methods coupled with AugmentHE yielded similar results while being much slower. In conclusion, we have validated an open-source tool that can be used in any deep learning-based digital pathology project on H&E whole slide images (WSI) that efficiently reduces stain-induced bias and later on might help increase pathologists' confidence when using AI-based products.