A Combination of Multilayer Perceptron, Radial Basis Function Artificial Neural Networks and Machine Learning Image Segmentation for the Dimension Reduction and the Prognosis Assessment of Diffuse Large B-Cell Lymphoma

Joaquim Carreras,Atsushi Ito,Sakura Tomita,Haruka Ikoma,Yusuke Kondo,Shinichiro Hiraiwa,Yara Yukie Kikuti,Masashi Miyaoka,Rifat Hamoudi,Naoya Nakamura

doi:10.3390/ai2010008

Joaquim Carreras, Atsushi Ito + Show 8 more

Open Access

https://doi.org/10.3390/ai2010008

Copy DOI

Abstract

The prognosis of diffuse large B-cell lymphoma (DLBCL) is heterogeneous. Therefore, we aimed to highlight predictive biomarkers. First, artificial intelligence was applied into a discovery series of gene expression of 414 patients (GSE10846). A dimension reduction algorithm aimed to correlate with the overall survival and other clinicopathological variables; and included a combination of Multilayer Perceptron (MLP) and Radial Basis Function (RBF) artificial neural networks, gene-set enrichment analysis (GSEA), Cox regression and other machine learning and predictive analytics modeling [C5.0 algorithm, logistic regression, Bayesian Network, discriminant analysis, random trees, tree-AS, Chi-squared Automatic Interaction Detection CHAID tree, Quest, classification and regression (C&R) tree and neural net)]. From an initial 54,613 gene-probes, a set of 488 genes and a final set of 16 genes were defined. Secondly, two identified markers of the immune checkpoint, PD-L1 (CD274) and IKAROS (IKZF4), were validated in an independent series from Tokai University, and the immunohistochemical expression was quantified, using a machine-learning-based Weka segmentation. High PD-L1 associated with poor overall and progression-free survival, non-GCB phenotype, Epstein–Barr virus infection (EBER+), high RGS1 expression and several clinicopathological variables, such as high IPI and absence of clinical response. Conversely, high expression of IKAROS was associated with a good overall and progression-free survival, GCB phenotype and a positive clinical response to treatment. Finally, the set of 16 genes (PAF1, USP28, SORT1, MAP7D3, FITM2, CENPO, PRCC, ALDH6A1, CSNK2A1, TOR1AIP1, NUP98, UBE2H, UBXN7, SLC44A2, NR2C2AP and LETM1), in combination with PD-L1, IKAROS, BCL2, MYC, CD163 and TNFAIP8, predicted the survival outcome of DLBCL with an overall accuracy of 82.1%. In conclusion, building predictive models of DLBCL is a feasible analytical strategy.

Highlights

Diffuse large B-cell lymphoma (DLBCL) is the most common histologic subtype of non-Hodgkin lymphoma (NHL)
According to the cell-of-origin (COO) molecular classification of DLBCL based on the gene expression [1,2,3,4,5], 44.2% of the cases were of germinal center B-cell subtype (GCB), 40.3% of activated B-cell subtype (ABC)
The target variables included the survival outcome and other relevant clinicopathological variables such as the International Prognostic Index (IPI) and cell-of-origin as germinal centre B-cell (GCB) vs. activated B-cell–like (ABC) that are relevant for the prognosis of the DLBCL patients

Summary

Introduction

Diffuse large B-cell lymphoma (DLBCL) is the most common histologic subtype of non-Hodgkin lymphoma (NHL). DLBCL accounts for approximately 25 percent of adult. It is increasingly appreciated that the diagnostic category of “DLBCL” is quite heterogeneous in terms of morphology, genetics and biologic behavior. AI 2021, 2 curable in approximately half of cases with current therapy, in those who achieve a complete remission with first-line treatment. The molecular pathogenesis of DLBCL is a complex, multistep process that results in the transformation and expansion of a malignant B-cell clone. This neoplastic B-cell is of germinal or post-germinal

Objectives

Methods

Results

Conclusion