Diffusion histology imaging differentiates distinct pediatric brain tumor histology

Peng Sun,Chunyu Song,Zezhong Ye,Sonika Dahiya,Komal Srinivasa,Joshua B. Rubin,Ashely Meyer,Joshua Lin,Jeffrey D. Viox,Sheng-Kwei Song,Anthony T. Wu

doi:10.1038/s41598-021-84252-3

Abstract

High-grade pediatric brain tumors exhibit the highest cancer mortality rates in children. While conventional MRI has been widely adopted for examining pediatric high-grade brain tumors clinically, accurate neuroimaging detection and differentiation of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation, remains an unmet need in their clinical management. We employed a novel Diffusion Histology Imaging (DHI) approach employing diffusion basis spectrum imaging (DBSI) derived metrics as the input classifiers for deep neural network analysis. DHI aims to detect, differentiate, and quantify heterogeneous areas in pediatric high-grade brain tumors, which include normal white matter (WM), densely cellular tumor, less densely cellular tumor, infiltrating edge, necrosis, and hemorrhage. Distinct diffusion metric combination would thus indicate the unique distributions of each distinct tumor histology features. DHI, by incorporating DBSI metrics and the deep neural network algorithm, classified pediatric tumor histology with an overall accuracy of 85.8%. Receiver operating analysis (ROC) analysis suggested DHI’s great capability in distinguishing individual tumor histology with AUC values (95% CI) of 0.984 (0.982–0.986), 0.960 (0.956–0.963), 0.991 (0.990–0.993), 0.950 (0.944–0.956), 0.977 (0.973–0.981) and 0.976 (0.972–0.979) for normal WM, densely cellular tumor, less densely cellular tumor, infiltrating edge, necrosis and hemorrhage, respectively. Our results suggest that DBSI-DNN, or DHI, accurately characterized and classified multiple tumor histologic features in pediatric high-grade brain tumors. If these results could be further validated in patients, the novel DHI might emerge as a favorable alternative to the current neuroimaging techniques to better guide biopsy and resection as well as monitor therapeutic response in patients with high-grade brain tumors.

Highlights

Background ofneurofibromatosis 1 (NF1) with three tumors at different time pointsDiffuse astrocytoma, WHO grade II (2006)18 non-synonymous variants were identified by generation sequencing TP53, p.R213Dfs*34, TP53 and p.T211IPilocytic astrocytoma, WHO grade I MAP2K2,p.I369VEmbryonal tumor with multilayered rosettes, medulloepithelioma phenotype, WHO grade IV, NECFISH could not demonstrate C19MC alteration but multifocal LIN28A protein expression was seen by immunohistochemistryLoss of 10q (PTEN) and monosomy 10; no EGFR amplification or polysomy of chromosome 7H3K 27M negative image (DWI) and hypointense in apparent diffusion coefficient (ADC) map comparing with the densely cellular tumor regions
We have previously developed diffusion basis spectrum imaging (DBSI)[10] demonstrating its ability to quantitatively characterize pathologies in multiple central nervous system diseases, including, multiple s clerosis[11,12,13,14], spinal cord injury[15], and e pilepsy[16]
Histologic assessment of tumor cellularity, infiltration and necrosis is critical in the diagnosis and grading, as well as subsequent clinical decision-making for patient management and follow-up[27]

Summary

Introduction

Background ofNF1 with three tumors at different time pointsDiffuse astrocytoma, WHO grade II (2006)18 non-synonymous variants were identified by generation sequencing TP53, p.R213Dfs*34, TP53 and p.T211IPilocytic astrocytoma, WHO grade I (not sampled until post-mortem) MAP2K2,p.I369VEmbryonal tumor with multilayered rosettes, medulloepithelioma phenotype, WHO grade IV, NECFISH could not demonstrate C19MC alteration but multifocal LIN28A protein expression was seen by immunohistochemistryLoss of 10q (PTEN) and monosomy 10 (by FISH); no EGFR amplification or polysomy of chromosome 7H3K 27M negative (by immunohistochemistry) image (DWI) and hypointense in ADC map comparing with the densely cellular tumor regions. And less densely cellular tumors exhibited the least highly restricted fraction values among all histologic features (Fig. 4d). Densely cellular tumor (0.35 ± 0.10) showed 35%, 21%, 21% and 59% higher (all p < 0.05) values than normal WM (0.26 ± 0.11), less densely cellular tumor (0.29 ± 0.09), infiltrative edges (0.29 ± 0.12) and necrosis (0.22 ± 0.15), respectively. This result correlated well with the expected cellularity decrease from densely cellular, less densely cellular tumor regions to necrotic tissue (Fig. 4e). Normal WM (0.38 ± 0.12) and infiltrative edge (0.36 ± 0.17) had similar values; this anisotropic component was much higher than other histologic components

Methods

Results

Conclusion