Assessment of associations between clinical and immune microenvironmental factors and tumor mutation burden in resected nonsmall cell lung cancer by applying machine learning to whole‐slide images

Abstract

BackgroundIt is unclear whether clinical factors and immune microenvironment (IME) factors are associated with tumor mutation burden (TMB) in patients with nonsmall cell lung cancer (NSCLC).Materials and methodsWe assessed TMB in surgical tumor specimens by performing whole exome sequencing. IME profiles, including PD‐L1 tumor proportion score (TPS), stromal CD8 tumor‐infiltrating lymphocyte (TIL) density, and stromal Foxp3 TIL density, were quantified by digital pathology using a machine learning algorithm. To detect factors associated with TMB, clinical data, and IME factors were assessed by means of a multiple regression model.ResultsWe analyzed tumors from 200 of the 246 surgically resected NSCLC patients between September 2014 and September 2015. Patient background: median age (range) 70 years (39‐87); male 37.5%; smoker 27.5%; pathological stage (p‐stage) I/II/III, 63.5/22.5/14.0%; histological type Ad/Sq, 77.0/23.0%; primary tumor location upper/lower, 58.5/41.5%; median PET SUV 7.5 (0.86‐29.8); median serum CEA (sCEA) level 3.4 ng/mL (0.5‐144.3); median serum CYFRA 21‐1 (sCYFRA) level 1.2 ng/mL (1.0‐38.0); median TMB 2.19/ Mb (0.12‐64.38); median PD‐L1 TPS 15.1% (0.09‐77.4); median stromal CD8 TIL density 582.1/mm2 (120.0‐4967.6);, and median stromal Foxp3 TIL density 183.7/mm2 (6.3‐544.0).The multiple regression analysis identified three factors associated with higher TMB: smoking status: smoker, increase PET SUV, and sCEA level: >5 ng/mL (P < .001, P < .001, and P = .006, respectively).ConclusionsThe IME factors assessed were not associated with TMB, but our findings showed that, in addition to smoking, PET SUV and sCEA levels may be independent predictors of TMB. TMB and IME factors are independent factors in resected NSCLC.

Role of Tumor Mutation Burden Analysis in Detecting Lynch Syndrome in Precision Medicine: Analysis of 2,501 Japanese Cancer Patients

“…Actually, most of our hTMB cancer groups (TMB ≥10) exhibited hypermutators and ultramutators and shared several demographic features, such as frequent LS-associated cancers and skin cancer (Table 2), modestly increasing cases meeting the revised Bethesda criteria (Table 3), and cases with personal and family histories of LS-related cancers (Table 4). Although TMB is affected by mutagenic exposures, such as smoking for lung cancer (35,36) and ultraviolet light for skin cancer (5,35), current results demonstrated no correlation between Brinkman index and A variant of MLH1 (exon 5 del) was not detected either by the hTMB approach or by the universal g.MMR sequencing approach as the variant was a large deletion and the TMB was 8.5 (<10/Mb). This variant was detected in cases of family history, MSI, and MMR IHC using the MLPA method.…”

Artificial Intelligence–Powered Prediction of ALK Gene Rearrangement in Patients With Non–Small-Cell Lung Cancer

“…10,11 WSI systems have led to a number of new opportunities that are impossible by conventional microscopic evaluations, including quantitative immunohistochemical (IHC) analyses and measurements of immune phenotypes and their relationship to the immune microenvironment (eg, tumor v stroma) by artificial intelligence (AI). [12][13][14][15] A digital workflow would further simplify the work of pathologists by automating time-consuming repetitive tasks, extracting more data from tissues, and supporting precision medicine. 16 There has been a report of using DL models to predict cancer-related genetic abnormalities as genotypes on the basis of phenotypic WSI data, but there have been no data on ALKr.…”

Dynamic monitoring serum tumor markers to predict molecular features of EGFR‐mutated lung cancer during targeted therapy

“…41,42 Moreover, the conversion of dominant STMs sometimes might be suggestive of tumoral transformation, and the STM levels are often related to the tumor mutational burdens. 43,44 In addition to the acquired T790M mutation, the transformation from adenocarcinoma to other components is one of many mechanisms of acquired resistance to an EGFR TKI. 45 Our results showed that compared with the T790M subgroup and the non-T790M subgroup, SCC showed a distinctive pattern from other tumor markers at baseline, in the responsive phase, or in the resistant phase.…”