Comprehensive Molecular and Pathologic Evaluation of Transitional Mesothelioma Assisted by Deep Learning Approach: A Multi-Institutional Study of the International Mesothelioma Panel from the MESOPATH Reference Center

Abstract

Introduction: Histologic subtypes of malignant pleural mesothelioma are a major prognostic indicator and decision denominator for all therapeutic strategies. In an ambiguous case, a rare transitional mesothelioma (TM) pattern may be diagnosed by pathologists either as epithelioid mesothelioma (EM), biphasic mesothelioma (BM), or sarcomatoid mesothelioma (SM). This study aimed to better characterize the TM subtype from a histological, immunohistochemical, and molecular standpoint. Deep learning of pathologic slides was applied to this cohort.

Methods: A random selection of 49 representative digitalized sections from surgical biopsies of TM was reviewed by 16 panelists. We evaluated BAP1 expression and CDKN2A (p16) homozygous deletion. We conducted a comprehensive, integrated, transcriptomic analysis. An unsupervised deep learning algorithm was trained to classify tumors.

Results: The 16 panelists recorded 784 diagnoses on the 49 cases. Even though a Kappa value of 0.42 is moderate, the presence of a TM component was diagnosed in 51%. In 49% of the histological evaluation, the reviewers classified the lesion as EM in 53%, SM in 33%, or BM in 14%. Median survival was 6.7 months. Loss of BAP1 observed in 44% was less frequent in TM than in EM and BM. p16 homozygous deletion was higher in TM (73%), followed by BM (63%) and SM (46%). RNA sequencing unsupervised clustering analysis revealed that TM grouped together and were closer to SM than to EM. Deep learning analysis achieved 94% accuracy for TM identification.

Conclusion: These results revealed that the TM pattern should be classified as non-EM or at minimum as a subgroup of the SM type.

Keywords: Histology; Mesothelioma; Surgery; Systemic treatment.

Figure 1.

Transitional pattern of cohesive, large, plump epithelioid cells with a well-defined border, high nucleocytoplasmic ratio, and prominent nucleoli.

Figure 2.

Distribution of Kappa scores for the recognition of the transitional mesothelioma histological component in mesothelioma.

Figure 3.

Results of the interobserver agreement.

Figure 4.

Distribution of diagnosis made by the reviewers by histologic types according to the WHO 2015 classification. X-axis visualizes the percentage of diagnosis made by the reviewers for each case of the study. The Y-axis corresponds to the case number. TMM, transitional malignant mesothelioma; EMM, epithelioid malignant mesothelioma; BMM, biphasic malignant mesothelioma; SMM, sarcomatoid malignant mesothelioma.

Figure 5.

(A) Image illustrating the lack of frankly sarcomatous features; (B) Large ovoid nuclei with prominent nucleoli and presence of mitosis).

Figure 6.

(A, B, C) Reticulin staining in TM, SM, and EM showing the thin banding of individual transitional cells compared with the strong banding of individual sarcomatoid cells and the strapping of large cluster of EM cells. TM, transitional mesothelioma; EM, epithelioid mesothelioma; BM, biphasic mesothelioma; SM, sarcomatoid mesothelioma.

Figure 7.

(A) OS of the series of 49 TM cases compared with the epithelioid biphasic and sarcomatoid conventional histologic types from the large MESOBANK cohort; (B) overall survival curves of the TM series by histologic types when comparing the 49 TM cases with more aggressive patterns of epithelioid subtypes (solid and nonsolid epithelioid subtypes); (C) OS curves of the TM series by histologic types when comparing the 49 TM cases to epithelioid, biphasic, sarcomatoid and pleomorphic type. TM, transitional mesothelioma; OS overall survival; CI, confidence interval.

Figure 8.

RNASeq analyses of a series of 30 mesotheliomas. (A) Hierarchical unsupervised clustering demonstrating that transitional mesotheliomas (gray) clustered together with the sarcomatoid (black) but away from the epithelioid (white) mesotheliomas. (B) Volcano plot presenting the DEGs between the TMM and EMM. Gray squares delineate significant up- or down-regulated DEGs (Welch two samples test p value, Bonferroni corrected < 10-2 and absolute difference of mean expression >1). (C) Gene ontology analyses of DEGs using DAVID tool. Enrichment and Fisher exact test p value is represented for the 20 most significant pathways. (D) Boxplot of the NES from the single sample Gene Set Enrichment Analysis using the Hallmark_G2M_checkpoint gene set. Welch t test p values are indicated. DAVID, The Database for Annotation, Visualization and Integrated Discovery; DEGs, differentially expressed genes; EMM, epithelioid malignant mesothelioma; NES, normalized enrichment score; ns, not significant; RNASeq, RNA sequencing; TMM, transitional malignant mesothelioma.

Figure 9.

Distribution and characterization of top five tiles for histological tiles per patient with transitional features.