High Histological Entropy Is Correlated with Poor Overall Survival and Death Within the First 2 Years in Diffuse...

Background/Objectives: Diffuse large B-cell lymphoma (DLBCL) is an aggressive lymphoma and one of the most common hematological neoplasia. Entropy is a statistical measure of randomness that characterizes the texture of an input image and measures tissue complexity. Methods: Image processing and computer vision analysis were performed on a series of 114 diagnostic DLBCL cases and 44 reactive lymphoid tissues stained with hematoxylin and eosin (H&E). Histological entropy was measured to differentiate between reactive lymphoid tissue and DLBCL and predict clinical evolution. At protein level, immunohistochemistry analyzed Ki67, LMO2, MYC, MDM2, CDK6, E2F1, BCL2, CASP8, MYOB, TP53, cPARP, cCASP3, ISY1, TNFAIP8, CSF1R, CD163, PD-L1 and IL-10 markers. Gene expression analysis using the NanoString nCounter PanCancer Immune Profiling Panel was performed in 29 cases. Results: In comparison with reactive lymphoid tissue, DLBCL was characterized by lower entropy (7.32 ± 0.16 vs. 6.82 ± 0.44, respectively; p < 0.001). Within the DLBCL diagnostic category, higher entropy was associated with poor overall survival and death events within the first 2 years (hazard-risk = 2.4, p = 0.004) and lower entropy with a moderate and more favorable outcome (hazard-risk = 0.4, p = 0.004). High entropy was also correlated with ECOG performance status ≥ 2, lower protein expression of apoptosis markers of cPARP and cCASP3, and upregulation of specific immuno-oncology genes such as STAT3, BTK, CASP8, CD47, VCAM1, and MYD88. The prognostic value of entropy was independent of the international prognostic index (IPI), Epstein-Barr virus (EBER), and cell of origin (Hans). Conclusions: The histological evaluation of entropy is useful for the differential diagnosis of reactive lymphoid tissue and DLBCL and is a predictive factor of DLBCL prognosis.