Dataset Information

Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms.

ABSTRACT: Lung neuroendocrine neoplasms (lung NENs) are categorised by morphology, defining a classification sometimes unable to reflect ultimate clinical outcome. Subjectivity and poor reproducibility characterise diagnosis and prognosis assessment of all NENs. Here, we propose a machine learning framework for tumour prognosis assessment based on a quantitative, automated and repeatable evaluation of the spatial distribution of cells immunohistochemically positive for the proliferation marker Ki-67, performed on the entire extent of high-resolution whole slide images. Combining features from the fields of graph theory, fractality analysis, stochastic geometry and information theory, we describe the topology of replicating cells and predict prognosis in a histology-independent way. We demonstrate how our approach outperforms the well-recognised prognostic role of Ki-67 Labelling Index on a multi-centre dataset comprising the most controversial lung NENs. Moreover, we show that our system identifies arrangement patterns in the cells positive for Ki-67 that appear independently of tumour subtyping. Strikingly, the subset of these features whose presence is also independent of the value of the Labelling Index and the density of Ki-67-positive cells prove to be especially relevant in discerning prognostic classes. These findings disclose a possible path for the future of grading and classification of NENs.

SUBMITTER: Bulloni M

PROVIDER: S-EPMC8508355 | biostudies-literature | 2021 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms.

Bulloni Matteo M Sandrini Giada G Stacchiotti Irene I Barberis Massimo M Calabrese Fiorella F Carvalho Lina L Fontanini Gabriella G Alì Greta G Fortarezza Francesco F Hofman Paul P Hofman Veronique V Kern Izidor I Maiorano Eugenio E Maragliano Roberta R Marchiori Deborah D Metovic Jasna J Papotti Mauro M Pezzuto Federica F Pisa Eleonora E Remmelink Myriam M Serio Gabriella G Marzullo Andrea A Trabucco Senia Maria Rosaria SMR Pennella Antonio A De Palma Angela A Marulli Giuseppe G Fassina Ambrogio A Maffeis Valeria V Nesi Gabriella G Naheed Salma S Rea Federico F Ottensmeier Christian H CH Sessa Fausto F Uccella Silvia S Pelosi Giuseppe G Pattini Linda L

Cancers 20210929 19

Lung neuroendocrine neoplasms (lung NENs) are categorised by morphology, defining a classification sometimes unable to reflect ultimate clinical outcome. Subjectivity and poor reproducibility characterise diagnosis and prognosis assessment of all NENs. Here, we propose a machine learning framework for tumour prognosis assessment based on a quantitative, automated and repeatable evaluation of the spatial distribution of cells immunohistochemically positive for the proliferation marker Ki-67, perf ...[more]

PMID: 34638359

Similar Datasets

Project description:DNA methylation is a crucial epigenetic mechanism for gene expression regulation and cell differentiation. Furthermore, it was found to play a major role in multiple pathological processes, including cancer. In pancreatic neuroendocrine neoplasms (PNENs), epigenetic deregulation is also considered to be of significance, as the most frequently mutated genes have an important function in epigenetic regulation. However, the exact changes in DNA methylation between PNENs and the endocrine cells of the pancreas, their likely cell-of-origin, remain largely unknown. Recently, two subtypes of PNENs have been described which were linked to cell-of-origin and have a different prognosis. A difference in the expression of the transcription factor PDX1 was one of the key molecular differences. In this study, we performed an exploratory genome-wide DNA methylation analysis using Infinium Methylation EPIC arrays (Illumina) on 26 PNENs and pancreatic islets of five healthy donors. In addition, the methylation profile of the PDX1 region was used to perform subtyping in a global cohort of 83 PNEN, 2 healthy alpha cell and 3 healthy beta cell samples. In our exploratory analysis, we identified 26,759 differentially methylated CpGs and 79 differentially methylated regions. The gene set enrichment analysis highlighted several interesting pathways targeted by altered DNA methylation, including MAPK, platelet-related and immune system-related pathways. Using the PDX1 methylation in 83 PNEN, 2 healthy alpha cell and 3 healthy beta cell samples, two subtypes were identified, subtypes A and B, which were similar to alpha and beta cells, respectively. These subtypes had different clinicopathological characteristics, a different pattern of chromosomal alterations and a different prognosis, with subtype A having a significantly worse prognosis compared with subtype B (HR 0.22 [95% CI: 0.051-0.95], p = 0.043). Hence, this study demonstrates that several cancer-related pathways are differently methylated between PNENs and normal islet cells. In addition, we validated the use of the PDX1 methylation status for the subtyping of PNENs and its prognostic importance.

Dataset Information

Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms.

Publications

Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets