Cancers (Sep 2021)
Automated Analysis of Proliferating Cells Spatial Organisation Predicts Prognosis in Lung Neuroendocrine Neoplasms
- Matteo Bulloni,
- Giada Sandrini,
- Irene Stacchiotti,
- Massimo Barberis,
- Fiorella Calabrese,
- Lina Carvalho,
- Gabriella Fontanini,
- Greta Alì,
- Francesco Fortarezza,
- Paul Hofman,
- Veronique Hofman,
- Izidor Kern,
- Eugenio Maiorano,
- Roberta Maragliano,
- Deborah Marchiori,
- Jasna Metovic,
- Mauro Papotti,
- Federica Pezzuto,
- Eleonora Pisa,
- Myriam Remmelink,
- Gabriella Serio,
- Andrea Marzullo,
- Senia Maria Rosaria Trabucco,
- Antonio Pennella,
- Angela De Palma,
- Giuseppe Marulli,
- Ambrogio Fassina,
- Valeria Maffeis,
- Gabriella Nesi,
- Salma Naheed,
- Federico Rea,
- Christian H. Ottensmeier,
- Fausto Sessa,
- Silvia Uccella,
- Giuseppe Pelosi,
- Linda Pattini
Affiliations
- Matteo Bulloni
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy
- Giada Sandrini
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy
- Irene Stacchiotti
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy
- Massimo Barberis
- Division of Pathology, IRCCS European Institute of Oncology, 20136 Milan, Italy
- Fiorella Calabrese
- Pathology Unit, Department of Cardiac, Thoracic, Vascular Sciences, and Public Health, Medical School, University of Padua, 35122 Padua, Italy
- Lina Carvalho
- Anatomical Pathology Unit-Hospitais da Universidade de Coimbra/Centro Hospitalar e Universitário de Coimbra-Portugal, Faculty of Medicine, University of Coimbra-Portugal, 3004-504 Coimbra, Portugal
- Gabriella Fontanini
- Department of Surgical Pathology, Medical, Molecular and Critical Area, University of Pisa, 56126 Pisa, Italy
- Greta Alì
- Operative Unit of Anatomic Pathology, Azienda Ospedaliero-Universitaria Pisana, 56126 Pisa, Italy
- Francesco Fortarezza
- Operative Unit of Anatomic Pathology, Azienda Ospedaliero-Universitaria Pisana, 56126 Pisa, Italy
- Paul Hofman
- Laboratory of Clinical and Experimental Pathology, FHU OncoAge, Louis Pasteur Hospital BB-0033-00025, IRCAN, Université Côte d’Azur, 06100 Nice, France
- Veronique Hofman
- Laboratory of Clinical and Experimental Pathology, FHU OncoAge, Louis Pasteur Hospital BB-0033-00025, IRCAN, Université Côte d’Azur, 06100 Nice, France
- Izidor Kern
- Department of Pathology, University Clinic of Respiratory and Allergic Diseases Golnik, 4204 Golnik, Slovenia
- Eugenio Maiorano
- Pathology Section, Department of Emergency and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Roberta Maragliano
- Pathology Unit, Department of Medicine and Surgery, University of Insubria, 21100 Varese, Italy
- Deborah Marchiori
- Pathology Unit, Department of Medicine and Surgery, University of Insubria, 21100 Varese, Italy
- Jasna Metovic
- Department of Oncology, University of Turin, 10124 Turin, Italy
- Mauro Papotti
- Department of Oncology, University of Turin, 10124 Turin, Italy
- Federica Pezzuto
- Pathology Unit, Department of Cardiac, Thoracic, Vascular Sciences, and Public Health, Medical School, University of Padua, 35122 Padua, Italy
- Eleonora Pisa
- Division of Pathology, IRCCS European Institute of Oncology, 20136 Milan, Italy
- Myriam Remmelink
- Department of Pathology, Erasme Hospital, Université Libre de Bruxelles, 1050 Brussels, Belgium
- Gabriella Serio
- Pathology Section, Department of Emergency and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Andrea Marzullo
- Pathology Section, Department of Emergency and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Senia Maria Rosaria Trabucco
- Pathology Section, Department of Emergency and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Antonio Pennella
- Pathology Division, Department of Surgery, University of Foggia, 71122 Foggia, Italy
- Angela De Palma
- Thoracic Surgery Section, Department of Surgery and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Giuseppe Marulli
- Thoracic Surgery Section, Department of Surgery and Organ Transplantation, University of Bari, 70121 Bari, Italy
- Ambrogio Fassina
- Surgical Pathology & Cytopathology Unit, Department of Medicine (DIMED), University of Padova, Via Aristide Gabelli, 61, 35121 Padova, Italy
- Valeria Maffeis
- Surgical Pathology & Cytopathology Unit, Department of Medicine (DIMED), University of Padova, Via Aristide Gabelli, 61, 35121 Padova, Italy
- Gabriella Nesi
- Department of Health Sciences, University of Florence, 50139 Florence, Italy
- Salma Naheed
- Cancer Sciences Unit, Faculty of Medicine, University of Southampton, Southampton SO17 1BJ, UK
- Federico Rea
- Thoracic Surgery Unit, Department of Cardiac, Thoracic, Vascular Sciences, and Public Health, Medical School, University of Padua, 35122 Padua, Italy
- Christian H. Ottensmeier
- Liverpool Head and Neck Centre, Department of Molecular & Clinical Cancer Medicine, Institute of Translational Medicine, University of Liverpool, Liverpool L1 8JX, UK
- Fausto Sessa
- Pathology Unit, Department of Medicine and Surgery, University of Insubria, 21100 Varese, Italy
- Silvia Uccella
- Pathology Unit, Department of Medicine and Surgery, University of Insubria, 21100 Varese, Italy
- Giuseppe Pelosi
- Department of Oncology and Hemato-Oncology, University of Milan, 20122 Milan, Italy
- Linda Pattini
- Department of Electronics, Information and Bioengineering, Politecnico di Milano, 20133 Milan, Italy
- DOI
- https://doi.org/10.3390/cancers13194875
- Journal volume & issue
-
Vol. 13,
no. 19
p. 4875
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.
Keywords