Texture analysis and multiple-instance learning for the classification of malignant lymphomas.


Journal

Computer methods and programs in biomedicine
ISSN: 1872-7565
Titre abrégé: Comput Methods Programs Biomed
Pays: Ireland
ID NLM: 8506513

Informations de publication

Date de publication:
Mar 2020
Historique:
received: 13 02 2019
revised: 16 10 2019
accepted: 23 10 2019
pubmed: 5 11 2019
medline: 7 1 2021
entrez: 4 11 2019
Statut: ppublish

Résumé

Malignant lymphomas are cancers of the immune system and are characterized by enlarged lymph nodes that typically spread across many different sites. Many different histological subtypes exist, whose diagnosis is typically based on sampling (biopsy) of a single tumor site, whereas total body examinations with computed tomography and positron emission tomography, though not diagnostic, are able to provide a comprehensive picture of the patient. In this work, we exploit a data-driven approach based on multiple-instance learning algorithms and texture analysis features extracted from positron emission tomography, to predict differential diagnosis of the main malignant lymphomas subtypes. We exploit a multiple-instance learning setting where support vector machines and random forests are used as classifiers both at the level of single VOIs (instances) and at the level of patients (bags). We present results on two datasets comprising patients that suffer from four different types of malignant lymphomas, namely diffuse large B cell lymphoma, follicular lymphoma, Hodgkin's lymphoma, and mantle cell lymphoma. Despite the complexity of the task, experimental results show that, with sufficient data samples, some cancer subtypes, such as the Hodgkin's lymphoma, can be identified from texture information: in particular, we achieve a 97.0% of sensitivity (recall) and a 94.1% of predictive positive value (precision) on a dataset that consists in 60 patients. The presented study indicates that texture analysis features extracted from positron emission tomography, combined with multiple-instance machine learning algorithms, can be discriminating for different malignant lymphomas subtypes.

Sections du résumé

BACKGROUND AND OBJECTIVES OBJECTIVE
Malignant lymphomas are cancers of the immune system and are characterized by enlarged lymph nodes that typically spread across many different sites. Many different histological subtypes exist, whose diagnosis is typically based on sampling (biopsy) of a single tumor site, whereas total body examinations with computed tomography and positron emission tomography, though not diagnostic, are able to provide a comprehensive picture of the patient. In this work, we exploit a data-driven approach based on multiple-instance learning algorithms and texture analysis features extracted from positron emission tomography, to predict differential diagnosis of the main malignant lymphomas subtypes.
METHODS METHODS
We exploit a multiple-instance learning setting where support vector machines and random forests are used as classifiers both at the level of single VOIs (instances) and at the level of patients (bags). We present results on two datasets comprising patients that suffer from four different types of malignant lymphomas, namely diffuse large B cell lymphoma, follicular lymphoma, Hodgkin's lymphoma, and mantle cell lymphoma.
RESULTS RESULTS
Despite the complexity of the task, experimental results show that, with sufficient data samples, some cancer subtypes, such as the Hodgkin's lymphoma, can be identified from texture information: in particular, we achieve a 97.0% of sensitivity (recall) and a 94.1% of predictive positive value (precision) on a dataset that consists in 60 patients.
CONCLUSIONS CONCLUSIONS
The presented study indicates that texture analysis features extracted from positron emission tomography, combined with multiple-instance machine learning algorithms, can be discriminating for different malignant lymphomas subtypes.

Identifiants

pubmed: 31678792
pii: S0169-2607(19)30205-6
doi: 10.1016/j.cmpb.2019.105153
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

105153

Informations de copyright

Copyright © 2019. Published by Elsevier B.V.

Déclaration de conflit d'intérêts

Declaration of Competing Interest The authors declare that they have no competing interests.

Auteurs

Marco Lippi (M)

Department of Sciences and Methods for Engineering, University of Modena and Reggio Emilia, Italy; Artificial Intelligence Research and Innovation center, University of Modena and Reggio Emilia, Italy; InterMech Center, University of Modena and Reggio Emilia, Italy. Electronic address: marco.lippi@unimore.it.

Stefania Gianotti (S)

Department of Sciences and Methods for Engineering, University of Modena and Reggio Emilia, Italy. Electronic address: ste.gianotti93@gmail.com.

Angelo Fama (A)

Hematology, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: angelo.fama@ausl.re.it.

Massimiliano Casali (M)

Nuclear Medicine, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: massimiliano.casali@ausl.re.it.

Elisa Barbolini (E)

Gr.A.D.E. Onlus Foundation, Reggio Emilia, Italy. Electronic address: elisa.barbolini@ausl.re.it.

Angela Ferrari (A)

Hematology, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: angela.ferrari@ausl.re.it.

Federica Fioroni (F)

Medical Physics, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: federica.fioroni@ausl.re.it.

Mauro Iori (M)

Medical Physics, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: mauro.iori@ausl.re.it.

Stefano Luminari (S)

Hematology, Azienda USL-IRCCS di Reggio Emilia, Italy; Surgical, Medical and Dental Department of Morphological Sciences related to Transplant, Oncology and Regenerative Medicine, University of Modena and Reggio Emilia, Italy. Electronic address: stefano.luminari@unimore.it.

Massimo Menga (M)

Nuclear Medicine, ASUITS, Trieste, Italy. Electronic address: massimo.menga@asuits.sanita.fvg.it.

Francesco Merli (F)

Hematology, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: francesco.merli@ausl.re.it.

Valeria Trojani (V)

School of Specialization in Health Physics, University of Bologna, Italy. Electronic address: valeria.trojani@studio.unibo.it.

Annibale Versari (A)

Nuclear Medicine, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: annibale.versari@ausl.re.it.

Magda Zanelli (M)

Pathology Unit, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: magda.zanelli@ausl.re.it.

Marco Bertolini (M)

Medical Physics, Azienda USL-IRCCS di Reggio Emilia, Italy. Electronic address: marco.bertolini@ausl.re.it.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH