Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/mbarbetti/mediastinal-lymphoma-classification

Machine-learning-based classification of bulky mediastinal lymphomas using radiomic features
https://github.com/mbarbetti/mediastinal-lymphoma-classification

diagnosis-prediction lymphoma-classification machine-learning personalized-treatment precision-medicine radiomics-analysis scikit-learn texture-analysis

Last synced: about 1 month ago
JSON representation

Machine-learning-based classification of bulky mediastinal lymphomas using radiomic features

Awesome Lists containing this project

README

        

# Machine-learning-based classification of bulky mediastinal lymphomas using radiomic features

This repository contains a set of Jupyter notebooks and Python scripts to reproduce the machine learning results shown in the paper "Characterization of Mediastinal Bulky Lymphomas with FDG-PET-Based Radiomics and Machine Learning Techniques" published on [Cancers **15** (2023) 1931](https://doi.org/10.3390/cancers15071931).

## Abstract

**Background:** This study tested the diagnostic value of 18F-FDG PET/CT (FDG-PET) volumetric and texture parameters in the histological differentiation of mediastinal bulky disease due to classical Hodgkin lymphoma (cHL), primary mediastinal B-cell lymphoma (PMBCL) and grey zone lymphoma (GZL), using machine learning techniques. **Methods:** reviewed 80 cHL, 29 PMBCL and 8 GZL adult patients with mediastinal bulky disease and histopathological diagnoses who underwent FDG-PET pre-treatment. Volumetric and radiomic parameters were measured using FDG-PET both for bulky lesions (BL) and for all lesions (AL) using LIFEx software (threshold SUV ≥ 2.5). Binary and multiclass classifications were performed with various machine learning techniques fed by a relevant subset of radiomic features. **Results:** The analysis showed significant differences between the lymphoma groups in terms of SUVmax, SUVmean, MTV, TLG and several textural features of both first- and second-order grey level. Among machine learning classifiers, the tree-based ensembles achieved the best performance both for binary and multiclass classifications in histological differentiation. **Conclusions:** Our results support the value of metabolic heterogeneity as an imaging biomarker, and the use of radiomic features for early characterization of mediastinal bulky lymphoma.

**Keywords:** [bulky lymphoma](https://www.mdpi.com/search?q=bulky+lymphoma); [diagnosis](https://www.mdpi.com/search?q=diagnosis); [textural analysis](https://www.mdpi.com/search?q=textural+analysis); [machine learning](https://www.mdpi.com/search?q=machine+learning); [FDG-PET](https://www.mdpi.com/search?q=FDG-PET); [radiomics](https://www.mdpi.com/search?q=radiomics); [precision medicine](https://www.mdpi.com/search?q=precision+medicine); [personalized treatment](https://www.mdpi.com/search?q=personalized+treatment)

## Cite us

Are you referring to our research project? Please cite us!

> E. M. Abenavoli _et al._, **Characterization of Mediastinal Bulky Lymphomas with FDG-PET-Based Radiomics and Machine Learning Techniques**, [Cancers **15** (2023) 1931](https://doi.org/10.3390/cancers15071931)

```bibtex
@article{cancers15071931,
author = {Abenavoli, Elisabetta Maria and Barbetti, Matteo and Linguanti, Flavia and
Mungai, Francesco and Nassi, Luca and Puccini, Benedetta and Romano, Ilaria and
Sordi, Benedetta and Santi, Raffaella and Passeri, Alessandro and
Sciagrà, Roberto and Talamonti, Cinzia and Cistaro, Angelina and
Vannucchi, Alessandro Maria and Berti, Valentina},
title = {Characterization of Mediastinal Bulky Lymphomas with FDG-PET-Based Radiomics
and Machine Learning Techniques},
journal = {Cancers},
volume = {15},
number = {7},
pages = {1931},
doi = {10.3390/cancers15071931},
url = {https://doi.org/10.3390/cancers15071931},
month = {03},
year = {2023},
}
```