Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI
Objective: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/14/1/61 |
| _version_ | 1797358943693963264 |
|---|---|
| author | Marta Forestieri Antonio Napolitano Paolo Tomà Stefano Bascetta Marco Cirillo Emanuela Tagliente Donatella Fracassi Paola D’Angelo Ines Casazza |
| author_facet | Marta Forestieri Antonio Napolitano Paolo Tomà Stefano Bascetta Marco Cirillo Emanuela Tagliente Donatella Fracassi Paola D’Angelo Ines Casazza |
| author_sort | Marta Forestieri |
| collection | DOAJ |
| description | Objective: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis. Materials and methods: We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model’s performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model. Results: Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91–0.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8–0.84, F1-score = 0.9, PPV = 90%. Conclusions: Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods. |
| first_indexed | 2024-03-08T15:09:29Z |
| format | Article |
| id | doaj.art-82882ede5e954ee0b9d3f8a934ef261a |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-08T15:09:29Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-82882ede5e954ee0b9d3f8a934ef261a2024-01-10T14:53:50ZengMDPI AGDiagnostics2075-44182023-12-011416110.3390/diagnostics14010061Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRIMarta Forestieri0Antonio Napolitano1Paolo Tomà2Stefano Bascetta3Marco Cirillo4Emanuela Tagliente5Donatella Fracassi6Paola D’Angelo7Ines Casazza8Imaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyMedical Physics Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyMedical Physics Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyMedical Physics Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyImaging Department, Bambino Gesù Children’s Hospital, IRCCS, 00165 Rome, ItalyObjective: The purpose of this study is to analyze the texture characteristics of chronic non-bacterial osteomyelitis (CNO) bone lesions, identified as areas of altered signal intensity on short tau inversion recovery (STIR) sequences, and to distinguish them from bone marrow growth-related changes through Machine Learning (ML) and Deep Learning (DL) analysis. Materials and methods: We included a group of 66 patients with confirmed diagnosis of CNO and a group of 28 patients with suspected extra-skeletal systemic disease. All examinations were performed on a 1.5 T MRI scanner. Using the opensource 3D Slicer software version 4.10.2, the ROIs on CNO lesions and on the red bone marrow were sampled. Texture analysis (TA) was carried out using Pyradiomics. We applied an optimization search grid algorithm on nine classic ML classifiers and a Deep Learning (DL) Neural Network (NN). The model’s performance was evaluated using Accuracy (ACC), AUC-ROC curves, F1-score, Positive Predictive Value (PPV), Mean Absolute Error (MAE) and Root-Mean-Square Error (RMSE). Furthermore, we used Shapley additive explanations to gain insight into the behavior of the prediction model. Results: Most predictive characteristics were selected by Boruta algorithm for each combination of ROI sequences for the characterization and classification of the two types of signal hyperintensity. The overall best classification result was obtained by the NN with ACC = 0.91, AUC = 0.93 with 95% CI 0.91–0.94, F1-score = 0.94 and PPV = 93.8%. Between classic ML methods, ensemble learners showed high model performance; specifically, the best-performing classifier was the Stack (ST) with ACC = 0.85, AUC = 0.81 with 95% CI 0.8–0.84, F1-score = 0.9, PPV = 90%. Conclusions: Our results show the potential of ML methods in discerning edema-like lesions, in particular by distinguishing CNO lesions from hematopoietic bone marrow changes in a pediatric population. The Neural Network showed the overall best results, while a Stacking classifier, based on Gradient Boosting and Random Forest as principal estimators and Logistic Regressor as final estimator, achieved the best results between the other ML methods.https://www.mdpi.com/2075-4418/14/1/61whole-body magnetic resonance imagingchronic non-bacterial osteomyelitisbone marrowmachine learningtexture analysischildren |
| spellingShingle | Marta Forestieri Antonio Napolitano Paolo Tomà Stefano Bascetta Marco Cirillo Emanuela Tagliente Donatella Fracassi Paola D’Angelo Ines Casazza Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI Diagnostics whole-body magnetic resonance imaging chronic non-bacterial osteomyelitis bone marrow machine learning texture analysis children |
| title | Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI |
| title_full | Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI |
| title_fullStr | Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI |
| title_full_unstemmed | Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI |
| title_short | Machine Learning Algorithm: Texture Analysis in CNO and Application in Distinguishing CNO and Bone Marrow Growth-Related Changes on Whole-Body MRI |
| title_sort | machine learning algorithm texture analysis in cno and application in distinguishing cno and bone marrow growth related changes on whole body mri |
| topic | whole-body magnetic resonance imaging chronic non-bacterial osteomyelitis bone marrow machine learning texture analysis children |
| url | https://www.mdpi.com/2075-4418/14/1/61 |
| work_keys_str_mv | AT martaforestieri machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT antonionapolitano machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT paolotoma machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT stefanobascetta machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT marcocirillo machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT emanuelatagliente machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT donatellafracassi machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT paoladangelo machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri AT inescasazza machinelearningalgorithmtextureanalysisincnoandapplicationindistinguishingcnoandbonemarrowgrowthrelatedchangesonwholebodymri |