Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI : a comparison between conventional and fused models
© 2022. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB)..
OBJECTIVES: Multiparametric MRI (mp-MRI) has been significantly used for detection, localization and staging of Prostate cancer (PCa). However, all the assessment suffers from poor reproducibility among the readers. The aim of this study was to evaluate radiomics models to diagnose PCa using high-resolution T2-weighted (T2-W) and dynamic contrast-enhanced (DCE) MRI.
MATERIALS AND METHODS: Thirty two patients who had high prostate specific antigen level were recruited. The prostate biopsies considered as the reference to differentiate between 66 benign and 36 malignant prostate lesions. 181 features were extracted from each modality. K-nearest neighbors, artificial neural network, decision tree, and linear discriminant analysis were used for machine-learning study. The leave-one-out cross-validation method was used to prevent overfitting and build robust models.
RESULTS: Radiomics analysis showed that T2-W images were more effective in PCa detection compare to DCE images. Local binary pattern features and speeded up robust features had the highest ability for prediction in T2-W and DCE images, respectively. The classifier fusion using decision template method showed the highest performance with accuracy, specificity, and sensitivity of 100%.
DISCUSSION: The findings of this framework provide researchers on PCa with a promising method for reliable detection of prostate lesions in MR images by fused model.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:36 |
|---|---|
| Enthalten in: |
Magma (New York, N.Y.) - 36(2023), 1 vom: 17. Feb., Seite 55-64 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Jamshidi, Ghazaleh [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Dynamic contrast-enhanced MRI |
|---|
| Anmerkungen: |
Date Completed 09.03.2023 Date Revised 09.03.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1007/s10334-022-01037-z |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM346316286 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM346316286 | ||
| 003 | DE-627 | ||
| 005 | 20231226031137.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1007/s10334-022-01037-z |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1154.xml |
| 035 | |a (DE-627)NLM346316286 | ||
| 035 | |a (NLM)36114898 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Jamshidi, Ghazaleh |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Radiomics-based machine-learning method to diagnose prostate cancer using mp-MRI |b a comparison between conventional and fused models |
| 264 | 1 | |c 2023 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Completed 09.03.2023 | ||
| 500 | |a Date Revised 09.03.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2022. The Author(s), under exclusive licence to European Society for Magnetic Resonance in Medicine and Biology (ESMRMB). | ||
| 520 | |a OBJECTIVES: Multiparametric MRI (mp-MRI) has been significantly used for detection, localization and staging of Prostate cancer (PCa). However, all the assessment suffers from poor reproducibility among the readers. The aim of this study was to evaluate radiomics models to diagnose PCa using high-resolution T2-weighted (T2-W) and dynamic contrast-enhanced (DCE) MRI | ||
| 520 | |a MATERIALS AND METHODS: Thirty two patients who had high prostate specific antigen level were recruited. The prostate biopsies considered as the reference to differentiate between 66 benign and 36 malignant prostate lesions. 181 features were extracted from each modality. K-nearest neighbors, artificial neural network, decision tree, and linear discriminant analysis were used for machine-learning study. The leave-one-out cross-validation method was used to prevent overfitting and build robust models | ||
| 520 | |a RESULTS: Radiomics analysis showed that T2-W images were more effective in PCa detection compare to DCE images. Local binary pattern features and speeded up robust features had the highest ability for prediction in T2-W and DCE images, respectively. The classifier fusion using decision template method showed the highest performance with accuracy, specificity, and sensitivity of 100% | ||
| 520 | |a DISCUSSION: The findings of this framework provide researchers on PCa with a promising method for reliable detection of prostate lesions in MR images by fused model | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Dynamic contrast-enhanced MRI | |
| 650 | 4 | |a Machine-learning | |
| 650 | 4 | |a Mp-MRI | |
| 650 | 4 | |a Prostate cancer | |
| 650 | 4 | |a T2-weighted imaging | |
| 700 | 1 | |a Abbasian Ardakani, Ali |e verfasserin |4 aut | |
| 700 | 1 | |a Ghafoori, Mahyar |e verfasserin |4 aut | |
| 700 | 1 | |a Babapour Mofrad, Farshid |e verfasserin |4 aut | |
| 700 | 1 | |a Saligheh Rad, Hamidreza |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Magma (New York, N.Y.) |d 1997 |g 36(2023), 1 vom: 17. Feb., Seite 55-64 |w (DE-627)NLM074735586 |x 1352-8661 |7 nnns |
| 773 | 1 | 8 | |g volume:36 |g year:2023 |g number:1 |g day:17 |g month:02 |g pages:55-64 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1007/s10334-022-01037-z |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 36 |j 2023 |e 1 |b 17 |c 02 |h 55-64 | ||