Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer
Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.
| Errataetall: |
CommentIn: Radiol Artif Intell. 2024 Mar;6(2):e230547. - PMID 38416038 |
|---|---|
| Medienart: |
E-Artikel |
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:6 |
|---|---|
| Enthalten in: |
Radiology. Artificial intelligence - 6(2024), 2 vom: 01. März, Seite e230118 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Prior, Olivia [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
CT |
|---|
| Anmerkungen: |
Date Completed 29.02.2024 Date Revised 24.04.2024 published: Print CommentIn: Radiol Artif Intell. 2024 Mar;6(2):e230547. - PMID 38416038 Citation Status MEDLINE |
|---|
| doi: |
10.1148/ryai.230118 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM367846136 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM367846136 | ||
| 003 | DE-627 | ||
| 005 | 20240424231937.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240131s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1148/ryai.230118 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1385.xml |
| 035 | |a (DE-627)NLM367846136 | ||
| 035 | |a (NLM)38294307 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Prior, Olivia |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer |
| 264 | 1 | |c 2024 | |
| 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 29.02.2024 | ||
| 500 | |a Date Revised 24.04.2024 | ||
| 500 | |a published: Print | ||
| 500 | |a CommentIn: Radiol Artif Intell. 2024 Mar;6(2):e230547. - PMID 38416038 | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a CT | |
| 650 | 4 | |a Diffusion-weighted Imaging | |
| 650 | 4 | |a Dynamic Contrast-enhanced MRI | |
| 650 | 4 | |a Liver | |
| 650 | 4 | |a Lung | |
| 650 | 4 | |a MRI | |
| 650 | 4 | |a Oncology | |
| 650 | 4 | |a Radiomics | |
| 650 | 4 | |a Unsupervised Learning | |
| 700 | 1 | |a Macarro, Carlos |e verfasserin |4 aut | |
| 700 | 1 | |a Navarro, Víctor |e verfasserin |4 aut | |
| 700 | 1 | |a Monreal, Camilo |e verfasserin |4 aut | |
| 700 | 1 | |a Ligero, Marta |e verfasserin |4 aut | |
| 700 | 1 | |a Garcia-Ruiz, Alonso |e verfasserin |4 aut | |
| 700 | 1 | |a Serna, Garazi |e verfasserin |4 aut | |
| 700 | 1 | |a Simonetti, Sara |e verfasserin |4 aut | |
| 700 | 1 | |a Braña, Irene |e verfasserin |4 aut | |
| 700 | 1 | |a Vieito, Maria |e verfasserin |4 aut | |
| 700 | 1 | |a Escobar, Manuel |e verfasserin |4 aut | |
| 700 | 1 | |a Capdevila, Jaume |e verfasserin |4 aut | |
| 700 | 1 | |a Byrne, Annette T |e verfasserin |4 aut | |
| 700 | 1 | |a Dienstmann, Rodrigo |e verfasserin |4 aut | |
| 700 | 1 | |a Toledo, Rodrigo |e verfasserin |4 aut | |
| 700 | 1 | |a Nuciforo, Paolo |e verfasserin |4 aut | |
| 700 | 1 | |a Garralda, Elena |e verfasserin |4 aut | |
| 700 | 1 | |a Grussu, Francesco |e verfasserin |4 aut | |
| 700 | 1 | |a Bernatowicz, Kinga |e verfasserin |4 aut | |
| 700 | 1 | |a Perez-Lopez, Raquel |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Radiology. Artificial intelligence |d 2019 |g 6(2024), 2 vom: 01. März, Seite e230118 |w (DE-627)NLM304586358 |x 2638-6100 |7 nnns |
| 773 | 1 | 8 | |g volume:6 |g year:2024 |g number:2 |g day:01 |g month:03 |g pages:e230118 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1148/ryai.230118 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 6 |j 2024 |e 2 |b 01 |c 03 |h e230118 | ||