Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

Martijn Starmans; Li Shen Ho; Fokko Smits; Nick Beije; Inge de Kruijff; Joep de Jong; Diederik M. Somford; Egbert R. Boevé; E. te Slaa; Evelyne C.C. Cauberg; Sjoerd Klaver; Antoine G. van der Heijden; Carl J. Wijburg; Addy C.M. van de Luijtgaarden; Harm H.E. van Melick; Ella Cauffman; Peter de Vries; Rens Jacobs; Wiro Niessen; J.J. Visser; Stefan Klein; Joost Boormans; Astrid van der Veldt

doi:10.3390/jpm12050726

Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

Martijn Starmans, Li Shen Ho, Fokko Smits, Nick Beije, Inge de Kruijff, Joep de Jong, Diederik M. Somford, Egbert R. Boevé, E. te Slaa, Evelyne C.C. Cauberg, Sjoerd Klaver, Antoine G. van der Heijden, Carl J. Wijburg, Addy C.M. van de Luijtgaarden, Harm H.E. van Melick, Ella Cauffman, Peter de Vries, Rens Jacobs, Wiro Niessen, J.J. VisserStefan Klein, Joost Boormans, Astrid van der Veldt

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.

Original language	English
Journal	Journal of personalized medicine
Volume	12
Issue number	5
DOIs	https://doi.org/10.3390/jpm12050726
Publication status	Published - 30-Apr-2022
Externally published	Yes

Access to Document

10.3390/jpm12050726

Handle.net

Persistent link

Cite this

Starmans, M., Ho, L. S., Smits, F., Beije, N., de Kruijff, I., de Jong, J., Somford, D. M., Boevé, E. R., te Slaa, E., Cauberg, E. C. C., Klaver, S., van der Heijden, A. G., Wijburg, C. J., van de Luijtgaarden, A. C. M., van Melick, H. H. E., Cauffman, E., de Vries, P., Jacobs, R., Niessen, W., ... van der Veldt, A. (2022). Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography. Journal of personalized medicine, 12(5). https://doi.org/10.3390/jpm12050726

@article{6a97a96121e04d6eb85295be2dc08d07,

title = "Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography",

abstract = "Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.",

author = "Martijn Starmans and Ho, {Li Shen} and Fokko Smits and Nick Beije and {de Kruijff}, Inge and {de Jong}, Joep and Somford, {Diederik M.} and Boev{\'e}, {Egbert R.} and {te Slaa}, E. and Cauberg, {Evelyne C.C.} and Sjoerd Klaver and {van der Heijden}, {Antoine G.} and Wijburg, {Carl J.} and {van de Luijtgaarden}, {Addy C.M.} and {van Melick}, {Harm H.E.} and Ella Cauffman and {de Vries}, Peter and Rens Jacobs and Wiro Niessen and J.J. Visser and Stefan Klein and Joost Boormans and {van der Veldt}, Astrid",

year = "2022",

month = apr,

day = "30",

doi = "10.3390/jpm12050726",

language = "English",

volume = "12",

journal = "Journal of personalized medicine",

issn = "2075-4426",

publisher = "MDPI AG",

number = "5",

}

Starmans, M, Ho, LS, Smits, F, Beije, N, de Kruijff, I, de Jong, J, Somford, DM, Boevé, ER, te Slaa, E, Cauberg, ECC, Klaver, S, van der Heijden, AG, Wijburg, CJ, van de Luijtgaarden, ACM, van Melick, HHE, Cauffman, E, de Vries, P, Jacobs, R, Niessen, W, Visser, JJ, Klein, S, Boormans, J & van der Veldt, A 2022, 'Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography', Journal of personalized medicine, vol. 12, no. 5. https://doi.org/10.3390/jpm12050726

TY - JOUR

T1 - Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

AU - Starmans, Martijn

AU - Ho, Li Shen

AU - Smits, Fokko

AU - Beije, Nick

AU - de Kruijff, Inge

AU - de Jong, Joep

AU - Somford, Diederik M.

AU - Boevé, Egbert R.

AU - te Slaa, E.

AU - Cauberg, Evelyne C.C.

AU - Klaver, Sjoerd

AU - van der Heijden, Antoine G.

AU - Wijburg, Carl J.

AU - van de Luijtgaarden, Addy C.M.

AU - van Melick, Harm H.E.

AU - Cauffman, Ella

AU - de Vries, Peter

AU - Jacobs, Rens

AU - Niessen, Wiro

AU - Visser, J.J.

AU - Klein, Stefan

AU - Boormans, Joost

AU - van der Veldt, Astrid

PY - 2022/4/30

Y1 - 2022/4/30

N2 - Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.

AB - Approximately 25% of the patients with muscle-invasive bladder cancer (MIBC) who are clinically node negative have occult lymph node metastases at radical cystectomy (RC) and pelvic lymph node dissection. The aim of this study was to evaluate preoperative CT-based radiomics to differentiate between pN+ and pN0 disease in patients with clinical stage cT2-T4aN0-N1M0 MIBC. Patients with cT2-T4aN0-N1M0 MIBC, of whom preoperative CT scans and pathology reports were available, were included from the prospective, multicenter CirGuidance trial. After manual segmentation of the lymph nodes, 564 radiomics features were extracted. A combination of different machine-learning methods was used to develop various decision models to differentiate between patients with pN+ and pN0 disease. A total of 209 patients (159 pN0; 50 pN+) were included, with a total of 3153 segmented lymph nodes. None of the individual radiomics features showed significant differences between pN+ and pN0 disease, and none of the radiomics models performed substantially better than random guessing. Hence, CT-based radiomics does not contribute to differentiation between pN+ and pN0 disease in patients with cT2-T4aN0-N1M0 MIBC.

U2 - 10.3390/jpm12050726

DO - 10.3390/jpm12050726

M3 - Article

C2 - PMC9147130

SN - 2075-4426

VL - 12

JO - Journal of personalized medicine

JF - Journal of personalized medicine

IS - 5

ER -

Optimization of Preoperative Lymph Node Staging in Patients with Muscle-Invasive Bladder Cancer Using Radiomics on Computed Tomography

Abstract

Access to Document

Handle.net

Fingerprint

Cite this