DataSheet_1_A Bounding Box-Based Radiomics Model for Detecting Occult Peritoneal Metastasis in Advanced Gastric Cancer: A Multicenter Study.pdf
To develop a bounding box (BBOX)-based radiomics model for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC) patients.
Materials and Methods599 AGC patients from 3 centers were retrospectively enrolled and were divided into training, validation, and testing cohorts. The minimum circumscribed rectangle of the ROIs for the largest tumor area (R_BBOX), the nonoverlapping area between the tumor and R_BBOX (peritumoral area; PERI) and the smallest rectangle that could completely contain the tumor determined by a radiologist (M_BBOX) were used as inputs to extract radiomic features. Multivariate logistic regression was used to construct a radiomics model to estimate the preoperative probability of OPM in AGC patients.
ResultsThe M_BBOX model was not significantly different from R_BBOX in the validation cohort [AUC: M_BBOX model 0.871 (95% CI, 0.814–0.940) vs. R_BBOX model 0.873 (95% CI, 0.820–0.940); p = 0.937]. M_BBOX was selected as the final radiomics model because of its extremely low annotation cost and superior OPM discrimination performance (sensitivity of 85.7% and specificity of 82.8%) over the clinical model, and this radiomics model showed comparable diagnostic efficacy in the testing cohort.
ConclusionsThe BBOX-based radiomics could serve as a simpler reliable and powerful tool for the preoperative diagnosis of OPM in AGC patients. And M_BBOX-based radiomics is simpler and less time consuming.
History
References
- https://doi.org//10.3322/caac.21492
- https://doi.org//10.1001/archsurg.142.2.143
- https://doi.org//10.1016/j.ejso.2013.10.019
- https://doi.org//10.3892/ol.2017.7442
- https://doi.org//10.1002/ijc.28373
- https://doi.org//10.1002/ags3.12060
- https://doi.org//10.1093/jjco/hyt157
- https://doi.org//10.1093/jjco/hyw153
- https://doi.org//10.1001/jamasurg.2019.0153
- https://doi.org//10.1093/annonc/mdw350
- https://doi.org//10.1148/radiol.2532082272
- https://doi.org//10.1016/j.crad.2012.07.015
- https://doi.org//10.1001/jamanetworkopen.2020.32269
- https://doi.org//10.3389/fonc.2020.601869
- https://doi.org//10.1007/s00330-016-4540-y
- https://doi.org//10.1016/j.ejrad.2017.02.043
- https://doi.org//10.1007/s00330-017-4881-1
- https://doi.org//10.1016/j.crad.2018.03.005
- https://doi.org//10.1016/j.ejrad.2017.04.007
- https://doi.org//10.21037/qims.2018.05.01
- https://doi.org//10.1007/s00330-019-06368-5
- https://doi.org//10.1371/journal.pone.0194755
- https://doi.org//10.1093/annonc/mdz001
- https://doi.org//10.1109/TBME.2020.2969608
- https://doi.org//10.1016/j.compmedimag.2011.06.001
- https://doi.org//10.1002/jmri.26981
- https://doi.org//10.1007/s10278-019-00193-4
- https://doi.org//10.3390/biom10081123
- https://doi.org//10.1186/s40644-020-00358-3
- https://doi.org//10.1001/jamanetworkopen.2020.15927
- https://doi.org//10.3389/fonc.2020.552270
- https://doi.org//10.1016/j.annonc.2020.03.295
- https://doi.org//10.1158/0008-5472.CAN-17-0339
- https://doi.org//10.1148/radiol.2020191145
- https://doi.org//10.1111/j.1365-2125.1987.tb03030.x
- https://doi.org//10.1148/radiology.143.1.7063747
- https://doi.org//10.1002/jmri.25661
- https://doi.org//10.1186/s13058-017-0846-1
- https://doi.org//10.1007/s00330-019-06084-0
- https://doi.org//10.1200/JCO.1990.8.9.1457
- https://doi.org//10.1186/1472-6890-13-31
- https://doi.org//10.1186/s12885-015-1501-9
- https://doi.org//10.1245/s10434-016-5409-7
- https://doi.org//10.1016/j.ejso.2016.06.401
- https://doi.org//10.1186/s40880-019-0349-9
CC BY 4.0