Seyedehnafiseh Mirniaharikandehei1, Morteza Heidari2, Gopichandh Danala2, Sivaramakrishnan Lakshmivarahan3, Bin Zheng2. 1. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA. Electronic address: snmirnia@ou.edu. 2. School of Electrical and Computer Engineering, University of Oklahoma, Norman, OK 73019, USA. 3. School of Computer Sciences, University of Oklahoma, Norman, OK 73019, USA.
Abstract
BACKGROUND AND OBJECTIVE: Non-invasively predicting the risk of cancer metastasis before surgery can play an essential role in determining which patients can benefit from neoadjuvant chemotherapy. This study aims to investigate and test the advantages of applying a random projection algorithm to develop and optimize a radiomics-based machine learning model to predict peritoneal metastasis in gastric cancer patients using a small and imbalanced computed tomography (CT) image dataset. METHODS: A retrospective dataset involving CT images acquired from 159 patients is assembled, including 121 and 38 cases with and without peritoneal metastasis, respectively. A computer-aided detection scheme is first applied to segment primary gastric tumor volumes and initially compute 315 image features. Then, five gradients boosting machine (GBM) models embedded with five feature selection methods (including random projection algorithm, principal component analysis, least absolute shrinkage, and selection operator, maximum relevance and minimum redundancy, and recursive feature elimination) along with a synthetic minority oversampling technique, are built to predict the risk of peritoneal metastasis. All GBM models are trained and tested using a leave-one-case-out cross-validation method. RESULTS: Results show that the GBM model embedded with a random projection algorithm yields a significantly higher prediction accuracy (71.2%) than the other four GBM models (p<0.05). The precision, sensitivity, and specificity of this optimal GBM model are 65.78%, 43.10%, and 87.12%, respectively. CONCLUSIONS: This study demonstrates that CT images of the primary gastric tumors contain discriminatory information to predict the risk of peritoneal metastasis, and a random projection algorithm is a promising method to generate optimal feature vector, improving the performance of machine learning based prediction models.
BACKGROUND AND OBJECTIVE: Non-invasively predicting the risk of cancer metastasis before surgery can play an essential role in determining which patients can benefit from neoadjuvant chemotherapy. This study aims to investigate and test the advantages of applying a random projection algorithm to develop and optimize a radiomics-based machine learning model to predict peritoneal metastasis in gastric cancer patients using a small and imbalanced computed tomography (CT) image dataset. METHODS: A retrospective dataset involving CT images acquired from 159 patients is assembled, including 121 and 38 cases with and without peritoneal metastasis, respectively. A computer-aided detection scheme is first applied to segment primary gastric tumor volumes and initially compute 315 image features. Then, five gradients boosting machine (GBM) models embedded with five feature selection methods (including random projection algorithm, principal component analysis, least absolute shrinkage, and selection operator, maximum relevance and minimum redundancy, and recursive feature elimination) along with a synthetic minority oversampling technique, are built to predict the risk of peritoneal metastasis. All GBM models are trained and tested using a leave-one-case-out cross-validation method. RESULTS: Results show that the GBM model embedded with a random projection algorithm yields a significantly higher prediction accuracy (71.2%) than the other four GBM models (p<0.05). The precision, sensitivity, and specificity of this optimal GBM model are 65.78%, 43.10%, and 87.12%, respectively. CONCLUSIONS: This study demonstrates that CT images of the primary gastric tumors contain discriminatory information to predict the risk of peritoneal metastasis, and a random projection algorithm is a promising method to generate optimal feature vector, improving the performance of machine learning based prediction models.
Authors: Bin Zheng; Claudia Mello-Thoms; Xiao-Hui Wang; Gordon S Abrams; Jules H Sumkin; Denise M Chough; Marie A Ganott; Amy Lu; David Gur Journal: Acad Radiol Date: 2007-08 Impact factor: 3.173
Authors: F Coccolini; E Cotte; O Glehen; M Lotti; E Poiasina; F Catena; Y Yonemura; L Ansaloni Journal: Eur J Surg Oncol Date: 2013-11-05 Impact factor: 4.424
Authors: Alberto Biondi; Maria C Lirosi; Domenico D'Ugo; Valeria Fico; Riccardo Ricci; Francesco Santullo; Antonia Rizzuto; Ferdinando Cm Cananzi; Roberto Persiani Journal: World J Gastrointest Oncol Date: 2015-12-15
Authors: Philippe Lambin; Emmanuel Rios-Velazquez; Ralph Leijenaar; Sara Carvalho; Ruud G P M van Stiphout; Patrick Granton; Catharina M L Zegers; Robert Gillies; Ronald Boellard; André Dekker; Hugo J W L Aerts Journal: Eur J Cancer Date: 2012-01-16 Impact factor: 9.162
Authors: Gopichandh Danala; Masoom Desai; Bappaditya Ray; Morteza Heidari; Sai Kiran R Maryada; Calin I Prodan; Bin Zheng Journal: Ann Biomed Eng Date: 2022-02-02 Impact factor: 3.934