A quantitative histogram-based approach to predict treatment outcome for Soft Tissue Sarcomas using pre- and post-treatment MRIs

The goal of this paper is to show the use of data mining techniques to predict the Soft Tissue Sarcoma (STS) tumor progression. STS are cancers which occur in different parts of the body such as fat, muscle and nerves. The lack of effective treatments and the difficulty in predicting treatment response make them challenging for physicians, and has likely slowed the evolution of new therapeutic agents. To design a prediction model, we propose a novel quantitative histogram-based method to analyze the difference in histograms obtained from pre and post-treatment multi-modality magnetic resonance images. Here, we used Radiomics techniques as a non-invasive method for outcome prediction. This study could help physicians identify distinctive patterns within each tumor to find more patient-specific treatments. We demonstrated the new approach on two practical tasks: tumor recurrence prediction (metastasis) and rate of necrosis prediction. Our learned model shows 87.79% prediction accuracy for metastasis with a 0.73 AUC and 82.22% prediction accuracy for necrosis with a 0.65 AUC.

[1]  Shyam Visweswaran,et al.  Measuring Stability of Feature Selection in Biomedical Datasets , 2009, AMIA.

[2]  L. Pusztai,et al.  Cancer heterogeneity: implications for targeted therapeutics , 2013, British Journal of Cancer.

[3]  A. Skubitz,et al.  Identification of heterogeneity among soft tissue sarcomas by gene expression profiles from different tumors , 2008, Journal of Translational Medicine.

[4]  H. Hassan,et al.  Primary retroperitoneal synovial sarcoma in CT and MRI , 2010, Urology annals.

[5]  Eric Stindel,et al.  Prognosis classification in glioblastoma multiforme using multimodal MRI derived heterogeneity textural features: impact of pre-processing choices , 2016, SPIE Medical Imaging.

[6]  Abhijit J Chaudhari,et al.  Semi-automated volumetric quantification of tumor necrosis in soft tissue sarcoma using contrast-enhanced MRI. , 2012, Anticancer research.

[7]  Mitsuo Ochi,et al.  Prognostic significance of (18)F-FDG PET at diagnosis in patients with soft tissue sarcoma and bone sarcoma; systematic review and meta-analysis. , 2016, European journal of cancer.

[8]  Robert J. Gillies,et al.  Decoding brain cancer dynamics: a quantitative histogram-based approach using temporal MRI , 2015, Medical Imaging.

[9]  Eric Stindel,et al.  A framework for multimodal imaging-based prognostic model building: Preliminary study on multimodal MRI in Glioblastoma Multiforme , 2015 .

[10]  Jan Sijbers,et al.  Machine learning study of several classifiers trained with texture analysis features to differentiate benign from malignant soft‐tissue tumors in T1‐MRI images , 2010, Journal of magnetic resonance imaging : JMRI.

[11]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[12]  Baishali Chaudhury,et al.  Heterogeneity in intratumoral regions with rapid gadolinium washout correlates with estrogen receptor status and nodal metastasis , 2015, Journal of magnetic resonance imaging : JMRI.

[13]  Teruaki Oka,et al.  Cell nucleus segmentation of skin tumor using image processing , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[14]  Kevin Leder,et al.  Minimizing metastatic risk in radiotherapy fractionation schedules , 2013, Physics in medicine and biology.

[15]  R. Gillies,et al.  Quantitative imaging in cancer evolution and ecology. , 2013, Radiology.

[16]  I. El Naqa,et al.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities , 2015, Physics in medicine and biology.

[17]  Robert J. Gillies,et al.  Texture Feature Analysis to Predict Metastatic and Necrotic Soft Tissue Sarcomas , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[18]  Kevin Leder,et al.  Optimal radiotherapy dose schedules under parametric uncertainty , 2016, Physics in medicine and biology.

[19]  Laurel Beckett,et al.  Comparison of two-dimensional and three-dimensional iterative watershed segmentation methods in hepatic tumor volumetrics. , 2008, Medical physics.

[20]  Mukesh A. Zaveri,et al.  Region Based Image Fusion for Detection of Ewing Sarcoma , 2009, 2009 Seventh International Conference on Advances in Pattern Recognition.

[21]  Robert J. Gillies,et al.  Developing a classifier model for lung tumors in CT-scan images , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[22]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[23]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[24]  D. Longo,et al.  Tumor heterogeneity and personalized medicine. , 2012, The New England journal of medicine.

[25]  Robert J. Gillies,et al.  Prediction of treatment outcome in soft tissue sarcoma based on radiologically defined habitats , 2015, Medical Imaging.

[26]  Mark A. Hall,et al.  Correlation-based Feature Selection for Machine Learning , 2003 .

[27]  G. Parker,et al.  Imaging Intratumor Heterogeneity: Role in Therapy Response, Resistance, and Clinical Outcome , 2014, Clinical Cancer Research.

[28]  Urvashi Surti,et al.  Correlation of Classic and Molecular Cytogenetic Alterations in Soft-Tissue Sarcomas: Analysis of 46 Tumors With Emphasis on Adipocytic Tumors and Synovial Sarcoma , 2017, Applied immunohistochemistry & molecular morphology : AIMM.

[29]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[30]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[31]  Lawrence O. Hall,et al.  Exploring Brain Tumor Heterogeneity for Survival Time Prediction , 2014, 2014 22nd International Conference on Pattern Recognition.

[32]  F. Turkheimer,et al.  A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities , 2015 .

[33]  Robert J. Gillies,et al.  Predicting Outcomes of Nonsmall Cell Lung Cancer Using CT Image Features , 2014, IEEE Access.

[34]  K. Premalatha,et al.  A Survey on Feature Selection Methods in Microarray Gene Expression Data for Cancer Classification , 2017 .