Ji Young Lee1, Kwang-Sig Lee2, Bo Kyoung Seo3, Kyu Ran Cho4, Ok Hee Woo5, Sung Eun Song4, Eun-Kyung Kim6, Hye Yoon Lee7, Jung Sun Kim8, Jaehyung Cha9. 1. Department of Radiology, Ilsan Paik Hospital, Inje University College of Medicine, 170 Juhwa-ro, Ilsanseo-gu, Goyang, Gyeonggi-do, 10380, Republic of Korea. 2. AI Center, Korea University Anam Hospital, Korea University College of Medicine, 73 Inchon-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea. 3. Department of Radiology, Korea University Ansan Hospital, Korea University College of Medicine, 123 Jeokgeum-ro, Danwon-gu, Ansan-si, Gyeonggi-do, 15355, Republic of Korea. seoboky@korea.ac.kr. 4. Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, 73, Goryeodae-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea. 5. Department of Radiology, Korea University Guro Hospital, Korea University College of Medicine, 148 Gurodong-ro, Guro-gu, Seoul, 08308, Republic of Korea. 6. Department of Radiology, Yongin Severance Hospital, Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 363, Dongbaekjukjeon-daero, Giheung-gu, Yongin-si, Gyeonggi-do, 16995, Republic of Korea. 7. Division of Breast and Endocrine Surgery, Department of Surgery, Korea University Ansan Hospital, Korea University College of Medicine, Gyeonggi-do, Republic of Korea. 8. Division of Hematology/Oncology, Department of Internal Medicine, Korea University Ansan Hospital, Korea University College of Medicine, Gyeonggi-do, Republic of Korea. 9. Medical Science Research Center, Korea University Ansan Hospital, Korea University College of Medicine, Gyeonggi-do, Republic of Korea.
Abstract
OBJECTIVES: To investigate machine learning approaches for radiomics-based prediction of prognostic biomarkers and molecular subtypes of breast cancer using quantification of tumor heterogeneity and angiogenesis properties on magnetic resonance imaging (MRI). METHODS: This prospective study examined 291 invasive cancers in 288 patients who underwent breast MRI at 3 T before treatment between May 2017 and July 2019. Texture and perfusion analyses were performed and a total of 160 parameters for each cancer were extracted. Relationships between MRI parameters and prognostic biomarkers were analyzed using five machine learning algorithms. Each model was built using only texture features, only perfusion features, or both. Model performance was compared using the area under the receiver-operating characteristic curve (AUC) and the DeLong method, and the importance of MRI parameters in prediction was derived. RESULTS: Texture parameters were associated with the status of hormone receptors, human epidermal growth factor receptor 2, and Ki67, tumor size, grade, and molecular subtypes (p < 0.002). Perfusion parameters were associated with the status of hormone receptors and Ki67, grade, and molecular subtypes (p < 0.003). The random forest model integrating texture and perfusion parameters showed the highest performance (AUC = 0.75). The performance of the random forest model was the best with a special scale filter of 0 (AUC = 0.80). The important parameters for prediction were texture irregularity (entropy) and relative extracellular extravascular space (Ve). CONCLUSIONS: Radiomic machine learning that integrates tumor heterogeneity and angiogenesis properties on MRI has the potential to noninvasively predict prognostic factors of breast cancer. KEY POINTS: • Machine learning, integrating tumor heterogeneity and angiogenesis properties on MRI, can be applied to predict prognostic biomarkers and molecular subtypes in breast cancer. • The random forest model showed the best predictive performance among the five machine learning models (logistic regression, decision tree, naïve Bayes, random forest, and artificial neural network). • The most important MRI parameters for predicting prognostic factors in breast cancer were texture irregularity (entropy) among texture parameters and relative extracellular extravascular space (Ve) among perfusion parameters.
OBJECTIVES: To investigate machine learning approaches for radiomics-based prediction of prognostic biomarkers and molecular subtypes of breast cancer using quantification of tumor heterogeneity and angiogenesis properties on magnetic resonance imaging (MRI). METHODS: This prospective study examined 291 invasive cancers in 288 patients who underwent breast MRI at 3 T before treatment between May 2017 and July 2019. Texture and perfusion analyses were performed and a total of 160 parameters for each cancer were extracted. Relationships between MRI parameters and prognostic biomarkers were analyzed using five machine learning algorithms. Each model was built using only texture features, only perfusion features, or both. Model performance was compared using the area under the receiver-operating characteristic curve (AUC) and the DeLong method, and the importance of MRI parameters in prediction was derived. RESULTS: Texture parameters were associated with the status of hormone receptors, human epidermal growth factor receptor 2, and Ki67, tumor size, grade, and molecular subtypes (p < 0.002). Perfusion parameters were associated with the status of hormone receptors and Ki67, grade, and molecular subtypes (p < 0.003). The random forest model integrating texture and perfusion parameters showed the highest performance (AUC = 0.75). The performance of the random forest model was the best with a special scale filter of 0 (AUC = 0.80). The important parameters for prediction were texture irregularity (entropy) and relative extracellular extravascular space (Ve). CONCLUSIONS: Radiomic machine learning that integrates tumor heterogeneity and angiogenesis properties on MRI has the potential to noninvasively predict prognostic factors of breast cancer. KEY POINTS: • Machine learning, integrating tumor heterogeneity and angiogenesis properties on MRI, can be applied to predict prognostic biomarkers and molecular subtypes in breast cancer. • The random forest model showed the best predictive performance among the five machine learning models (logistic regression, decision tree, naïve Bayes, random forest, and artificial neural network). • The most important MRI parameters for predicting prognostic factors in breast cancer were texture irregularity (entropy) among texture parameters and relative extracellular extravascular space (Ve) among perfusion parameters.
Authors: Garry Choy; Omid Khalilzadeh; Mark Michalski; Synho Do; Anthony E Samir; Oleg S Pianykh; J Raymond Geis; Pari V Pandharipande; James A Brink; Keith J Dreyer Journal: Radiology Date: 2018-06-26 Impact factor: 11.105
Authors: Fergus Davnall; Connie S P Yip; Gunnar Ljungqvist; Mariyah Selmi; Francesca Ng; Bal Sanghera; Balaji Ganeshan; Kenneth A Miles; Gary J Cook; Vicky Goh Journal: Insights Imaging Date: 2012-10-24
Authors: Melissa M Chen; Admir Terzic; Anton S Becker; Jason M Johnson; Carol C Wu; Max Wintermark; Christoph Wald; Jia Wu Journal: Eur J Radiol Open Date: 2022-09-29