Jin Cheng1, Jingwei Wei2,3,4, Tong Tong5, Weiqi Sheng6, Yinli Zhang7, Yuqi Han2,3,4, Dongsheng Gu2,3,4, Nan Hong1, Yingjiang Ye8, Jie Tian9,10,11,12,13, Yi Wang14. 1. Department of Radiology, Peking University People's Hospital, Beijing, China. 2. Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China. 3. Beijing Key Laboratory of Molecular Imaging, Beijing, China. 4. University of Chinese Academy of Sciences, Beijing, China. 5. Department of Radiology, Department of Oncology, Fudan University Shanghai Cancer Center, Shanghai Medical College, Fudan University, Shanghai, China. 6. Department of Pathology, Department of Oncology, Fudan University Shanghai Cancer Center, Shanghai Medical College, Fudan University, Shanghai, China. 7. Department of Pathology, Peking University People's Hospital, Beijing, China. 8. Department of Gastrointestinal Surgery, Peking University People' Hospital, Beijing, China. 9. Key Laboratory of Molecular Imaging, Institute of Automation, Chinese Academy of Sciences, Beijing, China. tian@ieee.org. 10. Beijing Key Laboratory of Molecular Imaging, Beijing, China. tian@ieee.org. 11. University of Chinese Academy of Sciences, Beijing, China. tian@ieee.org. 12. Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine, Beihang University, Beijing, China. tian@ieee.org. 13. Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education, School of Life Science and Technology, Xidian University, Xi'an, Shaanxi, China. tian@ieee.org. 14. Department of Radiology, Peking University People's Hospital, Beijing, China. wangyi@pkuph.edu.cn.
Abstract
OBJECTIVES: To predict histopathologic growth patterns (HGPs) in colorectal liver metastases (CRLMs) with a noninvasive radiomics model. METHODS: Patients with chemotherapy-naive CRLMs who underwent abdominal contrast-enhanced multidetector CT (MDCT) followed by partial hepatectomy between January 2007 and January 2019 from two institutions were included in this retrospective study. Hematoxylin- and eosin-stained histopathologic sections of CRLMs were reviewed, with HGPs defined according to international consensus. Lesions were divided into training and validation datasets based on patients' sources. Radiomic features were extracted from pre- and post-contrast (arterial and portal venous) phase MDCT images, with review focusing on the segmented tumor-liver interface zones of CRLMs. Minimum redundancy maximum relevance and decision tree methods were used for radiomics modeling. Multivariable logistic regression analyses and ROC curves were used to assess the predictive performance of these models in predicting HGP types. RESULTS: A total of 126 CRLMs with histopathologic-demonstrated desmoplastic (n = 68) or replacement (n = 58) HGPs were assessed. The radiomics signature consisted of 20 features of each phase selected. The 3 phases fused radiomics signature demonstrated the best predictive performance in distinguishing between replacement and desmoplastic HGPs (AUCs of 0.926 and 0.939 in the training and external validation cohorts, respectively). The clinical-radiomics combined model showed good discrimination (C-indices of 0.941 and 0.833 in the training and external validation cohorts, respectively). CONCLUSIONS: A radiomics model derived from MDCT images may effectively predict the HGP of CRLMs, thus providing a basis for prognostic stratification and therapeutic decision-making.
OBJECTIVES: To predict histopathologic growth patterns (HGPs) in colorectal liver metastases (CRLMs) with a noninvasive radiomics model. METHODS:Patients with chemotherapy-naive CRLMs who underwent abdominal contrast-enhanced multidetector CT (MDCT) followed by partial hepatectomy between January 2007 and January 2019 from two institutions were included in this retrospective study. Hematoxylin- and eosin-stained histopathologic sections of CRLMs were reviewed, with HGPs defined according to international consensus. Lesions were divided into training and validation datasets based on patients' sources. Radiomic features were extracted from pre- and post-contrast (arterial and portal venous) phase MDCT images, with review focusing on the segmented tumor-liver interface zones of CRLMs. Minimum redundancy maximum relevance and decision tree methods were used for radiomics modeling. Multivariable logistic regression analyses and ROC curves were used to assess the predictive performance of these models in predicting HGP types. RESULTS: A total of 126 CRLMs with histopathologic-demonstrated desmoplastic (n = 68) or replacement (n = 58) HGPs were assessed. The radiomics signature consisted of 20 features of each phase selected. The 3 phases fused radiomics signature demonstrated the best predictive performance in distinguishing between replacement and desmoplastic HGPs (AUCs of 0.926 and 0.939 in the training and external validation cohorts, respectively). The clinical-radiomics combined model showed good discrimination (C-indices of 0.941 and 0.833 in the training and external validation cohorts, respectively). CONCLUSIONS: A radiomics model derived from MDCT images may effectively predict the HGP of CRLMs, thus providing a basis for prognostic stratification and therapeutic decision-making.
Authors: L Viganò; B Branciforte; V Laurenti; G Costa; F Procopio; M Cimino; D Del Fabbro; L Di Tommaso; G Torzilli Journal: Ann Surg Oncol Date: 2022-06-10 Impact factor: 4.339
Authors: Emily Latacz; Diederik Höppener; Ali Bohlok; Vincent Donckier; Peter M Siegel; Raymond Barnhill; Marco Gerling; Cornelis Verhoef; Peter B Vermeulen; Sophia Leduc; Sébastien Tabariès; Carlos Fernández Moro; Claire Lugassy; Hanna Nyström; Béla Bozóky; Giuseppe Floris; Natalie Geyer; Pnina Brodt; Laura Llado; Laura Van Mileghem; Maxim De Schepper; Ali W Majeed; Anthoula Lazaris; Piet Dirix; Qianni Zhang; Stéphanie K Petrillo; Sophie Vankerckhove; Ines Joye; Yannick Meyer; Alexander Gregorieff; Nuria Ruiz Roig; Fernando Vidal-Vanaclocha; Larsimont Denis; Rui Caetano Oliveira; Peter Metrakos; Dirk J Grünhagen; Iris D Nagtegaal; David G Mollevi; William R Jarnagin; Michael I D'Angelica; Andrew R Reynolds; Michail Doukas; Christine Desmedt; Luc Dirix Journal: Br J Cancer Date: 2022-06-01 Impact factor: 9.075
Authors: Natally Horvat; Joao Miranda; Maria El Homsi; Jacob J Peoples; Niamh M Long; Amber L Simpson; Richard K G Do Journal: Abdom Radiol (NY) Date: 2021-11-26
Authors: Raymond Barnhill; Pieter-Jan van Dam; Peter Vermeulen; Gabriel Champenois; André Nicolas; Robert V Rawson; James S Wilmott; John F Thompson; Georgina V Long; Nathalie Cassoux; Sergio Roman-Roman; Klaus J Busam; Richard A Scolyer; Alexander J Lazar; Claire Lugassy Journal: J Pathol Clin Res Date: 2020-04-18
Authors: Gemma Garcia-Vicién; Artur Mezheyeuski; María Bañuls; Núria Ruiz-Roig; David G Molleví Journal: Int J Mol Sci Date: 2021-02-03 Impact factor: 5.923
Authors: Diederik J Höppener; Boris Galjart; Pieter M H Nierop; Florian E Buisman; Eric P van der Stok; Robert R J Coebergh van den Braak; Martin J van Amerongen; Vinod P Balachandran; William R Jarnagin; T Peter Kingham; Michail Doukas; Jinru Shia; Iris D Nagtegaal; Peter B Vermeulen; Bas Groot Koerkamp; Dirk J Grünhagen; Johannes H W de Wilt; Michael I D'Angelica; Cornelis Verhoef Journal: JNCI Cancer Spectr Date: 2021-03-21