Yun Bian1, Yan Fang Liu2, Hui Jiang2, Yinghao Meng1, Fang Liu1, Kai Cao1, Hao Zhang1, Xu Fang1, Jing Li1, Jieyu Yu1, Xiaochen Feng1, Qi Li1, Li Wang1, Jianping Lu1, Chengwei Shao3,4. 1. Department of Radiology, Changhai Hospital, Navy Medical University, Shanghai, 200434, China. 2. Department of Pathology, Changhai Hospital, Navy Medical University, Shanghai, China. 3. Department of Radiology, Changhai Hospital, Navy Medical University, Shanghai, 200434, China. chengweishaoch@163.com. 4. Department of Radiology, Changhai Hospital, 168 Changhai Road, Shanghai, 200433, China. chengweishaoch@163.com.
Abstract
OBJECTIVE: To develop and validate a machine learning classifier based on magnetic resonance imaging (MRI), for the preoperative prediction of tumor-infiltrating lymphocytes (TILs) in patients with pancreatic ductal adenocarcinoma (PDAC). MATERIALS AND METHODS: In this retrospective study, 156 patients with PDAC underwent MR scan and surgical resection. The expression of CD4, CD8 and CD20 was detected and quantified using immunohistochemistry, and TILs score was achieved by Cox regression model. All patients were divided into TILs score-low and TILs score-high groups. The least absolute shrinkage and selection operator method and the extreme gradient boosting (XGBoost) were used to select the features and to construct a prediction model. The performance of the models was assessed using the training cohort (116 patients) and the validation cohort (40 patients), and decision curve analysis (DCA) was applied for clinical use. RESULTS: The XGBoost prediction model showed good discrimination in the training (AUC 0.86; 95% CI 0.79-0.93) and validation sets (AUC 0.79; 95% CI 0.64-0.93). The sensitivity, specificity, and accuracy for the training set were 86.67%, 75.00%, and 0.81, respectively, whereas those for the validation set were 84.21%, 66.67%, and 0.75, respectively. Decision curve analysis indicated the clinical usefulness of the XGBoost classifier. CONCLUSION: The model constructed by XGBoost could predict PDAC TILs and may aid clinical decision making for immune therapy.
OBJECTIVE: To develop and validate a machine learning classifier based on magnetic resonance imaging (MRI), for the preoperative prediction of tumor-infiltrating lymphocytes (TILs) in patients with pancreatic ductal adenocarcinoma (PDAC). MATERIALS AND METHODS: In this retrospective study, 156 patients with PDAC underwent MR scan and surgical resection. The expression of CD4, CD8 and CD20 was detected and quantified using immunohistochemistry, and TILs score was achieved by Cox regression model. All patients were divided into TILs score-low and TILs score-high groups. The least absolute shrinkage and selection operator method and the extreme gradient boosting (XGBoost) were used to select the features and to construct a prediction model. The performance of the models was assessed using the training cohort (116 patients) and the validation cohort (40 patients), and decision curve analysis (DCA) was applied for clinical use. RESULTS: The XGBoost prediction model showed good discrimination in the training (AUC 0.86; 95% CI 0.79-0.93) and validation sets (AUC 0.79; 95% CI 0.64-0.93). The sensitivity, specificity, and accuracy for the training set were 86.67%, 75.00%, and 0.81, respectively, whereas those for the validation set were 84.21%, 66.67%, and 0.75, respectively. Decision curve analysis indicated the clinical usefulness of the XGBoost classifier. CONCLUSION: The model constructed by XGBoost could predict PDAC TILs and may aid clinical decision making for immune therapy.
Entities:
Keywords:
CD4 positive T lymphocytes; CD8 positive T lymphocytes; Carcinoma; Magnetic resonance imaging; Pancreatic neoplasm; Radiomics; Tumor microenvironment
Authors: Caroline Robert; Georgina V Long; Benjamin Brady; Caroline Dutriaux; Michele Maio; Laurent Mortier; Jessica C Hassel; Piotr Rutkowski; Catriona McNeil; Ewa Kalinka-Warzocha; Kerry J Savage; Micaela M Hernberg; Celeste Lebbé; Julie Charles; Catalin Mihalcioiu; Vanna Chiarion-Sileni; Cornelia Mauch; Francesco Cognetti; Ana Arance; Henrik Schmidt; Dirk Schadendorf; Helen Gogas; Lotta Lundgren-Eriksson; Christine Horak; Brian Sharkey; Ian M Waxman; Victoria Atkinson; Paolo A Ascierto Journal: N Engl J Med Date: 2014-11-16 Impact factor: 91.245
Authors: Thierry Conroy; Françoise Desseigne; Marc Ychou; Olivier Bouché; Rosine Guimbaud; Yves Bécouarn; Antoine Adenis; Jean-Luc Raoul; Sophie Gourgou-Bourgade; Christelle de la Fouchardière; Jaafar Bennouna; Jean-Baptiste Bachet; Faiza Khemissa-Akouz; Denis Péré-Vergé; Catherine Delbaldo; Eric Assenat; Bruno Chauffert; Pierre Michel; Christine Montoto-Grillot; Michel Ducreux Journal: N Engl J Med Date: 2011-05-12 Impact factor: 91.245
Authors: H A Burris; M J Moore; J Andersen; M R Green; M L Rothenberg; M R Modiano; M C Cripps; R K Portenoy; A M Storniolo; P Tarassoff; R Nelson; F A Dorr; C D Stephens; D D Von Hoff Journal: J Clin Oncol Date: 1997-06 Impact factor: 44.544
Authors: Leisha A Emens; Paolo A Ascierto; Phillip K Darcy; Sandra Demaria; Alexander M M Eggermont; William L Redmond; Barbara Seliger; Francesco M Marincola Journal: Eur J Cancer Date: 2017-06-15 Impact factor: 9.162
Authors: Nigel B Jamieson; Mohamed Mohamed; Karin A Oien; Alan K Foulis; Euan J Dickson; Clem W Imrie; C Ross Carter; Colin J McKay; Donald C McMillan Journal: Ann Surg Oncol Date: 2012-05-04 Impact factor: 5.344
Authors: Julie R Brahmer; Scott S Tykodi; Laura Q M Chow; Wen-Jen Hwu; Suzanne L Topalian; Patrick Hwu; Charles G Drake; Luis H Camacho; John Kauh; Kunle Odunsi; Henry C Pitot; Omid Hamid; Shailender Bhatia; Renato Martins; Keith Eaton; Shuming Chen; Theresa M Salay; Suresh Alaparthy; Joseph F Grosso; Alan J Korman; Susan M Parker; Shruti Agrawal; Stacie M Goldberg; Drew M Pardoll; Ashok Gupta; Jon M Wigginton Journal: N Engl J Med Date: 2012-06-02 Impact factor: 91.245