Yoshifumi Shimada1,2, Shujiro Okuda3,4, Yu Watanabe5,6, Yosuke Tajima1, Masayuki Nagahashi1, Hiroshi Ichikawa1, Masato Nakano1, Jun Sakata1, Yasumasa Takii7, Takashi Kawasaki8, Kei-Ichi Homma8, Tomohiro Kamori9, Eiji Oki9, Yiwei Ling5, Shiho Takeuchi5,6, Toshifumi Wakai10,11. 1. Division of Digestive and General Surgery, Niigata University Graduate School of Medical and Dental Sciences, 1-757 Asahimachi-dori, Chuo-ku, Niigata, Niigata, 951-8510, Japan. 2. Medical Genome Center, Niigata University Medical and Dental Hospital, Niigata, Japan. 3. Division of Bioinformatics, Niigata University Graduate School of Medical and Dental Sciences, 1-757 Asahimachi-dori, Chuo-ku, Niigata, Niigata, 951-8510, Japan. okd@med.niigata-u.ac.jp. 4. Medical Genome Center, Niigata University Medical and Dental Hospital, Niigata, Japan. okd@med.niigata-u.ac.jp. 5. Division of Bioinformatics, Niigata University Graduate School of Medical and Dental Sciences, 1-757 Asahimachi-dori, Chuo-ku, Niigata, Niigata, 951-8510, Japan. 6. Division of Cancer Genome Informatics, Niigata University Graduate School of Medical and Dental Sciences, Niigata, Japan. 7. Department of Surgery, Niigata Cancer Center Hospital, Niigata, Japan. 8. Department of Pathology, Niigata Cancer Center Hospital, Niigata, Japan. 9. Department of Surgery and Science, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan. 10. Division of Digestive and General Surgery, Niigata University Graduate School of Medical and Dental Sciences, 1-757 Asahimachi-dori, Chuo-ku, Niigata, Niigata, 951-8510, Japan. wakait@med.niigata-u.ac.jp. 11. Medical Genome Center, Niigata University Medical and Dental Hospital, Niigata, Japan. wakait@med.niigata-u.ac.jp.
Abstract
BACKGROUND: Tumor mutational burden-high (TMB-H), which is detected with gene panel testing, is a promising biomarker for immune checkpoint inhibitors (ICIs) in colorectal cancer (CRC). However, in clinical practice, not every patient is tested for TMB-H using gene panel testing. We aimed to identify the histopathological characteristics of TMB-H CRC for efficient selection of patients who should undergo gene panel testing. Moreover, we attempted to develop a convolutional neural network (CNN)-based algorithm to predict TMB-H CRC directly from hematoxylin and eosin (H&E) slides. METHODS: We used two CRC cohorts tested for TMB-H, and whole-slide H&E digital images were obtained from the cohorts. The Japanese CRC (JP-CRC) cohort (N = 201) was evaluated to detect the histopathological characteristics of TMB-H using H&E slides. The JP-CRC cohort and The Cancer Genome Atlas (TCGA) CRC cohort (N = 77) were used to develop a CNN-based TMB-H prediction model from the H&E digital images. RESULTS: Tumor-infiltrating lymphocytes (TILs) were significantly associated with TMB-H CRC (P < 0.001). The area under the curve (AUC) for predicting TMB-H CRC was 0.910. We developed a CNN-based TMB-H prediction model. Validation tests were conducted 10 times using randomly selected slides, and the average AUC for predicting TMB-H slides was 0.934. CONCLUSIONS: TILs, a histopathological characteristic detected with H&E slides, are associated with TMB-H CRC. Our CNN-based model has the potential to predict TMB-H CRC directly from H&E slides, thereby reducing the burden on pathologists. These approaches will provide clinicians with important information about the applications of ICIs at low cost.
BACKGROUND: Tumor mutational burden-high (TMB-H), which is detected with gene panel testing, is a promising biomarker for immune checkpoint inhibitors (ICIs) in colorectal cancer (CRC). However, in clinical practice, not every patient is tested for TMB-H using gene panel testing. We aimed to identify the histopathological characteristics of TMB-H CRC for efficient selection of patients who should undergo gene panel testing. Moreover, we attempted to develop a convolutional neural network (CNN)-based algorithm to predict TMB-H CRC directly from hematoxylin and eosin (H&E) slides. METHODS: We used two CRC cohorts tested for TMB-H, and whole-slide H&E digital images were obtained from the cohorts. The Japanese CRC (JP-CRC) cohort (N = 201) was evaluated to detect the histopathological characteristics of TMB-H using H&E slides. The JP-CRC cohort and The Cancer Genome Atlas (TCGA) CRC cohort (N = 77) were used to develop a CNN-based TMB-H prediction model from the H&E digital images. RESULTS: Tumor-infiltrating lymphocytes (TILs) were significantly associated with TMB-H CRC (P < 0.001). The area under the curve (AUC) for predicting TMB-H CRC was 0.910. We developed a CNN-based TMB-H prediction model. Validation tests were conducted 10 times using randomly selected slides, and the average AUC for predicting TMB-H slides was 0.934. CONCLUSIONS: TILs, a histopathological characteristic detected with H&E slides, are associated with TMB-H CRC. Our CNN-based model has the potential to predict TMB-H CRC directly from H&E slides, thereby reducing the burden on pathologists. These approaches will provide clinicians with important information about the applications of ICIs at low cost.
Authors: Aaron M Goodman; Shumei Kato; Lyudmila Bazhenova; Sandip P Patel; Garrett M Frampton; Vincent Miller; Philip J Stephens; Gregory A Daniels; Razelle Kurzrock Journal: Mol Cancer Ther Date: 2017-08-23 Impact factor: 6.261
Authors: Aaron M Goodman; Ethan S Sokol; Garrett M Frampton; Scott M Lippman; Razelle Kurzrock Journal: Cancer Immunol Res Date: 2019-08-12 Impact factor: 11.151
Authors: Dung T Le; Jennifer N Uram; Hao Wang; Bjarne R Bartlett; Holly Kemberling; Aleksandra D Eyring; Andrew D Skora; Brandon S Luber; Nilofer S Azad; Dan Laheru; Barbara Biedrzycki; Ross C Donehower; Atif Zaheer; George A Fisher; Todd S Crocenzi; James J Lee; Steven M Duffy; Richard M Goldberg; Albert de la Chapelle; Minori Koshiji; Feriyl Bhaijee; Thomas Huebner; Ralph H Hruban; Laura D Wood; Nathan Cuka; Drew M Pardoll; Nickolas Papadopoulos; Kenneth W Kinzler; Shibin Zhou; Toby C Cornish; Janis M Taube; Robert A Anders; James R Eshleman; Bert Vogelstein; Luis A Diaz Journal: N Engl J Med Date: 2015-05-30 Impact factor: 91.245
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
Authors: Janice M Mehnert; Arta M Monjazeb; Johanna M T Beerthuijzen; Deborah Collyar; Larry Rubinstein; Lyndsay N Harris Journal: Clin Cancer Res Date: 2017-09-01 Impact factor: 12.531
Authors: Robert M Samstein; Chung-Han Lee; Alexander N Shoushtari; Matthew D Hellmann; Ronglai Shen; Yelena Y Janjigian; David A Barron; Ahmet Zehir; Emmet J Jordan; Antonio Omuro; Thomas J Kaley; Sviatoslav M Kendall; Robert J Motzer; A Ari Hakimi; Martin H Voss; Paul Russo; Jonathan Rosenberg; Gopa Iyer; Bernard H Bochner; Dean F Bajorin; Hikmat A Al-Ahmadie; Jamie E Chaft; Charles M Rudin; Gregory J Riely; Shrujal Baxi; Alan L Ho; Richard J Wong; David G Pfister; Jedd D Wolchok; Christopher A Barker; Philip H Gutin; Cameron W Brennan; Viviane Tabar; Ingo K Mellinghoff; Lisa M DeAngelis; Charlotte E Ariyan; Nancy Lee; William D Tap; Mrinal M Gounder; Sandra P D'Angelo; Leonard Saltz; Zsofia K Stadler; Howard I Scher; Jose Baselga; Pedram Razavi; Christopher A Klebanoff; Rona Yaeger; Neil H Segal; Geoffrey Y Ku; Ronald P DeMatteo; Marc Ladanyi; Naiyer A Rizvi; Michael F Berger; Nadeem Riaz; David B Solit; Timothy A Chan; Luc G T Morris Journal: Nat Genet Date: 2019-01-14 Impact factor: 38.330
Authors: Ramaswamy Govindan; Li Ding; Malachi Griffith; Janakiraman Subramanian; Nathan D Dees; Krishna L Kanchi; Christopher A Maher; Robert Fulton; Lucinda Fulton; John Wallis; Ken Chen; Jason Walker; Sandra McDonald; Ron Bose; David Ornitz; Donghai Xiong; Ming You; David J Dooling; Mark Watson; Elaine R Mardis; Richard K Wilson Journal: Cell Date: 2012-09-14 Impact factor: 41.582
Authors: Razvan Cristescu; Robin Mogg; Mark Ayers; Andrew Albright; Erin Murphy; Jennifer Yearley; Xinwei Sher; Xiao Qiao Liu; Hongchao Lu; Michael Nebozhyn; Chunsheng Zhang; Jared K Lunceford; Andrew Joe; Jonathan Cheng; Andrea L Webber; Nageatte Ibrahim; Elizabeth R Plimack; Patrick A Ott; Tanguy Y Seiwert; Antoni Ribas; Terrill K McClanahan; Joanne E Tomassini; Andrey Loboda; David Kaufman Journal: Science Date: 2018-10-12 Impact factor: 47.728