Eoghan R Malone1, Hao-Wen Sim1, Audrius Stundzia2, Sacha Pierre3, Ur Metser4, Martin O'Malley3, Adrian G Sacher1,5, Srikala S Sridhar1,5, Aaron R Hansen1,5. 1. Division of Medical Oncology and Hematology, Princess Margaret Cancer Centre, UHN, Toronto, ON, Canada. 2. Tomographix IP Ltd., Toronto, ON, Canada. 3. Division of Abdominal Imaging, Joint Department of Medical Imaging, University of Toronto, Toronto, ON, Canada. 4. Division of Molecular Imaging, Joint Department of Medical Imaging, University of Toronto, Toronto, ON, Canada. 5. Department of Medicine, University of Toronto, Toronto, ON, Canada.
Abstract
INTRODUCTION: The anti-programmed cell death protein-1 (PD-1) immune checkpoint inhibitor nivolumab is currently approved for the treatment of patients with metastatic renal cell carcinoma (mRCC); approximately 25% of patients respond. We hypothesized that we could identify a biomarker of response using radiomics to train a machine learning classifier to predict nivolumab response outcomes. METHODS: Patients with mRCC of different histologies treated with nivolumab in a single institution between 2013 and 2017 were retrospectively identified. Patients were labelled as responders (complete response [CR]/partial response [PR]/durable stable disease [SD]) or non-responders based on investigator tumor assessment using RECIST 1.1 criteria. For each patient, lesions were contoured from pre-treatment and first post-treatment computed tomography (CT) scans. This information was used to train a radial basis function support vector machine classifier to learn a prediction rule to distinguish responders from non-responders. The classifier was internally validated by a 10-fold nested cross-validation. RESULTS: Thirty-seven patients were identified; 27 (73%) met the inclusion criteria. One hundred and four lesions were contoured from these 27 patients. The median patient age was 56 years, 78% were male, 89% had clear-cell histology, 89% had prior nephrectomy, and 89% had prior systemic therapy. There were 19 responders vs. eight non-responders. The lesions selected were lymph nodes (60%), lung metastases (23%), and renal/adrenal metastases (17%). For the classifier trained on the baseline CT scans, 69% accuracy was achieved. For the classifier trained on the first post-treatment CT scans, 66% accuracy was achieved. CONCLUSIONS: The set of radiomic signatures was found to have limited ability to discriminate nivolumab responders from non-responders. The use of novel texture features (two-point correlation measure, two-point cluster measure, and minimum spanning tree measure) did not improve performance.
INTRODUCTION: The anti-programmed cell death protein-1 (PD-1) immune checkpoint inhibitor nivolumab is currently approved for the treatment of patients with metastatic renal cell carcinoma (mRCC); approximately 25% of patients respond. We hypothesized that we could identify a biomarker of response using radiomics to train a machine learning classifier to predict nivolumab response outcomes. METHODS: Patients with mRCC of different histologies treated with nivolumab in a single institution between 2013 and 2017 were retrospectively identified. Patients were labelled as responders (complete response [CR]/partial response [PR]/durable stable disease [SD]) or non-responders based on investigator tumor assessment using RECIST 1.1 criteria. For each patient, lesions were contoured from pre-treatment and first post-treatment computed tomography (CT) scans. This information was used to train a radial basis function support vector machine classifier to learn a prediction rule to distinguish responders from non-responders. The classifier was internally validated by a 10-fold nested cross-validation. RESULTS: Thirty-seven patients were identified; 27 (73%) met the inclusion criteria. One hundred and four lesions were contoured from these 27 patients. The median patient age was 56 years, 78% were male, 89% had clear-cell histology, 89% had prior nephrectomy, and 89% had prior systemic therapy. There were 19 responders vs. eight non-responders. The lesions selected were lymph nodes (60%), lung metastases (23%), and renal/adrenal metastases (17%). For the classifier trained on the baseline CT scans, 69% accuracy was achieved. For the classifier trained on the first post-treatment CT scans, 66% accuracy was achieved. CONCLUSIONS: The set of radiomic signatures was found to have limited ability to discriminate nivolumab responders from non-responders. The use of novel texture features (two-point correlation measure, two-point cluster measure, and minimum spanning tree measure) did not improve performance.
Authors: Radka Stoyanova; Mandeep Takhar; Yohann Tschudi; John C Ford; Gabriel Solórzano; Nicholas Erho; Yoganand Balagurunathan; Sanoj Punnen; Elai Davicioni; Robert J Gillies; Alan Pollack Journal: Transl Cancer Res Date: 2016-08 Impact factor: 1.241
Authors: Brian I Rini; Elizabeth R Plimack; Viktor Stus; Rustem Gafanov; Robert Hawkins; Dmitry Nosov; Frédéric Pouliot; Boris Alekseev; Denis Soulières; Bohuslav Melichar; Ihor Vynnychenko; Anna Kryzhanivska; Igor Bondarenko; Sergio J Azevedo; Delphine Borchiellini; Cezary Szczylik; Maurice Markus; Raymond S McDermott; Jens Bedke; Sophie Tartas; Yen-Hwa Chang; Satoshi Tamada; Qiong Shou; Rodolfo F Perini; Mei Chen; Michael B Atkins; Thomas Powles Journal: N Engl J Med Date: 2019-02-16 Impact factor: 91.245
Authors: Yoganand Balagurunathan; Yuhua Gu; Hua Wang; Virendra Kumar; Olya Grove; Sam Hawkins; Jongphil Kim; Dmitry B Goldgof; Lawrence O Hall; Robert A Gatenby; Robert J Gillies Journal: Transl Oncol Date: 2014-02-01 Impact factor: 4.243
Authors: Balaji Ganeshan; Sandra Abaleke; Rupert C D Young; Christopher R Chatwin; Kenneth A Miles Journal: Cancer Imaging Date: 2010-07-06 Impact factor: 3.909
Authors: E A Eisenhauer; P Therasse; J Bogaerts; L H Schwartz; D Sargent; R Ford; J Dancey; S Arbuck; S Gwyther; M Mooney; L Rubinstein; L Shankar; L Dodd; R Kaplan; D Lacombe; J Verweij Journal: Eur J Cancer Date: 2009-01 Impact factor: 9.162
Authors: Hugo J W L Aerts; Patrick Grossmann; Yongqiang Tan; Geoffrey R Oxnard; Naiyer Rizvi; Lawrence H Schwartz; Binsheng Zhao Journal: Sci Rep Date: 2016-09-20 Impact factor: 4.379
Authors: Stephen S F Yip; Thibaud P Coroller; Nina N Sanford; Harvey Mamon; Hugo J W L Aerts; Ross I Berbeco Journal: Front Oncol Date: 2016-03-29 Impact factor: 6.244