Dataset Information

Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma.

ABSTRACT: In the context of precision medicine with immunotherapies there is an increasing need for companion diagnostic tests to identify potential therapy responders and avoid treatment coming along with severe adverse events for non-responders. Here, we present a retrospective case study to discover image-based signatures for developing a potential companion diagnostic test for ipilimumab (IPI) in malignant melanoma. Signature discovery is based on digital pathology and fully automatic quantitative image analysis using virtual multiplexing as well as machine learning and deep learning on whole-slide images. We systematically correlated the patient outcome data with potentially relevant local image features using a Tissue Phenomics approach with a sound cross validation procedure for reliable performance evaluation. Besides uni-variate models we also studied combinations of signatures in several multi-variate models. The most robust and best performing model was a decision tree model based on relative densities of CD8+ tumor infiltrating lymphocytes in the intra-tumoral infiltration region. Our results are well in agreement with observations described in previously published studies regarding the predictive value of the immune contexture, and thus, provide predictive potential for future development of a companion diagnostic test.

SUBMITTER: Harder N

PROVIDER: S-EPMC6520405 | biostudies-literature | 2019 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma.

Harder Nathalie N Schönmeyer Ralf R Nekolla Katharina K Meier Armin A Brieu Nicolas N Vanegas Carolina C Madonna Gabriele G Capone Mariaelena M Botti Gerardo G Ascierto Paolo A PA Schmidt Günter G

Scientific reports 20190515 1

In the context of precision medicine with immunotherapies there is an increasing need for companion diagnostic tests to identify potential therapy responders and avoid treatment coming along with severe adverse events for non-responders. Here, we present a retrospective case study to discover image-based signatures for developing a potential companion diagnostic test for ipilimumab (IPI) in malignant melanoma. Signature discovery is based on digital pathology and fully automatic quantitative ima ...[more]

PMID: 31092853

Similar Datasets

Project description:BackgroundIpilimumab has shown long-term overall survival (OS) in patients with advanced melanoma in clinical trials, but robust real-world evidence is lacking. We present long-term outcomes from the IMAGE study (NCT01511913) in patients receiving ipilimumab and/or non-ipilimumab (any approved treatment other than ipilimumab) systemic therapies.MethodsIMAGE was a multinational, prospective, observational study assessing adult patients with advanced melanoma treated with ipilimumab or non-ipilimumab systemic therapies between June 2012 and March 2015 with ≥3 years of follow-up. Adjusted OS curves based on multivariate Cox regression models included covariate effects. Safety and patient-reported outcomes were assessed.ResultsAmong 1356 patients, 1094 (81%) received ipilimumab and 262 (19%) received non-ipilimumab index therapy (systemic therapy [chemotherapy, anti-programmed death 1 antibodies, or BRAF ± MEK inhibitors], radiotherapy, and radiosurgery). In the overall population, median age was 64 years, 60% were male, 78% were from Europe, and 78% had received previous treatment for advanced melanoma. In the ipilimumab-treated cohort, 780 (71%) patients did not receive subsequent therapy (IPI-noOther) and 314 (29%) received subsequent non-ipilimumab therapy (IPI-Other) on study. In the non-ipilimumab-treated cohort, 205 (78%) patients remained on or received other subsequent non-ipilimumab therapy (Other-Other) and 57 (22%) received subsequent ipilimumab therapy (Other-IPI) on study. Among 1151 patients who received ipilimumab at any time during the study (IPI-noOther, IPI-Other, and Other-IPI), 296 (26%) reported CTCAE grade ≥ 3 treatment-related adverse events, most occurring in year 1. Ipilimumab-treated and non-ipilimumab-treated patients who switched therapy (IPI-Other and Other-IPI) had longer OS than those who did not switch (IPI-noOther and Other-Other). Patients with prior therapy who did not switch therapy (IPI-noOther and Other-Other) showed similar OS. In treatment-naive patients, those in the IPI-noOther group tended to have longer OS than those in the Other-Other group. Patient-reported outcomes were similar between treatment cohorts.ConclusionsWith long-term follow-up (≥ 3 years), safety and OS in this real-world population of patients treated with ipilimumab 3 mg/kg were consistent with those reported in clinical trials. Patient-reported quality of life was maintained over the study period. OS analysis across both pretreated and treatment-naive patients suggested a beneficial role of ipilimumab early in treatment.Trial registrationClinicalTrials.gov , NCT01511913. Registered January 19, 2012 - Retrospectively registered, https://clinicaltrials.gov/ct2/show/NCT01511913.

Project description:BackgroundIn a phase 1 dose-escalation study, combined inhibition of T-cell checkpoint pathways by nivolumab and ipilimumab was associated with a high rate of objective response, including complete responses, among patients with advanced melanoma.MethodsIn this double-blind study involving 142 patients with metastatic melanoma who had not previously received treatment, we randomly assigned patients in a 2:1 ratio to receive ipilimumab (3 mg per kilogram of body weight) combined with either nivolumab (1 mg per kilogram) or placebo once every 3 weeks for four doses, followed by nivolumab (3 mg per kilogram) or placebo every 2 weeks until the occurrence of disease progression or unacceptable toxic effects. The primary end point was the rate of investigator-assessed, confirmed objective response among patients with BRAF V600 wild-type tumors.ResultsAmong patients with BRAF wild-type tumors, the rate of confirmed objective response was 61% (44 of 72 patients) in the group that received both ipilimumab and nivolumab (combination group) versus 11% (4 of 37 patients) in the group that received ipilimumab and placebo (ipilimumab-monotherapy group) (P<0.001), with complete responses reported in 16 patients (22%) in the combination group and no patients in the ipilimumab-monotherapy group. The median duration of response was not reached in either group. The median progression-free survival was not reached with the combination therapy and was 4.4 months with ipilimumab monotherapy (hazard ratio associated with combination therapy as compared with ipilimumab monotherapy for disease progression or death, 0.40; 95% confidence interval, 0.23 to 0.68; P<0.001). Similar results for response rate and progression-free survival were observed in 33 patients with BRAF mutation-positive tumors. Drug-related adverse events of grade 3 or 4 were reported in 54% of the patients who received the combination therapy as compared with 24% of the patients who received ipilimumab monotherapy. Select adverse events with potential immunologic causes were consistent with those in a phase 1 study, and most of these events resolved with immune-modulating medication.ConclusionsThe objective-response rate and the progression-free survival among patients with advanced melanoma who had not previously received treatment were significantly greater with nivolumab combined with ipilimumab than with ipilimumab monotherapy. Combination therapy had an acceptable safety profile. (Funded by Bristol-Myers Squibb; ClinicalTrials.gov number, NCT01927419.).

Dataset Information

Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma.

Publications

Automatic discovery of image-based signatures for ipilimumab response prediction in malignant melanoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets