Introduction: Immunotherapy is regarded as one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds-urging the quest for predictive biomarkers.... Show moreIntroduction: Immunotherapy is regarded as one of the major breakthroughs in cancer treatment. Despite its success, only a subset of patients responds-urging the quest for predictive biomarkers. We hypothesize that artificial intelligence (AI) algorithms can automatically quantify radiographic characteristics that are related to and may therefore act as noninvasive radiomic biomarkers for immunotherapy response.Patients and methods: In this study, we analyzed 1055 primary and metastatic lesions from 203 patients with advanced melanoma and non-small-cell lung cancer (NSCLC) undergoing anti-PD1 therapy. We carried out an AI-based characterization of each lesion on the pretreatment contrast-enhanced CT imaging data to develop and validate a noninvasive machine learning biomarker capable of distinguishing between immunotherapy responding and nonresponding. To define the biological basis of the radiographic biomarker, we carried out gene set enrichment analysis in an independent dataset of 262 NSCLC patients.Results: The biomarker reached significant performance on NSCLC lesions (up to 0.83 AUC, P < 0.001) and borderline significant for melanoma lymph nodes (0.64 AUC, P = 0.05). Combining these lesion-wide predictions on a patient level, immunotherapy response could be predicted with an AUC of up to 0.76 for both cancer types (P < 0.001), resulting in a 1-year survival difference of 24% (P = 0.02). We found highly significant associations with pathways involved in mitosis, indicating a relationship between increased proliferative potential and preferential response to immunotherapy.Conclusions: These results indicate that radiographic characteristics of lesions on standard-of-care imaging may function as noninvasive biomarkers for response to immunotherapy, and may show utility for improved patient stratification in both neoadjuvant and palliative settings. Show less
Patients with brain metastases (BM) from melanoma have an overall survival (OS) of 2-6 months after whole-brain radiotherapy. Targeted therapy (TT) is an effective treatment for BRAF-mutated... Show morePatients with brain metastases (BM) from melanoma have an overall survival (OS) of 2-6 months after whole-brain radiotherapy. Targeted therapy (TT) is an effective treatment for BRAF-mutated metastatic melanoma. Moreover, recent studies indicate intracranial responses of TT in patients with BM. We analyzed 146 patients with BM from BRAF-mutated melanoma treated with vemurafenib, dabrafenib, or dabrafenib+trametinib between 2010 and 2016. We determined clinical and radiological response, progression-free survival (PFS), and OS. Median OS of patients treated with dabrafenib+trametinib was 11.2 months [n=30; 95% confidence interval (CI): 6.8-15.7], 8.8 months for dabrafenib alone (n=31; 95% CI: 3.9-13.7), and 5.7 months for vemurafenib (n=85; 95% CI: 4.6-6.8). A significantly longer OS was observed in the dabrafenib+trametinib group than in the vemurafenib group (hazard ratio for death, 0.52; 95% CI: 0.30-0.89; P=0.02). Median intracranial PFS of all patients was 4.1 months. Median intracranial PFS for patients treated with dabrafenib+trametinib was 5.8 months (95% CI: 3.2-8.5), 5.7 months (95% CI: 3.0-8.4) for dabrafenib, and 3.6 months (95% CI: 3.5-3.8) for vemurafenib (P=0.54). A total of 63 (43%) patients had symptomatic BM. Intracranial disease control rate at 8 weeks in these patients was 65 versus 70% extracranially. Neurological symptoms improved in 46% of patients with symptomatic BM, whereas in 21%, they remained stable. Median OS in patients with BM from BRAF-mutated melanoma treated with dabrafenib+trametinib was significantly longer than for vemurafenib. Improvement of neurological symptoms was seen in almost half of the patients with symptomatic BM treated with TT. Show less
Background: Historically leptomeningeal metastases (LM) from melanoma have a poor prognosis, with a median survival of only 2 months despite treatment. Targeted therapy and immune checkpoint... Show moreBackground: Historically leptomeningeal metastases (LM) from melanoma have a poor prognosis, with a median survival of only 2 months despite treatment. Targeted therapy and immune checkpoint inhibitors are promising new treatment options in advanced melanoma. We sought to determine the impact of targeted therapy and immunotherapy on the outcome of melanoma patients with LM and to evaluate the influence of prognostic factors.We analyzed a series of 39 consecutive patients diagnosed with LM from melanoma between May 2010 and March 2015 treated at the Netherlands Cancer Institute. Thirty-four of these patients also had brain metastases (BM). Statistical analyses assessed the influence of clinical and biological characteristics on survival.Median overall survival of the entire cohort was 6.9 weeks (95% confidence interval 0.9-12.8). Due to a poor performance status or rapidly progressive disease, 14 patients received no treatment. Median overall survival of untreated patients after the diagnosis of LM was 2.9 versus 16.9 weeks for treated patients (P < 0.001). The median survival of 21 patients treated with systemic targeted therapy and/or immunotherapy, with or without RT was 21.7 weeks (range 2-235 weeks). Five patients had LM without BM. Three of these patients died within 3 weeks before any treatment was given, whereas 2 patients are in ongoing remission for 26 weeks (following dabrafenib) and 235 weeks (following WBRT and ipilimumab). Elevated serum lactate dehydrogenase and S100B at diagnosis of LM were associated with shorter survival.LM from melanoma still has an extremely poor prognosis. As observed in extracranial metastatic disease, new treatment modalities such as systemic targeted therapy and immune checkpoint inhibitors seem to increase overall survival in LM, and may result in long-term remission. These new treatment options should be considered in patients with LM. Show less
Kelderman, S.; Heemskerk, B.; Tinteren, H. van; Brom, R.R.H. van den; Hospers, G.A.P.; Eertwegh, A.J.M. van den; ... ; Blank, C.U. 2014