BackgroundCheckpoint inhibitors provided sustained clinical benefit to metastatic lung cancer patients. Nonetheless, prognostic markers in metastatic settings are still under research. Imaging... Show moreBackgroundCheckpoint inhibitors provided sustained clinical benefit to metastatic lung cancer patients. Nonetheless, prognostic markers in metastatic settings are still under research. Imaging offers distinctive advantages, providing whole-body information non-invasively, while routinely available in most clinics. We hypothesized that more prognostic information can be extracted by employing artificial intelligence (AI) for treatment monitoring, superior to 2D tumor growth criteria.MethodsA cohort of 152 stage-IV non-small-cell lung cancer patients (NSCLC) (73 discovery, 79 test, 903CTs), who received nivolumab were retrospectively collected. We trained a neural network to identify morphological changes on chest CT acquired during patients' follow-ups. A classifier was employed to link imaging features learned by the network with overall survival.ResultsOur results showed significant performance in the independent test set to predict 1-year overall survival from the date of image acquisition, with an average area under the curve (AUC) of 0.69 (p < 0.01), up to AUC 0.75 (p < 0.01) in the first 3 to 5 months of treatment, and 0.67 AUC (p = 0.01) for durable clinical benefit (6 months progression-free survival). We found the AI-derived survival score to be independent of clinical, radiological, PDL1, and histopathological factors. Visual analysis of AI-generated prognostic heatmaps revealed relative prognostic importance of morphological nodal changes in the mediastinum, supraclavicular, and hilar regions, lung and bone metastases, as well as pleural effusions, atelectasis, and consolidations.ConclusionsOur results demonstrate that deep learning can quantify tumor- and non-tumor-related morphological changes important for prognostication on serial imaging. Further investigation should focus on the implementation of this technique beyond thoracic imaging. Show less
Breeschoten, J. van; Wouters, M.W.J.M.; Wreede, L.C. de; Hilarius, D.H.; Haanen, J.B.; Blank, C.U.; ... ; Eertwegh, A.J.M. van den 2021
Objective: The aim of this study was to evaluate treatment patterns and overall survival (OS) of patients with BRAF(V600) wild-type and BRAF(V600)-mutant advanced melanoma in the Netherlands.... Show moreObjective: The aim of this study was to evaluate treatment patterns and overall survival (OS) of patients with BRAF(V600) wild-type and BRAF(V600)-mutant advanced melanoma in the Netherlands. Methods: We selected patients of 18 years and over, diagnosed between 2016 and 2017 with unresectable stage IIIC or IV melanoma, registered in the Dutch Melanoma Treatment Registry. To assess the association of BRAF(V600)-mutation status with OS we used the Cox proportional-hazards model. Results: A total of 642 BRAF(V600) wild-type and 853 mutant patients were included in the analysis. Median OS did not differ significantly between both groups, 15.2 months (95% confidence interval [CI]: 13.2-19.2) versus 20.6 months (95% CI: 18.3-25.0). Survival rates at 6 and 12 months were significantly lower for BRAF(V600) wild-type patients compared with BRAF(V600)-mutant patients, 72.0% (95% CI: 68.6-75.6) and 56.0% (95% CI: 52.2-60.0) versus 83.4% (95% CI: 80.9-85.9) and 65.7% (95% CI: 62.6-69.0). Two-year survival was not significantly different between both groups, 41.1% (95% CI: 37.2-45.3) versus 47.0% (95% CI: 43.6-60.6). Between 0 and 10 months, BRAF(V600) wild-type patients had a decreased survival with a hazard ratio for OS of 2.00 (95% CI: 1.62-2.46) but this effect disappeared after 10 months. At 12 months, BRAF(V600)-mutant patients had started with second-line systemic treatment more often compared with BRAF(V600) wild-type patients (50% vs. 19%). Conclusion: These results suggest that advanced BRAF(V600) wild-type melanoma patients have worse survival than BRAF(V600)-mutated patients during the first 10 months after diagnosis because of less available treatment options. Show less
Kooij, M.K. van der; Wetzels, M.J.A.L.; Aarts, M.J.B.; Berkmortel, F.W.P.J. van den; Blank, C.U.; Boers-Sonderen, M.J.; ... ; Kapiteijn, E. 2020
Cutaneous melanoma is a common type of cancer in Adolescents and Young Adults (AYAs, 15-39 years of age). However, AYAs are underrepresented in clinical trials investigating new therapies and the... Show moreCutaneous melanoma is a common type of cancer in Adolescents and Young Adults (AYAs, 15-39 years of age). However, AYAs are underrepresented in clinical trials investigating new therapies and the outcomes from these therapies for AYAs are therefore unclear. Using prospectively collected nation-wide data from the Dutch Melanoma Treatment Registry (DMTR), we compared baseline characteristics, mutational profiles, treatment strategies, grade 3-4 adverse events (AEs), responses and outcomes in AYAs (n= 210) and older adults (n= 3775) who were diagnosed with advanced melanoma between July 2013 and July 2018. Compared to older adults, AYAs were more frequently female (51% versus 40%,p= 0.001), and had a better Eastern Cooperative Oncology Group performance status (ECOG 0 in 54% versus 45%,p= 0.004). BRAF and NRAS mutations were age dependent, with more BRAF V600 mutations in AYAs (68% versus 46%) and more NRAS mutations in older adults (13% versus 21%),p< 0.001. This finding translated in distinct first-line treatment patterns, where AYAs received more initial targeted therapy. Overall, grade 3-4 AE percentages following first-line systemic treatment were similar for AYAs and older adults; anti-PD-1 (7% versus 14%,p= 0.25), anti-CTLA-4 (16% versus 33%,p= 0.12), anti-PD-1 + anti-CTLA-4 (67% versus 56%,p= 0.34) and BRAF/MEK-inhibition (14% versus 23%,p= 0.06). Following anti-CTLA-4 treatment, no AYAs experienced a grade 3-4 colitis, while 17% of the older adults did (p= 0.046). There was no difference in response to treatment between AYAs and older adults. The longer overall survival observed in AYAs (hazard ratio (HR) 0.7; 95% CI 0.6-0.8) was explained by the increased cumulative incidence of non-melanoma related deaths in older adults (sub-distribution HR 2.8; 95% CI 1.5-4.9), calculated by competing risk analysis. The results of our national cohort study show that baseline characteristics and mutational profiles differ between AYAs and older adults with advanced melanoma, leading to different treatment choices made in daily practice. Once treatment is initiated, AYAs and older adults show similar tumor responses and melanoma-specific survival. Show less