Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform.

OBJECTIVE: To investigate the effects of Image Biomarker Standardisation Initiative (IBSI) compliance, harmonisation of calculation settings and platform version on the statistical reliability of radiomic features and their corresponding ability to predict clinical outcome. METHODS: The statistical reliability of radiomic features was assessed retrospectively in three clinical datasets (patient numbers: 108 head and neck cancer, 37 small-cell lung cancer, 47 non-small-cell lung cancer). Features were calculated using four platforms (PyRadiomics, LIFEx, CERR and IBEX). PyRadiomics, LIFEx and CERR are IBSI-compliant, whereas IBEX is not. The effects of IBSI compliance, user-defined calculation settings and platform version were assessed by calculating intraclass correlation coefficients and confidence intervals. The influence of platform choice on the relationship between radiomic biomarkers and survival was evaluated using univariable cox regression in the largest dataset. RESULTS: The reliability of radiomic features calculated by the different software platforms was only excellent (ICC > 0.9) for 4/17 radiomic features when comparing all four platforms. Reliability improved to ICC > 0.9 for 15/17 radiomic features when analysis was restricted to the three IBSI-compliant platforms. Failure to harmonise calculation settings resulted in poor reliability, even across the IBSI-compliant platforms. Software platform version also had a marked effect on feature reliability in CERR and LIFEx. Features identified as having significant relationship to survival varied between platforms, as did the direction of hazard ratios. CONCLUSION: IBSI compliance, user-defined calculation settings and choice of platform version all influence the statistical reliability and corresponding performance of prognostic models in radiomics. KEY POINTS: • Reliability of radiomic features varies between feature calculation platforms and with choice of software version. • Image Biomarker Standardisation Initiative (IBSI) compliance improves reliability of radiomic features across platforms, but only when calculation settings are harmonised. • IBSI compliance, user-defined calculation settings and choice of platform version collectively affect the prognostic value of features.

Tumor infiltrating lymphocytes in lymph node metastases of stage III melanoma correspond to response and survival in nine patients treated with ipilimumab at the time of stage IV disease.

Prognosis of metastatic melanoma improved with the development of checkpoint inhibitors. The role of tumor infiltrating lymphocytes (TILs) in lymph node metastases of stage III melanoma remains unclear. We retrospectively characterized TILs in primary melanomas and matched lymph node metastases (stage III melanoma) of patients treated with the checkpoint inhibitor ipilimumab. Tumor infiltrating lymphocytes were characterized for CD3, CD4, and CD8 expressions by immunohistochemistry. 4/9 patients (44%) responded to treatment with ipilimumab (1 complete and 2 partial remissions, 1 stable disease). All responders exhibited CD4 and CD8 T-cell infiltration in their lymph node metastases, whereas all non-responders did not show an infiltration of the lymph node metastasis with TILs. The correlation between the presence and absence of TILs in responders vs. non-responders was statistically significant (p = 0.008). Median distant metastases free survival, i.e., progression from stage III to stage IV melanoma, was similar in responders and non-responders (22.1 vs. 19.3 months; p = 0.462). Median progression free and overall survival show a trend in favor of the patients having TIL rich lymph node metastases (6.8 vs. 3.3 months, p = 0.09; and all alive at last follow-up vs. 8.2 months, respectively, p = 0.08). Our data suggest a correlation between the T-cell infiltration of the lymph node metastases in stage III melanoma and the response to ipilimumab once these patients progress to stage IV disease.

First-line durvalumab in patients with PD-L1 positive, advanced non-small cell lung cancer (NSCLC) with a performance status of 2 (PS2). Primary analysis of the multicenter, single-arm phase II trial SAKK 19/17.

INTRODUCTION: The safety and efficacy of first-line durvalumab in PS2 patients with advanced NSCLC is unknown. Here, we present the primary analysis of first-line durvalumab in PS2 patients, unsuitable for combination chemotherapy. METHODS: In this single-arm, multicenter, phase II trial patients with PD-L1 positive (tumor proportional score ≥25%), advanced NSCLC with PS2, received four-weekly durvalumab 1500 mg. The primary endpoint was overall survival (OS) at 6 months. RESULTS: Forty-eight patients were included. Median follow-up was 23.3 months (95% CI: 14.3-28.6). OS at 6 months was 60% (95% CI: 45-74%). Median OS was 8.5 months (95%CI: 4.4-16.7). Objective response rate and median progression free survival were 17% (95% CI: 8-30%) and 2.5 months (95% CI: 1.8-7.1), respectively. Thirty-three deaths were observed at the time point of the analysis. Seven early fatal events considered not treatment-related occurred during the first 5 weeks of treatment. Four out of the first 7 early fatal events (4/7; 57%) were respiratory failure in patients with advanced symptomatic primary lung tumors. Three more early fatal events occurred after exclusion of patients with grade ≥ 3 dyspnea. Treatment-related AEs ≥G3 were reported in 9 patients (19%) and included colonic perforation in one patient (grade 5), colitis in 4 patients (8%), increased lipase in 3 patients (6%), and hepatitis in 2 patients (4%). CONCLUSIONS: First-line durvalumab in PS2 patients with advanced PD-L1 positive NSCLC results in a high number of early fatal events. When patients with grade ≥ 3 dyspnea are excluded a promising 6-month OS with an acceptable toxicity profile can be observed. Durvalumab could be an option instead of single agent chemotherapy for PS2 patients who are not candidates for platinum doublet chemotherapy provided they are well selected.

Association of Checkpoint Inhibitor-Induced Toxic Effects With Shared Cancer and Tissue Antigens in Non-Small Cell Lung Cancer.

IMPORTANCE: Immunotherapy with checkpoint inhibitors targeting the PD-1 (programmed cell death 1) axis has brought notable progress in patients with non-small cell lung cancer (NSCLC) and other cancers. However, autoimmune toxic effects are frequent and poorly understood, making it important to understand the pathophysiologic processes of autoimmune adverse effects induced by checkpoint inhibitor therapy. OBJECTIVE: To gain mechanistic insight into autoimmune skin toxic effects induced by anti-PD-1 treatment in patients with non-small cell lung cancer. DESIGN, SETTING, AND PARTICIPANTS: This prospective cohort study was conducted from July 1, 2016, to December 31, 2018. Patients (n = 73) with non-small cell lung cancer who received anti-PD-1 therapy (nivolumab or pembrolizumab) were recruited from 4 different centers in Switzerland (Kantonsspital St Gallen, Spital Grabs, Spital Wil, and Spital Flawil). Peripheral blood mononuclear cells, tumor biopsy specimens and biopsies from sites of autoimmune skin toxic effects were collected over a 2-year period, with patient follow-up after 1 year. MAIN OUTCOMES AND MEASURES: Response to treatment, overall survival, progression-free survival, and development of autoimmune toxic effects (based on standard laboratory values and clinical examinations). RESULTS: Of the cohort of 73 patients with NSCLC (mean [SD] age, 68.1 [8.9] years; 44 [60%] men), 25 (34.2% [95% CI, 24.4%-45.7%]) developed autoimmune skin toxic effects, which were more frequent in patients with complete remission or partial remission (68.2% [95% CI, 47.3%-83.6%]) than those with progressive or stable disease (19.6% [95% CI, 11.0%-32.5%]) (χ2 = 14.02, P < .001). Nine T-cell antigens shared between tumor tissue and skin were identified. These antigens were able to stimulate CD8+ and CD4+ T cells in vitro. Several of the antigen-specific T cells found in blood samples were also present in autoimmune skin lesions and lung tumors of patients who responded to anti-PD-1 therapy. CONCLUSIONS AND RELEVANCE: These findings highlight a potential mechanism of checkpoint inhibitor-mediated autoimmune toxic effects and describe the association between toxic effects and response to therapy; such an understanding will help in controlling adverse effects, deciphering new cancer antigens, and further improving immunotherapy.