Search

Abstract Background [18F]FDG PET denoising by SubtlePET™ using deep learning artificial intelligence (AI) was previously found to induce slight modifications in lesion and reference organs’ quantification and in lesion detection. As a next step, we aimed to evaluate its clinical impact on [18F]FDG PET solid tumour treatment response assessments, while comparing “standard PET” to “AI denoised half-duration PET” (“AI PET”) during follow-up. Results 110 patients referred for baseline and follow-up standard digital [18F]FDG PET/CT were prospectively included. “Standard” EORTC and, if applicable, PERCIST response classifications by 2 readers between baseline standard PET1 and follow-up standard PET2 as a “gold standard” were compared to “mixed” classifications between standard PET1 and AI PET2 (group 1; n = 64), or between AI PET1 and standard PET2 (group 2; n = 46). Separate classifications were established using either standardized uptake values from ultra-high definition PET with or without AI denoising (simplified to “UHD”) or EANM research limited v2 (EARL2)-compliant values (by Gaussian filtering in standard PET and using the same filter in AI PET). Overall, pooling both study groups, in 11/110 (10%) patients at least one EORTCUHD or EARL2 or PERCISTUHD or EARL2 mixed vs. standard classification was discordant, with 369/397 (93%) concordant classifications, unweighted Cohen’s kappa = 0.86 (95% CI: 0.78–0.94). These modified mixed vs. standard classifications could have impacted management in 2% of patients. Conclusions Although comparing similar PET images is preferable for therapy response assessment, the comparison between a standard [18F]FDG PET and an AI denoised half-duration PET is feasible and seems clinically satisfactory.

Non-small cell lung cancer (NSCLC) is the most common cause of brain metastasis (BM). Little is known about immune checkpoint inhibitor activity in the central nervous system, especially in patients receiving monotherapy for tumors with a tumor proportion score (TPS) ≥ 50%. This noninterventional, retrospective, multicenter study, conducted with the GFPC, included treatment-naïve patients strongly positive for PD-L1 (TPS ≥ 50%) with BM receiving first-line single-agent pembrolizumab treatment between May 2017 and November 2019. The primary endpoints were centrally reviewed intracranial overall response rates (ORRs), centrally reviewed intracranial progression-free survival (cPFS), extracranial PFS, and overall survival were secondary endpoints. Forty-three patients from five centers were included. Surgical or local radiation therapy was administered to 31 (72%) patients, mostly before initiating ICI therapy (25/31). Among 38/43 (88.4%) evaluable patients, the intracranial ORR was 73%. The median PFS was 8.3 months. The cerebral and extracerebral median PFS times were 9.2 and 5.3 months, respectively. The median OS was 25.5 months. According to multivariate analysis, BM surgery before ICI therapy was the only factor significantly associated with both improved PFS (HR = 0.44) and OS (HR = 0.45). This study revealed the feasibility and outcome of front-line pembrolizumab treatment in this population with BM.

Background: Few epidemiological data are available on surgically treated Caucasian patients with non-small-cell lung cancers (NSCLCs) harboring epidermal growth factor receptor ( EGFR ) mutations. The main objective of this study was to describe, in the real-world setting, these patients’ incidence, clinical, and tumoral characteristics. Methods: The participating centers included all consecutive localized non-squamous NSCLC patients undergoing surgery between January 2018 and December 2019 in France. EGFR status was determined retrospectively when not available before surgery. Results: The study includes 1391 no squamous NSCLC patients from 16 centers; EGFR status was determined before surgery in 692 (49.7%) of the cases and conducted as part of the study for 699 (50.3%); 171 (12.3%) were EGFR mutated; median age: 70 (range: 36–88) years; female: 59.6%; never smokers: 75.7%; non-squamous histology 97.7%, programmed death ligand-1 expression 0%/1–49%/⩾50 in 60.5%/25.7%/13.8%, respectively. Surgery was predominantly lobectomy (81%) or segmentectomy (14.9%), with systematic lymph node dissection in 95.9%. Resection completeness was R0 for 97%. Post-surgery staging was as follows: IA: 52%, IB: 16%, IIA: 4%, IIB: 10%, IIIA: 16%, and IIIB: 0.05%; EGFR mutation exon was Del19/exon 21 ( L858R )/20/18 in 37.4%/36.8%/14%, and 6.4% of cases, respectively; 31 (18%) patients received adjuvant treatment (chemotherapy: 93%, EGFR tyrosine kinase inhibitor: 0%, radiotherapy: 20%). After a median follow-up of 31 (95% confidence interval: 29.6–33.1) months, 45 (26%) patients relapsed: 11/45 (24%) locally and 34 (76%) with metastatic progression. Median disease-free survival (DFS) and overall survival were not reached and 3-year DFS was 60%. Conclusion: This real-world analysis provides the incidence and outcomes of resected EGFR -mutated NSCLCs in a European patient cohort.