Weineng Feng

BACKGROUND: Computed tomography (CT) is essential for pulmonary nodule detection in diagnosing lung cancer. As deep learning algorithms have recently been regarded as a promising technique in medical fields, we attempt to integrate a well-trained deep learning algorithm to detect and classify pulmonary nodules derived from clinical CT images. MATERIALS AND METHODS: Open-source data sets and multicenter data sets have been used in this study. A three-dimensional convolutional neural network (CNN) was designed to detect pulmonary nodules and classify them into malignant or benign diseases based on pathologically and laboratory proven results. RESULTS: The sensitivity and specificity of this well-trained model were found to be 84.4% (95% confidence interval [CI], 80.5%-88.3%) and 83.0% (95% CI, 79.5%-86.5%), respectively. Subgroup analysis of smaller nodules (<10 mm) have demonstrated remarkable sensitivity and specificity, similar to that of larger nodules (10-30 mm). Additional model validation was implemented by comparing manual assessments done by different ranks of doctors with those performed by three-dimensional CNN. The results show that the performance of the CNN model was superior to manual assessment. CONCLUSION: Under the companion diagnostics, the three-dimensional CNN with a deep learning algorithm may assist radiologists in the future by providing accurate and timely information for diagnosing pulmonary nodules in regular clinical practices. IMPLICATIONS FOR PRACTICE: The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment. Although it still warrants further improvement and validation in larger screening cohorts, its clinical application could definitely facilitate and assist doctors in clinical practice.

Importance: For patients with non-small cell lung cancer whose disease progressed while receiving EGFR tyrosine kinase inhibitor (EGFR-TKI) therapy, particularly third-generation TKIs, optimal treatment options remain limited. Objective: To compare the efficacy of ivonescimab plus chemotherapy with chemotherapy alone for patients with relapsed advanced or metastatic non-small cell lung cancer with the epidermal growth factor receptor (EGFR) variant. Design, Setting, and Participants: Double-blind, placebo-controlled, randomized, phase 3 trial at 55 sites in China enrolled participants from January 2022 to November 2022; a total of 322 eligible patients were enrolled. Interventions: Participants received ivonescimab (n = 161) or placebo (n = 161) plus pemetrexed and carboplatin once every 3 weeks for 4 cycles, followed by maintenance therapy of ivonescimab plus pemetrexed or placebo plus pemetrexed. Main Outcomes and Measures: The primary end point was progression-free survival in the intention-to-treat population assessed by an independent radiographic review committee (IRRC) per Response Evaluation Criteria in Solid Tumors version 1.1. The results of the first planned interim analysis are reported. Results: Among 322 enrolled patients in the ivonescimab and placebo groups, the median age was 59.6 vs 59.4 years and 52.2% vs 50.9% of patients were female. As of March 10, 2023, median follow-up time was 7.89 months. Median progression-free survival was 7.1 (95% CI, 5.9-8.7) months in the ivonescimab group vs 4.8 (95% CI, 4.2-5.6) months for placebo (difference, 2.3 months; hazard ratio [HR], 0.46 [95% CI, 0.34-0.62]; P < .001). The prespecified subgroup analysis showed progression-free survival benefit favoring patients receiving ivonescimab over placebo across almost all subgroups, including patients whose disease progressed while receiving third-generation EGFR-TKI therapy (HR, 0.48 [95% CI 0.35-0.66]) and those with brain metastases (HR, 0.40 [95% CI, 0.22-0.73]). The objective response rate was 50.6% (95% CI, 42.6%-58.6%) with ivonescimab and 35.4% (95% CI, 28.0%-43.3%) with placebo (difference, 15.6% [95% CI, 5.3%-26.0%]; P = .006). The median overall survival data were not mature; at data cutoff, 69 patients (21.4%) had died. Grade 3 or higher treatment-emergent adverse events occurred in 99 patients (61.5%) in the ivonescimab group vs 79 patients (49.1%) in the placebo group, the most common of which were chemotherapy-related. Grade 3 or higher immune-related adverse events occurred in 10 patients (6.2%) in the ivonescimab group vs 4 (2.5%) in the placebo group. Grade 3 or higher vascular endothelial growth factor-related adverse events occurred in 5 patients (3.1%) in the ivonescimab group vs 4 (2.5%) in the placebo group. Conclusions: Ivonescimab plus chemotherapy significantly improved progression-free survival with tolerable safety profile in TKI-treated non-small cell lung cancer. Trial Registration: ClinicalTrials.gov Identifier: NCT05184712.

Acquired resistance represents a bottleneck for effective molecular targeted therapy in lung cancer. Metabolic adaptation is a distinct hallmark of human lung cancer that might contribute to acquired resistance. In this study, we discovered a novel mechanism of acquired resistance to EGFR tyrosine kinase inhibitors (TKI) mediated by IGF2BP3-dependent cross-talk between epigenetic modifications and metabolic reprogramming through the IGF2BP3-COX6B2 axis. IGF2BP3 was upregulated in patients with TKI-resistant non-small cell lung cancer, and high IGF2BP3 expression correlated with reduced overall survival. Upregulated expression of the RNA binding protein IGF2BP3 in lung cancer cells reduced sensitivity to TKI treatment and exacerbated the development of drug resistance via promoting oxidative phosphorylation (OXPHOS). COX6B2 mRNA bound IGF2BP3, and COX6B2 was required for increased OXPHOS and acquired EGFR-TKI resistance mediated by IGF2BP3. Mechanistically, IGF2BP3 bound to the 3'-untranslated region of COX6B2 in an m6A-dependent manner to increase COX6B2 mRNA stability. Moreover, the IGF2BP3-COX6B2 axis regulated nicotinamide metabolism, which can alter OXPHOS and promote EGFR-TKI acquired resistance. Inhibition of OXPHOS with IACS-010759, a small-molecule inhibitor, resulted in strong growth suppression in vitro and in vivo in a gefitinib-resistant patient-derived xenograft model. Collectively, these findings suggest that metabolic reprogramming by the IGF2BP3-COX6B2 axis plays a critical role in TKI resistance and confers a targetable metabolic vulnerability to overcome acquired resistance to EGFR-TKIs in lung cancer. SIGNIFICANCE: IGF2BP3 stabilizes COX6B2 to increase oxidative phosphorylation and to drive resistance to EGFR inhibitors in lung cancer, which provides a therapeutic strategy to overcome acquired resistance by targeting metabolic transitions.