Introduction: Epidermal growth factor receptor (EGFR) alterations exist in 15–50% of non-small cell lung cancer (NSCLC) diagnoses. Although effective therapeutics have been developed in the form of tyrosine kinase inhibitors (TKI), various mechanisms of resistance lead to treatment failure after exposure to EGFR TKI-based therapy. Of these, histologic transformation (HT) into small cell lung cancer (SCLC) represents approximately 14% of cases. Methods: Within a single institution, we retrospectively reviewed longitudinal data from both tissue and liquid biopsies of patients with histologic transformation after a diagnosis of EGFR-mutant NSCLC. We sought to further characterize the baseline and emergent genomic alterations after HT to SCLC in the context of TKI exposure, along with germline alterations that may contribute to lineage plasticity and outcomes. Results: Fifteen patients were included in our analysis. Of these, EGFR exon 19 deletions were the most frequent (n = 11, 73.3%), followed by L858R (n = 3, 20%) and L861Q (n = 1, 6.7%). The median time for transformation was 17 months (95%CI, 8.9–41.9 months). The median OS of our cohort was 51.6 months (95%CI, 26.3—NE) with a median OS post-transformation of 13.4 months. Recurrent genomic alterations included TP53, Rb1, PIK3CA, and BRAF. Germline testing revealed a pathogenic alteration in FBN1, with a recurrent variant of unknown significance (VUS) in PALLD. Conclusion: Post-transformation somatic mutation testing and germline testing at presentation revealed unique mutational profiles not previously reported in the setting of HT to SCLC. Further investigations are required to determine the optimal treatment and sequencing following HT.

Operable non-small cell lung cancer (NSCLC) has been traditionally managed with surgical resection, often followed by adjuvant chemotherapy with or without radiotherapy. However, disease recurrence still occurs approximately 50% of the time. Most recently, (neo) adjuvant/perioperative systemic therapy has evolved to include checkpoint inhibitor therapy and targeted therapies that have proved successful in advanced disease settings. We provide a comprehensive review of the trials investigating neoadjuvant, adjuvant, and perioperative systemic therapies in resectable lung cancer, including a discussion on surrogate survival endpoints. We review the management of N2 disease, the utility of circulating tumor DNA (ctDNA) in determining the risk and benefit from systemic therapy in operable NSCLC, as well as future directions of investigation.

Thymic epithelial tumors (TETs) are a diverse group of rare thymic tumors that arise from thymic epithelial cells. The rarity of these tumors has limited therapeutic advancements due to difficulty to enroll patients into Phase II and III clinical trials. Historically surgery, radiotherapy, and chemotherapy have been the mainstay therapeutic options for these patients with the development of new therapeutics hindered by the rarity, histological and molecular heterogeneity, and lack of actionable mutations. However, more recently, innovations in immunotherapy, next-generation tyrosine kinase inhibitors, and hyperthermic intrathoracic chemotherapy (HITHOC) have transformed the therapeutic landscape with more promising therapies currently under investigation. In this review we evaluate the histology and molecular subtypes of TETs, and discuss the therapeutic landscape including the current standard-of-care regimen as well as drugs that are currently in clinical trials.

Lung cancer remains the leading cause of cancer-related death globally, despite significant advances in diagnosis and treatment. Single biomarker approaches used clinically, such as programmed death ligand-1 (PD-L1) expression levels, have limited capacity for predicting treatment response. Multimodal data analysis using artificial intelligence (AI) offers an innovative scope to integrate diverse data sources—including radiologic imaging, digital pathology, genomics, immunohistochemistry, and Cell Painting morphology—to improve clinical predictions. This review aims to examine multimodal AI applications across the lung cancer treatment landscape related to such data sources. We analyze technical architectures spanning convolutional neural networks for imaging, vision transformers for pathology, and graph neural networks for genomics. We discuss how integrating and learning from heterogeneous data sources requires cross-attention fusion mechanisms. We further analyze critical studies demonstrating that multimodal AI clinical applications achieve superior predictive performance compared to unimodal biomarker methods. Multimodal AI models can augment clinicians in treatment selection, longitudinal monitoring using circulating tumor DNA (ctDNA), and variant interpretation through morphological profiling. We propose developing a multimodal AI model to optimize precision oncology for lung cancer.