Reliable entity subtyping is paramount for therapy stratification in lung cancer. Morphological evaluation remains the basis for entity subtyping and directs the application of additional methods such as immunohistochemistry (IHC). The decision of whether to perform IHC for subtyping is subjective, and access to IHC is not available worldwide. Thus, the application of additional methods to support morphological entity subtyping is desirable. Therefore, the ability of convolutional neuronal networks (CNNs) to classify the most common lung cancer subtypes, pulmonary adenocarcinoma (ADC), pulmonary squamous cell carcinoma (SqCC), and small-cell lung cancer (SCLC), was evaluated. A cohort of 80 ADC, 80 SqCC, 80 SCLC, and 30 skeletal muscle specimens was assembled; slides were scanned; tumor areas were annotated; image patches were extracted; and cases were randomly assigned to a training, validation or test set. Multiple CNN architectures (VGG16, InceptionV3, and InceptionResNetV2) were trained and optimized to classify the four entities. A quality control (QC) metric was established. An optimized InceptionV3 CNN architecture yielded the highest classification accuracy and was used for the classification of the test set. Image patch and patient-based CNN classification results were 95% and 100% in the test set after the application of strict QC. Misclassified cases mainly included ADC and SqCC. The QC metric identified cases that needed further IHC for definite entity subtyping. The study highlights the potential and limitations of CNN image classification models for tumor differentiation.

Immunotherapies targeting the PD1/PD-L1 pathway have had a large impact on the treatment of advanced NSCLC. Concerning multimodality tumor therapy, only few trials until today have been performed investigating neoadjuvant treatment with anti PD-1 immunotherapy prior to curative intent surgery. Aim of the NEOMUN investigator initiated trial (EudraCT-Number: 2017–000105-20; ClinicalTrials.gov Identifier: NCT03197467) is to assess feasibility and safety of pre-surgical anti PD-1 treatment in order to improve long term survival. The study is designed as an open-label, single arm, prospective, monocenter, phase II study including 30 patients with NSCLC stage II/IIIA suitable for curative intent surgery. Investigational drug is Pembrolizumab. After 2 cycles of immunotherapy (à 200 mg q3w i.v.), tumor resection with lobectomy or bilobectomy will be performed. Primary objectives are to assess the feasibility and safety of a neoadjuvant immunotherapy and to assess antitumor activity of Pembrolizumab with regard to clinical and pathological tumor response. Secondary objective is disease free and overall survival. Exploratory objective is to analyze potential predictive biomarkers and to evaluate the therapeutic efficacy of Pembrolizumab by extended immune cell and cytokine analysis of tumor tissue. The study protocol was approved by the local ethics committee and the federal authority. Start of patient enrollment is scheduled for June 2018. The NEOMUN trial will be one of the first clinical trials investigating a multimodal treatment strategy including neoadjuvant immunotherapy using Pembrolizumab as an investigational drug. Assessing the safety and therapeutic potential of neoadjuvant immunotherapy in connection with lung surgery will be of great interest for thoracic surgeons. Prospectively, the NEOMUN study has been registered on www.clinicaltrials.gov ; NCT03197467 (first post: June 23rd, 2017).

There is controversy whether patients diagnosed with large-cell neuroendocrine carcinoma (LCNEC) should be treated according to protocols for non-small cell lung cancers (NSCLC) or small cell lung cancers (SCLC), especially with regard to the administration of prophylactic cranial irradiation (PCI). This study was set up to determine the incidence of brain metastases and to investigate the outcome following multimodal treatment in 70 patients with LCNEC. Seventy patients with histologically confirmed LCNEC were treated at the University Hospital of Heidelberg between 2001 and 2014. Data were collected retrospectively. Al most all patients received thoracic surgery as initial treatment (94 %). Chemotherapy was administered in 32 patients as part of the initial treatment. Fourteen patients were treated with adjuvant or definitive thoracic radiotherapy according to NSCLC protocols. Cranial radiotherapy due to brain metastases, mostly given as whole brain radiotherapy (WBRT), was received by fourteen patients. Statistical analysis was performed using the long-rank test and the Kaplan–Meier method. Without PCI, the detected rate for brain metastases was 25 % after a median follow-up time of 23.4 months, which is comparable to NSCLC patients in general. Overall (OS), local (LPFS), brain metastases-free survival (BMFS) and extracranial distant progression-free survival (eDPFS) was 43, 50, 63 and 50 % at 5 years, respectively. Patients with incomplete resection showed a survival benefit from adjuvant radiotherapy. The administration of adjuvant chemotherapy improved the general worse prognosis in higher pathologic stages. In LCNEC patients, the administration of radiotherapy according to NSCLC guidelines appears reasonable and contributes to acceptable results of multimodal treatment regimes. The low incidence of spontaneous brain metastases questions a possible role of PCI.