Lymph node micrometastases could be one of the reasons for the high recurrence rate after complete surgical resection in stage I-IIIA non-small cell lung cancer (NSCLC). The standard evaluation of... Show moreLymph node micrometastases could be one of the reasons for the high recurrence rate after complete surgical resection in stage I-IIIA non-small cell lung cancer (NSCLC). The standard evaluation of a single haematoxylin and eosin (H&E) slide of a paraffin-embedded section of a lymph node is insufficient for the detection of micrometastases, and there is a need for additional histopathological evaluation. The association of lymph node micrometastases with survival remains as yet unresolved. The aim of this systematic review and meta-analysis is to investigate if lymph node micrometastases and isolated tumour cells in patients with stage I-IIIA NSCLC, detected with multiple sectioning and/or immunohistochemistry (IHC) and/or reverse transcriptase polymerase chain reaction (RT-PCR), are associated with overall survival (OS) and disease-free survival (DFS) after surgical resection. We performed a meta-analysis of time-to-event outcomes based on 15 articles using ancillary techniques to detect micrometastases. We extracted the OS and DFS every 3-6 months after surgery, for patients with and without occult lymph node micrometastasis, from the survival curves published in each article. These data were used to reconstruct OS and DFS for 'micrometastasis' and 'no micrometastasis' groups. Based on all included studies that used IHC, serial sectioning, or RT-PCR, we found a 5-year OS of 55% (micrometastasis) vs. 75% (no micrometastasis), and a 5-year DFS of 53% (micrometastasis) vs. 75% (no micrometastasis). Patients with stage I-IIIA NSCLC with lymph node micrometastases detected by ancillary histopathological and molecular techniques have a significantly poorer OS and DFS compared to patients without lymph node micrometastases. Show less
Hondelink, L.M.; Huyuk, M.; Postmus, P.E.; Smit, V.T.H.B.M.; Blom, S.; Thusen, J.H. von der; Cohen, D. 2021
Aims Immunohistochemical programmed death-ligand 1 (PD-L1) staining to predict responsiveness to immunotherapy in patients with advanced non-small cell lung cancer (NSCLC) has several drawbacks: a... Show moreAims Immunohistochemical programmed death-ligand 1 (PD-L1) staining to predict responsiveness to immunotherapy in patients with advanced non-small cell lung cancer (NSCLC) has several drawbacks: a robust gold standard is lacking, and there is substantial interobserver and intraobserver variance, with up to 20% discordance around cutoff points. The aim of this study was to develop a new deep learning-based PD-L1 tumour proportion score (TPS) algorithm, trained and validated on a routine diagnostic dataset of digitised PD-L1 (22C3, laboratory-developed test)-stained samples. Methods and results We designed a fully supervised deep learning algorithm for whole-slide PD-L1 assessment, consisting of four sequential convolutional neural networks (CNNs), using aiforia create software. We included 199 whole slide images (WSIs) of 'routine diagnostic' histology samples from stage IV NSCLC patients, and trained the algorithm by using a training set of 60 representative cases. We validated the algorithm by comparing the algorithm TPS with the reference score in a held-out validation set. The algorithm had similar concordance with the reference score (79%) as the pathologists had with one another (75%). The intraclass coefficient was 0.96 and Cohen's kappa coefficient was 0.69 for the algorithm. Around the 1% and 50% cutoff points, concordance was also similar between pathologists and the algorithm. Conclusions We designed a new, deep learning-based PD-L1 TPS algorithm that is similarly able to assess PD-L1 expression in daily routine diagnostic cases as pathologists. Successful validation on routine diagnostic WSIs and detailed visual feedback show that this algorithm meets the requirements for functioning as a 'scoring assistant'. Show less
