Abstract 364P
Background
Lung cancer treatment gets on the stage of precision medicine. Histopathological classification of lung cancer is crucial in determining optimum treatment. Artificial intelligence (AI) models have been widely shown to be useful in pathological diagnosis and we previously established a reliable AI model to detect the presence of lung cancer on whole slide images (WSIs). However, AI models for the differentiation of major histological types of lung cancer, such as adenocarcinoma (ADC), squamous cell carcinoma (SCC) and small-cell lung cancer (SCLC), are yet to be established.
Methods
We trained a convolution neural network (CNN) based on the EfficientNet-B1 architecture to classify ADC, SCC, SCLC, and non-neoplastic lesion from biopsy specimen WSIs (70, 23, 12 and 171 specimens with ADC, SCC, SCLC and non-neoplastic lesion, respectively) using a training dataset of 276 images of which 60 were reserved for validation. The WSIs were manually annotated by pathologists by drawing around the regions that contain each subtype. We used a transfer learning approach, in which the starting weights were obtained from a pre-trained model on ImageNet. The model was then trained on our dataset using a supervised learning approach. To classify a WSI, the model was applied in a sliding window fashion with an input tile size of 224x224 and a stride of 128 on a magnification of x10. The maximum probability was then used as a WSI diagnosis.
Results
We evaluated our model on a total of 533 WSIs that only had WSI diagnoses. The model achieved a Receiver Operator Curve Area Under the Curves of 0.888 (CI 0.872-0.9075), 0.8913 (CI 0.8596-0.9221), 0.9526 (CI 0.9276-0.9646) for ADC, SCC, and SCLC, respectively.
Conclusions
The obtained results on a large test set are a promising first step towards developing a model for the classification of lung cancer. Our model was only trained on a small dataset of 276 WSIs; however, we hope that the model would be further improved with the collection of additional annotated WSIs for training. Having a high performing model could help reduce the burden on pathologists and be useful for the decision of optimum treatment strategies, such as molecular-targeted therapy, immunotherapy and chemotherapy, according to the histological types of lung cancer.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
372P - Treatment patterns and outcomes in stage III non-small cell lung cancer (NSCLC): Real-world experience in Singapore from the KINDLE study
Presenter: Ross A. Soo
Session: e-Poster Display Session
373P - Chromatin accessibility reveals potential prognostic value of the peak set associated with smoking history in patients with lung adenocarcinoma
Presenter: Jianlian Deng
Session: e-Poster Display Session
384P - BLU-945, a highly potent and selective 4th generation EGFR TKI for the treatment of EGFR T790M/C797S resistant NSCLC
Presenter: Stefanie Schalm
Session: e-Poster Display Session
385P - Patient reported outcomes (PROs) analysis for patients with ROS1 fusion-positive (ROS1+) non-small cell lung cancer (NSCLC) receiving entrectinib in the global phase II STARTRK-2 study
Presenter: Fabrice Barlesi
Session: e-Poster Display Session
386P - A single-arm phase Ib study of autologous cytokine-induced killer (CIK) cell immunotherapy in combination with sintilimab plus chemotherapy in patients with advanced non-small cell lung cancer (NSCLC)
Presenter: LI Zhou
Session: e-Poster Display Session
387P - Phase Ib study of savolitinib ± osimertinib in Japanese patients (pts) with advanced solid malignancies & EGFRm NSCLC: TATTON part C
Presenter: Tomonori Hirashima
Session: e-Poster Display Session
388P - Biosimilar TAB008 compared with bevacizumab in advanced non-squamous, non-small cell, EGFR wildtype lung cancer patients
Presenter: Zhen Zhou
Session: e-Poster Display Session
389P - Updated analysis from the KEYNOTE-042 China study: 1L pembrolizumab (pembro) vs chemotherapy (chemo) in Chinese patients (pts) with advanced NSCLC with PD-L1 TPS ≥1%
Presenter: Yi-Long Wu
Session: e-Poster Display Session
391P - Economic impact of next-generation sequencing (NGS) versus single-gene testing modalities to detect genomic alterations (GAs) in metastatic non-small cell lung cancer (mNSCLC) in Asia
Presenter: Herbert Loong
Session: e-Poster Display Session
392P - Clinical data from the real world: Efficacy analysis of ceritinib (450mg) in ALK-positive non-small cell lung cancer patients with brain metastases in China
Presenter: Zhixin Qiu
Session: e-Poster Display Session