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
143P - Lymph nodes metastasis is the most important factor associated with pattern of recurrence following curative resection of gastric adenocarcinoma
Presenter: Fu-Hai Wang
Session: e-Poster Display Session
144P - Clinical implication of DNA damage response gene in patients with stage II or III gastric cancer
Presenter: In Gyu Hwang
Session: e-Poster Display Session
145P - A nomogram for predicting the benefit of adjuvant chemotherapy after resection in patients with Borrmann type IV gastric cancer
Presenter: Qing-Zhu Qiu
Session: e-Poster Display Session
146P - Red cell distribution width and mean corpuscular volume ratio as a promising new marker for chemotherapy effects in remnant gastric cancer: An analysis of a multi-institutional database
Presenter: Kai-Xiang Xu
Session: e-Poster Display Session
147P - Can the clinical stage of the 8th edition of the Union for International Cancer Control TNM classification stratify prognosis of patients with Siewert type II/III cancer?
Presenter: Hayato Watanabe
Session: e-Poster Display Session
148P - MCV-the ideal answer to predict the prognosis of remnant gastric cancer: An analysis from a multi-institutional database
Presenter: Kai Weng
Session: e-Poster Display Session
149P - Molecular and clinical characteristics of patients with resectable gastric cancer
Presenter: Zhi Zheng
Session: e-Poster Display Session
150P - Real-world assessment of the treatment patterns associated with unresectable advanced and metastatic gastric cancer in China
Presenter: Xiao Sun
Session: e-Poster Display Session
151P - Treatment patterns, healthcare resource use, economic and survival outcomes associated with unresectable advanced metastatic gastric cancers in Taiwan
Presenter: Chee Jen Chang
Session: e-Poster Display Session
152P - ARID1A deficiency in EBV-positive gastric cancer is partially regulated by EBV-encoded miRNAs, but not by DNA promotor hypermethylation
Presenter: Koji Kase
Session: e-Poster Display Session