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
183P - Textbook outcome as a measure of surgical quality assessment and prognosis in gastric neuroendocrine carcinoma: A large multicenter sample analysis
Presenter: You-Xin Gao
Session: e-Poster Display Session
184P - Development and external validation of a nomogram to predict recurrence-free survival after R0 resection for stage II/III gastric adenocarcinoma: An international multicenter study
Presenter: Bin-Bin Xu
Session: e-Poster Display Session
185P - Effect of sarcopenia on short- and long-term outcomes of patients with gastric neuroendocrine tumour after radical surgery: Results from a large, two-institutional series
Presenter: Ling-Qian Wang
Session: e-Poster Display Session
186P - Characterization of the gastroenteropancreatic neuroendocrine tumour patient journey
Presenter: George Fisher Jr
Session: e-Poster Display Session
187P - More is not always better: A multicenter study in lymphadenectomy during gastrectomy for gastric neuroendocrine carcinoma
Presenter: Qi-Yue Chen
Session: e-Poster Display Session
188P - The impact of sarcopenia on chemotherapy toxicity and survival rate among pancreatic cancer patients who underwent chemotherapy: A systematic review and meta-analysis
Presenter: Billy Susanto
Session: e-Poster Display Session
189P - Prognostic value of inflammation-based score for patients treated with FOLFIRINOX (FFX) or gemcitabine plus nab-paclitaxel (GnP)
Presenter: Takahiro Yamamura
Session: e-Poster Display Session
190P - Outcomes from the Asian region of the phase III APACT trial of adjuvant nab-paclitaxel plus gemcitabine (nab-P/G) vs gemcitabine (G) alone for patients (pts) with resected pancreatic cancer (PC)
Presenter: Joon Oh Park
Session: e-Poster Display Session
191P - First-line liposomal irinotecan + 5 fluorouracil/leucovorin + oxaliplatin in patients with pancreatic ductal adenocarcinoma: Results from a phase I/II study
Presenter: Andrew Dean
Session: e-Poster Display Session
192P - A multicenter crossover analysis of first and second-line FOLFIRINOX or gemcitabine plus nab-paclitaxel administered to pancreatic cancer patients: Results from the NAPOLEON study
Presenter: Kenta Nio
Session: e-Poster Display Session