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
420TiP - UpSwinG: Real-world study of TKI activity in patients with EGFR mutation-positive (EGFRm+) NSCLC with uncommon mutations, and sequencing of afatinib followed by osimertinib
Presenter: Satoru Miura
Session: e-Poster Display Session
443TiP - A multicenter, open-label, randomized phase II study to compare the efficacy and safety of lenvatinib in combination with ifosfamide and etoposide versus ifosfamide and etoposide in children, adolescents, and young adults with relapsed or refractory osteosarcoma (OLIE; ITCC-082)
Presenter: Nathalie Gaspar
Session: e-Poster Display Session
7P - Machine learning intratumoral and axillary lymph node magnetic resonance imaging radiomics for predicting axillary lymph node metastasis in patients with early-stage invasive breast cancer (RBC-01 Study)
Presenter: Yujie Tan
Session: e-Poster Display Session
8P - Knowledge, practice and attitudes of physicians in low- and middle-income countries (LMIC) on fertility and pregnancy-related issues in young breast cancer patients
Presenter: Shah Zeb Khan
Session: e-Poster Display Session
9P - Survival status of elderly women with HR+ early breast cancer: An analysis of SEER database
Presenter: Wang Hao
Session: e-Poster Display Session
10P - Neoadjuvant immunotherapy plus chemotherapy in early triple-negative breast cancer: A meta-analysis of randomized controlled trials
Presenter: Jessa Gilda Pandy
Session: e-Poster Display Session
11P - Genetically predicted bipolar disorder is causally associated with increased risk of breast cancer: A Mendelian randomization analysis
Presenter: Haoxin Peng
Session: e-Poster Display Session
12P - Stromal tumour-infiltrating lymphocytes in human epidermal growth factor receptor 2-overexpressing breast cancer: Association with negative nodal metastasis
Presenter: Ren Xiaoqiu
Session: e-Poster Display Session
13P - A retrospective observational study on neoadjuvant chemotherapy in older adults based on the Joint Breast Cancer Registry Singapore
Presenter: Johan Chan
Session: e-Poster Display Session