Novel network improves accuracy of lymph node metastasis prediction in patients with T1 lung adenocarcinoma

Lung cancer is the most lethal cancer in the world. Surgical lobectomy combined with systematic lymph node dissection (LND) is the current preferred treatment for patients with lung cancer.

Accurate prediction of lymph node (LN) metastasis status before operation will avoid invalid LNDs, and thus reduce the risk of recurrence and complications.

A research team led by Prof. Gao Xin from the Suzhou Institute of Biomedical Engineering and Technology (SIBET) of the Chinese Academy of Sciences proposed a novel multi-scale, multi-task, and multi-label classification network (3M-CN) aiming at the LN metastasis prediction for patients with T1 lung adenocarcinoma.

Present image-based preoperative evaluation of LN status for T1 pulmonary adenocarcinoma mainly depends on the judgment of radiologists, which is subjective, time-consuming and with relatively low average accuracy.

The new model, with a backbone of 3D DenseNet, extracts three-dimensional CT features of pulmonary nodules, and fuses different levels of features of pulmonary nodules, with the help of multi-scale feature fusion (MFF) module.

GAO and his team designed a multi-task segmentation module to guide the model to focus more on the nodule region and less on the surrounding structures. This helped realize accurate prediction of LN metastasis risk and multiple related signs evaluation on the basis of multi-label classification task.

Results showed that the accuracy of 3M-CN could achieve 0.948, which is the highest in the current reports. The advantage of the proposed method is that the model can predict the LN metastasis without any intervention of doctors, which is fully automated and intelligent, according to GAO.

Meanwhile, the model provides more semantic explanations related to LN metastasis, enhancing the interpretability of the deep learning model. It increases doctors’ confidence in the model results, and conforms to doctors’ diagnostic process for LN metastasis diagnoses in their workflows.