Longitudinal prediction of lung nodule invasiveness by sequential modelling with common clinical computed tomography (CT) measurements: a prediction accuracy study

Guangyu Tao; Dejun Shi; Lingming Yu; Chunji Chen; Zheng Zhang; Chang Min Park; Edyta Szurowska; Yinan Chen; Rui Wang; Hong Yu

doi:10.21037/tlcr-22-319

Longitudinal prediction of lung nodule invasiveness by sequential modelling with common clinical computed tomography (CT) measurements: a prediction accuracy study

Transl Lung Cancer Res. 2022 May;11(5):845-857. doi: 10.21037/tlcr-22-319.

Authors

Guangyu Tao^#¹, Dejun Shi^#², Lingming Yu^#¹, Chunji Chen³, Zheng Zhang⁴, Chang Min Park^{5

6

7

8}, Edyta Szurowska⁹, Yinan Chen¹, Rui Wang³, Hong Yu¹

Affiliations

¹ Department of Radiology, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China.
² Keya Medical Technology Co. Ltd., Beijing, China.
³ Department of Thoracic Surgery, Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, China.
⁴ School of Biological Science & Medical Engineering, Southeast University, Nanjing, China.
⁵ Department of Radiology, Seoul National University Hospital, Seoul, Korea.
⁶ Department of Radiology, Seoul National University College of Medicine, Seoul, Korea.
⁷ Integrated Major in Innovative Medical Science, Seoul National University, Seoul, Korea.
⁸ Institute of Medical and Biological Engineering, Medical Research Center, Seoul National University, Seoul, Korea.
⁹ 2nd Department of Radiology, Medical University of Gdańsk, Gdańsk, Poland.

^# Contributed equally.

Abstract

Background: Accurate preoperative prediction of the invasiveness of lung nodules on computed tomography (CT) can avoid unnecessary invasive procedures and costs for low-risk patients. While previous studies approached this task using cross-sectional data, this study aimed to utilize the commonly available longitudinal data of lung nodules through sequential modelling based on long short-term memory (LSTM) networks.

Methods: We retrospectively included 171 patients with lung nodules that were followed-up at least once and pathologically diagnosed with adenocarcinoma for model development. Pathological diagnosis was the gold standard for deciding lung nodule invasiveness. For each nodule, a handful of semantic features, including size intensity and interval since first discovery, were obtained from an arbitrary number of CT scans available to individual patients and used as input variables to pre-operatively predict nodule invasiveness. The LSTM-based classifier was optimized by extensive experiments and compared to logistic regression (LR) as baseline with five-fold cross-validation.

Results: The best LSTM-based classifier, capable of receiving data from an arbitrary number of time points, achieved better preoperative prediction of lung nodule invasiveness [area under the curve (AUC), 0.982; accuracy, 0.924; sensitivity, 0.946; specificity, 0.881] than the best LR (AUC, 0.947; accuracy, 0.906; sensitivity, 0.938; specificity, 0.847) classifier.

Conclusions: The longitudinal data of lung nodules, though unevenly spaced and varying in length, can be well modeled by the LSTM, allowing for the accurate prediction of nodule invasiveness. Given that the input variables of the sequential modelling consist of a few semantic features that are easily obtained and interpreted by clinicians, our approach is worthy further investigation for the optimal management of lung nodules.

Keywords: Lung nodule; follow-up computed tomography (follow-up CT); long short-term memory (LSTM); sequential modelling; tumor invasiveness.