Xiaoling Ma1, Liming Xia2, Jun Chen3, Weijia Wan4, Wen Zhou4. 1. Medical Imaging Center, People's Hospital of Ningxia Hui Autonomous Region, Yinchuan, China. 2. Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, 1095 Jiefang Road, Qiaokou District, Wuhan, 430030, Hubei, China. xialiming2017@outlook.com. 3. GE Healthcare, Wuhan, China. 4. Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, 1095 Jiefang Road, Qiaokou District, Wuhan, 430030, Hubei, China.
Abstract
OBJECTIVE: To develop and validate a deep learning (DL) signature for predicting lymph node (LN) metastasis in patients with lung adenocarcinoma. METHODS: A total of 612 patients with pathologically-confirmed lung adenocarcinoma were retrospectively enrolled and were randomly divided into training cohort (n = 489) and internal validation cohort (n = 123). Besides, 108 patients were enrolled and constituted an independent test cohort (n = 108). Patients' clinical characteristics and CT semantic features were collected. The radiomics features were derived from contrast-enhanced CT images. The clinical-semantic model and radiomics signature were built to predict LN metastasis. Furthermore, Swin Transformer was adopted to develop a DL signature predictive of LN metastasis. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, calibration curve, and decision curve analysis. The comparisons of AUC were conducted by the DeLong test. RESULTS: The proposed DL signature yielded an AUC of 0.948-0.961 across all three cohorts, significantly superior to both clinical-semantic model and radiomics signature (all p < 0.05). The calibration curves show that DL signature predicted probabilities fit well the actual observed probabilities of LN metastasis. DL signature gained a higher net benefit than both clinical-semantic model and radiomics signature. The incorporation of radiomics signature or clinical-semantic risk predictors failed to reveal an incremental value over the DL signature. CONCLUSIONS: The proposed DL signature based on Swin Transformer achieved a promising performance in predicting LN metastasis and could confer important information in noninvasive mediastinal LN staging and individualized therapeutic options. KEY POINTS: • Accurate prediction for lymph node metastasis is crucial to formulate individualized therapeutic options for patients with lung adenocarcinoma. • The deep learning signature yielded an AUC of 0.948-0.961 across all three cohorts in predicting lymph node metastasis, superior to both radiomics signature and clinical-semantic model. • The incorporation of radiomics signature or clinical-semantic risk predictors into deep learning signature failed to reveal an incremental value over deep learning signature.
OBJECTIVE: To develop and validate a deep learning (DL) signature for predicting lymph node (LN) metastasis in patients with lung adenocarcinoma. METHODS: A total of 612 patients with pathologically-confirmed lung adenocarcinoma were retrospectively enrolled and were randomly divided into training cohort (n = 489) and internal validation cohort (n = 123). Besides, 108 patients were enrolled and constituted an independent test cohort (n = 108). Patients' clinical characteristics and CT semantic features were collected. The radiomics features were derived from contrast-enhanced CT images. The clinical-semantic model and radiomics signature were built to predict LN metastasis. Furthermore, Swin Transformer was adopted to develop a DL signature predictive of LN metastasis. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), sensitivity, specificity, calibration curve, and decision curve analysis. The comparisons of AUC were conducted by the DeLong test. RESULTS: The proposed DL signature yielded an AUC of 0.948-0.961 across all three cohorts, significantly superior to both clinical-semantic model and radiomics signature (all p < 0.05). The calibration curves show that DL signature predicted probabilities fit well the actual observed probabilities of LN metastasis. DL signature gained a higher net benefit than both clinical-semantic model and radiomics signature. The incorporation of radiomics signature or clinical-semantic risk predictors failed to reveal an incremental value over the DL signature. CONCLUSIONS: The proposed DL signature based on Swin Transformer achieved a promising performance in predicting LN metastasis and could confer important information in noninvasive mediastinal LN staging and individualized therapeutic options. KEY POINTS: • Accurate prediction for lymph node metastasis is crucial to formulate individualized therapeutic options for patients with lung adenocarcinoma. • The deep learning signature yielded an AUC of 0.948-0.961 across all three cohorts in predicting lymph node metastasis, superior to both radiomics signature and clinical-semantic model. • The incorporation of radiomics signature or clinical-semantic risk predictors into deep learning signature failed to reveal an incremental value over deep learning signature.
Authors: Asha Kandathil; Fernando U Kay; Yasmeen M Butt; Jason W Wachsmann; Rathan M Subramaniam Journal: Radiographics Date: 2018 Nov-Dec Impact factor: 5.333
Authors: Nasser K Altorki; Xiaofei Wang; Dennis Wigle; Lin Gu; Gail Darling; Ahmad S Ashrafi; Rodney Landrenau; Daniel Miller; Moishe Liberman; David R Jones; Robert Keenan; Massimo Conti; Gavin Wright; Linda J Veit; Suresh S Ramalingam; Mohamed Kamel; Harvey I Pass; John D Mitchell; Thomas Stinchcombe; Everett Vokes; Leslie J Kohman Journal: Lancet Respir Med Date: 2018-11-12 Impact factor: 30.700
Authors: Kyoungjune Pak; Sohyun Park; Gi Jeong Cheon; Keon Wook Kang; In-Joo Kim; Dong Soo Lee; E Edmund Kim; June-Key Chung Journal: Ann Nucl Med Date: 2015-02-06 Impact factor: 2.668