Deep Multi-path Network Integrating Incomplete Biomarker and Chest CT Data for Evaluating Lung Cancer Risk

Longitudinal Multimodal Transformer Integrating Imaging and Latent Clinical Signatures From Routine EHRs for Pulmonary Nodule Classification

The accuracy of predictive models for solitary pulmonary nodule (SPN) diagnosis can be greatly increased by incorporating repeat imaging and medical context, such as electronic health records (EHRs). However, clinically routine modalities such as imaging and diagnostic codes can be asynchronous and irregularly sampled over different time scales which are obstacles to longitudinal multimodal learning. In this work, we propose a transformer-based multimodal strategy to integrate repeat imaging with longitudinal clinical signatures from routinely collected EHRs for SPN classification. We perform unsupervised disentanglement of latent clinical signatures and leverage time-distance scaled self-attention to jointly learn from clinical signatures expressions and chest computed tomography (CT) scans. Our classifier is pretrained on 2,668 scans from a public dataset and 1,149 subjects with longitudinal chest CTs, billing codes, medications, and laboratory tests from EHRs of our home institution. Evaluation on 227 subjects with challenging SPNs revealed a significant AUC improvement over a longitudinal multimodal baseline (0.824 vs 0.752 AUC), as well as improvements over a single cross-section multimodal scenario (0.809 AUC) and a longitudinal imaging-only scenario (0.741 AUC). This work demonstrates significant advantages with a novel approach for co-learning longitudinal imaging and non-imaging phenotypes with transformers. Code available at https://github.com/MASILab/lmsignatures.

The impact of the lung EDRN-CVC on Phase 1, 2, & 3 biomarker validation studies

The Early Detection Research Network’s (EDRN) purpose is to discover, develop and validate biomarkers and imaging methods to detect early-stage cancers or at-risk individuals. The EDRN is composed of sites that fall into four categories: Biomarker Developmental Laboratories (BDL), Biomarker Reference Laboratories (BRL), Clinical Validation Centers (CVC) and Data Management and Coordinating Centers. Each component has a crucial role to play within the mission of the EDRN. The primary role of the CVCs is to support biomarker developers through validation trials on promising biomarkers discovered by both EDRN and non-EDRN investigators. The second round of funding for the EDRN Lung CVC at Vanderbilt University Medical Center (VUMC) was funded in October 2016 and we intended to accomplish the three missions of the CVCs: To conduct innovative research on the validation of candidate biomarkers for early cancer detection and risk assessment of lung cancer in an observational study; to compare biomarker performance; and to serve as a resource center for collaborative research within the Network and partner with established EDRN BDLs and BRLs, new laboratories and industry partners. This report outlines the impact of the VUMC EDRN Lung CVC and describes the role in promoting and validating biological and imaging biomarkers.

Cancer Risk Estimation Combining Lung Screening CT with Clinical Data Elements

Purpose

To develop a model to estimate lung cancer risk using lung cancer screening CT and clinical data elements (CDEs) without manual reading efforts.

Materials and Methods

Two screening cohorts were retrospectively studied: the National Lung Screening Trial (NLST; participants enrolled between August 2002 and April 2004) and the Vanderbilt Lung Screening Program (VLSP; participants enrolled between 2015 and 2018). Fivefold cross-validation using the NLST dataset was used for initial development and assessment of the co-learning model using whole CT scans and CDEs. The VLSP dataset was used for external testing of the developed model. Area under the receiver operating characteristic curve (AUC) and area under the precision-recall curve were used to measure the performance of the model. The developed model was compared with published risk-prediction models that used only CDEs or imaging data alone. The Brock model was also included for comparison by imputing missing values for patients without a dominant pulmonary nodule.

Results

A total of 23 505 patients from the NLST (mean age, 62 years ± 5 [standard deviation]; 13 838 men, 9667 women) and 147 patients from the VLSP (mean age, 65 years ± 5; 82 men, 65 women) were included. Using cross-validation on the NLST dataset, the AUC of the proposed co-learning model (AUC, 0.88) was higher than the published models predicted with CDEs only (AUC, 0.69; P < .05) and with images only (AUC, 0.86; P < .05). Additionally, using the external VLSP test dataset, the co-learning model had a higher performance than each of the published individual models (AUC, 0.91 [co-learning] vs 0.59 [CDE-only] and 0.88 [image-only]; P < .05 for both comparisons).

Conclusion

The proposed co-learning predictive model combining chest CT images and CDEs had a higher performance for lung cancer risk prediction than models that contained only CDE or only image data; the proposed model also had a higher performance than the Brock model.Keywords: Computer-aided Diagnosis (CAD), CT, Lung, Thorax Supplemental material is available for this article. © RSNA, 2021.