Deep Learning Based Long Term Mortality Prediction in the National Lung Screening Trial

In this study, the long-term mortality in the National Lung Screening Trial (NLST) was investigated using a deep learning-based method. Binary classification of the non-lung-cancer mortality (i.e. cardiovascular and respiratory mortality) was performed using neural network models centered around a 3D-ResNet. The models were trained on a participant age, gender, and smoking history matched cohort. Utilising both the 3D CT scan and clinical information, the models can achieve an AUC of 0.73 which outperforms humans at cardiovascular mortality prediction. By interpreting the trained models with 3D saliency maps, we examined the features on the CT scans that correspond to the mortality signal. The saliency maps can potentially assist the clinicians' and radiologists' to identify regions of concern on the image that may indicate the need to adopt preventative healthcare management strategies to prolong the patients' life expectancy.

Lung Images Segmentation and Classification Based on Deep Learning: A New Automated CNN Approach

Lung cancer became a significant health problem worldwide over the past decades. This paper introduces a new generalized framework for lung cancer detection where many different strategies are explored for the classification. The ResNet50 model is applied to classify CT lung images into benign or malignant. Also, the U-Net, which is one of the most used architectures in deep learning for image segmentation, is employed to segment CT images before classification to increase system performance. Moreover, Image Size Dependent Normalization Technique (ISDNT) and Wiener filter are utilized as the preprocessing phase to enhance the images and suppress the noise. Our proposed framework which comprises preprocessing, segmentation and classification phases, is applied on two databases: Lung Nodule Analysis 2016 (Luna 16) and National Lung Screening Trial (NLST). Data augmentation technique is applied to solve the problem of lung CT images deficiency, and consequently, the overfitting of deep models will be avoided. The classification results show that the preprocessing for the CT lung image as the input for ResNet50-U-Net hybrid model achieves the best performance. The proposed model achieves 98.98% accuracy (ACC), 98.65% area under the ROC curve (AUC), 98.99% sensitivity (Se), 98.43% precision (Pr), 98.86% F1- score and 1.9876 s computational time.

Scan-based competing death risk model for reevaluating lung cancer computed tomography screening eligibility

PurposeA baseline CT scan for lung cancer (LC) screening may reveal information indicating that certain LC screening participants can be screened less, and instead require dedicated early cardiac and respiratory clinical input. We aimed to develop and validate competing death (CD) risk models using CT information to identify participants with a low LC and a high CD risk.MethodsParticipant demographics and quantitative CT measures of LC, cardiovascular disease, and chronic obstructive pulmonary disease were considered for deriving a logistic regression model for predicting five-year CD risk using a sample from the National Lung Screening Trial (n=15 000). Multicentric Italian Lung Detection data was used to perform external validation (n=2287).ResultsOur final CD model outperformed an external pre-scan model (CDRAT) in both the derivation (Area under the curve=0.744 [95% confidence interval=0.727 to 0.761] and 0.677 [0.658 to 0.695], respectively) and validation cohorts (0.744 [0.652 to 0.835] and 0.725 [0.633 to 0.816], respectively). By also taking LC incidence risk into consideration, we suggested a risk threshold where a subgroup (6258/23 096, 27%) was identified with a number needed to screen to detect one LC of 216 (versus 23 in the remainder of the cohort) and ratio of 5.41 CDs per LC case (versus 0.88). The respective values in the validation cohort subgroup (774/2287, 34%) were 129 (versus 29) and 1.67 (versus 0.43).ConclusionsEvaluating both LC and CD risks post-scan may improve the efficiency of LC screening and facilitate the initiation of multidisciplinary trajectories among certain participants.

High incidence of concurrent disease states detected during mobile lung cancer screening in an underserved population.

6540 Background: Studies such as the National Lung Screening Trial (NLST; N Engl J Med 2011;365:395-409) have shown a survival benefit to low-dose Lung CT screening in high-risk smokers. Levine Cancer Institute (LCI) initiated the first mobile low dose computerized tomographic (LDCT) lung screening program for underserved populations in 2017. In addition to being able to intervene early in the natural history of lung cancer, the project has also shown a previously unreported high incidence of incidental diseases in this population. We characterize these findings in 1198 patients. Methods: From May 2017, subjects with criteria eligible for NLST screening were identified and underwent LDCT for lung cancer detection. Patients screened in the program were all uninsured or underinsured, mean age 60.8 years, 18% were African American, 3% Latin-x and 78% were rural with an overall 47.1 mean pack-year smoking history. These patients were screened using a novel mobile LDCT (J Clin Oncol 37, 2019 suppl; abstr 6567) created for this program. By December 2020, 1198 patients completed their first screening. All CT scans were reviewed by two separate radiologists and were reviewed for quality assurance by a separate expert multidisciplinary team. Results: Of the 1198 subjects, 84% (1006 subjects) were found by LDCT to have a least one incidental disease. More than half of the subjects (645, 53.8%) had coronary atherosclerosis. Of those, 25% (183) were described to have at least moderate disease with 8% (96) described as severe. Overall, 42% (504) were found to have emphysema and 25% (299) had vascular atherosclerotic disease; 1.8% (22) of those screened had a detected aortic aneurysm. In total, thirty separate disease findings were found (listed from fourth to tenth most common finding: degenerative spine changes [205], cholelithiasis [59], hiatal hernia [52], pericardial effusions [38], fatty liver [32], kidney stone [3]), and cardiomegaly [30]). 3.5% (42) were found to have an undiscovered breast, adrenal, liver or kidney mass that required further workup. Conclusions: The number of incidental findings in our mainly rural underserved subject group was very high (84%). 35.5% of patients in the National Lung Screening Trial died from heart disease or respiratory disease. These numbers have not been overtly discussed and our study confirms the number of concerning incidental diseases that can lead to morbidity or mortality. In this high-risk, underserved population of heavy smokers, the opportunity for positive impact on other disease states can be increased by a mobile lung cancer screening program by increasing access to care.