Current status of lung cancer screening

Validation of a Deep Learning Algorithm for the Detection of Malignant Pulmonary Nodules in Chest Radiographs

IMPORTANCE

The improvement of pulmonary nodule detection, which is a challenging task when using chest radiographs, may help to elevate the role of chest radiographs for the diagnosis of lung cancer.

OBJECTIVE

To assess the performance of a deep learning-based nodule detection algorithm for the detection of lung cancer on chest radiographs from participants in the National Lung Screening Trial (NLST).

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study used data from participants in the NLST ro assess the performance of a deep learning-based artificial intelligence (AI) algorithm for the detection of pulmonary nodules and lung cancer on chest radiographs using separate training (in-house) and validation (NLST) data sets. Baseline (T0) posteroanterior chest radiographs from 5485 participants (full T0 data set) were used to assess lung cancer detection performance, and a subset of 577 of these images (nodule data set) were used to assess nodule detection performance. Participants aged 55 to 74 years who currently or formerly (ie, quit within the past 15 years) smoked cigarettes for 30 pack-years or more were enrolled in the NLST at 23 US centers between August 2002 and April 2004. Information on lung cancer diagnoses was collected through December 31, 2009. Analyses were performed between August 20, 2019, and February 14, 2020.

EXPOSURES

Abnormality scores produced by the AI algorithm.

MAIN OUTCOMES AND MEASURES

The performance of an AI algorithm for the detection of lung nodules and lung cancer on radiographs, with lung cancer incidence and mortality as primary end points.

RESULTS

A total of 5485 participants (mean [SD] age, 61.7 [5.0] years; 3030 men [55.2%]) were included, with a median follow-up duration of 6.5 years (interquartile range, 6.1-6.9 years). For the nodule data set, the sensitivity and specificity of the AI algorithm for the detection of pulmonary nodules were 86.2% (95% CI, 77.8%-94.6%) and 85.0% (95% CI, 81.9%-88.1%), respectively. For the detection of all cancers, the sensitivity was 75.0% (95% CI, 62.8%-87.2%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.8% (95% CI, 2.6%-5.0%), and the negative predictive value was 99.8% (95% CI, 99.6%-99.9%). For the detection of malignant pulmonary nodules in all images of the full T0 data set, the sensitivity was 94.1% (95% CI, 86.2%-100.0%), the specificity was 83.3% (95% CI, 82.3%-84.3%), the positive predictive value was 3.4% (95% CI, 2.2%-4.5%), and the negative predictive value was 100.0% (95% CI, 99.9%-100.0%). In digital radiographs of the nodule data set, the AI algorithm had higher sensitivity (96.0% [95% CI, 88.3%-100.0%] vs 88.0% [95% CI, 75.3%-100.0%]; P = .32) and higher specificity (93.2% [95% CI, 89.9%-96.5%] vs 82.8% [95% CI, 77.8%-87.8%]; P = .001) for nodule detection compared with the NLST radiologists. For malignant pulmonary nodule detection on digital radiographs of the full T0 data set, the sensitivity of the AI algorithm was higher (100.0% [95% CI, 100.0%-100.0%] vs 94.1% [95% CI, 82.9%-100.0%]; P = .32) compared with the NLST radiologists, and the specificity (90.9% [95% CI, 89.6%-92.1%] vs 91.0% [95% CI, 89.7%-92.2%]; P = .91), positive predictive value (8.2% [95% CI, 4.4%-11.9%] vs 7.8% [95% CI, 4.1%-11.5%]; P = .65), and negative predictive value (100.0% [95% CI, 100.0%-100.0%] vs 99.9% [95% CI, 99.8%-100.0%]; P = .32) were similar to those of NLST radiologists.

CONCLUSIONS AND RELEVANCE

In this study, the AI algorithm performed better than NLST radiologists for the detection of pulmonary nodules on digital radiographs. When used as a second reader, the AI algorithm may help to detect lung cancer.

Synchrotron tomographic images from human lung adenocarcinoma: Three-dimensional reconstruction and histologic correlations

High-resolution tomographic images using synchrotron X-rays are expected to provide detailed reflection of microstructures, thereby allowing for the examination of histologic structures without destruction of the specimen. This study aims to evaluate the synchrotron tomographic images of mixed ground-glass opacity excised on 5-mm sections in comparison to pathologic examination. The Institutional Review Board of our institute approved this retrospective study, and written informed consent was obtained from each patient whose lung tissue would be used. Obtained lung cancer specimens were brought to the multiple Wiggler 6C beam line at the Pohang Light Source (PLS-II) in Korea, and phase contrast X-ray images were obtained in November 2016. The X-ray emanated from a bending magnet of the electron storage ring with electron energy of 3 GeV, and a typical beam current was 320 mA. Reconstructed tomographic images were compared with images from histologic slides obtained from the same samples. Pulmonary microstructures including terminal bronchioles, alveolar sacs, and vasculature were identified with phase contrast X-ray images. Images from normal lung tissue and mixed ground-glass opacity were clearly distinguishable. Hyperplasia of the interalveolar septum and dysplasia of microstructure were clearly identified. The imaging findings correlated well with hematoxylin-eosin stained specimens. Tomographic images using synchrotron radiation have the potential for clinical applications. With refinement, this technique may become a diagnostic tool for detection of lung cancer.

Video-assisted thoracic surgery and open chest surgery in lung cancer treatment: present and future

Surgical resection remains the most effective treatment of early stage lung cancer. The surgical approach has evolved, and now consists primarily of video-assisted thoracic surgery (VATS) and more limited incisions even with open techniques. Both approaches have their place. Many factors contribute to deciding whether one or the other is better for a particular tumor, patient and in a particular setting and region. Video assisted surgery, where appropriate, is associated with fewer complications and a shorter hospital stay, and similar long term survival. But modern open surgery is also associated with good results. This article reviews the data and discusses considerations to weigh in finding the right balance between the video-assisted and the open approaches.

SCT Promoter Methylation is a Highly Discriminative Biomarker for Lung and Many Other Cancers

Aberrant DNA methylation has long been implicated in cancers. In this work we present a highly discriminative DNA methylation biomarker for non-small cell lung cancers and fourteen other cancers. Based on 69 NSCLC cell lines and 257 cancer-free lung tissues we identified a CpG island in SCT gene promoter which was verified by qMSP experiment in 15 NSCLC cell lines and 3 immortalized human respiratory epithelium cells. In addition, we found that SCT promoter was methylated in 23 cancer cell lines involving >10 cancer types profiled by ENCODE. We found that SCT promoter is hyper-methylated in primary tumors from TCGA lung cancer cohort. Additionally, we found that SCT promoter is methylated at high frequencies in fifteen malignancies and is not methylated in~1000 non-cancerous tissues across >30 organ types. Our study indicates that SCT promoter methylation is a highly discriminative biomarker for lung and many other cancers.

Multimodal non-linear optical imaging for label-free differentiation of lung cancerous lesions from normal and desmoplastic tissues

Lung carcinoma is the leading cause of cancer-related death in the United States, and non-small cell carcinoma accounts for 85% of all lung cancer cases. One major characteristic of non-small cell carcinoma is the appearance of desmoplasia and deposition of dense extracellular collagen around the tumor. The desmoplastic response provides a radiologic target but may impair sampling during traditional image-guided needle biopsy and is difficult to differentiate from normal tissues using single label free imaging modality; for translational purposes, label-free techniques provide a more promising route to clinics. We thus investigated the potential of using multimodal, label free optical microscopy that incorporates Coherent Anti-Stokes Raman Scattering (CARS), Two-Photon Excited AutoFluorescence (TPEAF), and Second Harmonic Generation (SHG) techniques for differentiating lung cancer from normal and desmoplastic tissues. Lung tissue samples from patients were imaged using CARS, TPEAF, and SHG for comparison and showed that the combination of the three non-linear optics techniques is essential for attaining reliable differentiation. These images also illustrated good pathological correlation with hematoxylin and eosin (H&E) stained sections from the same tissue samples. Automated image analysis algorithms were developed for quantitative segmentation and feature extraction to enable lung tissue differentiation. Our results indicate that coupled with automated morphology analysis, the proposed tri-modal nonlinear optical imaging technique potentially offers a powerful translational strategy to differentiate cancer lesions reliably from surrounding non-tumor and desmoplastic tissues.