Sensitivity and specificity of chest x-ray screening for lung cancer

Better performance of deep learning pulmonary nodule detection using chest radiography with pixel level labels in reference to computed tomography: data quality matters

Labeling errors can significantly impact the performance of deep learning models used for screening chest radiographs. The deep learning model for detecting pulmonary nodules is particularly vulnerable to such errors, mainly because normal chest radiographs and those with nodules obscured by ribs appear similar. Thus, high-quality datasets referred to chest computed tomography (CT) are required to prevent the misclassification of nodular chest radiographs as normal. From this perspective, a deep learning strategy employing chest radiography data with pixel-level annotations referencing chest CT scans may improve nodule detection and localization compared to image-level labels. We trained models using a National Institute of Health chest radiograph-based labeling dataset and an AI-HUB CT-based labeling dataset, employing DenseNet architecture with squeeze-and-excitation blocks. We developed four models to assess whether CT versus chest radiography and pixel-level versus image-level labeling would improve the deep learning model's performance to detect nodules. The models' performance was evaluated using two external validation datasets. The AI-HUB dataset with image-level labeling outperformed the NIH dataset (AUC 0.88 vs 0.71 and 0.78 vs. 0.73 in two external datasets, respectively; both p < 0.001). However, the AI-HUB data annotated at the pixel level produced the best model (AUC 0.91 and 0.86 in external datasets), and in terms of nodule localization, it significantly outperformed models trained with image-level annotation data, with a Dice coefficient ranging from 0.36 to 0.58. Our findings underscore the importance of accurately labeled data in developing reliable deep learning algorithms for nodule detection in chest radiography.

Knowledge, Attitudes, and Practice Patterns of Lung Cancer Screening Among Physicians in Saudi Arabia

BACKGROUND

Lung cancer remains the primary cause of death connected to cancer on a worldwide scale. Obtaining a deep understanding of the knowledge, attitudes, and behavior patterns of doctors is essential for developing successful strategies to improve lung cancer screening. This study aims to identify the attitudes, beliefs, referral practices, and knowledge of lung cancer screening among physicians in Saudi Arabia.

METHODS

An online survey was conducted from July to December 2023 to investigate the attitudes, beliefs, referral practices, and knowledge of lung cancer screening, and adherence to lung cancer screening recommendations among physicians in Saudi Arabia. Internal medicine, family medicine, and pulmonology physicians of all levels (consultants, senior registrars, and residents) who are currently practicing medicine in Saudi Arabia formed the study population. This study employed a previously developed questionnaire. Binary logistic regression analysis was employed to identify factors that indicate a better degree of knowledge and a positive attitude toward lung cancer screening.

RESULTS

This study involved a total of 96 physicians. The study participants demonstrated a significant degree of understanding regarding lung cancer screening, with an average knowledge score of 5.8 (SD: 1.7) out of 8, equivalent to 72.5% of the highest possible score. The accuracy rate for knowledge items varied from 44.8% to 91.7%. The study participants had a moderately favorable attitude toward lung cancer screening, as shown by a mean attitude score of 14.4 (SD: 3.7) out of a maximum possible score of 30, which corresponds to 48.0% of the highest achievable score. Around 36.5% of the survey participants reported engaging in the practice of discussing the results of lung cancer screening with patients. The primary obstacles frequently cited were challenges in patient scheduling, insufficient time to discuss lung cancer screening during clinic appointments, and patient refusal, constituting 59.4%, 53.1%, and 53.1% of the identified barriers, respectively. Physicians in Saudi Arabia, particularly those employed in private hospitals, demonstrated a higher level of knowledge of lung cancer screening compared to others (p < 0.05). In contrast, individuals with 11-15 years of experience were shown to have a 78.0% lower likelihood of being educated about lung cancer screening compared to their counterparts (p < 0.05).

CONCLUSION

The study's results indicate that there is a need for the development of specialized educational initiatives aimed at Saudi Arabian physicians, particularly those with 11 to 15 years of experience who exhibit a limited understanding of lung cancer screening. Utilizing programs that provide continuing medical education would aid in their education. There is a need to facilitate communication between physicians and patients. It is critical to address the identified issues, such as streamlining the appointment scheduling process and ensuring patients have sufficient time during clinic visits. Furthermore, it is critical for the success of nationwide screening initiatives to foster collaboration between the public and private healthcare sectors.

Development of a novel artificial intelligence algorithm to detect pulmonary nodules on chest radiography

BACKGROUND

In this study, we aimed to develop a novel artificial intelligence (AI) algorithm to support pulmonary nodule detection, which will enable physicians to efficiently interpret chest radiographs for lung cancer diagnosis.

METHODS

We analyzed chest X-ray images obtained from a health examination center in Fukushima and the National Institutes of Health (NIH) Chest X-ray 14 dataset. We categorized these data into two types: type A included both Fukushima and NIH datasets, and type B included only the Fukushima dataset. We also demonstrated pulmonary nodules in the form of a heatmap display on each chest radiograph and calculated the positive probability score as an index value.

RESULTS

Our novel AI algorithms had a receiver operating characteristic (ROC) area under the curve (AUC) of 0.74, a sensitivity of 0.75, and a specificity of 0.60 for the type A dataset. For the type B dataset, the respective values were 0.79, 0.72, and 0.74. The algorithms in both the type A and B datasets were superior to the accuracy of radiologists and similar to previous studies.

CONCLUSIONS

The proprietary AI algorithms had a similar accuracy for interpreting chest radiographs when compared with previous studies and radiologists. Especially, we could train a high quality AI algorithm, even with our small type B data set. However, further studies are needed to improve and further validate the accuracy of our AI algorithm.

Lung Cancer Screening in Asia: An Expert Consensus Report

INTRODUCTION

The incidence and mortality of lung cancer are highest in Asia compared with Europe and USA, with the incidence and mortality rates being 34.4 and 28.1 per 100,000 respectively in East Asia. Diagnosing lung cancer at early stages makes the disease amenable to curative treatment and reduces mortality. In some areas in Asia, limited availability of robust diagnostic tools and treatment modalities, along with variations in specific health care investment and policies, make it necessary to have a more specific approach for screening, early detection, diagnosis, and treatment of patients with lung cancer in Asia compared with the West.

METHOD

A group of 19 advisors across different specialties from 11 Asian countries, met on a virtual Steering Committee meeting, to discuss and recommend the most affordable and accessible lung cancer screening modalities and their implementation, for the Asian population.

RESULTS

Significant risk factors identified for lung cancer in smokers in Asia include age 50 to 75 years and smoking history of more than or equal to 20 pack-years. Family history is the most common risk factor for nonsmokers. Low-dose computed tomography screening is recommended once a year for patients with screening-detected abnormality and persistent exposure to risk factors. However, for high-risk heavy smokers and nonsmokers with risk factors, reassessment scans are recommended at an initial interval of 6 to 12 months with subsequent lengthening of reassessment intervals, and it should be stopped in patients more than 80 years of age or are unable or unwilling to undergo curative treatment.

CONCLUSIONS

Asian countries face several challenges in implementing low-dose computed tomography screening, such as economic limitations, lack of efforts for early detection, and lack of specific government programs. Various strategies are suggested to overcome these challenges in Asia.

Biosensors for the detection of lung cancer biomarkers: A review on biomarkers, transducing techniques and recent graphene-based implementations

Lung cancer remains the leading cause of cancer-related death. In addition to chest X-rays and computerised tomography, the detection of cancer biomarkers serves as an emerging diagnostic tool for lung cancer. This review explores biomarkers including the rat sarcoma gene, the tumour protein 53 gene, the epidermal growth factor receptor, the neuron-specific enolase, the cytokeratin-19 fragment 21-1 and carcinoembryonic antigen as potential indicators of lung cancer. Biosensors, which utilise various transduction techniques, present a promising solution for the detection of lung cancer biomarkers. Therefore, this review also explores the working principles and recent implementations of transducers in the detection of lung cancer biomarkers. The transducing techniques explored include optical techniques, electrochemical techniques and mass-based techniques for detecting biomarkers and cancer-related volatile organic compounds. Graphene has outstanding properties in terms of charge transfer, surface area, thermal conductivity and optical characteristics, on top of allowing easy incorporation of other nanomaterials. Exploiting the collective merits of both graphene and biosensor is an emerging trend, as evidenced by the growing number of studies on graphene-based biosensors for the detection of lung cancer biomarkers. This work provides a comprehensive review of these studies, including information on modification schemes, nanomaterials, amplification strategies, real sample applications, and sensor performance. The paper concludes with a discussion of the challenges and future outlook of lung cancer biosensors, including scalable graphene synthesis, multi-biomarker detection, portability, miniaturisation, financial support, and commercialisation.

A systematic approach to deep learning-based nodule detection in chest radiographs

Lung cancer is a serious disease responsible for millions of deaths every year. Early stages of lung cancer can be manifested in pulmonary lung nodules. To assist radiologists in reducing the number of overseen nodules and to increase the detection accuracy in general, automatic detection algorithms have been proposed. Particularly, deep learning methods are promising. However, obtaining clinically relevant results remains challenging. While a variety of approaches have been proposed for general purpose object detection, these are typically evaluated on benchmark data sets. Achieving competitive performance for specific real-world problems like lung nodule detection typically requires careful analysis of the problem at hand and the selection and tuning of suitable deep learning models. We present a systematic comparison of state-of-the-art object detection algorithms for the task of lung nodule detection. In this regard, we address the critical aspect of class imbalance and and demonstrate a data augmentation approach as well as transfer learning to boost performance. We illustrate how this analysis and a combination of multiple architectures results in state-of-the-art performance for lung nodule detection, which is demonstrated by the proposed model winning the detection track of the Node21 competition. The code for our approach is available at https://github.com/FinnBehrendt/node21-submit.

Leveraging Deep Learning Decision-Support System in Specialized Oncology Center: A Multi-Reader Retrospective Study on Detection of Pulmonary Lesions in Chest X-ray Images

Chest X-ray (CXR) is considered to be the most widely used modality for detecting and monitoring various thoracic findings, including lung carcinoma and other pulmonary lesions. However, X-ray imaging shows particular limitations when detecting primary and secondary tumors and is prone to reading errors due to limited resolution and disagreement between radiologists. To address these issues, we developed a deep-learning-based automatic detection algorithm (DLAD) to automatically detect and localize suspicious lesions on CXRs. Five radiologists were invited to retrospectively evaluate 300 CXR images from a specialized oncology center, and the performance of individual radiologists was subsequently compared with that of DLAD. The proposed DLAD achieved significantly higher sensitivity (0.910 (0.854–0.966)) than that of all assessed radiologists (RAD 10.290 (0.201–0.379), p < 0.001, RAD 20.450 (0.352–0.548), p < 0.001, RAD 30.670 (0.578–0.762), p < 0.001, RAD 40.810 (0.733–0.887), p = 0.025, RAD 50.700 (0.610–0.790), p < 0.001). The DLAD specificity (0.775 (0.717–0.833)) was significantly lower than for all assessed radiologists (RAD 11.000 (0.984–1.000), p < 0.001, RAD 20.970 (0.946–1.000), p < 0.001, RAD 30.980 (0.961–1.000), p < 0.001, RAD 40.975 (0.953–0.997), p < 0.001, RAD 50.995 (0.985–1.000), p < 0.001). The study results demonstrate that the proposed DLAD could be utilized as a decision-support system to reduce radiologists’ false negative rate.

Development and Validation of a Deep Learning-Based Synthetic Bone-Suppressed Model for Pulmonary Nodule Detection in Chest Radiographs

Importance

Dual-energy chest radiography exhibits better sensitivity than single-energy chest radiography, partly due to its ability to remove overlying anatomical structures.

Objectives

To develop and validate a deep learning-based synthetic bone-suppressed (DLBS) nodule-detection algorithm for pulmonary nodule detection on chest radiographs.

Design, Setting, and Participants

This decision analytical modeling study used data from 3 centers between November 2015 and July 2019 from 1449 patients. The DLBS nodule-detection algorithm was trained using single-center data (institute 1) of 998 chest radiographs. The DLBS algorithm was validated using 2 external data sets (institute 2, 246 patients; and institute 3, 205 patients). Statistical analysis was performed from March to December 2021.

Exposures

DLBS nodule-detection algorithm.

Main Outcomes and Measures

The nodule-detection performance of DLBS model was compared with the convolution neural network nodule-detection algorithm (original model). Reader performance testing was conducted by 3 thoracic radiologists assisted by the DLBS algorithm or not. Sensitivity and false-positive markings per image (FPPI) were compared.

Results

Training data consisted of 998 patients (539 men [54.0%]; mean [SD] age, 54.2 [9.82] years), and 2 external validation data sets consisted of 246 patients (133 men [54.1%]; mean [SD] age, 55.3 [8.7] years) and 205 patients (105 men [51.2%]; mean [SD] age, 51.8 [9.1] years). Using the external validation data set of institute 2, the bone-suppressed model showed higher sensitivity compared with that of the original model for nodule detection (91.5% [109 of 119] vs 79.8% [95 of 119]; P < .001). The overall mean of FPPI with the bone-suppressed model was reduced compared with the original model (0.07 [17 of 246] vs 0.09 [23 of 246]; P < .001). For the observer performance testing with the data of institute 3, the mean sensitivity of 3 radiologists was 77.5% (95% [CI], 69.9%-85.2%), whereas that of radiologists assisted by DLBS modeling was 92.1% (95% CI, 86.3%-97.3%; P < .001). The 3 radiologists had a reduced number of FPPI when assisted by the DLBS model (0.071 [95% CI, 0.041-0.111] vs 0.151 [95% CI, 0.111-0.210]; P < .001).

Conclusions and Relevance

This decision analytical modeling study found that the DLBS model was more sensitive to detecting pulmonary nodules on chest radiographs compared with the original model. These findings suggest that the DLBS model could be beneficial to radiologists in the detection of lung nodules in chest radiographs without need of the specialized equipment or increase of radiation dose.

A Comprehensive Survey on the Progress, Process, and Challenges of Lung Cancer Detection and Classification

Lung cancer is the primary reason of cancer deaths worldwide, and the percentage of death rate is increasing step by step. There are chances of recovering from lung cancer by detecting it early. In any case, because the number of radiologists is limited and they have been working overtime, the increase in image data makes it hard for them to evaluate the images accurately. As a result, many researchers have come up with automated ways to predict the growth of cancer cells using medical imaging methods in a quick and accurate way. Previously, a lot of work was done on computer-aided detection (CADe) and computer-aided diagnosis (CADx) in computed tomography (CT) scan, magnetic resonance imaging (MRI), and X-ray with the goal of effective detection and segmentation of pulmonary nodule, as well as classifying nodules as malignant or benign. But still, no complete comprehensive review that includes all aspects of lung cancer has been done. In this paper, every aspect of lung cancer is discussed in detail, including datasets, image preprocessing, segmentation methods, optimal feature extraction and selection methods, evaluation measurement matrices, and classifiers. Finally, the study looks into several lung cancer-related issues with possible solutions.

Deep Learning and Binary Relevance Classification of Multiple Diseases using Chest X-Ray images. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:2794-2797. [PMID: 34891829 DOI: 10.1109/embc46164.2021.9629846]

Disease detection using chest X-ray (CXR) images is one of the most popular radiology methods to diagnose diseases through a visual inspection of abnormal symptoms in the lung region. A wide variety of diseases such as pneumonia, heart failure and lung cancer can be detected using CXRs. Although CXRs can show the symptoms of a variety of diseases, detecting and manually classifying those diseases can be difficult and time-consuming adding to clinicians' work burden. Research shows that nearly 90% of mistakes made in a lung cancer diagnosis involved chest radiography. A variety of algorithms and computer-assisted diagnosis tools (CAD) were proposed to assist radiologists in the interpretation of medical images to reduce diagnosis errors. In this work, we propose a deep learning approach to screen multiple diseases using more than 220,000 images from the CheXpert dataset. The proposed binary relevance approach using Deep Convolutional Neural Networks (CNNs) achieves high performance results and outperforms past published work in this area.Clinical relevance- This application can be used to support physicians ans speed-up the diagnosis work. The proposed CAD can increase the confidence in the diagnosis or suggest a second opinion. The CAD can also be used in emergency situations when a radiologist is not available immediately.

Artificial intelligence-supported lung cancer detection by multi-institutional readers with multi-vendor chest radiographs: a retrospective clinical validation study

Background

We investigated the performance improvement of physicians with varying levels of chest radiology experience when using a commercially available artificial intelligence (AI)-based computer-assisted detection (CAD) software to detect lung cancer nodules on chest radiographs from multiple vendors.

Methods

Chest radiographs and their corresponding chest CT were retrospectively collected from one institution between July 2017 and June 2018. Two author radiologists annotated pathologically proven lung cancer nodules on the chest radiographs while referencing CT. Eighteen readers (nine general physicians and nine radiologists) from nine institutions interpreted the chest radiographs. The readers interpreted the radiographs alone and then reinterpreted them referencing the CAD output. Suspected nodules were enclosed with a bounding box. These bounding boxes were judged correct if there was significant overlap with the ground truth, specifically, if the intersection over union was 0.3 or higher. The sensitivity, specificity, accuracy, PPV, and NPV of the readers’ assessments were calculated.

Results

In total, 312 chest radiographs were collected as a test dataset, including 59 malignant images (59 nodules of lung cancer) and 253 normal images. The model provided a modest boost to the reader’s sensitivity, particularly helping general physicians. The performance of general physicians was improved from 0.47 to 0.60 for sensitivity, from 0.96 to 0.97 for specificity, from 0.87 to 0.90 for accuracy, from 0.75 to 0.82 for PPV, and from 0.89 to 0.91 for NPV while the performance of radiologists was improved from 0.51 to 0.60 for sensitivity, from 0.96 to 0.96 for specificity, from 0.87 to 0.90 for accuracy, from 0.76 to 0.80 for PPV, and from 0.89 to 0.91 for NPV. The overall increase in the ratios of sensitivity, specificity, accuracy, PPV, and NPV were 1.22 (1.14–1.30), 1.00 (1.00–1.01), 1.03 (1.02–1.04), 1.07 (1.03–1.11), and 1.02 (1.01–1.03) by using the CAD, respectively.

Conclusion

The AI-based CAD was able to improve the ability of physicians to detect nodules of lung cancer in chest radiographs. The use of a CAD model can indicate regions physicians may have overlooked during their initial assessment.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-021-08847-9.

A Highly Reliable Convolutional Neural Network Based Soft Tissue Sarcoma Metastasis Detection from Chest X-ray Images: A Retrospective Cohort Study

Simple Summary

Soft tissue sarcomas are relatively rare malignant diseases. Part of the diagnosis and follow-up includes medical imaging of the thorax for detection of lung metastases. A Python script was created and trained using a set of lung X-rays and concordant CT scans from a high-volume German-speaking sarcoma center. It is capable of detecting malignant metastasis in the lung with a precision of 71.2%, specificity of 90.5%, sensitivity of 94% and accuracy of 91.2%. Furthermore, the program was able to detect even small nodules with a size <1 cm in conventional X-rays of the thorax. This algorithm was implemented into our daily clinical practice alongside with the radiologists’ findings. With this tool we aim to improve the quality of our service and reduce the expenditure of time.

Abstract

Introduction: soft tissue sarcomas are a subset of malignant tumors that are relatively rare and make up 1% of all malignant tumors in adulthood. Due to the rarity of these tumors, there are significant differences in quality in the diagnosis and treatment of these tumors. One paramount aspect is the diagnosis of hematogenous metastases in the lungs. Guidelines recommend routine lung imaging by means of X-rays. With the ever advancing AI-based diagnostic support, there has so far been no implementation for sarcomas. The aim of the study was to utilize AI to obtain analyzes regarding metastasis on lung X-rays in the most possible sensitive and specific manner in sarcoma patients. Methods: a Python script was created and trained using a set of lung X-rays with sarcoma metastases from a high-volume German-speaking sarcoma center. 26 patients with lung metastasis were included. For all patients chest X-ray with corresponding lung CT scans, and histological biopsies were available. The number of trainable images were expanded to 600. In order to evaluate the biological sensitivity and specificity, the script was tested on lung X-rays with a lung CT as control. Results: in this study we present a new type of convolutional neural network-based system with a precision of 71.2%, specificity of 90.5%, sensitivity of 94%, recall of 94% and accuracy of 91.2%. A good detection of even small findings was determined. Discussion: the created script establishes the option to check lung X-rays for metastases at a safe level, especially given this rare tumor entity.

Deep Learning for Detection of Pulmonary Metastasis on Chest Radiographs

Background A computer-aided detection (CAD) system may help surveillance for pulmonary metastasis at chest radiography in situations where there is limited access to CT. Purpose To evaluate whether a deep learning (DL)-based CAD system can improve diagnostic yield for newly visible lung metastasis on chest radiographs in patients with cancer. Materials and Methods A regulatory-approved CAD system for lung nodules was implemented to interpret chest radiographs from patients referred by the medical oncology department in clinical practice. In this retrospective diagnostic cohort study, chest radiographs interpreted with assistance from a CAD system after the implementation (January to April 2019, CAD-assisted interpretation group) and those interpreted before the implementation (September to December 2018, conventional interpretation group) of the CAD system were consecutively included. The diagnostic yield (frequency of true-positive detections) and false-referral rate (frequency of false-positive detections) of formal reports of chest radiographs for newly visible lung metastasis were compared between the two groups using generalized estimating equations. Propensity score matching was performed between the two groups for age, sex, and primary cancer. Results A total of 2916 chest radiographs from 1521 patients (1546 men, 1370 women; mean age, 62 years) and 5681 chest radiographs from 3456 patients (2941 men, 2740 women; mean age, 62 years) were analyzed in the CAD-assisted interpretation and conventional interpretation groups, respectively. The diagnostic yield for newly visible metastasis was higher in the CAD-assisted interpretation group (0.86%, 25 of 2916 [95% CI: 0.58, 1.3] vs 0.32%, 18 of 568 [95% CI: 0.20, 0.50%]; P = .004). The false-referral rate in the CAD-assisted interpretation group (0.34%, 10 of 2916 [95% CI: 0.19, 0.64]) was not inferior to that in the conventional interpretation group (0.25%, 14 of 5681 [95% CI: 0.15, 0.42]) at the noninferiority margin of 0.5% (95% CI of difference: -0.15, 0.35). Conclusion A deep learning-based computer-aided detection system improved the diagnostic yield for newly visible metastasis on chest radiographs in patients with cancer with a similar false-referral rate. © RSNA, 2021 Online supplemental material is available for this article.

Augmenting lung cancer diagnosis on chest radiographs: positioning artificial intelligence to improve radiologist performance

AIM

To evaluate the role that artificial intelligence (AI) could play in assisting radiologists as the first reader of chest radiographs (CXRs), to increase the accuracy and efficiency of lung cancer diagnosis by flagging positive cases before passing the remaining examinations to standard reporting.

MATERIALS AND METHODS

A dataset of 400 CXRs including 200 difficult lung cancer cases was curated. Examinations were reviewed by three FRCR radiologists and an AI algorithm to establish performance in tumour identification. AI and radiologist labels were combined retrospectively to simulate the proposed AI triage workflow.

RESULTS

When used as a standalone algorithm, AI classification was equivalent to the average radiologist performance. The best overall performances were achieved when AI was combined with radiologists, with an average reduction of missed cancers of 60%. Combination with AI also standardised the performance of radiologists. The greatest improvements were observed when common sources of errors were present, such as distracting findings.

DISCUSSION

The proposed AI implementation pathway stands to reduce radiologist errors and improve clinician reporting performance. Furthermore, taking a radiologist-centric approach in the development of clinical AI holds promise for catching systematically missed lung cancers. This represents a tremendous opportunity to improve patient outcomes for lung cancer diagnosis.

Added Value of Deep Learning-based Detection System for Multiple Major Findings on Chest Radiographs: A Randomized Crossover Study

Background Previous studies assessing the effects of computer-aided detection on observer performance in the reading of chest radiographs used a sequential reading design that may have biased the results because of reading order or recall bias. Purpose To compare observer performance in detecting and localizing major abnormal findings including nodules, consolidation, interstitial opacity, pleural effusion, and pneumothorax on chest radiographs without versus with deep learning-based detection (DLD) system assistance in a randomized crossover design. Materials and Methods This study included retrospectively collected normal and abnormal chest radiographs between January 2016 and December 2017 (https://cris.nih.go.kr/; registration no. KCT0004147). The radiographs were randomized into two groups, and six observers, including thoracic radiologists, interpreted each radiograph without and with use of a commercially available DLD system by using a crossover design with a washout period. Jackknife alternative free-response receiver operating characteristic (JAFROC) figure of merit (FOM), area under the receiver operating characteristic curve (AUC), sensitivity, specificity, false-positive findings per image, and reading times of observers with and without the DLD system were compared by using McNemar and paired t tests. Results A total of 114 normal (mean patient age ± standard deviation, 51 years ± 11; 58 men) and 114 abnormal (mean patient age, 60 years ± 15; 75 men) chest radiographs were evaluated. The radiographs were randomized to two groups: group A (n = 114) and group B (n = 114). Use of the DLD system improved the observers' JAFROC FOM (from 0.90 to 0.95, P = .002), AUC (from 0.93 to 0.98, P = .002), per-lesion sensitivity (from 83% [822 of 990 lesions] to 89.1% [882 of 990 lesions], P = .009), per-image sensitivity (from 80% [548 of 684 radiographs] to 89% [608 of 684 radiographs], P = .009), and specificity (from 89.3% [611 of 684 radiographs] to 96.6% [661 of 684 radiographs], P = .01) and reduced the reading time (from 10-65 seconds to 6-27 seconds, P < .001). The DLD system alone outperformed the pooled observers (JAFROC FOM: 0.96 vs 0.90, respectively, P = .007; AUC: 0.98 vs 0.93, P = .003). Conclusion Observers including thoracic radiologists showed improved performance in the detection and localization of major abnormal findings on chest radiographs and reduced reading time with use of a deep learning-based detection system. © RSNA, 2021 Online supplemental material is available for this article.

Performance of a Deep Learning Algorithm Compared with Radiologic Interpretation for Lung Cancer Detection on Chest Radiographs in a Health Screening Population

Background The performance of a deep learning algorithm for lung cancer detection on chest radiographs in a health screening population is unknown. Purpose To validate a commercially available deep learning algorithm for lung cancer detection on chest radiographs in a health screening population. Materials and Methods Out-of-sample testing of a deep learning algorithm was retrospectively performed using chest radiographs from individuals undergoing a comprehensive medical check-up between July 2008 and December 2008 (validation test). To evaluate the algorithm performance for visible lung cancer detection, the area under the receiver operating characteristic curve (AUC) and diagnostic measures, including sensitivity and false-positive rate (FPR), were calculated. The algorithm performance was compared with that of radiologists using the McNemar test and the Moskowitz method. Additionally, the deep learning algorithm was applied to a screening cohort undergoing chest radiography between January 2008 and December 2012, and its performances were calculated. Results In a validation test comprising 10 285 radiographs from 10 202 individuals (mean age, 54 years ± 11 [standard deviation]; 5857 men) with 10 radiographs of visible lung cancers, the algorithm's AUC was 0.99 (95% confidence interval: 0.97, 1), and it showed comparable sensitivity (90% [nine of 10 radiographs]) to that of the radiologists (60% [six of 10 radiographs]; P = .25) with a higher FPR (3.1% [319 of 10 275 radiographs] vs 0.3% [26 of 10 275 radiographs]; P < .001). In the screening cohort of 100 525 chest radiographs from 50 070 individuals (mean age, 53 years ± 11; 28 090 men) with 47 radiographs of visible lung cancers, the algorithm's AUC was 0.97 (95% confidence interval: 0.95, 0.99), and its sensitivity and FPR were 83% (39 of 47 radiographs) and 3% (2999 of 100 478 radiographs), respectively. Conclusion A deep learning algorithm detected lung cancers on chest radiographs with a performance comparable to that of radiologists, which will be helpful for radiologists in healthy populations with a low prevalence of lung cancer. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Armato in this issue.

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.

Clinical Implementation of Deep Learning in Thoracic Radiology: Potential Applications and Challenges

Chest X-ray radiography and computed tomography, the two mainstay modalities in thoracic radiology, are under active investigation with deep learning technology, which has shown promising performance in various tasks, including detection, classification, segmentation, and image synthesis, outperforming conventional methods and suggesting its potential for clinical implementation. However, the implementation of deep learning in daily clinical practice is in its infancy and facing several challenges, such as its limited ability to explain the output results, uncertain benefits regarding patient outcomes, and incomplete integration in daily workflow. In this review article, we will introduce the potential clinical applications of deep learning technology in thoracic radiology and discuss several challenges for its implementation in daily clinical practice.

Sensitive detection of lung cancer biomarkers using an aptameric graphene-based nanosensor with enhanced stability

We present an electrolyte-gated graphene field effect transistor (GFET) nanosensor using aptamer for rapid, highly sensitive and specific detection of a lung cancer biomarker interleukin-6 (IL-6) with enhanced stability. The negatively charged aptamer folds into a compact secondary conformation upon binding with IL-6, thus altering the carrier concentration of graphene and yielding a detectable change in the drain-source current I_ds. Aptamer has smaller size than other receptors (e.g. antibodies), making it possible to bring the charged IL-6 more closely to the graphene surface upon affinity binding, thereby enhancing the sensitivity of the detection. Thanks to the higher stability of aptamer over antibodies, which degrade easily with increasing storage time, consistent sensing performance was obtained by our nanosensor over extended-time (>24 h) storage at 25 °C. Additionally, due to the GFET-enabled rapid transduction of the affinity recognition to IL-6, detection of IL-6 can be achieved in several minutes (<10 min). Experimental results indicate that this nanosensor can rapidly and specifically respond to the change in IL-6 levels with high consistency after extended-time storage and a detection limit (DL) down to 139 fM. Therefore, our nanosensor holds great potential for lung cancer diagnosis at its early stage.

Development and Validation of Deep Learning-based Automatic Detection Algorithm for Malignant Pulmonary Nodules on Chest Radiographs

Purpose To develop and validate a deep learning-based automatic detection algorithm (DLAD) for malignant pulmonary nodules on chest radiographs and to compare its performance with physicians including thoracic radiologists. Materials and Methods For this retrospective study, DLAD was developed by using 43 292 chest radiographs (normal radiograph-to-nodule radiograph ratio, 34 067:9225) in 34 676 patients (healthy-to-nodule ratio, 30 784:3892; 19 230 men [mean age, 52.8 years; age range, 18-99 years]; 15 446 women [mean age, 52.3 years; age range, 18-98 years]) obtained between 2010 and 2015, which were labeled and partially annotated by 13 board-certified radiologists, in a convolutional neural network. Radiograph classification and nodule detection performances of DLAD were validated by using one internal and four external data sets from three South Korean hospitals and one U.S. hospital. For internal and external validation, radiograph classification and nodule detection performances of DLAD were evaluated by using the area under the receiver operating characteristic curve (AUROC) and jackknife alternative free-response receiver-operating characteristic (JAFROC) figure of merit (FOM), respectively. An observer performance test involving 18 physicians, including nine board-certified radiologists, was conducted by using one of the four external validation data sets. Performances of DLAD, physicians, and physicians assisted with DLAD were evaluated and compared. Results According to one internal and four external validation data sets, radiograph classification and nodule detection performances of DLAD were a range of 0.92-0.99 (AUROC) and 0.831-0.924 (JAFROC FOM), respectively. DLAD showed a higher AUROC and JAFROC FOM at the observer performance test than 17 of 18 and 15 of 18 physicians, respectively (P < .05), and all physicians showed improved nodule detection performances with DLAD (mean JAFROC FOM improvement, 0.043; range, 0.006-0.190; P < .05). Conclusion This deep learning-based automatic detection algorithm outperformed physicians in radiograph classification and nodule detection performance for malignant pulmonary nodules on chest radiographs, and it enhanced physicians' performances when used as a second reader. © RSNA, 2018 Online supplemental material is available for this article.

A Study of Diagnostic Accuracy Using a Chemical Sensor Array and a Machine Learning Technique to Detect Lung Cancer

Lung cancer is the leading cause of cancer death around the world, and lung cancer screening remains challenging. This study aimed to develop a breath test for the detection of lung cancer using a chemical sensor array and a machine learning technique. We conducted a prospective study to enroll lung cancer cases and non-tumour controls between 2016 and 2018 and analysed alveolar air samples using carbon nanotube sensor arrays. A total of 117 cases and 199 controls were enrolled in the study of which 72 subjects were excluded due to having cancer at another site, benign lung tumours, metastatic lung cancer, carcinoma in situ, minimally invasive adenocarcinoma, received chemotherapy or other diseases. Subjects enrolled in 2016 and 2017 were used for the model derivation and internal validation. The model was externally validated in subjects recruited in 2018. The diagnostic accuracy was assessed using the pathological reports as the reference standard. In the external validation, the areas under the receiver operating characteristic curve (AUCs) were 0.91 (95% CI = 0.79–1.00) by linear discriminant analysis and 0.90 (95% CI = 0.80–0.99) by the supportive vector machine technique. The combination of the sensor array technique and machine learning can detect lung cancer with high accuracy.

Potential circulating miRNA signature for early detection of NSCLC

Circulating microRNAs (c-miRNAs) are promising biomarkers for screening, early detection and prognosis of cancer. The purpose of this investigation was to identify a panel of c-miRNAs in plasma that could contribute to early detection of non-small cell lung cancer (NSCLC). We profiled the expression of 44 unique plasma miRNAs in training set of 34 NSCLC patients and 20 matched healthy individuals by miRCURY LNA™ Universal RT microRNA PCR Panel and calculated dysregulation fold changes using the 2-ΔΔCt equation. Selected plasma miRNAs were then validated by SYBR green q-RT PCR using an independent validation set of plasma samples from NSCLC patients (n: 72) and NC (n: 50). In the validation set, the receiver operating characteristic (ROC) curves were generated for four miRNAs. In the training set, 17 miRNAs were significantly up-regulated and nine were down-regulated in the plasma from NSCLC patients versus matched normal controls. Four miRNAs (miR-21, miR-328, miR-375 and miR-141) were selected for validating their diagnostic value in the testing set. ROC plot analysis showed that a high specificity (98%) and sensitivity (82.7%) in miR-141 in comparing early NSCLC patient and controls. So among these four plasma miRNAs only miR-141 could be promising biomarkers for early detection of NSCLC. In addition to, we found a significant positive correlation between stage and miR-21 expression level (95% CI: 0.687-0.863; p-value < 0.0001). Considering the accessibility and stability of circulating miRNAs, plasma miR-141 is a useful biomarker early detection of NSCLC as a supplement in future screening studies.

A prognostic model for lung adenocarcinoma patient survival with a focus on four miRNAs

There is currently no effective biomarker for determining the survival of patients with lung adenocarcinoma. The purpose of the present study was to construct a prognostic survival model using microRNA (miRNA) expression data from patients with lung adenocarcinoma. miRNA data were obtained from The Cancer Genome Atlas, and patients with lung adenocarcinoma were divided into either the training or validation set based on the random allocation principle. The prognostic model focusing on miRNA was constructed, and patients were divided into high-risk or low-risk groups as per the scores, to assess their survival time. The 5-year survival rate from the subgroups within the high- and low-risk groups was assessed. P-values of the prognostic model in the total population, the training set and validation set were 0.0017, 0.01986 and 0.02773, respectively, indicating that the survival time of the lung adenocarcinoma high-risk group was less than that of the low-risk group. Thus, the model had a good assessment effectiveness for the untreated group (P=0.00088) and the Caucasian patient group (P=0.00043). In addition, the model had the best prediction effect for the 5-year survival rate of the Caucasian patient group (AUC=0.629). In conclusion, the prognostic model developed in the present study can be used as an independent prognostic model for patients with lung adenocarcinoma.

Is chest X-ray screening for lung cancer in smokers cost-effective? Evidence from a population-based study in Italy

Background

After implementation of the PREDICA annual chest X-ray (CXR) screening program in smokers in the general practice setting of Varese-Italy a significant reduction in lung cancer-specific mortality (18 %) was observed. The objective of this study covering July 1997 through December 2006 was to estimate the cost-effectiveness of this intervention.

Methods

We examined detailed information on lung cancer (LC) cases that occurred among smokers invited to be screened in the PREDICA study (Invitation-to-screening Group, n = 5815 subjects) to estimate costs and quality-adjusted life-years (QALYs) from LC diagnosis until death. The control group consisted of 156 screening-eligible smokers from the same area, uninvited and unscreened, who developed LC and were treated by usual care. We calculated the incremental net monetary benefit (INMB) by comparing LC management in screening participants (n = 1244 subjects) and in the Invitation-to-screening group versus control group.

Results

The average number of QALYs since LC diagnosis was 1.7, 1.49 and 1.07, respectively, in screening participants, the invitation-to-screening group, and the control group. The average total cost (screening + management) per LC case was higher in screening participants (€17,516) and the Invitation-to-screening Group (€16,167) than in the control group (€15,503). Assuming a maximum willingness to pay of €30,000/QALY, we found that the intervention was cost-effective with high probability: 79 % for screening participation (screening participants vs. control group) and 95 % for invitation-to-screening (invitation-to-screening group vs. control group).

Conclusions

Based on the PREDICA study, annual CXR screening of high-risk smokers in a general practice setting has high probability of being cost-effective with a maximum willingness to pay of €30,000/QALY.

Evidenced-based management of haemoptysis by otolaryngologists

BACKGROUND

Haemoptysis is an uncommon presenting symptom to the ENT clinic and ward, but has potentially sinister aetiology. This article aims to provide a systematic and evidence-based method of managing patients with haemoptysis.

METHODS

The data in this article are based on a literature search performed using PubMed in August 2013. The keywords used included 'haemoptysis' in combination with 'otolaryngology', 'ENT', 'head & neck', 'diagnosis', 'management', 'investigations' and 'treatment'.

RESULTS

The majority of published literature on the subject is level IV evidence. However, this can guide ENT specialists in assessing, investigating and managing presentations of haemoptysis.

CONCLUSION

Understanding the different causes of haemoptysis is important for the otolaryngologist. The main concern is the detection of a malignant lesion in the upper aerodigestive tract or tracheobronchial tree. A thorough history and systematic examination can aid diagnosis.

Aberrant methylation of genes in sputum samples as diagnostic biomarkers for non-small cell lung cancer: a meta-analysis

BACKGROUND

We aimed to comprehensively review the evidence for using sputum DNA to detect non-small cell lung cancer (NSCLC).

MATERIALS AND METHODS

We searched PubMed, Science Direct, Web of Science, Chinese Biological Medicine (CBM), Chinese National Knowledge Infrastructure (CNKI), Wanfang, Vip Databases and Google Scholar from 2003 to 2013. The meta-analysis was carried out using a random-effect model with sensitivity, specificity, diagnostic odd ratios (DOR), summary receiver operating characteristic curves (ROC curves), area under the curve (AUC), and 95% confidence intervals (CI) as effect measurements.

RESULTS

There were twenty-two studies meeting the inclusion criteria for the meta-analysis. Combined sensitivity and specificity were 0.62 (95%CI: 0.59-0.65) and 0.73 (95%CI: 0.70-0.75), respectively. The DOR was 10.3 (95%CI: 5.88-18.1) and the AUC was 0.78.

CONCLUSIONS

The overall accuracy of the test was currently not strong enough for the detection of NSCLC for clinical application. Discovery and evaluation of additional biomarkers with improved sensitivity and specificity from studies rated high quality deserve further attention.

TGF-β1 serum concentration as a complementary diagnostic biomarker of lung cancer: establishment of a cut-point value

Lung cancer is a malignant disease with increasing mortality rates. Cytokines play a role in normal cell growth regulation and differentiation and are also implicated in malignant disease. Among these cytokines, Transforming Growth Factor β type 1 (TGF-β1) acts as a tumor promoter in malignant cells. Several clinical studies have found high levels of TGF-β1 in various cancer types. The aim of this study was to establish a TGF-β1 cut-off point as a complementary diagnostic tool in lung cancer detection. Therefore, 72 clinically well-characterized individuals were studied, 41 lung cancer patients and 31 healthy subjects. Serum TGF-β1 concentration was measured by an enzyme-linked immunosorbent assay (ELISA). We compared statistically the serum TGF-β1 concentration between both groups with analysis of variance, linear regression and receiver operating curve analysis. We observed that lung cancer patients produced higher TGF-β1 levels than healthy individuals (37,225±9,436 vs. 28,416±9,324 pg/ml, P<0.001). The cut-point diagnostic value was 30,500 pg/ml with 80.5% sensitivity, 64.5% specificity and odds ratio: 7.5, 95% CI: 2.6-21.8.

CONCLUSIONS

We found significantly higher TGF-β1 levels in lung cancer patients than in healthy individuals. We propose the measurement of serum TGF-β1 levels as a complementary diagnostic test in lung cancer detection.

DNA methylation-based biomarkers for early detection of non-small cell lung cancer: an update

Lung cancer is the number one cancer killer in the United States. This disease is clinically divided into two sub-types, small cell lung cancer, (10–15% of lung cancer cases), and non-small cell lung cancer (NSCLC; 85–90% of cases). Early detection of NSCLC, which is the more common and less aggressive of the two sub-types, has the highest potential for saving lives. As yet, no routine screening method that enables early detection exists, and this is a key factor in the high mortality rate of this disease. Imaging and cytology-based screening strategies have been employed for early detection, and while some are sensitive, none have been demonstrated to reduce lung cancer mortality. However, mortality might be reduced by developing specific molecular markers that can complement imaging techniques. DNA methylation has emerged as a highly promising biomarker and is being actively studied in multiple cancers. The analysis of DNA methylation-based biomarkers is rapidly advancing, and a large number of potential biomarkers have been identified. Here we present a detailed review of the literature, focusing on DNA methylation-based markers developed using primary NSCLC tissue. Viable markers for clinical diagnosis must be detectable in 'remote media' such as blood, sputum, bronchoalveolar lavage, or even exhaled breath condensate. We discuss progress on their detection in such media and the sensitivity and specificity of the molecular marker panels identified to date. Lastly, we look to future advancements that will be made possible with the interrogation of the epigenome.

Identification of a panel of sensitive and specific DNA methylation markers for squamous cell lung cancer

Background

Lung cancer is the leading cause of cancer death in men and women in the United States and Western Europe. Over 160,000 Americans die of this disease every year. The five-year survival rate is 15% – significantly lower than that of other major cancers. Early detection is a key factor in increasing lung cancer patient survival. DNA hypermethylation is recognized as an important mechanism for tumor suppressor gene inactivation in cancer and could yield powerful biomarkers for early detection of lung cancer. Here we focused on developing DNA methylation markers for squamous cell carcinoma of the lung. Using the sensitive, high-throughput DNA methylation analysis technique MethyLight, we examined the methylation profile of 42 loci in a collection of 45 squamous cell lung cancer samples and adjacent non-tumor lung tissues from the same patients.

Results

We identified 22 loci showing significantly higher DNA methylation levels in tumor tissue than adjacent non-tumor lung. Of these, eight showed highly significant hypermethylation in tumor tissue (p < 0.0001): GDNF, MTHFR, OPCML, TNFRSF25, TCF21, PAX8, PTPRN2 and PITX2. Used in combination on our specimen collection, this eight-locus panel showed 95.6% sensitivity and specificity.

Conclusion

We have identified 22 DNA methylation markers for squamous cell lung cancer, several of which have not previously been reported to be methylated in any type of human cancer. The top eight markers show great promise as a sensitive and specific DNA methylation marker panel for squamous cell lung cancer.

Mean sojourn time and effectiveness of mortality reduction for lung cancer screening with computed tomography

This study aimed to estimate the mean sojourn time (MST) and sensitivity of asymptomatic lung cancer (ALC) detected by computed tomography (CT) or chest X-ray (CXR). Translation of early diagnosis into mortality reduction by 2 detection modalities and inter-screening interval was projected using a Markov model. On the basis of systematic literature review, data from 6 prospective CT screening studies were retrieved. The MST in association with the natural history of lung cancer depicted by a 3-state Markov model was estimated with a Bayesian approach. To project mortality reduction attributed to screening, the model was further extended to 5 health states for the inclusion of prognostic part. The analysis was run with a 10-year time horizon of follow-up, mimicking the Dutch-Belgian randomized lung cancer screening trial (NELSON). Screening for lung cancer with CT had high sensitivity (median: 97%) and may advance 1 year earlier than CXR in detecting ALC. By simulating the scenario similar to NELSON study, CT screen may gain an extra of 0.019 year of life expectancy per person, yields 15% mortality reduction (relative risk (RR): 0.85, 95% confidence interval [95%CI: (0.58-1.01)]. Approximate 23% [RR: 0.77, 95%CI: (0.43-0.98)] mortality reduction would be achieved by annual CT screening program. The mortality findings in conjunction with higher sensitivity and shorter MST estimate given data on prevalent and incident (2nd) screen may provide a tentative evidence, suggesting that annual CT screening may be required in order to be effective in reducing mortality before the results of randomized controlled studies available.

Optimization of image acquisition techniques for dual-energy imaging of the chest

Experimental and theoretical studies were conducted to determine optimal acquisition techniques for a prototype dual-energy (DE) chest imaging system. Technique factors investigated included the selection of added x-ray filtration, kVp pair, and the allocation of dose between low- and high-energy projections, with total dose equal to or less than that of a conventional chest radiograph. Optima were computed to maximize lung nodule detectability as characterized by the signal-difference-to-noise ratio (SDNR) in DE chest images. Optimal beam filtration was determined by cascaded systems analysis of DE image SDNR for filter selections across the periodic table (Z(filter) = 1-92), demonstrating the importance of differential filtration between low- and high-kVp projections and suggesting optimal high-kVp filters in the range Z(filter) = 25-50. For example, added filtration of approximately 2.1 mm Cu, approximately 1.2 mm Zr, approximately 0.7 mm Mo, and approximately 0.6 mm Ag to the high-kVp beam provided optimal (and nearly equivalent) soft-tissue SDNR. Optimal kVp pair and dose allocation were investigated using a chest phantom presenting simulated lung nodules and ribs for thin, average, and thick body habitus. Low- and high-energy techniques ranged from 60-90 kVp and 120-150 kVp, respectively, with peak soft-tissue SDNR achieved at [60/120] kVp for all patient thicknesses and all levels of imaging dose. A strong dependence on the kVp of the low-energy projection was observed. Optimal allocation of dose between low- and high-energy projections was such that approximately 30% of the total dose was delivered by the low-kVp projection, exhibiting a fairly weak dependence on kVp pair and dose. The results have guided the implementation of a prototype DE imaging system for imaging trials in early-stage lung nodule detection and diagnosis.

Clinical decision modeling system

Background

Decision analysis techniques can be applied in complex situations involving uncertainty and the consideration of multiple objectives. Classical decision modeling techniques require elicitation of too many parameter estimates and their conditional (joint) probabilities, and have not therefore been applied to the problem of identifying high-performance, cost-effective combinations of clinical options for diagnosis or treatments where many of the objectives are unknown or even unspecified.

Methods

We designed a Java-based software resource, the Clinical Decision Modeling System (CDMS), to implement Naïve Decision Modeling, and provide a use case based on published performance evaluation measures of various strategies for breast and lung cancer detection. Because cost estimates for many of the newer methods are not yet available, we assume equal cost. Our use case reveals numerous potentially high-performance combinations of clinical options for the detection of breast and lung cancer.

Results

Naïve Decision Modeling is a highly practical applied strategy which guides investigators through the process of establishing evidence-based integrative translational clinical research priorities. CDMS is not designed for clinical decision support. Inputs include performance evaluation measures and costs of various clinical options. The software finds trees with expected emergent performance characteristics and average cost per patient that meet stated filtering criteria. Key to the utility of the software is sophisticated graphical elements, including a tree browser, a receiver-operator characteristic surface plot, and a histogram of expected average cost per patient. The analysis pinpoints the potentially most relevant pairs of clinical options ('critical pairs') for which empirical estimates of conditional dependence may be critical. The assumption of independence can be tested with retrospective studies prior to the initiation of clinical trials designed to estimate clinical impact. High-performance combinations of clinical options may exist for breast and lung cancer detection.

Conclusion

The software could be found useful in simplifying the objective-driven planning of complex integrative clinical studies without requiring a multi-attribute utility function, and it could lead to efficient integrative translational clinical study designs that move beyond simple pair wise competitive studies. Collaborators, who traditionally might compete to prioritize their own individual clinical options, can use the software as a common framework and guide to work together to produce increased understanding on the benefits of using alternative clinical combinations to affect strategic and cost-effective clinical workflows.

Optimization of dual-energy imaging systems using generalized NEQ and imaging task

Dual-energy (DE) imaging is a promising advanced application of flat-panel detectors (FPDs) with a potential host of applications ranging from thoracic and cardiac imaging to interventional procedures. The performance of FPD-based DE imaging systems is investigated in this work by incorporating the noise-power spectrum associated with overlying anatomical structures ("anatomical noise" modeled according to a 1/f characteristic) into descriptions of noise-equivalent quanta (NEQ) to yield the generalized NEQ (GNEQ). Signal and noise propagation in the DE imaging chain is modeled by cascaded systems analysis. A Fourier-based description of the imaging task is integrated with the GNEQ to yield a detectability index used as an objective function for optimizing DE image reconstruction, allocation of dose between low- and high-energy images, and selection of low- and high-kVp. Optimal reconstruction and acquisition parameters were found to depend on dose; for example, optimal kVp varied from [60/150] kVp at typical radiographic dose levels (approximately 0.5 mGy entrance surface dose, ESD) but increased to [90/150] kVp at high dose (ESD approximately 5.0 mGy). At very low dose (ESD approximately 0.05 mGy), detectability index indicates an optimal low-energy technique of 60 kVp but was largely insensitive to the choice of high-kVp in the range 120-150 kVp. Similarly, optimal dose allocation, defined as the ratio of low-energy ESD and the total ESD, varied from 0.2 to 0.4 over the range ESD=(0.05-5.0) mGy. Furthermore, two applications of the theoretical framework were explored: (i) the increase in detectability for DE imaging compared to conventional radiography; and (ii) the performance of single-shot vs double-shot DE imaging, wherein the latter is found to have a DQE approximately twice that of the former. Experimental and theoretical analysis of GNEQ and task-based detectability index provides a fundamental understanding of the factors governing DE imaging performance and offers a framework for system design and optimization.

Generalized DQE analysis of radiographic and dual-energy imaging using flat-panel detectors

Analysis of detective quantum efficiency (DQE) is an important component of the investigation of imaging performance for flat-panel detectors (FPDs). Conventional descriptions of DQE are limited, however, in that they take no account of anatomical noise (i.e., image fluctuations caused by overlying anatomy), even though such noise can be the most significant limitation to detectability, often outweighing quantum or electronic noise. We incorporate anatomical noise in experimental and theoretical descriptions of the "generalized DQE" by including a spatial-frequency-dependent noise-power term, S(B), corresponding to background anatomical fluctuations. Cascaded systems analysis (CSA) of the generalized DQE reveals tradeoffs between anatomical noise and the factors that govern quantum noise. We extend such analysis to dual-energy (DE) imaging, in which the overlying anatomical structure is selectively removed in image reconstructions by combining projections acquired at low and high kVp. The effectiveness of DE imaging in removing anatomical noise is quantified by measurement of S(B) in an anthropomorphic phantom. Combining the generalized DQE with an idealized task function to yield the detectability index, we show that anatomical noise dramatically influences task-based performance, system design, and optimization. For the case of radiography, the analysis resolves a fundamental and illustrative quandary: The effect of kVp on imaging performance, which is poorly described by conventional DQE analysis but is clarified by consideration of the generalized DQE. For the case of DE imaging, extension of a generalized CSA methodology reveals a potentially powerful guide to system optimization through the optimal selection of the tissue cancellation parameter. Generalized task-based analysis for DE imaging shows an improvement in the detectability index by more than a factor of 2 compared to conventional radiography for idealized detection tasks.

HASTE MRI Versus Chest Radiography in the Detection of Pulmonary Nodules: Comparison with MDCT

OBJECTIVE

The purpose of our study was to compare the diagnostic accuracy of an ultrafast ECG-triggered black blood-prepared HASTE sequence with chest radiography for the detection of pulmonary nodules. SUBJECTS AND METHODS. Sixty-four patients with various primary malignancies who had undergone radiography and MDCT of the chest also underwent ECG-triggered black blood-prepared HASTE MRI of the lung. MR images and radiographs were interpreted separately. The number, location, and size of detected lesions were recorded, and each hemithorax was classified as affected or not affected on the basis of a grade reflecting the conspicuity of nodular involvement. Sensitivity, specificity, and positive and negative predictive values for the detection of pulmonary nodules with diameters of 5 mm or larger were determined, using MDCT findings as the standard of reference. Lesions with diameters smaller than 5 mm were not evaluated. Additional lesion-by-lesion comparisons between MDCT and MRI findings were performed.

RESULTS

MDCT confirmed pulmonary lesions in 32 patients, whereas HASTE MRI revealed lesions in 30 patients and chest radiography, in 19 patients. MDCT revealed 226 nodules in 32 patients, whereas MRI HASTE revealed 227 lesions in 30 patients. Conspicuity scale-based sensitivity and specificity for chest radiography were 55.8% and 92.4%, respectively, whereas HASTE MRI had a sensitivity of 93.0% and a specificity of 96.2%. Positive and negative predictive values for chest radiography were 80% and 79.3%, respectively, and for HASTE MRI, 93.0% and 96.2%, respectively. The sensitivity of HASTE MRI increased with lesion size, ranging from 94.9% for nodules between 5 and 10 mm in diameter to 100% for lesions exceeding 3 cm in diameter.

CONCLUSION

ECG-triggered black blood-prepared HASTE MRI is reliable for detecting pulmonary nodules exceeding 5 mm and has proven significantly more accurate than conventional chest radiography. The technique appears useful as an adjunct to MRI of the heart, great vessels, or chest, potentially increasing the diagnostic yield of MRI examinations.

Primary lung carcinoma after heart or lung transplantation: management and outcome

OBJECTIVE

We sought to examine our management and outcome of lung carcinoma occurring after thoracic organ transplantation.

METHODS

We performed a retrospective review of cases of primary lung carcinoma diagnosed between 1990 and 2000 in patients who have previously undergone thoracic transplantation at our institution.

RESULTS

Seventeen patients were identified (1 lung and 16 heart transplants). Median time from transplantation to diagnosis of lung carcinoma was 89 months (range, 46-138 months). Predominant presentation was as an incidental finding at chest radiography (13/17). All patients had smoked cigarettes before transplantation, with 5 continuing to smoke after transplantation. Histologic types were squamous (n = 11), adenocarcinoma (n = 3), small cell (n = 2), and undifferentiated (n = 1). Revised International Union Against Cancer (UICC) clinical stage at the time of diagnosis was stage I or II in 11 of 17 patients. Of these, 9 underwent surgical resection; 2 patients unfit for surgical intervention had radiotherapy. Surgical procedures were lobectomy (n = 5), wedge excision (n = 3), and no resection (n = 1). Median survival after diagnosis was 12 months for all patients and 24 months if the tumor was resected. Six patients who had surgical resection subsequently died (survival of 2, 9, 21, 21, 36, and 67 months); 2 remain alive after 12 and 54 months, respectively.

CONCLUSIONS

When possible, surgical intervention should be undertaken for early stage lung cancer occurring after thoracic transplantation because medium-term survival is achievable. Sublobar excisions and definitive radiotherapy should be considered if comorbidity prevents optimal surgical treatment.