Sensitivity Of Nodule Detection Research Articles

Effect of emphysema on AI software and human reader performance in lung nodule detection from low-dose chest CT.

Emphysema influences the appearance of lung tissue in computed tomography (CT). We evaluated whether this affects lung nodule detection by artificial intelligence (AI) and human readers (HR). Individuals were selected from the "Lifelines" cohort who had undergone low-dose chest CT. Nodules in individuals without emphysema were matched to similar-sized nodules in individuals with at least moderate emphysema. AI results for nodular findings of 30-100 mm3 and 101-300 mm3 were compared to those of HR; two expert radiologists blindly reviewed discrepancies. Sensitivity and false positives (FPs)/scan were compared for emphysema and non-emphysema groups. Thirty-nine participants with and 82 without emphysema were included (n = 121, aged 61 ± 8years (mean ± standard deviation), 58/121 males (47.9%)). AI and HR detected 196 and 206 nodular findings, respectively, yielding 109 concordant nodules and 184 discrepancies, including 118 true nodules. For AI, sensitivity was 0.68 (95% confidence interval 0.57-0.77) in emphysema versus 0.71 (0.62-0.78) in non-emphysema, with FPs/scan 0.51 and 0.22, respectively (p = 0.028). For HR, sensitivity was 0.76 (0.65-0.84) and 0.80 (0.72-0.86), with FPs/scan of 0.15 and 0.27 (p = 0.230). Overall sensitivity was slightly higher for HR than for AI, but this difference disappeared after the exclusion of benign lymph nodes. FPs/scan were higher for AI in emphysema than in non-emphysema (p = 0.028), while FPs/scan for HR were higher than AI for 30-100 mm3 nodules in non-emphysema (p = 0.009). AI resulted in more FPs/scan in emphysema compared to non-emphysema, a difference not observed for HR. In the creation of a benchmark dataset to validate AI software for lung nodule detection, the inclusion of emphysema cases is important due to the additional number of FPs. • The sensitivity of nodule detection by AI was similar in emphysema and non-emphysema. • AI had more FPs/scan in emphysema compared to non-emphysema. • Sensitivity and FPs/scan by the human reader were comparable for emphysema and non-emphysema. • Emphysema and non-emphysema representation in benchmark dataset is important for validating AI.

Artificial intelligence in lung cancer screening: Detection, classification, prediction, and prognosis.

The exceptional capabilities of artificial intelligence (AI) in extracting image information and processing complex models have led to its recognition across various medical fields. With the continuous evolution of AI technologies based on deep learning, particularly the advent of convolutional neural networks (CNNs), AI presents an expanded horizon of applications in lung cancer screening, including lung segmentation, nodule detection, false-positive reduction, nodule classification, and prognosis. This review initially analyzes the current status of AI technologies. It then explores the applications of AI in lung cancer screening, including lung segmentation, nodule detection, and classification, and assesses the potential of AI in enhancing the sensitivity of nodule detection and reducing false-positive rates. Finally, it addresses the challenges and future directions of AI in lung cancer screening. AI holds substantial prospects in lung cancer screening. It demonstrates significant potential in improving nodule detection sensitivity, reducing false-positive rates, and classifying nodules, while also showing value in predicting nodule growth and pathological/genetic typing. AI offers a promising supportive approach to lung cancer screening, presenting considerable potential in enhancing nodule detection sensitivity, reducing false-positive rates, and classifying nodules. However, the universality and interpretability of AI results need further enhancement. Future research should focus on the large-scale validation of new deep learning-based algorithms and multi-center studies to improve the efficacy of AI in lung cancer screening.

LGDNet: local feature coupling global representations network for pulmonary nodules detection.

Detection of suspicious pulmonary nodules from lung CT scans is a crucial task in computer-aided diagnosis (CAD) systems. In recent years, various deep learning-based approaches have been proposed and demonstrated significant potential for addressing this task. However, existing deep convolutional neural networks exhibit limited long-range dependency capabilities and neglect crucial contextual information, resulting in reduced performance on detecting small-size nodules in CT scans. In this work, we propose a novel end-to-end framework called LGDNet for the detection of suspicious pulmonary nodules in lung CT scans by fusing local features and global representations. To overcome the limited long-range dependency capabilities inherent in convolutional operations, a dual-branch module is designed to integrate the convolutional neural network (CNN) branch that extracts local features with the transformer branch that captures global representations. To further address the issue of misalignment between local features and global representations, an attention gate module is proposed in the up-sampling stage to selectively combine misaligned semantic data from both branches, resulting in more accurate detection of small-size nodules. Our experiments on the large-scale LIDC dataset demonstrate that the proposed LGDNet with the dual-branch module and attention gate module could significantly improve the nodule detection sensitivity by achieving a final competition performance metric (CPM) score of 89.49%, outperforming the state-of-the-art nodule detection methods, indicating its potential for clinical applications in the early diagnosis of lung diseases.

Performance of artificial intelligence-based software for the automatic detection of lung lesions on chest radiographs of patients with suspected lung cancer

PurposeThis study aimed to evaluate the performance of the commercially available artificial intelligence-based software CXR-AID for the automatic detection of pulmonary nodules on the chest radiographs of patients suspected of having lung cancer.Materials and methodsThis retrospective study included 399 patients with clinically suspected lung cancer who underwent CT and chest radiography within 1 month between June 2020 and May 2022. The candidate areas on chest radiographs identified by CXR-AID were categorized into target (properly detected areas) and non-target (improperly detected areas) areas. The non-target areas were further divided into non-target normal areas (false positives for normal structures) and non-target abnormal areas. The visibility score, characteristics and location of the nodules, presence of overlapping structures, and background lung score and presence of pulmonary disease were manually evaluated and compared between the nodules detected or undetected by CXR-AID. The probability indices calculated by CXR-AID were compared between the target and non-target areas.ResultsAmong the 450 nodules detected in 399 patients, 331 nodules detected in 313 patients were visible on chest radiographs during manual evaluation. CXR-AID detected 264 of these 331 nodules with a sensitivity of 0.80. The detection sensitivity increased significantly with the visibility score. No significant correlation was observed between the background lung score and sensitivity. The non-target area per image was 0.85, and the probability index of the non-target area was lower than that of the target area. The non-target normal area per image was 0.24. Larger and more solid nodules exhibited higher sensitivities, while nodules with overlapping structures demonstrated lower detection sensitivities.ConclusionThe nodule detection sensitivity of CXR-AID on chest radiographs was 0.80, and the non-target and non-target normal areas per image were 0.85 and 0.24, respectively. Larger, solid nodules without overlapping structures were detected more readily by CXR-AID.

Application value of a computer-aided diagnosis and management system for the detection of lung nodules.

Computer-aided diagnosis (CAD) systems can help reduce radiologists' workload. This study assessed the value of a CAD system for the detection of lung nodules on chest computed tomography (CT) images. The study retrospectively analyzed the CT images of patients who underwent routine health checkups between August 2019 and November 2019 at 3 hospitals in China. All images were first assessed by 2 radiologists manually in a blinded manner, which was followed by assessment with the CAD system. The location and classification of the lung nodules were determined. The final diagnosis was made by a panel of experts, including 2 associate chief radiologists and 1 chief radiologist at the radiology department. The sensitivity for nodule detection and false-positive nodules per case were calculated. A total of 1,002 CT images were included in the study, and the process was completed for 999 images. The sensitivity of the CAD system and manual detection was 90.19% and 49.88% (P<0.001), respectively. Similar sensitivity was observed between manual detection and the CAD system in lung nodules >15 mm (P=0.08). The false-positive nodules per case for the CAD system were 0.30±0.84 and those for manual detection were 0.24±0.68 (P=0.12). The sensitivity of the CAD system was higher than that of the radiologists, but the increase in the false-positive rate was only slight. In addition to reducing the workload for medical professionals, a CAD system developed using a deep-learning model was highly effective and accurate in detecting lung nodules and did not demonstrate a meaningfully higher the false-positive rate.

Application of an artificial intelligence ensemble for detection of important secondary findings on lung ventilation and perfusion SPECT-CT

RationaleSingle-photon-emission-computerized-tomography/computed-tomography(SPECT/CT) is commonly used for pulmonary disease. Scant work has been done to determine ability of AI for secondary findings using low-dose-CT(LDCT) attenuation correction series of SPECT/CT. Methods120 patients with ventilation-perfusion-SPECT/CT from 9/1/21–5/1/22 were included in this retrospective study. AI-RAD companion(VA10A,Siemens-Healthineers, Erlangen, Germany), an ensemble of deep-convolutional-neural-networks was evaluated for the detection of pulmonary nodules, coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss. Accuracy, sensitivity, specificity was measured for the outcomes. Inter-rater reliability were measured. Inter-rater reliability was measured using the intraclass correlation coefficient (ICC) by comparing the number of nodules identified by the AI to radiologist. ResultsOverall per-nodule accuracy, sensitivity, and specificity for detection of lung nodules were 0.678(95%CI 0.615–0.732), 0.956(95%CI 0.900–0.985), and 0.456(95%CI 0.376–0.543), respectively, with an intraclass correlation coefficient (ICC) between AI and radiologist of 0.78(95%CI 0.71–0.83). Overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.939(95%CI 0.878–0.975), 0.974(95%CI 0.925–0.995), and 0.857(95%CI 0.781–0.915), respectively. Sensitivity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.898(95%CI 0.778–0.966), 1 (95%CI 0.958–1), and 1 (95%CI 0.961–1), respectively. Specificity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.969(95% CI 0.893–0.996), 0.897 (95% CI 0.726–0.978), and 0.346 (95% CI 0.172–0.557), respectively. ConclusionAI ensemble was accurate for coronary artery calcium and aortic ectasia/aneurysm, while sensitive for aortic ectasia/aneurysm, lung nodules and vertebral height loss on LDCT attenuation correction series of SPECT/CT.

MRI Compared with Low-Dose CT for Incidental Lung Nodule Detection in COPD: A Multicenter Trial.

To investigate morphofunctional chest MRI for the detection and management of incidental pulmonary nodules in participants with chronic obstructive pulmonary disease (COPD). In this prospective study, 567 participants (mean age, 66 years ± 9 [SD]; 340 men) underwent same-day contrast-enhanced MRI and nonenhanced low-dose CT (LDCT) in a nationwide multicenter trial (clinicaltrials.gov: NCT01245933). Nodule dimensions, morphologic features, and Lung Imaging Reporting and Data System (Lung-RADS) category were assessed at MRI by two blinded radiologists, and consensual LDCT results served as the reference standard. Comparisons were performed using the Student t test, and agreements were assessed using the Cohen weighted κ. A total of 525 nodules larger than 3 mm in diameter were detected at LDCT in 178 participants, with a mean diameter of 7.2 mm ± 6.1 (range, 3.1-63.1 mm). Nodules were not detected in the remaining 389 participants. Sensitivity and positive predictive values with MRI for readers 1 and 2, respectively, were 63.0% and 84.8% and 60.2% and 83.9% for solid nodules (n = 495), 17.6% and 75.0% and 17.6% and 60.0% for part-solid nodules (n = 17), and 7.7% and 100% and 7.7% and 50.0% for ground-glass nodules (n = 13). For nodules 6 mm or greater in diameter, sensitivity and positive predictive values were 73.3% and 92.2% for reader 1 and 71.4% and 93.2% for reader 2, respectively. Readers underestimated the long-axis diameter at MRI by 0.5 mm ± 1.7 (reader 1) and 0.5 mm ± 1.5 (reader 2) compared with LDCT (P < .001). For Lung-RADS categorization per nodule using MRI, there was substantial to perfect interreader agreement (κ = 0.75-1.00) and intermethod agreement compared with LDCT (κ = 0.70-1.00 and 0.69-1.00). In a multicenter setting, morphofunctional MRI showed moderate sensitivity for detection of incidental pulmonary nodules in participants with COPD but high agreement with LDCT for Lung-RADS classification of nodules.Clinical trial registration no. NCT01245933 and NCT02629432Keywords: MRI, CT, Thorax, Lung, Chronic Obstructive Pulmonary Disease, Screening© RSNA, 2023 Supplemental material is available for this article.

BiRPN-YOLOvX: A weighted bidirectional recursive feature pyramid algorithm for lung nodule detection.

Lung cancer has the second highest cancer mortality rate in the world today. Although lung cancer screening using CT images is a common way for early lung cancer detection, accurately detecting lung nodules remains a challenged issue in clinical practice. This study aims to develop a new weighted bidirectional recursive pyramid algorithm to address the problems of small size of lung nodules, large proportion of background region, and complex lung structures in lung nodule detection of CT images. First, the weighted bidirectional recursive feature pyramid network (BiPRN) is proposed, which can increase the ability of network model to extract feature information and achieve multi-scale fusion information. Second, a CBAM_CSPDarknet53 structure is developed to incorporate an attention mechanism as a feature extraction module, which can aggregate both spatial information and channel information of the feature map. Third, the weighted BiRPN and CBAM_CSPDarknet53 are applied to the YOLOvX model for lung nodule detection experiments, named BiRPN-YOLOvX, where YOLOvX represents different versions of YOLO. To verify the effectiveness of our weighted BiRPN and CBAM_ CSPDarknet53 algorithm, they are fused with different models of YOLOv3, YOLOv4 and YOLOv5, and extensive experiments are carried out using the publicly available lung nodule datasets LUNA16 and LIDC-IDRI. The training set of LUNA16 contains 949 images, and the validation and testing sets each contain 118 images. There are 1987, 248 and 248 images in LIDC-IDRI's training, validation and testing sets, respectively. The sensitivity of lung nodule detection using BiRPN-YOLOv5 reaches 98.7% on LUNA16 and 96.2% on LIDC-IDRI, respectively. This study demonstrates that the proposed new method has potential to help improve the sensitivity of lung nodule detection in future clinical practice.

Computer-Aided Detection of Subsolid Nodules on Chest Computed Tomography: Assessment of Visualization on Vessel-Suppressed Images.

This study aimed to clarify the performance of automatic detection of subsolid nodules by commercially available software on computed tomography (CT) images of various slice thicknesses and compare it with visualization on the accompanying vessel-suppression CT (VS-CT) images. A total of 95 subsolid nodules from 84 CT examinations of 84 patients were included. The reconstructed CT image series of each case with 3-, 2-, and 1-mm slice thicknesses were loaded into a commercially available software application (ClearRead CT) for automatic detection of subsolid nodules and generation of VS-CT images. Automatic nodule detection sensitivity was assessed for 95 nodules on each series of images acquired at 3 slice thicknesses. Four radiologists subjectively evaluated visual assessment of the nodules on VS-CT. ClearRead CT automatically detected 69.5% (66/95 nodules), 68.4% (65/95 nodules), and 70.5% (67/95 nodules) of all subsolid nodules in 3-, 2-, and 1-mm slices, respectively. The detection rate was higher for part-solid nodules than for pure ground-glass nodules at all slice thicknesses. In the visualization assessment on VS-CT, 3 nodules at each slice thickness (3.2%) were judged as invisible, while 26 of 29 (89.7%), 27 of 30 (90.0%), and 25 of 28 (89.3%) nodules, which were missed by computer-aided detection, were judged as visible in 3-, 2-, and 1-mm slices, respectively. The automatic detection rate of subsolid nodules by ClearRead CT was approximately 70% at all slice thicknesses. More than 95% of subsolid nodules were visualized on VS-CT, including nodules undetected by the automated software. Computed tomography acquisition at slices thinner than 3 mm did not confer any benefits.

Detection and size quantification of pulmonary nodules in ultralow-dose versus regular-dose CT: a comparative study in COPD patients.

To evaluate detectability and semi-automatic diameter and volume measurements of pulmonary nodules in ultralow-dose CT (ULDCT) vs regular-dose CT (RDCT). Fifty patients with chronic obstructive pulmonary disease (COPD) underwent RDCT on 64-multidetector CT (120 kV, filtered back projection), and ULDCT on third-generation dual source CT (100 kV with tin filter, advanced modeled iterative reconstruction). One radiologist evaluated the presence of nodules on both scans in random order, with discrepancies judged by two independent radiologists and consensus reading. Sensitivity of nodule detection on RDCT and ULDCT was compared to reader consensus. Systematic error in semi-automatically derived diameter and volume, and 95% limits of agreement (LoA) were evaluated. Nodule classification was compared by κ statistics. ULDCT resulted in 83.1% (95% CI: 81.0-85.2) dose reduction compared to RDCT (p < 0.001). 45 nodules were present, with diameter range 4.0-25.3 mm and volume range 16.0-4483.0 mm3. Detection sensitivity was non-significant (p = 0.503) between RDCT 88.8% (95% CI: 76.0-96.3) and ULDCT 95.5% (95% CI: 84.9-99.5). No systematic bias in diameter measurements (median difference: -0.2 mm) or volumetry (median difference: -6 mm3) was found for ULDCT compared to RDCT. The 95% LoA for diameter and volume measurements were ±3.0 mm and ±33.5%, respectively. κ value for nodule classification was 0.852 for diameter measurements and 0.930 for volumetry. ULDCT based on Sn100 kV enables comparable detectability of solid pulmonary nodules in COPD patients, at 83% reduced radiation dose compared to RDCT, without relevant difference in nodule measurement and size classification. Pulmonary nodule detectability and measurements in ULDCT are comparable to RDCT.

A deep convolutional neural network ensemble for composite identification of pulmonary nodules and incidental findings on routine PET/CT

To evaluate primary and secondary pathologies of interest using an artificial intelligence (AI) platform, AI-Rad Companion, on low-dose computed tomography (CT) series from integrated positron-emission tomography (PET)/CT to detect CT findings that might be overlooked. One hundred and eighty-nine sequential patients who had undergone PET/CT were included. Images were evaluated using an ensemble of convolutional neural networks (AI-Rad Companion, Siemens Healthineers, Erlangen, Germany). The primary outcome was detection of pulmonary nodules for which the accuracy, identity, and intra-rater reliability was calculated. For secondary outcomes (binary detection of coronary artery calcium, aortic ectasia, vertebral height loss), accuracy and diagnostic performance were calculated. The overall per-nodule accuracy for detection of lung nodules was 0.847. The overall sensitivity and specificity for detection of lung nodules was 0.915 and 0.781. The overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia, and vertebral height loss was 0.979, 0.966, and 0.840, respectively. The sensitivity and specificity for coronary artery calcium was 0.989 and 0.969. The sensitivity and specificity for aortic ectasia was 0.806 and 1. The neural network ensemble accurately assessed the number of pulmonary nodules and presence of coronary artery calcium and aortic ectasia on low-dose CT series of PET/CT. The neural network was highly specific for the diagnosis of vertebral height loss, but not sensitive. The use of the AI ensemble can help radiologists and nuclear medicine physicians to catch CT findings that might be overlooked.

Observer Sensitivity for Detection of Pulmonary Nodules in Ultra-Low Dose Computed Tomography Protocols Using a Third-Generation Dual-Source CT with Ultra-High Pitch—A Phantom Study

This study evaluates ultra-low-dose computed tomography (ULDCT) protocols concerning the detectability of pulmonary nodules. The influence of tube current settings, kernels, strength levels of third-generation iterative reconstruction algorithms, and pitch was investigated. A chest phantom with artificial spherical nodules of different densities and diameters was examined with a third-generation dual-source CT. Scanning and post-processing protocols, tube current levels, and ultra-high and non-high pitch modes were applied. Images were reconstructed with filtered back-projection (FBP) or advanced model-based iterative reconstruction (ADMIRE) algorithms. Sharp (Bl57) or medium-soft (Br36) convolution kernels were applied. The reading was performed by an experienced and an inexperienced reader. The highest observer sensitivity was found using a non-high pitch protocol at tube currents of 120 mAs and 90 mAs with the sharp kernel and iterative reconstruction level of 5. Non-high pitch protocols showed better detectability of solid nodules. Combinations with the medium-soft kernel achieved slightly higher observer sensitivity than with the sharp kernel. False positives (FP) occurred more often for subsolid nodules, at a tube current level of 120 mAs, and with the sharp kernel. A tube current level of 90 mAs combined with the highest iterative reconstruction level achieved the highest accuracy in lung nodule detection regardless of size, density, and reader experience.

Evaluation of ultralow-dose computed tomography on detection of pulmonary nodules in overweight or obese adult patients.

PurposeTo evaluate the accuracy of pulmonary nodule (PN) detection in overweight or obese adult patients using ultralow‐dose computed tomography (ULDCT) with tin filtration at 100 kV and advanced model‐based iterative reconstruction (ADMIRE).MethodsEighty‐one patients with body mass indices of ≥25 kg/m2 were enrolled. All patients underwent low‐dose chest CT (LDCT), followed by ULDCT. Two radiologists experienced in LDCT established the standard of reference (SOR) for PNs. The number, type, size, and location of PNs were identified in the SOR. Effective dose, objective image quality (IQ), and subjective IQ based on two radiologists’ scores were compared between ULDCT and LDCT. The detection performances of radiologists based on ULDCT were calculated according to the nodule analyses. Logistic regression was used to test for independent predictors of PN detection sensitivity.ResultsBoth the effective dose and objective IQ were lower for ULDCT than for LDCT (both p < 0.001). Both radiologists rated the subjective IQ of the overall IQ on ULDCT to be diagnostically sufficient. In total, 234 nodules (mean diameter, 3.4 ± 1.9 mm) were classified into 32 subsolid, 149 solid, and 53 calcified nodules according to the SOR. The overall sensitivity of ULDCT for nodule detection was 93.6%. Based on multivariate analyses, the nodule types (p = 0.015) and sizes (p = 0.013) were independent predictors of nodule detection.ConclusionsCompared with LDCT, ULDCT with tin filtration at 100 kV and ADMIRE could significantly reduce the radiation dose in overweight or obese patients while maintaining good sensitivity for nodule detection.

Lung Nodule Detectability of Artificial Intelligence-assisted CT Image Reading in Lung Cancer Screening.

Artificial Intelligence (AI)-based automatic lung nodule detection system improves the detection rate of nodules. It is important to evaluate the clinical value of the AI system by comparing AI-assisted nodule detection with actual radiology reports. To compare the detection rate of lung nodules between the actual radiology reports and AI-assisted reading in lung cancer CT screening. Participants in chest CT screening from November to December 2019 were retrospectively included. In the real-world radiologist observation, 14 residents and 15 radiologists participated in finalizing radiology reports. In AI-assisted reading, one resident and one radiologist reevaluated all subjects with the assistance of an AI system to locate and measure the detected lung nodules. A reading panel determined the type and number of detected lung nodules between these two methods. In 860 participants (57±7 years), the reading panel confirmed 250 patients with >1 solid nodule, while radiologists observed 131, lower than 247 by AI-assisted reading (p<0.001). The panel confirmed 111 patients with >1 non-solid nodule, whereas radiologist observation identified 28, lower than 110 by AI-assisted reading (p<0.001). The accuracy and sensitivity of radiologist observation for solid nodules were 86.2% and 52.4%, lower than 99.1% and 98.8% by AI-assisted reading, respectively. These metrics were 90.4% and 25.2% for non-solid nodules, lower than 98.8% and 99.1% by AI-assisted reading, respectively. Comparing with the actual radiology reports, AI-assisted reading greatly improves the accuracy and sensitivity of nodule detection in chest CT, which benefits lung nodule detection, especially for non-solid nodules.

Applying Compressed Sensing Volumetric Interpolated Breath-Hold Examination and Spiral Ultrashort Echo Time Sequences for Lung Nodule Detection in MRI.

This prospective study aimed to investigate the ability of spiral ultrashort echo time (UTE) and compressed sensing volumetric interpolated breath-hold examination (CS-VIBE) sequences in magnetic resonance imaging (MRI) compared to conventional VIBE and chest computed tomography (CT) in terms of image quality and small nodule detection. Patients with small lung nodules scheduled for video-assisted thoracoscopic surgery (VATS) for lung wedge resection were prospectively enrolled. Each patient underwent non-contrast chest CT and non-contrast MRI on the same day prior to thoracic surgery. The chest CT was performed to obtain a standard reference for nodule size, location, and morphology. The chest MRI included breath-hold conventional VIBE and CS-VIBE with scanning durations of 11 and 13 s, respectively, and free-breathing spiral UTE for 3.5–5 min. The signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and normal structure visualizations were measured to evaluate MRI quality. Nodule detection sensitivity was evaluated on a lobe-by-lobe basis. Inter-reader and inter-modality reliability analyses were performed using the Cohen κ statistic and the nodule size comparison was performed using Bland–Altman plots. Among 96 pulmonary nodules requiring surgery, the average nodule diameter was 7.7 ± 3.9 mm (range: 4–20 mm); of the 73 resected nodules, most were invasive cancer (74%) or pre-invasive carcinoma in situ (15%). Both spiral UTE and CS-VIBE images achieved significantly higher overall image quality scores, SNRs, and CNRs than conventional VIBE. Spiral UTE (81%) and CS-VIBE (83%) achieved a higher lung nodule detection rate than conventional VIBE (53%). Specifically, the nodule detection rate for spiral UTE and CS-VIBE reached 95% and 100% for nodules >8 and >10 mm, respectively. A 90% detection rate was achieved for nodules of all sizes with a part-solid or solid morphology. Spiral UTE and CS-VIBE under-estimated the nodule size by 0.2 ± 1.4 mm with 95% limits of agreement from −2.6 to 2.9 mm and by 0.2 ± 1.7 mm with 95% limits of agreement from −3.3 to 3.5 mm, respectively, compared to the reference CT. In conclusion, chest CT remains the gold standard for lung nodule detection due to its high image resolutions. Both spiral UTE and CS-VIBE MRI could detect small lung nodules requiring surgery and could be considered a potential alternative to chest CT; however, their clinical application requires further investigation.

An Artificial Intelligence–Based Chest X-ray Model on Human Nodule Detection Accuracy From a Multicenter Study

Most early lung cancers present as pulmonary nodules on imaging, but these can be easily missed on chest radiographs. To assess if a novel artificial intelligence (AI) algorithm can help detect pulmonary nodules on radiographs at different levels of detection difficulty. This diagnostic study included 100 posteroanterior chest radiograph images taken between 2000 and 2010 of adult patients from an ambulatory health care center in Germany and a lung image database in the US. Included images were selected to represent nodules with different levels of detection difficulties (from easy to difficult), and comprised both normal and nonnormal control. All images were processed with a novel AI algorithm, the AI Rad Companion Chest X-ray. Two thoracic radiologists established the ground truth and 9 test radiologists from Germany and the US independently reviewed all images in 2 sessions (unaided and AI-aided mode) with at least a 1-month washout period. Each test radiologist recorded the presence of 5 findings (pulmonary nodules, atelectasis, consolidation, pneumothorax, and pleural effusion) and their level of confidence for detecting the individual finding on a scale of 1 to 10 (1 representing lowest confidence; 10, highest confidence). The analyzed metrics for nodules included sensitivity, specificity, accuracy, and receiver operating characteristics curve area under the curve (AUC). Images from 100 patients were included, with a mean (SD) age of 55 (20) years and including 64 men and 36 women. Mean detection accuracy across the 9 radiologists improved by 6.4% (95% CI, 2.3% to 10.6%) with AI-aided interpretation compared with unaided interpretation. Partial AUCs within the effective interval range of 0 to 0.2 false positive rate improved by 5.6% (95% CI, -1.4% to 12.0%) with AI-aided interpretation. Junior radiologists saw greater improvement in sensitivity for nodule detection with AI-aided interpretation as compared with their senior counterparts (12%; 95% CI, 4% to 19% vs 9%; 95% CI, 1% to 17%) while senior radiologists experienced similar improvement in specificity (4%; 95% CI, -2% to 9%) as compared with junior radiologists (4%; 95% CI, -3% to 5%). In this diagnostic study, an AI algorithm was associated with improved detection of pulmonary nodules on chest radiographs compared with unaided interpretation for different levels of detection difficulty and for readers with different experience.

Performance of a deep learning-based lung nodule detection system as an alternative reader in a Chinese lung cancer screening program

ObjectiveTo evaluate the performance of a deep learning-based computer-aided detection (DL-CAD) system in a Chinese low-dose CT (LDCT) lung cancer screening program. Materials and methodsOne-hundred-and-eighty individuals with a lung nodule on their baseline LDCT lung cancer screening scan were randomly mixed with screenees without nodules in a 1:1 ratio (total: 360 individuals). All scans were assessed by double reading and subsequently processed by an academic DL-CAD system. The findings of double reading and the DL-CAD system were then evaluated by two senior radiologists to derive the reference standard. The detection performance was evaluated by the Free Response Operating Characteristic curve, sensitivity and false-positive (FP) rate. The senior radiologists categorized nodules according to nodule diameter, type (solid, part-solid, non-solid) and Lung-RADS. ResultsThe reference standard consisted of 262 nodules ≥ 4 mm in 196 individuals; 359 findings were considered false positives. The DL-CAD system achieved a sensitivity of 90.1% with 1.0 FP/scan for detection of lung nodules regardless of size or type, whereas double reading had a sensitivity of 76.0% with 0.04 FP/scan (P = 0.001). The sensitivity for detection of nodules ≥ 4 - ≤ 6 mm was significantly higher with DL-CAD than with double reading (86.3% vs. 58.9% respectively; P = 0.001). Sixty-three nodules were only identified by the DL-CAD system, and 27 nodules only found by double reading. The DL-CAD system reached similar performance compared to double reading in Lung-RADS 3 (94.3% vs. 90.0%, P = 0.549) and Lung-RADS 4 nodules (100.0% vs. 97.0%, P = 1.000), but showed a higher sensitivity in Lung-RADS 2 (86.2% vs. 65.4%, P < 0.001). ConclusionsThe DL-CAD system can accurately detect pulmonary nodules on LDCT, with an acceptable false-positive rate of 1 nodule per scan and has higher detection performance than double reading. This DL-CAD system may assist radiologists in nodule detection in LDCT lung cancer screening.

Detection of lung lesions in breath-hold VIBE and free-breathing Spiral VIBE MRI compared to CT

BackgroundDetection of pulmonary nodules in MRI requires fast imaging strategies without respiratory motion impairment, such as single-breath-hold Cartesian VIBE. As patients with pulmonary diseases have limited breath-hold capacities, this study investigates the clinical feasibility of non-Cartesian Spiral VIBE under free-breathing compared to CT as the gold standard.MethodsProspective analysis of 27 oncological patients examined in PET/CT and PET/MR. A novel motion-robust 3D ultrashort-echo-time (UTE) MR sequence was evaluated in comparison with CT and conventional breath-hold MR. CT scans were performed under breath-hold in end-expiratory and end-inspiratory position (CT ex, CT in). MR data was acquired with non-contrast-enhanced breath-hold Cartesian VIBE followed by a free-breathing 3D UTE Spiral VIBE. Impact of respiratory motion on pulmonary evaluation was investigated by two readers in Cartesian VIBE, followed by UTE Spiral VIBE and CT ex and the reference standard of CT in. Diagnostic accuracy was calculated, and visual image quality assessed.ResultsHigher detection rate and sensitivity of pulmonary nodules in free-breathing UTE Spiral VIBE in comparison with breath-hold Cartesian VIBE were found for lesions > 10 mm (UTE Spiral VIBE/VIBE/CT ex): 93%/54%/100%; Lesions 5–10 mm: 67%/25%/ 92%; Lesions < 5 mm: 11%/11%/78%. Lobe-based analysis revealed sensitivities and specificities of 64%/96%/41% and 96%/93%/100% for UTE Spiral VIBE/VIBE/CT ex.ConclusionFree-breathing UTE Spiral VIBE indicates higher sensitivity for detection of pulmonary nodules than breath-hold Cartesian VIBE and is a promising but time-consuming approach. However, sensitivity and specificity of inspiratory CT remain superior in comparison and should be preferred for detection of pulmonary lesions.

Dual Skip Connections Minimize the False Positive Rate of Lung Nodule Detection in CT images.

Pulmonary cancer is one of the most commonly diagnosed and fatal cancers and is often diagnosed by incidental findings on computed tomography. Automated pulmonary nodule detection is an essential part of computer-aided diagnosis, which is still facing great challenges and difficulties to quickly and accurately locate the exact nodules' positions. This paper proposes a dual skip connection upsampling strategy based on Dual Path network in a U-Net structure generating multiscale feature maps, which aims to minimize the ratio of false positives and maximize the sensitivity for lesion detection of nodules. The results show that our new upsampling strategy improves the performance by having 85.3% sensitivity at 4 FROC per image compared to 84.2% for the regular upsampling strategy or 81.2% for VGG16-based Faster-R-CNN.

Role of chest MRI for the diagnosis of malignant pulmonary nodules: a systematic review and a meta-analysis

AIM: To evaluate the ability of magnetic resonance imaging (MRI) of the chest to detect malignant pulmonary nodules compared to compute tomography (CT).&#x0D; MATERIALS AND METHODS: We searched the following databases with the final date of search on April 7th, 2021: PubMed, Google Scholar. We selected studies according to the inclusion and exclusion criteria that assessed the detection of malignant lung nodules by MRI and CT and included information about sensitivity and specificity. Method of the analysis and data grouping was chosen with regard to statistical heterogeneity of the studies included in the analysis. We used the 2 test and I2 statistic to evaluate the heterogeneity.&#x0D; RESULTS: We selected 168 articles for the systematic review from the PubMed and Google Scholar databases. We included 21 studies on 1,188 patients in the meta-analysis and revealed statistically significant heterogeneity (р0,00001 for 2 test; I2=99%) for sensitivity and specificity. Hence, we used a random-effect model for further analysis. As a result, values of sensitivity for detection of pulmonary nodules with MRI of 70.4%100%, specificity ― from 60.6% to 100%.&#x0D; CONCLUSIONS: Thus, MRI has sufficient sensitivity and specificity for detecting malignant pulmonary nodules primarily discovered with CT.