A method of rapid quantification of patient-specific organ doses for CT using deep-learning-based multi-organ segmentation and GPU-accelerated Monte Carlo dose computing

PURPOSE

One technical barrier to patient-specific computed tomography (CT) dosimetry has been the lack of computational tools for the automatic patient-specific multi-organ segmentation of CT images and rapid organ dose quantification. When previous CT images are available for the same body region of the patient, the ability to obtain patient-specific organ doses for CT - in a similar manner as radiation therapy treatment planning - will open the door to personalized and prospective CT scan protocols. This study aims to demonstrate the feasibility of combining deep-learning algorithms for automatic segmentation of multiple radiosensitive organs from CT images with the GPU-based Monte Carlo rapid organ dose calculation.

METHODS

A deep convolutional neural network (CNN) based on the U-Net for organ segmentation is developed and trained to automatically delineate multiple radiosensitive organs from CT images. Two databases are used: The lung CT segmentation challenge 2017 (LCTSC) dataset that contains 60 thoracic CT scan patients, each consisting of five segmented organs, and the Pancreas-CT (PCT) dataset, which contains 43 abdominal CT scan patients each consisting of eight segmented organs. A fivefold cross-validation method is performed on both sets of data. Dice similarity coefficients (DSCs) are used to evaluate the segmentation performance against the ground truth. A GPU-based Monte Carlo dose code, ARCHER, is used to calculate patient-specific CT organ doses. The proposed method is evaluated in terms of relative dose errors (RDEs). To demonstrate the potential improvement of the new method, organ dose results are compared against those obtained for population-average patient phantoms used in an off-line dose reporting software, VirtualDose, at Massachusetts General Hospital.

RESULTS

The median DSCs are found to be 0.97 (right lung), 0.96 (left lung), 0.92 (heart), 0.86 (spinal cord), 0.76 (esophagus) for the LCTSC dataset, along with 0.96 (spleen), 0.96 (liver), 0.95 (left kidney), 0.90 (stomach), 0.87 (gall bladder), 0.80 (pancreas), 0.75 (esophagus), and 0.61 (duodenum) for the PCT dataset. Comparing with organ dose results from population-averaged phantoms, the new patient-specific method achieved smaller absolute RDEs (mean ± standard deviation) for all organs: 1.8% ± 1.4% (vs 16.0% ± 11.8%) for the lung, 0.8% ± 0.7% (vs 34.0% ± 31.1%) for the heart, 1.6% ± 1.7% (vs 45.7% ± 29.3%) for the esophagus, 0.6% ± 1.2% (vs 15.8% ± 12.7%) for the spleen, 1.2% ± 1.0% (vs 18.1% ± 15.7%) for the pancreas, 0.9% ± 0.6% (vs 20.0% ± 15.2%) for the left kidney, 1.7% ± 3.1% (vs 19.1% ± 9.8%) for the gallbladder, 0.3% ± 0.3% (vs 24.2% ± 18.7%) for the liver, and 1.6% ± 1.7% (vs 19.3% ± 13.6%) for the stomach. The trained automatic segmentation tool takes <5 s per patient for all 103 patients in the dataset. The Monte Carlo radiation dose calculations performed in parallel to the segmentation process using the GPU-accelerated ARCHER code take <4 s per patient to achieve <0.5% statistical uncertainty in all organ doses for all 103 patients in the database.

CONCLUSION

This work shows the feasibility to perform combined automatic patient-specific multi-organ segmentation of CT images and rapid GPU-based Monte Carlo dose quantification with clinically acceptable accuracy and efficiency.

Knowledge-Based Analysis for Mortality Prediction From CT Images

Low-Dose CT (LDCT) can significantly improve the accuracy of lung cancer diagnosis and thus reduce cancer deaths compared to chest X-ray. The lung cancer risk population is also at high risk of other deadly diseases, for instance, cardiovascular diseases. Therefore, predicting the all-cause mortality risks of this population is of great importance. This paper introduces a knowledge-based analytical method using deep convolutional neural network (CNN) for all-cause mortality prediction. The underlying approach combines structural image features extracted from CNNs, based on LDCT volume at different scales, and clinical knowledge obtained from quantitative measurements, to predict the mortality risk of lung cancer screening subjects. The proposed method is referred as Knowledge-based Analysis of Mortality Prediction Network (KAMP-Net). It constitutes a collaborative framework that utilizes both imaging features and anatomical information, instead of completely relying on automatic feature extraction. Our work demonstrates the feasibility of incorporating quantitative clinical measurements to assist CNNs in all-cause mortality prediction from chest LDCT images. The results of this study confirm that radiologist defined features can complement CNNs in performance improvement. The experiments demonstrate that KAMP-Net can achieve a superior performance when compared to other methods.

Multiphase abdomen-pelvis CT in women of childbearing potential (WOCBP): Justification and radiation dose

To assess justification and radiation doses of abdomen-pelvis CT in women of childbearing potential (WOCBP) scanned in 2 tertiary hospitals in Qatar.The local ethical committee approved retrospective study of 451 WOCBP (14-55 years) who underwent abdomen-pelvis CT examinations. Patients' age, clinical indications for ordered CT, scanner types and vendors, number and type of scan phases (non-contrast, arterial, portal venous, and/or delayed phases), and radiation dose descriptors (CT dose index volume - CTDIvol and dose length product- DLP) were recorded. Patients undergoing simultaneous chest-abdomen-pelvis CT were excluded. We classified the clinical indications for all 451 CT into indicated and unindicated based on the ACR Appropriateness Criteria. Information regarding the date of last menstrual period, likelihood of pregnancy, and if available, results of the pregnancy test were recorded. Data were analyzed with descriptive statistics (median and inter-quartile range) and analysis of variance (ANOVA).None of the patients were pregnant at the time of their scanning. Amongst the 673 phases acquired for multiphase abdomen-pelvis CT in 451 patients, the 47% unindicated phases (315/673) included non-contrast (122/673, 18%), arterial (33/673, 5%), portal venous (125/673, 19%) and delayed (35/673, 5%) phases. The respective median DLP for indicated and unindicated phases were 266 and 758 mGy.cm (P < .0001).Multiphase abdomen-pelvis CT exams are frequent but seldom justified in WOCBP. They lead to a substantial increase in unindicated radiation dose compared to a single-phase CT.

Development and validation of image quality scoring criteria (IQSC) for pediatric CT: a preliminary study

OBJECTIVE

To develop and assess the value and limitations of an image quality scoring criteria (IQSC) for pediatric CT exams.

METHODS

IQSC was developed for subjective assessment of image quality using the scoring scale from 0 to 4, with 0 indicating desired anatomy or features not seen, 3 for adequate image quality, and 4 depicting higher than needed image quality. Pediatric CT examinations from 30 separate patients were selected, five each for routine chest, routine abdomen, kidney stone, appendicitis, craniosynostosis, and ventriculoperitoneal (VP) shunt. Five board-certified pediatric radiologists independently performed image quality evaluation using the proposed IQSC. The kappa statistics were used to assess the interobserver variability.

RESULTS

All five radiologists gave a score of 3 to two-third (67%) of all CT exams, followed by a score of 4 for 29% of CT exams, and 2 for 4% exams. The median image quality scores for all exams were 3 and the interobserver agreement among five readers (acceptable image quality [scores 3 or 4] vs sub-optimal image quality ([scores 1 and 2]) was moderate to very good (kappa 0.4-1). For all five radiologists, the lesion detection was adequate for all CT exams.

CONCLUSIONS

The image quality scoring criteria covering routine and some clinical indication-based imaging scenarios for pediatric CT examinations has potential to offer a simple and practical tool for assessing image quality with a reasonable degree of interobserver agreement. A more extensive and multi-centric study is recommended to establish wider usefulness of these criteria.

Hybrid Neural Networks for Mortality Prediction from LDCT Images

Known for its high morbidity and mortality rates, lung cancer poses a significant threat to human health and well-being. However, the same population is also at high risk for other deadly diseases, such as cardiovascular disease. Since Low-Dose CT (LDCT) has been shown to significantly improve the lung cancer diagnosis accuracy, it will be very useful for clinical practice to predict the all-cause mortality for lung cancer patients to take corresponding actions. In this paper, we propose a deep learning based method, which takes both chest LDCT image patches and coronary artery calcification risk scores as input to predict the mortality risk of lung cancer subjects. The proposed method is called Hybrid Risk Network (HyRiskNet) for mortality risk prediction, which is an end-to-end framework utilizing hybrid imaging features, instead of completely relying on automatic feature extraction. Our work demonstrates the feasibility of using deep learning techniques for all-cause lung cancer mortality prediction from chest LDCT images. The experimental results show that HyRiskNet can achieve superior performance compared with the neural networks with only image input and with other traditional semi-automatic scoring methods. The study also indicates that radiologist defined features can well complement convolutional neural networks for more comprehensive feature extraction.

Predicting malignant potential of subsolid nodules: can radiomics preempt longitudinal follow up CT?

Background

To assess if radiomics can differentiate benign and malignant subsolid lung nodules (SSNs) on baseline or follow up chest CT examinations. If radiomics can differentiate between benign and malignant subsolid lung nodules, the clinical implications are shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging.

Materials and methods

The IRB approved retrospective study included 36 patients (mean age 69 ± 8 years; 5 males, 31 females) with 108 SSNs (31benign, 77 malignant) who underwent follow up chest CT for evaluation of indeterminate SSN. All SSNs were identified on both baseline and follow up chest CT. DICOM CT images were deidentified and exported into the open access 3D Slicer software (version 4.7) to obtain radiomic features. Logistic regression analyses and receiver operating characteristic (ROC) curves for various quantitative parameters were generated with SPSS statistical software.

Results

Only 2/92 radiomic features (cluster shade and surface volume ratio) enabled differentiation between malignant and benign SSN on baseline chest CT (P = 0.01 and 0.03) with moderate accuracy [AUC 0.624 (0.505–0.743)]. On follow-up CT, 52/92 radiomic features were significantly different between benign and malignant SSN (P: 0.04 - < 0.0001) with improved accuracy [AUC: 0.708 (0.605–0.811), P = 0.04 - < 0.0001]. Radiomics of benign SSN were stable over time, whereas 63/92 radiomic features of malignant SSNs changed significantly between the baseline and follow up chest CT (P: 0.04 - < 0.0001).

Conclusions

Temporal changes in radiomic features of subsolid lung nodules favor malignant etiology over benign. The change in radiomics features of subsolid lung nodules can allow shorter follow up CT imaging and early recognition of lung adenocarcinoma on imaging. Radiomic features have limited application in differentiating benign and early malignant SSN on baseline chest CT.

Advanced CT Techniques for Decreasing Radiation Dose, Reducing Sedation Requirements, and Optimizing Image Quality in Children

CT is an invaluable diagnostic tool for pediatric patients; however, concerns have arisen about the potential risks of ionizing radiation associated with diagnostic imaging in young patients, particularly for pediatric populations that may require serial CT examinations. Recent attention has also been focused on the immediate and long-term risks of administration of anesthetic medications to infants and young children who require sedation to undergo imaging examinations. These concerns can be mitigated with use of advanced CT techniques that can decrease scan time and radiation dose while preserving image quality. In this article, current state-of-the-art CT acquisition techniques are reviewed as part of a comprehensive strategy to reduce radiation dose, decrease sedation needs, and optimize image quality in infants and young children. Three imaging strategies are discussed, including (a) dual-energy CT (DECT), (b) imaging with a low tube potential, and (c) rapid scanning. Consolidating multiphase imaging protocols into a single phase with virtual nonenhanced imaging on DECT scanners, as well as use of low tube voltage, can reduce the radiation dose while increasing the conspicuity of contrast material-enhanced structures with a reduced volume of iodinated contrast material and a reduced rate of injection. Rapid scanning techniques with either ultrahigh pitch at dual-source CT or with wide-area detector single-source CT facilitate scanning without the need for sedation in many children. ^©RSNA, 2019 See discussion on this article by Szczykutowicz .

Can CT radiomic analysis in NSCLC predict histology and EGFR mutation status?

To assess the role of radiomic features in distinguishing squamous and adenocarcinoma subtypes of nonsmall cell lung cancers (NSCLC) and predict EGFR mutations.Institution Review Board-approved study included chest CT scans of 93 consecutive patients (43 men, 50 women, mean age 60 ± 11 years) with biopsy-proven squamous and adenocarcinoma lung cancers greater than 1 cm. All cancers were evaluated for epidermal growth factor receptor (EGFR) mutation. The clinical parameters such as age, sex, and smoking history and standard morphology-based CT imaging features such as target lesion longest diameter (LD), longest perpendicular diameter (LPD), density, and presence of cavity were recorded. The radiomics data was obtained using commercial CT texture analysis (CTTA) software. The CTTA was performed on a single image of the dominant lung lesion. The predictive value of clinical history, standard imaging features, and radiomics was assessed with multivariable logistic regression and receiver operating characteristic (ROC) analyses.Between adenocarcinoma and squamous cell carcinomas, ROC analysis showed significant difference in 3/11 radiomic features (entropy, normalized SD, total) [AUC 0.686-0.744, P = .006 to <.0001], 1/3 clinical features (smoking) [AUC 0.732, P = .001], and 2/3 imaging features (LD and LPD) [AUC 0.646-0658, P = .020 to .032]. ROC analysis for probability variables showed higher values for radiomics (AUC 0.800, P < .0001) than clinical (AUC 0.676, P = .017) and standard imaging (AUC 0.708, P < .0001). Between EGFR mutant and wild-type adenocarcinoma, ROC analysis showed significant difference in 2/11 radiomic features (kurtosis, K2) [AUC 0.656-0.713, P = .03 to .003], 1/3 clinical features (smoking) [AUC 0.758, P < .0001]. The combined probability variable for radiomics, clinical and imaging features was higher (AUC 0.890, P < .0001) than independent probability variables.The radiomics evaluation adds incremental value to clinical history and standard imaging features in predicting histology and EGFR mutations.

Deep learning in chest radiography: Detection of findings and presence of change

Background

Deep learning (DL) based solutions have been proposed for interpretation of several imaging modalities including radiography, CT, and MR. For chest radiographs, DL algorithms have found success in the evaluation of abnormalities such as lung nodules, pulmonary tuberculosis, cystic fibrosis, pneumoconiosis, and location of peripherally inserted central catheters. Chest radiography represents the most commonly performed radiological test for a multitude of non-emergent and emergent clinical indications. This study aims to assess accuracy of deep learning (DL) algorithm for detection of abnormalities on routine frontal chest radiographs (CXR), and assessment of stability or change in findings over serial radiographs.

Methods and findings

We processed 874 de-identified frontal CXR from 724 adult patients (> 18 years) with DL (Qure AI). Scores and prediction statistics from DL were generated and recorded for the presence of pulmonary opacities, pleural effusions, hilar prominence, and enlarged cardiac silhouette. To establish a standard of reference (SOR), two thoracic radiologists assessed all CXR for these abnormalities. Four other radiologists (test radiologists), unaware of SOR and DL findings, independently assessed the presence of radiographic abnormalities. A total 724 radiographs were assessed for detection of findings. A subset of 150 radiographs with follow up examinations was used to asses change over time. Data were analyzed with receiver operating characteristics analyses and post-hoc power analysis.

Results

About 42% (305/ 724) CXR had no findings according to SOR; single and multiple abnormalities were seen in 23% (168/724) and 35% (251/724) of CXR. There was no statistical difference between DL and SOR for all abnormalities (p = 0.2–0.8). The area under the curve (AUC) for DL and test radiologists ranged between 0.837–0.929 and 0.693–0.923, respectively. DL had lowest AUC (0.758) for assessing changes in pulmonary opacities over follow up CXR. Presence of chest wall implanted devices negatively affected the accuracy of DL algorithm for evaluation of pulmonary and hilar abnormalities.

Conclusions

DL algorithm can aid in interpretation of CXR findings and their stability over follow up CXR. However, in its present version, it is unlikely to replace radiologists due to its limited specificity for categorizing specific findings.

Process improvement for reducing side discrepancies in radiology reports

Background

Laterality errors in radiology reports can lead to serious errors in management.

Purpose

To reduce errors related to side discrepancies in radiology reports from thoracic imaging by 50% over a six-month period with education and voice recognition software tools.

Material and Methods

All radiology reports at the Thoracic Imaging Division from the fourth quarter of 2016 were reviewed manually for presence of side discrepancies (baseline data). Side discrepancies were defined as a lack of consistency in side labeling of any abnormality in the “Findings” to “Impression” sections of the reports. Process map and Ishikawa fishbone diagram (Microsoft Visio) were created. All thoracic radiologists were educated on side-related errors in radiology reports for plan–design–study–act cycle 1 (PDSA #1). Two weeks later, voice recognition software was configured to capitalize sides (RIGHT and LEFT) in the reports during dictated (PDSA# 2). Radiology reports were analyzed to determine side-discrepancy errors following each PDSA cycle (post-interventional data). Statistical run charts were created using QI Macros statistical software.

Results

Baseline data revealed 33 side-discrepancy errors in 47,876 reports with an average of 2.5 errors per week (range = 1–8 errors). Following PDSA #1, there were seven errors pertaining to side discrepancies over a two-week period. Errors declined following implementation of PDSA #2 to meet the target of 0.85 side-discrepancy error per week over seven weeks.

Conclusion

Automated processes (such as capitalization of sides) help reduce left/right errors substantially without affecting reporting turnaround time.

Contrast Administration in CT: A Patient-Centric Approach

Patient-centric care has garnered the attention of the radiology community. The authors describe a patient-centric approach to iodinated contrast administration designed to optimize the diagnostic yield of contrast-enhanced CT while minimizing patient iodine load and exposure to ionizing radiation, thereby enhancing patient safety while providing reasonable diagnostic efficacy. Patient-centric CT hardware settings and contrast media administration are important considerations for clinical CT quality and safety.

3-D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning From a 2-D Trained Network

Low-dose computed tomography (LDCT) has attracted major attention in the medical imaging field, since CT-associated X-ray radiation carries health risks for patients. The reduction of the CT radiation dose, however, compromises the signal-to-noise ratio, which affects image quality and diagnostic performance. Recently, deep-learning-based algorithms have achieved promising results in LDCT denoising, especially convolutional neural network (CNN) and generative adversarial network (GAN) architectures. This paper introduces a conveying path-based convolutional encoder-decoder (CPCE) network in 2-D and 3-D configurations within the GAN framework for LDCT denoising. A novel feature of this approach is that an initial 3-D CPCE denoising model can be directly obtained by extending a trained 2-D CNN, which is then fine-tuned to incorporate 3-D spatial information from adjacent slices. Based on the transfer learning from 2-D to 3-D, the 3-D network converges faster and achieves a better denoising performance when compared with a training from scratch. By comparing the CPCE network with recently published work based on the simulated Mayo data set and the real MGH data set, we demonstrate that the 3-D CPCE denoising model has a better performance in that it suppresses image noise and preserves subtle structures.

Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss

The continuous development and extensive use of computed tomography (CT) in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists' judgment and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years, various low-dose CT methods have produced impressive results. However, most of the algorithms developed for this application, including the recently popularized deep learning techniques, aim for minimizing the mean-squared error (MSE) between a denoised CT image and the ground truth under generic penalties. Although the peak signal-to-noise ratio is improved, MSE- or weighted-MSE-based methods can compromise the visibility of important structural details after aggressive denoising. This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transport theory and promises to improve the performance of GAN. The perceptual loss suppresses noise by comparing the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN focuses more on migrating the data noise distribution from strong to weak statistically. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task and is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images.

CT texture analysis of histologically proven benign and malignant lung lesions

The purpose of our study was to determine accuracy of CT texture analysis (CTTA) for differentiating benign from malignant pulmonary nodules, and well-differentiated from poorly differentiated lung cancers, with histology as the standard of reference.In this IRB-approved study, 175 adult patients (average age 66 ± 12 years; age range 27-89 years, male 82: female 93) who underwent a noncontrast chest CT examination prior to CT-guided biopsy of pulmonary nodules were included. There were 57 benign (24 tumors or tumor-like lesions; 33 inflammatory conditions) and 120 malignant (29 well-differentiated adenocarcinomas, 48 poorly differentiated adenocarcinomas, and 43 squamous cell carcinomas) diagnoses on pathology. CTTA was performed on the prebiopsy noncontrast CT images using a commercially available software (TexRAD limited, UK). The CTCA features analyzed included mean HU values, percent positive pixels (PPP), mean value of positive pixels (MPP), standard deviation (SD), normalized SD, skewness, kurtosis, and entropy.The ROC analyses showed that normalized SD [AUC: 0.63, (CI: 0.55-72), P = .003] had moderate accuracy for differentiating between benign and malignant lesions. For differentiating among well-differentiated and poorly differentiated tumors, the ROC analysis showed that except skewness all other parameters were statistically significant The AUC values of other CTTA parameters were: mean (AUC: 0.73-0.76, P = .001- < .0001).CT texture analyses can reliably predict well- and poorly differentiated lung malignancies. However, inflammatory lung lesions with tissue heterogeneity negatively affect the performance of CTTA when it comes to differentiation between benign and malignant pulmonary nodules.

Submillisievert chest dual energy computed tomography: a pilot study

OBJECTIVE

To assess if diagnostic dual energy CT (DECT) of the chest can be achieved at submillisievert (sub-mSv) doses.

METHODS

Our IRB-approved prospective study included 20 patients who were scanned on dual-source multidector CT(MDCT). All patients gave written informed consent for acquisition of additional image series at reduced radiation dose on a dual-source MDCT (80/140 kV) within 10 s after the standard of care acquisition. Dose reduction was achieved by reducing the quality reference milliampere-second, with combined angular exposure control. Four readers, blinded to all clinical data, evaluated the image sets. Image noise, signal-to-noise and contrast-to-noise ratio were assessed. Volumetric CT dose index (CTDI_vol), doselength product (DLP), size specific dose estimate, and effective dose were also recorded.

RESULTS

The mean age and body mass index of the patients were 71 years ± 9 and 24 kg m^-2 ± 3, respectively. Although images became noisier, overall image quality and image sharpness on blended images were considered good or excellent in all cases (20/20). All findings made on the reduced dose images presented with good demarcation. The intraobserver and interobserver agreements were κ = 0.83 and 0.73, respectively. Mean CTDI_vol, size specific dose estimate, DLP and effective dose for reduced dose DECT were: 1.3 ± 0.2 mGy, 1.8 ± 0.2 mGy, 51 ± 9.9 mGy.cm and 0.7 ± 0.1 mSv, respectively.

CONCLUSION

Routine chest DECT can be performed at sub-mSv doses with good image quality and without loss of relevant diagnostic information. Advances in knowledge: (1) Contrast-enhanced DECT of the chest can be performed at sub-mSv doses, down to mean CTDI_vol 1.3 mGy and DLP 51 mGy.cm in patients with body mass index <31 kg m^-2. (2) To our knowledge, this is the first time that sub-mSv doses have been successfully applied in a patient study using a dual source DECT scanner.

Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network

Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data, whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Especially, our method has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection.

Incidental pulmonary nodules in emergent coronary CT angiography for suspected acute coronary syndrome: Impact of revised 2017 Fleischner Society Guidelines

BACKGROUND

Pulmonary nodules (PN) are frequently detected incidentally during coronary computed tomography angiography (CTA). We evaluated whether the 2017 Fleischner Society guidelines may result in a decrease of follow-up testing of incidental PN as compared to prior guidelines in patients undergoing coronary CTA.

METHODS

We conducted a retrospective study of a registry of emergency department patients who underwent coronary CTA for acute coronary syndrome assessment between 2012 and 2017. Based on guidelines, patients <35 years, history of cancer, or prior exams showing stability of PN were excluded. Patients >60 years, history of smoking, irregular/spiculated PN morphology, or PN size >20 mm were classified as high-risk for lung cancer. Radiological findings pertaining to PN were identified (PN size, morphology, quantity) through review of radiology reports. PN follow-up recommendations were established using 2017 Fleischner Society Guidelines and compared with prior guidelines for solid (2005) and subsolid (2013) PN. Data were analyzed with Student's t-test.

RESULTS

The registry included 2066 patients (female 45.1%, 52.9 ± 11.0 years), of which 578 (28.0%) reported PN. 438 of those (21.2%) were eligible for guideline-based follow-up evaluation. 205 (4 6.8%) were classified as high-risk for lung cancer. 2017 guidelines reduced the number of individuals requiring follow-up by 64.5%, from 264 (12.8%) to 94 patients (4.5%) when compared to prior guidelines (p < 0.001). The minimum number of follow-up chest CTs decreased by 55.8% from 430 to 190 (p < 0.001).

CONCLUSION

Application of the 2017 Fleischner Society Guidelines resulted in a significant decrease of follow-up testing for incidental PN in patients undergoing coronary CTA for suspected acute coronary syndrome.