Thoracic Radiologists’ Versus Computer Scientists’ Perspectives on the Future of Artificial Intelligence in Radiology Background: There is intense interest and speculation in the application of artificial intelligence (AI) to radiology. The goals of this investigation were (1) to assess thoracic radiologists’ perspectives on the role and expected impact of AI in radiology, and (2) to compare radiologists’ perspectives with those of computer science (CS) experts working in the AI development. Methods: An online survey was developed and distributed to chest radiologists and CS experts at leading academic centers and societies, comparing their expectations of AI’s influence on radiologists’ jobs, job satisfaction, salary, and role in society. Results: A total of 95 radiologists and 45 computer scientists responded. Computer scientists reported having read more scientific journal articles on AI/machine learning in the past year than radiologists (mean [95% confidence interval]=17.1 [9.01-25.2] vs. 7.3 [4.7-9.9], P=0.0047). The impact of AI in radiology is expected to be high, with 57.8% and 73.3% of computer scientists and 31.6% and 61.1% of chest radiologists predicting radiologists’ job will be dramatically different in 5 to 10 years, and 10 to 20 years, respectively. Although very few practitioners in both fields expect radiologists to become obsolete, with 0% expecting radiologist obsolescence in 5 years, in the long run, significantly more computer scientists (15.6%) predict radiologist obsolescence in 10 to 20 years, as compared with 3.2% of radiologists reporting the same (P=0.0128). Overall, both chest radiologists and computer scientists are optimistic about the future of AI in radiology, with large majorities expecting radiologists’ job satisfaction to increase or stay the same (89.5% of radiologists vs. 86.7% of CS experts, P=0.7767), radiologists’ salaries to increase or stay the same (83.2% of radiologists vs. 73.4% of CS experts, P=0.1827), and the role of radiologists in society to improve or stay the same (88.4% vs. 86.7%, P=0.7857). Conclusions: Thoracic radiologists and CS experts are generally positive on the impact of AI in radiology. However, a larger percentage, but still small minority, of computer scientists predict radiologist obsolescence in 10 to 20 years. As the future of AI in radiology unfolds, this study presents a historical timestamp of which group of experts’ perceptions were closer to eventual reality. The authors declare no conflicts of interest. Correspondence to: Haiwei H. Guo, MD, PhD, Department of Radiology, Stanford University School of Medicine, 300 Pasteur Drive S-074B, Stanford, CA 94305 (e-mail: henryguo@stanford.edu). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Imaging of Novel Oncologic Treatments in Lung Cancer Part 2: Local Ablative Therapies Conventional approaches to the treatment of early-stage lung cancer have focused on the use of surgical methods to remove the tumor. Recent progress in radiation therapy techniques and in the field of interventional oncology has seen the development of several novel ablative therapies that have gained widespread acceptance as alternatives to conventional surgical options in appropriately selected patients. Local control rates with stereotactic body radiation therapy for early-stage lung cancer now approach those of surgical resection, while percutaneous ablation is in widespread use for the treatment of lung cancer and oligometastatic disease for selected other malignancies. Tumors treated with targeted medical and ablative therapies can respond to treatment differently when compared with conventional therapies. For example, after stereotactic body radiation therapy, radiologic patterns of posttreatment change can mimic disease progression, and, following percutaneous ablation, the expected initial increase in the size of a treated lesion limits the utility of conventional size-based response assessment criteria. In addition, numerous treatment-related side effects have been described that are important to recognize, both to ensure appropriate treatment and to avoid misclassification as worsening tumor. Imaging plays a vital role in the assessment of patients receiving targeted ablative therapy, and it is essential that thoracic radiologists become familiar with these findings. This research was funded in part by the National Institute of Health/National Cancer Institute Cancer Center Support Grant P30 CA008748. The authors, faculty and all staff in a position to control the content of this CME activity and their spouses/life partners (if any) have disclosed that they have no financial relationships with, or financial interests in, any commercial organizations pertaining to this educational activity. Correspondence to: Darragh Halpenny, MBBCh, BAO, Department of Radiology, Memorial Sloan Kettering Cancer Center, 1275 York Avenue, New York, NY 10065 (e-mail: halpennd@mskcc.org). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Ballistic and Penetrating Injuries of the Chest Ballistic injuries are a major cause of morbidity and mortality in the United States. Unstable patients have high mortality, and only a small subset arrive at the hospital alive. Many patients undergo emergent surgery upon arrival, but a small subset undergo imaging with plain film, computed tomography, and echocardiography. We present a pictorial essay of ballistic and penetrating injuries and their complications with a focus on lung, cardiac, and vascular injury. The authors declare no conflicts of interest. Correspondence to: William Truesdell, MD, Department of Radiology, Long Island Jewish Medical Center, 270-05 76th Ave., Queens, NY 11040 (e-mail: wtruesdel1@northwell.edu). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Dual-Energy Computed Tomography in Thoracic Imaging—Current Practices and Utility: Survey of the Society of Thoracic Radiology Purpose: The purpose of this study was to determine the current practice patterns of utilization of dual-energy computed tomography (DECT) in thoracic imaging. Materials and Methods: In this IRB-approved study, the URL link for an anonymous 26-question survey was sent by email to all the members of the Society of Thoracic Radiology (STR). Survey questions focused on the practice type, case volume, DECT scanner availability, common indications, image types, and perceived utility of DECT. Study data were collected and managed using SurveyMonkey tools and analyzed with χ2 tests. Results: The survey response rate was 11% (104/962). DECT was available in 75% of respondents’ institutions, with 90% of these having 1 to 5 DECT scanners (P<0.001). Seventy percent performed 1 to 500 DECT chest CTs per month (P<0.001). Dual-source was the most common DECT scanner (81%) (P=0.239). DECT was opted depending on the clinical indication in 89% (P=0.433). The technologist reconstructs the additional DECT images in 75% of instances (P<0.001). Acute pulmonary embolism (PE) was the most common indication of DECT (53%) (P=0.006), while chronic PE was considered the most valuable use of DECT (33%) (P<0.001). Iodine map was the most commonly used DECT image (53%) (P<0.001) followed by low-energy virtual monoenergetic image (VMI) (29%). For VMI, 50 keV was the most commonly used energy level for improving vascular contrast (43%) (P=0.048), whereas 120 keV was the most commonly used energy in VMI for decreasing artifacts (25%) (P=0.027). Conclusions: There is wide variability on the utilization of DECT in thoracic imaging. PE is perceived to be the most valuable utility of DECT, and iodine map is considered the most valuable DECT image. The author declares no conflicts of interest. Correspondence to: Prabhakar Rajiah, MBBS, MD, FRCR, Department of Radiology, Mayo Clinic, Rochester, MN 55906 (e-mail: Rajiah.Prabhakar@mayo.edu). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Image Quality and Reliability of a Novel Dark-Blood Late Gadolinium Enhancement Sequence in Ischemic Cardiomyopathy Purpose: The aim of this study was to assess the reliability of a 2D dark-blood phase-sensitive late gadolinium enhancement sequence (2D-DBPSLGE) compared with 2D phase-sensitive inversion recovery late gadolinium enhancement sequence (2D-BBPSLGE) in patients with ischemic cardiomyopathy (ICM). Materials and Methods: A total of 73 patients with a clinical history of ICM were prospectively enrolled. The following endpoints were evaluated: (a) comparison of image quality between 2D-BBPSLGE and 2D-DBPSLGE for differentiation between blood pool-late gadolinium enhancement (LGE), remote myocardium-LGE, and blood pool-remote myocardium; (b) diagnostic accuracy of 2D-DBPSLGE compared with gold standard 2D-BBPSLGE for the evaluation of infarcted segments; (c) diagnostic accuracy of 2D-DBPSLGE for the evaluation of microvascular obstruction (MVO); (d) comparison of transmurality index between 2D-BBPSLGE and 2D-DBPSLGE; (e) comparison of papillary muscle hyperenhancement between 2D-BBPSLGE and 2D-DBPSLGE; inter-reader agreement for depiction of hyperenhanced segments in both LGE sequences. Data were analyzed using paired t test, Wilcoxon test, and McNemar test, and η2 coefficient and intercorrelation coefficient (ICC). Results: Image quality was superior for 2D-DBPSLGE for differentiation of blood pool-LGE (P<0.001). 2D-DBPSLGE, compared with 2D-BBPSLGE, showed a sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of 96.93%, 99.89%, 99.71%, 98.78, and 99.04%, respectively. Concerning MVO detection, 2D-DBPSLGE showed a sensitivity, specificity, positive predictive value, negative predictive value, and diagnostic accuracy of 66.67%, 100.00%, 100.00%, 80.95%, and 86.21%, respectively. 2D-DBPSLGE underestimated the transmurality (P=0.007) and identified papillary muscle hyperenhancement (P<0.001). Both LGE sequences showed comparable interobserver agreement for the evaluation of infarcted areas (2D-BBPSLGE: ICC 0.99;2D-DBPSLGE: ICC 0.99). Conclusions: Compared with 2D-BBPSLGE, 2D-DBPSLGE sequences provide better differentiation between LGE and blood-pool, while underestimating LGE trasmurality and the presence of MVO. The authors declare no conflicts of interest. Correspondence to: Gianluca Pontone, MD, PhD, FESC, FSCCT, Via C. Parea 4, Milan 20138, Italy (e-mail: gianluca.pontone@ccfm.it). Online date: September 13, 2019 Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

A Case of Pulmonary Langerhans Cell Histiocytosis With Acute Progressive Nodular Lesions Depicted on High-Resolution Computed Tomography No abstract available

A Case of Diffuse Intrapulmonary Malignant Mesothelioma No abstract available

Imaging in Cardio-oncology: An Overview of an Emerging Medical Discipline The world of cardio-oncology is an evolving field involving the assessment of cardiovascular disease in patients suffering from cancer. Cancer and cardiovascular diseases are the two leading causes of morbidity and mortality in the developed world. Globally, cancer is diagnosed in 12.7 million patients annually, and cancer incidence is projected to increase by 40% in high-income countries from 2008 to 2030. Chemotherapy is the main treatment for most cancers and improves survival, but is associated with significant cardiotoxicity. In recent years, the introduction of new biological anti-cancer treatments in addition to “classic” chemotherapy has further improved survival, but has also introduced new cardiovascular side effects beyond “pure” myocardial damage. The increasing number of patients with cancer and cancer survivors, and the growing complexity of cancer treatment and cardiovascular side effects, call for teamwork including cardiologists with specific training and expertise working in teams with oncologists, hematologists, and others. The purpose of this review was to describe the clinical background and importance of cardio-oncology, with an emphasis on the use of imaging in this clinical setting. The authors declare no conflicts of interest. Correspondence to: Dan Gilon, MD, Heart Institute, Hadassah-Hebrew University Medical Center, Jerusalen 91120, Israel (e-mail: dangi@ekmd.huji.ac.il). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Magnetic Resonance Imaging for the Follow-up of Treated Thymic Epithelial Malignancies Purpose: The purpose of this article was to compare magnetic resonance imaging (MRI) depiction of thymic malignancy progression/recurrence with that of computed tomography (CT). Methods: We retrospectively reviewed all surgically treated thymic epithelial malignancy (TEM) patients between 2011 and 2018 who were followed-up with chest CT and MRI. We compared the detection of recurrence and metastatic disease between the CT and MRI scans in each of these patients. Results: Of 187 patients treated in our institution for TEM, 22 were followed-up with both CT and MRI. TNM stage at diagnosis was as follows: I (n=14), II (n=1), IIIa (n=4), IIIb (n=2), IVa (n=1), and IVb (n=0). Patients were followed-up for a mean of 6.2 years, range 0.7 to 17.7 years. The mean interval between CT and MRI was 5.4 (range, 1 to 15) months. Most patients had no recurrence (n=16), 4 had recurrence after R0 or R1 resection, 1 had stable disease, and 1 had progression of disease after R2 resection. CT and MRI performed equally in the identification of pleural spread (n=5), lymphadenopathy (n=4), and pulmonary metastases (n=1). Retrosternal recurrence (n=1) was identified by MRI despite sternotomy wire artifacts. MRI identified bone involvement and extension of disease into the thecal sac earlier and more readily. Three patients had an indeterminate mediastinal finding on CT that was correctly identified as a benign cyst or pericardial fluid collection by MRI. Conclusion: MRI is an alternative option to follow-up patients after treatment for TEM. However, for those with metallic sternotomy wires, we recommend alternating the follow-up with CT as well. E.M.M. served as a lecturer for Bristol-Myers Squibb and for Boehringer Ingelheim. The authors declare no conflicts of interest. Correspondence to: Ariel Kerpel, MD, The Chaim Sheba Medical Center, 2 Derech Sheba St, Ramat Gan 5265601, Israel (e-mail: arikerp@gmail.com). Copyright © 2019 Wolters Kluwer Health, Inc. All rights reserved

Radiomics Toolkit: Available Chest Computed Tomography Data Sets No abstract available