Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever‑growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi‑society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.

Joint reconstruction and segmentation in undersampled 3D knee MRI combining shape knowledge and deep learning

Objective.Task-adapted image reconstruction methods using end-to-end trainable neural networks (NNs) have been proposed to optimize reconstruction for subsequent processing tasks, such as segmentation. However, their training typically requires considerable hardware resources and thus, only relatively simple building blocks, e.g. U-Nets, are typically used, which, albeit powerful, do not integrate model-specific knowledge.Approach.In this work, we extend an end-to-end trainable task-adapted image reconstruction method for a clinically realistic reconstruction and segmentation problem of bone and cartilage in 3D knee MRI by incorporating statistical shape models (SSMs). The SSMs model the prior information and help to regularize the segmentation maps as a final post-processing step. We compare the proposed method to a simultaneous multitask learning approach for image reconstruction and segmentation (MTL) and to a complex SSMs-informed segmentation pipeline (SIS).Main results.Our experiments show that the combination of joint end-to-end training and SSMs to further regularize the segmentation maps obtained by MTL highly improves the results, especially in terms of mean and maximal surface errors. In particular, we achieve the segmentation quality of SIS and, at the same time, a substantial model reduction that yields a five-fold decimation in model parameters and a computational speedup of an order of magnitude.Significance.Remarkably, even for undersampling factors of up toR= 8, the obtained segmentation maps are of comparable quality to those obtained by SIS from ground-truth images.

Projected Growth in FDA-Approved Artificial Intelligence Products Given Venture Capital Funding

PURPOSE

Medical imaging accounts for 85% of digital health's venture capital funding. As funding grows, it is expected that artificial intelligence (AI) products will increase commensurately. The study's objective is to project the number of new AI products given the statistical association between historical funding and FDA-approved AI products.

METHODS

The study used data from the ACR Data Science Institute and for the number of FDA-approved AI products (2008-2022) and data from Rock Health for AI funding (2013-2022). Employing a 6-year lag between funding and product approved, we used linear regression to estimate the association between new products approved in a certain year, based on the lagged funding (ie, product-year funding). Using this statistical relationship, we forecasted the number of new FDA-approved products.

RESULTS

The results show that there are 11.33 (95% confidence interval: 7.03-15.64) new AI products for every $1 billion in funding assuming a 6-year lag between funding and product approval. In 2022 there were 69 new FDA-approved products associated with $4.8 billion in funding. In 2035, product-year funding is projected to reach $30.8 billion, resulting in 350 new products that year.

CONCLUSIONS

FDA-approved AI products are expected to grow from 69 in 2022 to 350 in 2035 given the expected funding growth in the coming years. AI is likely to change the practice of diagnostic radiology as new products are developed and integrated into practice. As more AI products are integrated, it may incentivize increased investment for future AI products.

Proceedings from the 2022 ACR-RSNA Workshop on Safety, Effectiveness, Reliability, and Transparency in AI

Despite the surge in AI development for healthcare applications, particularly for medical imaging applications, there has been limited adoption of such AI tools into clinical practice. During a one-day workshop in November, 2022, co-organized by the American College of Radiology (ACR) and the Radiological Society of North America (RSNA), participants outlined experiences and problems with implementing AI in clinical practice, defined the needs of various stakeholders in the AI ecosystem, and elicited potential solutions and strategies related to the safety, effectiveness, reliability, and transparency of AI algorithms. Participants included radiologists from academic and community radiology practices, informatics leaders responsible for AI implementation, regulatory agency employees, and specialty society representatives. The major themes that emerged fell into two categories: 1) AI product development and 2) implementation of AI-based applications in clinical practice. In particular, participants highlighted key aspects of AI product development to include clear clinical task definitions; well-curated data from diverse geographic, economical, and healthcare settings; standards and mechanisms to monitor model reliability; and transparency regarding model performance, both in controlled and real-world settings. For implementation, participants emphasized the need for strong institutional governance; systematic evaluation, selection, and validation methods carried out by local teams; seamless integration into the clinical workflow; performance monitoring and support by local teams; performance monitoring by external entities; and alignment of incentives through credentialing and reimbursement. Participants predicted that clinical implementation of AI in radiology will continue to be limited until the safety, effectiveness, reliability, and transparency of such tools are more fully addressed.

Developing, purchasing, implementing and monitoring AI tools in radiology: Practical considerations. A multi-society statement from the ACR, CAR, ESR, RANZCR & RSNA

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.

Real-World Performance of Large Vessel Occlusion Artificial Intelligence-Based Computer-Aided Triage and Notification Algorithms-What the Stroke Team Needs to Know

PURPOSE

To evaluate the real-world performance of two FDA-approved artificial intelligence (AI)-based computer-aided triage and notification (CADt) detection devices and compare them with the manufacturer-reported performance testing in the instructions for use.

MATERIALS AND METHODS

Clinical performance of two FDA-cleared CADt large-vessel occlusion (LVO) devices was retrospectively evaluated at two separate stroke centers. Consecutive "code stroke" CT angiography examinations were included and assessed for patient demographics, scanner manufacturer, presence or absence of CADt result, CADt result, and LVO in the internal carotid artery (ICA), horizontal middle cerebral artery (MCA) segment (M1), Sylvian MCA segments after the bifurcation (M2), precommunicating part of cerebral artery, postcommunicating part of the cerebral artery, vertebral artery, basilar artery vessel segments. The original radiology report served as the reference standard, and a study radiologist extracted the above data elements from the imaging examination and radiology report.

RESULTS

At hospital A, the CADt algorithm manufacturer reports assessment of intracranial ICA and MCA with sensitivity of 97% and specificity of 95.6%. Real-world performance of 704 cases included 79 in which no CADt result was available. Sensitivity and specificity in ICA and M1 segments were 85.3% and 91.9%. Sensitivity decreased to 68.5% when M2 segments were included and to 59.9% when all proximal vessel segments were included. At hospital B the CADt algorithm manufacturer reports sensitivity of 87.8% and specificity of 89.6%, without specifying the vessel segments. Real-world performance of 642 cases included 20 cases in which no CADt result was available. Sensitivity and specificity in ICA and M1 segments were 90.7% and 97.9%. Sensitivity decreased to 76.4% when M2 segments were included and to 59.4% when all proximal vessel segments are included.

DISCUSSION

Real-world testing of two CADt LVO detection algorithms identified gaps in the detection and communication of potentially treatable LVOs when considering vessels beyond the intracranial ICA and M1 segments and in cases with absent and uninterpretable data.

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement From the ACR, CAR, ESR, RANZCR & RSNA

Artificial intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. KEY POINTS.

Developing, purchasing, implementing and monitoring AI tools in radiology: practical considerations. A multi-society statement from the ACR, CAR, ESR, RANZCR & RSNA

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones.This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools.Key points • The incorporation of artificial intelligence (AI) in radiological practice demands increased monitoring of its utility and safety.• Cooperation between developers, clinicians, and regulators will allow all involved to address ethical issues and monitor AI performance.• AI can fulfil its promise to advance patient well-being if all steps from development to integration in healthcare are rigorously evaluated.

Developing, Purchasing, Implementing and Monitoring AI Tools in Radiology: Practical Considerations. A Multi-Society Statement from the ACR, CAR, ESR, RANZCR and RSNA

Artificial Intelligence (AI) carries the potential for unprecedented disruption in radiology, with possible positive and negative consequences. The integration of AI in radiology holds the potential to revolutionize healthcare practices by advancing diagnosis, quantification, and management of multiple medical conditions. Nevertheless, the ever-growing availability of AI tools in radiology highlights an increasing need to critically evaluate claims for its utility and to differentiate safe product offerings from potentially harmful, or fundamentally unhelpful ones. This multi-society paper, presenting the views of Radiology Societies in the USA, Canada, Europe, Australia, and New Zealand, defines the potential practical problems and ethical issues surrounding the incorporation of AI into radiological practice. In addition to delineating the main points of concern that developers, regulators, and purchasers of AI tools should consider prior to their introduction into clinical practice, this statement also suggests methods to monitor their stability and safety in clinical use, and their suitability for possible autonomous function. This statement is intended to serve as a useful summary of the practical issues which should be considered by all parties involved in the development of radiology AI resources, and their implementation as clinical tools. This article is simultaneously published in Insights into Imaging (DOI 10.1186/s13244-023-01541-3), Journal of Medical Imaging and Radiation Oncology (DOI 10.1111/1754-9485.13612), Canadian Association of Radiologists Journal (DOI 10.1177/08465371231222229), Journal of the American College of Radiology (DOI 10.1016/j.jacr.2023.12.005), and Radiology: Artificial Intelligence (DOI 10.1148/ryai.230513). Keywords: Artificial Intelligence, Radiology, Automation, Machine Learning Published under a CC BY 4.0 license. ©The Author(s) 2024. Editor's Note: The RSNA Board of Directors has endorsed this article. It has not undergone review or editing by this journal.

Get With the Guidelines on MS Imaging by Leveraging Peer Learning

OBJECTIVES

To achieve consensus on the performance, interpretation and reporting of MS imaging according to up-to-date guidelines using the Peer Learning Methodology.

MATERIALS AND METHODS

We utilized the Peer Learning Methodology to engage our clinical and radiology colleagues, review the current guidelines, acheive consensus on imaging techniques and reporting standards. After implementing changes, we collected radiologist feedback on the impact of the optimized images on their interpretation.

RESULTS

Survey responders indicated a strong preference for the new protocol in terms of overall image quality, individual lesions conspicuity and confidence in the ability to detect an MS lesion. The new protocol was preferred for both MS diagnosis and MS surveillance in 25 of 28 responses.

CONCLUSION

The Peer Learning Methodology is an effective tool to standardize and improve MR imaging quality, interpretation and reporting for Multiple Sclerosis in accordance with current guidelines.

Keeping Patient Data Secure in the Age of Radiology Artificial Intelligence: Cybersecurity Considerations and Future Directions

Artificial intelligence (AI)-based solutions are increasingly being incorporated into radiology workflows. Implementation of AI comes along with cybersecurity risks and challenges that practices should be aware of and mitigate for a successful and secure deployment. In this article, these cybersecurity issues are examined through the lens of the "CIA" triad framework-confidentiality, integrity, and availability. We discuss the implications of implementation configurations and development approaches on data security and confidentiality and the potential impact that the insertion of AI can have on the truthfulness of data, access to data, and the cybersecurity attack surface. Finally, we provide a checklist to address important security considerations before deployment of an AI application, and discuss future advances in AI addressing some of these security concerns.

Use of Artificial Intelligence in Radiology: Impact on Pediatric Patients, a White Paper From the ACR Pediatric AI Workgroup

In this white paper, the ACR Pediatric AI Workgroup of the Commission on Informatics educates the radiology community about the health equity issue of the lack of pediatric artificial intelligence (AI), improves the understanding of relevant pediatric AI issues, and offers solutions to address the inadequacies in pediatric AI development. In short, the design, training, validation, and safe implementation of AI in children require careful and specific approaches that can be distinct from those used for adults. On the eve of widespread use of AI in imaging practice, the group invites the radiology community to align and join Image IntelliGently (www.imageintelligently.org) to ensure that the use of AI is safe, reliable, and effective for children.

Interstitial lung abnormalities in a large clinical lung cancer screening cohort: association with mortality and ILD diagnosis

BACKGROUND

Interstitial lung abnormalities (ILA) are CT findings suggestive of interstitial lung disease in individuals without a prior diagnosis or suspicion of ILD. Previous studies have demonstrated that ILA are associated with clinically significant outcomes including mortality. The aim of this study was to determine the prevalence of ILA in a large CT lung cancer screening program and the association with clinically significant outcomes including mortality, hospitalizations, cancer and ILD diagnosis.

METHODS

This was a retrospective study of individuals enrolled in a CT lung cancer screening program from 2012 to 2014. Baseline and longitudinal CT scans were scored for ILA per Fleischner Society guidelines. The primary analyses examined the association between baseline ILA and mortality, all-cause hospitalization, and incidence of lung cancer. Kaplan-Meier plots were generated to visualize the associations between ILA and lung cancer and all-cause mortality. Cox regression proportional hazards models were used to test for this association in both univariate and multivariable models.

RESULTS

1699 subjects met inclusion criteria. 41 (2.4%) had ILA and 101 (5.9%) had indeterminate ILA on baseline CTs. ILD was diagnosed in 10 (24.4%) of 41 with ILA on baseline CT with a mean time from baseline CT to diagnosis of 4.47 ± 2.72 years. On multivariable modeling, the presence of ILA remained a significant predictor of death, HR 3.87 (2.07, 7.21; p < 0.001) when adjusted for age, sex, BMI, pack years and active smoking, but not of lung cancer and all-cause hospital admission. Approximately 50% with baseline ILA had progression on the longitudinal scan.

CONCLUSIONS

ILA identified on baseline lung cancer screening exams are associated with all-cause mortality. In addition, a significant proportion of patients with ILA are subsequently diagnosed with ILD and have CT progression on longitudinal scans.

TRIAL REGISTRATION NUMBER

ClinicalTrials.gov; No.: NCT04503044.

Artificial intelligence in oncologic imaging

Radiology is integral to cancer care. Compared to molecular assays, imaging has its advantages. Imaging as a noninvasive tool can assess the entirety of tumor unbiased by sampling error and is routinely acquired at multiple time points in oncological practice. Imaging data can be digitally post-processed for quantitative assessment. The ever-increasing application of Artificial intelligence (AI) to clinical imaging is challenging radiology to become a discipline with competence in data science, which plays an important role in modern oncology. Beyond streamlining certain clinical tasks, the power of AI lies in its ability to reveal previously undetected or even imperceptible radiographic patterns that may be difficult to ascertain by the human sensory system. Here, we provide a narrative review of the emerging AI applications relevant to the oncological imaging spectrum and elaborate on emerging paradigms and opportunities. We envision that these technical advances will change radiology in the coming years, leading to the optimization of imaging acquisition and discovery of clinically relevant biomarkers for cancer diagnosis, staging, and treatment monitoring. Together, they pave the road for future clinical translation in precision oncology.

Importance of tumor subtypes in cancer imaging

Cancer therapy has evolved from being broadly directed towards tumor types, to highly specific treatment protocols that target individual molecular subtypes of tumors. With the ever-increasing data on imaging characteristics of tumor subtypes and advancements in imaging techniques, it is now often possible for radiologists to differentiate tumor subtypes on imaging. Armed with this knowledge, radiologists may be able to provide specific information that can obviate the need for invasive methods to identify tumor subtypes. Different tumor subtypes also differ in their patterns of metastatic spread. Awareness of these differences can direct radiologists to relevant anatomical sites to screen for early metastases that may otherwise be difficult to detect during cursory inspection. Likewise, this knowledge will help radiologists to interpret indeterminate findings in a more specific manner.

•

Tumor subtypes can be identified based on their different imaging characteristics.

•

Awareness of tumor subtype can help radiologists chose the appropriate modality for additional imaging workup.

•

Awareness of differences in metastatic pattern between tumor subtypes can be helpful to identify early metastases.

External COVID-19 Deep Learning Model Validation on ACR AI-LAB: It's a Brave New World

PURPOSE

Deploying external artificial intelligence (AI) models locally can be logistically challenging. We aimed to use the ACR AI-LAB software platform for local testing of a chest radiograph (CXR) algorithm for COVID-19 lung disease severity assessment.

METHODS

An externally developed deep learning model for COVID-19 radiographic lung disease severity assessment was loaded into the AI-LAB platform at an independent academic medical center, which was separate from the institution in which the model was trained. The data set consisted of CXR images from 141 patients with reverse transcription-polymerase chain reaction-confirmed COVID-19, which were routed to AI-LAB for model inference. The model calculated a Pulmonary X-ray Severity (PXS) score for each image. This score was correlated with the average of a radiologist-based assessment of severity, the modified Radiographic Assessment of Lung Edema score, independently interpreted by three radiologists. The associations between the PXS score and patient admission and intubation or death were assessed.

RESULTS

The PXS score deployed in AI-LAB correlated with the radiologist-determined modified Radiographic Assessment of Lung Edema score (r = 0.80). PXS score was significantly higher in patients who were admitted (4.0 versus 1.3, P < .001) or intubated or died within 3 days (5.5 versus 3.3, P = .001).

CONCLUSIONS

AI-LAB was successfully used to test an external COVID-19 CXR AI algorithm on local data with relative ease, showing generalizability of the PXS score model. For AI models to scale and be clinically useful, software tools that facilitate the local testing process, like the freely available AI-LAB, will be important to cross the AI implementation gap in health care systems.

FDA-regulated AI Algorithms: Trends, Strengths, and Gaps of Validation Studies

RATIONALE AND OBJECTIVES

To assess key trends, strengths, and gaps in validation studies of the Food and Drug Administration (FDA)-regulated imaging-based artificial intelligence/machine learning (AI/ML) algorithms.

MATERIALS AND METHODS

We audited publicly available details of regulated AI/ML algorithms in imaging from 2008 until April 2021. We reviewed 127 regulated software (118 AI/ML) to classify information related to their parent company, subspecialty, body area and specific anatomy type, imaging modality, date of FDA clearance, indications for use, target pathology (such as trauma) and findings (such as fracture), technique (CAD triage, CAD detection and/or characterization, CAD acquisition or improvement, and image processing/quantification), product performance, presence, type, strength and availability of clinical validation data. Pertaining to validation data, where available, we recorded the number of patients or studies included, sensitivity, specificity, accuracy, and/or receiver operating characteristic area under the curve, along with information on ground-truthing of use-cases. Data were analyzed with pivot tables and charts for descriptive statistics and trends.

RESULTS

We noted an increasing number of FDA-regulated AI/ML from 2008 to 2021. Seventeen (17/118) regulated AI/ML algorithms posted no validation claims or data. Just 9/118 reviewed AI/ML algorithms had a validation dataset sizes of over 1000 patients. The most common type of AI/ML included image processing/quantification (IPQ; n = 59/118), and triage (CADt; n = 27/118). Brain, breast, and lungs dominated the targeted body regions of interest.

CONCLUSION

Insufficient public information on validation datasets in several FDA-regulated AI/ML algorithms makes it difficult to justify clinical applications since their generalizability and presence of bias cannot be inferred.

Moving Toward Seamless Interinstitutional Electronic Image Transfer

The fact that medical images are still predominately exchanged between institutions via physical media is unacceptable in the era of value-driven health care. Although better solutions are technically possible, problems of coordination and market dynamics may be inhibiting progress more than technical factors. We provide a macrosystem analysis of the problem of interinstitutional medical image exchange and propose a strategy for nudging the market toward a patient-friendly solution. The system can be viewed as a network, with autonomous nodes interconnected by links through which information is exchanged. A variety of potential network configurations include those that depend on individual carriers, peer-to-peer links, one or multiple hubs, or a hybrid of models. We find the linked multihub model, in which individual institutions are connected to other institutions via image exchange companies, to be the configuration most likely to create a patient-friendly electronic image exchange system. To achieve this configuration, image exchange companies, which operate in a competitive marketplace, must exchange images with each other. We call on these vendors to immediately commit to coordinating in this manner. We call on all other stakeholders, including medical societies, payers, and regulators, to actively encourage and facilitate this behavior. Specifically, we call on institutions to create appropriate market incentives by only contracting with image exchange vendors who are committed to begin vendor-to-vendor image exchange by no later than 2024.

Virtual Monoenergetic Spectral Detector CT for Preoperative CT Angiography in Liver Donors

OBJECTIVE

The purpose of this study was to evaluate the use of virtual monoenergetic images (VMI) in pre-operative CT angiography of potential donors for living donor adult liver transplantation (LDALT), and to determine the optimal energy level to maximize vascular signal-to-noise and contrast-to-noise ratios (SNR and CNR, respectively).

MATERIALS AND METHODS

We retrospectively evaluated 29 CT angiography studies performed preoperatively in potential liver donors on a spectral detector CT scanner. All studies included arterial, early venous, and delayed venous phase imaging. Conventional polyenergetic images were generated for each patient, as well as virtual monoenergetic images in 10 keV increments from 40 -100 keV. Arteries (aorta and celiac, superior mesenteric, common hepatic, right and left hepatic arteries) were assessed on arterial phase images; portal venous system branches (splenic, superior mesenteric, main, right, and left portal veins) on early venous phase images; and hepatic veins on late venous phase images. Vascular attenuation, background parenchymal attenuation, and noise were measured on each set of virtual monoenergetic and conventional images.

RESULTS

Background hepatic and vascular noise decreased with increasing keV, with the lowest noise at 100 keV. Vascular SNR and CNR increased with decreasing keV and were highest at 40 keV, with statistical significance compared with conventional ( P < 0.05).

CONCLUSIONS

In preoperative CT angiography for potential liver donors, the optimal keV for assessing the vasculature to improve SNR and CNR is 40 keV. Use of low keV VMI in LDALT CT protocols may facilitate detection of vascular anatomical variants that can impact surgical planning.

International teleproctoring in neurointerventional surgery and its potential impact on clinical trials in the era of COVID-19: legal and technical considerations

BACKGROUND

Existing travel restrictions limit the mobility of proctors, significantly delaying clinical trials and the introduction of new neurointerventional devices. We aim to describe in detail technical and legal considerations regarding international teleproctoring, a tool that could waive the need for in-person supervision during procedures.

METHODS

International teleproctoring was chosen to provide remote supervision during the first three intracranial aneurysm treatments with a new flow diverter (currently subject of a clinical trial) in the US. Real-time, high-resolution transmission software streamed audiovisual data to a proctor located in Canada. The software allowed the transmission of images in a de-identified, HIPAA-compliant manner.

RESULTS

All three flow diverters were implanted as desired by operator and proctor and without complication. The proctor could swap between images from multiple sources and reported complete spatial and situational awareness, without any significant lag or delay in communication. Procedural times and radiologic dose were similar to those of uncomplicated, routine flow diversion cases at our institution.

CONCLUSIONS

International teleproctoring was successfully implemented in our clinical practice. Its first use provided important insights for establishing this tool in our field. With no clear horizon for lifting the current travel restrictions, teleproctoring has the potential to remove the need for proctor presence in the angiography suite, thereby allowing the field to advance through the continuation of trials and the introduction of new devices in clinical practice. In order for this tool to be used safely and effectively, highly reliable connection and high-resolution equipment is necessary, and multiple legal nuances have to be considered.

Evaluation and Real-World Performance Monitoring of Artificial Intelligence Models in Clinical Practice: Try It, Buy It, Check It

The pace of regulatory clearance of artificial intelligence (AI) algorithms for radiology continues to accelerate, and numerous algorithms are becoming available for use in clinical practice. End users of AI in radiology should be aware that AI algorithms may not work as expected when used beyond the institutions in which they were trained, and model performance may degrade over time. In this article, we discuss why regulatory clearance alone may not be enough to ensure AI will be safe and effective in all radiological practices and review strategies available resources for evaluating before clinical use and monitoring performance of AI models to ensure efficacy and patient safety.

Qualitative coronary artery calcification scores and risk of all cause, COPD and pneumonia hospital admission in a large CT lung cancer screening cohort

BACKGROUND

Patients at high-risk for lung cancer and qualified for CT lung cancer screening (CTLS) are at risk for numerous cardio-pulmonary comorbidities. We sought to examine if qualitatively assessed coronary artery calcifications (CAC) on CTLS exams could identify patients at increased risk for non-cardiovascular events such as all cause, COPD and pneumonia related hospitalization and to verify previously reported associations between CAC and mortality and cardiovascular events.

STUDY DESIGN AND METHODS

Patients (n = 4673) from Lahey Hospital and Medical Center who underwent CTLS from January 12, 2012 through September 30, 2017 were included with clinical follow-up through September 30, 2019. CTLS exams were qualitatively scored for the presence and severity of CAC at the time of exam interpretation using a four point scale: none, mild, moderate, and marked. Multivariable Cox regression models were used to evaluate the association between CT qualitative CAC and all-cause, COPD-related, and pneumonia-related hospital admissions.

RESULTS

3631 (78%) of individuals undergoing CTLS had some degree of CAC on their baseline exam: 1308 (28.0%), 1128 (24.1%), and 1195 (25.6%) had mild, moderate and marked coronary calcification, respectively. Marked CAC was associated with all-cause hospital admission and pneumonia related admissions HR 1.48; 95% CI 1.23-1.78 and HR 2.19; 95% 1.30-3.71, respectively. Mild, moderate and marked CAC were associated with COPD-related admission HR 2.30; 95% CI 1.31-4.03, HR 2.17; 95% CI 1.20-3.91 and HR 2.27; 95% CI 1.24-4.15.

CONCLUSION

Qualitative CAC on CTLS exams identifies individuals at elevated risk for all cause, pneumonia and COPD-related hospital admissions.

Spectral detector CT applications in advanced liver imaging

OBJECTIVE

Spectral detector CT (SDCT) has many applications in advanced liver imaging. If appropriately utilized, this technology has the potential to improve image quality, provide new diagnostic information, and allow for decreased radiation dose. The purpose of this review is to familiarize radiologists with the uses of SDCT in liver imaging.

CONCLUSION

SDCT has a variety of post-processing techniques, which can be used in advanced liver imaging and can significantly add value in clinical practice.

2020 ACR Data Science Institute Artificial Intelligence Survey

PURPOSE

The ACR Data Science Institute conducted its first annual survey of ACR members to understand how radiologists are using artificial intelligence (AI) in clinical practice and to provide a baseline for monitoring trends in AI use over time.

METHODS

The ACR Data Science Institute sent a brief electronic survey to all ACR members via email. Invitees were asked for demographic information about their practice and if and how they were currently using AI as part of their clinical work. They were also asked to evaluate the performance of AI models in their practices and to assess future needs.

RESULTS

Approximately 30% of radiologists are currently using AI as part of their practice. Large practices were more likely to use AI than smaller ones, and of those using AI in clinical practice, most were using AI to enhance interpretation, most commonly detection of intracranial hemorrhage, pulmonary emboli, and mammographic abnormalities. Of practices not currently using AI, 20% plan to purchase AI tools in the next 1 to 5 years.

CONCLUSION

The survey results indicate a modest penetrance of AI in clinical practice. Information from the survey will help researchers and industry develop AI tools that will enhance radiological practice and improve quality and efficiency in patient care.

Step by Step: A Structured Approach for Proposing, Developing and Implementing a Radiology Peer Learning Program

Similar to the experiences of other radiology practices, our radiology staff members felt that scored peer review identified few errors/learning opportunities while undermining team collegiality. They desired a more effective way to promote team collegiality and foster lifelong learning. We describe the steps our department took to transition from a peer review system to a peer learning program.

Towards radiologist-level cancer risk assessment in CT lung screening using deep learning

PURPOSE

Lung cancer is the leading cause of cancer mortality in the US, responsible for more deaths than breast, prostate, colon and pancreas cancer combined and large population studies have indicated that low-dose computed tomography (CT) screening of the chest can significantly reduce this death rate. Recently, the usefulness of Deep Learning (DL) models for lung cancer risk assessment has been demonstrated. However, in many cases model performances are evaluated on small/medium size test sets, thus not providing strong model generalization and stability guarantees which are necessary for clinical adoption. In this work, our goal is to contribute towards clinical adoption by investigating a deep learning framework on larger and heterogeneous datasets while also comparing to state-of-the-art models.

METHODS

Three low-dose CT lung cancer screening datasets were used: National Lung Screening Trial (NLST, n = 3410), Lahey Hospital and Medical Center (LHMC, n = 3154) data, Kaggle competition data (from both stages, n = 1397 + 505) and the University of Chicago data (UCM, a subset of NLST, annotated by radiologists, n = 132). At the first stage, our framework employs a nodule detector; while in the second stage, we use both the image context around the nodules and nodule features as inputs to a neural network that estimates the malignancy risk for the entire CT scan. We trained our algorithm on a part of the NLST dataset, and validated it on the other datasets. Special care was taken to ensure there was no patient overlap between the train and validation sets.

RESULTS AND CONCLUSIONS

The proposed deep learning model is shown to: (a) generalize well across all three data sets, achieving AUC between 86% to 94%, with our external test-set (LHMC) being at least twice as large compared to other works; (b) have better performance than the widely accepted PanCan Risk Model, achieving 6 and 9% better AUC score in our two test sets; (c) have improved performance compared to the state-of-the-art represented by the winners of the Kaggle Data Science Bowl 2017 competition on lung cancer screening; (d) have comparable performance to radiologists in estimating cancer risk at a patient level.

Enabling Your Radiology Business to Thrive Strategic Lessons Learned During the Initial and Subsequent Surges of the Covid-19 Pandemic

The Covid-19 pandemic surges of 2020 resulted in major operational, personal, and financial impacts on US radiology practices. In response, a series of strategic and intentional operational changes were implemented, varying by practice size, structure and model. In reviewing the many business lessons that we learned during the pandemic, it became clear that for a business to be successful, a host of additional supportive factors are necessary. In addition to timely expense reductions, optimizing revenue capture and close monitoring and management of cash and reserves available for use, we also consider effective leadership and communication strategies, maintenance of a healthy and adequately staffed team, support for a remote work environment and flexible staffing models. Other ingredients include effectively embracing digital media for communications, careful attention to current and new stakeholders and the service delivered to them, understanding federal and state regulatory changes issued in response to the pandemic, close collaboration with the Human Resources office, and an early focus on redesigning your future practice structure and function, including disaster and downtime planning. This review aims to share lessons to enable leaders of an imaging enterprise to be better prepared for similar and future surges.

Stochastic programming for outpatient scheduling with flexible inpatient exam accommodation

This study is concerned with the determination of an optimal appointment schedule in an outpatient-inpatient hospital system where the inpatient exams can be cancelled based on certain rules while the outpatient exams cannot be cancelled. Stochastic programming models were formulated and solved to tackle the stochasticity in the procedure durations and patient arrival patterns. The first model, a two-stage stochastic programming model, is formulated to optimize the slot size. The second model further optimizes the inpatient block (IPB) placement and slot size simultaneously. A computational method is developed to solve the second optimization problem. A case study is conducted using the data from Magnetic Resonance Imaging (MRI) centers of Lahey Hospital and Medical Center (LHMC). The current schedule and the schedules obtained from the optimization models are evaluated and compared using simulation based on FlexSim Healthcare. Results indicate that the overall weighted cost can be reduced by 11.6% by optimizing the slot size and can be further reduced by an additional 12.6% by optimizing slot size and IPB placement simultaneously. Three commonly used sequencing rules (IPBEG, OPBEG, and a variant of ALTER rule) were also evaluated. The results showed that when optimization tools are not available, ALTER variant which evenly distributes the IPBs across the day has the best performance. Sensitivity analysis of weights for patient waiting time, machine idle time and exam cancellations further supports the superiority of ALTER variant sequencing rules compared to the other sequencing methods. A Pareto frontier was also developed and presented between patient waiting time and machine idle time to enable medical centers with different priorities to obtain solutions that accurately reflect their respective optimal tradeoffs. An extended optimization model was also developed to incorporate the emergency patient arrivals. The optimal schedules from the extended model show only minor differences compared to those from the original model, thus proving the robustness of the scheduling solutions obtained from our optimal models against the impacts of emergency patient arrivals.

Identifying Areas for Operational Improvement and Growth in IR Workflow Using Workflow Modeling, Simulation, and Optimization Techniques

Identifying areas for workflow improvement and growth is essential for an interventional radiology (IR) department to stay competitive. Deployment of traditional methods such as Lean and Six Sigma helped in reducing the waste in workflows at a strategic level. However, achieving efficient workflow needs both strategic and tactical approaches. Uncertainties about patient arrivals, staff availability, and variability in procedure durations pose hindrances to efficient workflow and lead to delayed patient care and staff overtime. We present an alternative approach to address both tactical and strategic needs using discrete event simulation (DES) and simulation based optimization methods. A comprehensive digital model of the patient workflow in a hospital-based IR department was modeled based on expert interviews with the incumbent personnel and analysis of 192 days' worth of electronic medical record (EMR) data. Patient arrival patterns and process times were derived from 4393 individual patient appointments. Exactly 196 unique procedures were modeled, each with its own process time distribution and rule-based procedure-room mapping. Dynamic staff schedules for interventional radiologists, technologists, and nurses were incorporated in the model. Stochastic model simulation runs revealed the resource "computed tomography (CT) suite" as the major workflow bottleneck during the morning hours. This insight compelled the radiology department leadership to re-assign time blocks on a diagnostic CT scanner to the IR group. Moreover, this approach helped identify opportunities for additional appointments at times of lower diagnostic scanner utilization. Demand for interventional service from Outpatients during late hours of the day required the facility to extend hours of operations. Simulation-based optimization methods were used to model a new staff schedule, stretching the existing pool of resources to support the additional 2.5 h of daily operation. In conclusion, this study illustrates that the combination of workflow modeling, stochastic simulations, and optimization techniques is a viable and effective approach for identifying workflow inefficiencies and discovering and validating improvement options through what-if scenario testing.

Qualitative emphysema and risk of COPD hospitalization in a multicenter CT lung cancer screening cohort study

BACKGROUND

In the United States, 9 to 10 million Americans are estimated to be eligible for computed tomographic lung cancer screening (CTLS). Those meeting criteria for CTLS are at high-risk for numerous cardio-pulmonary co-morbidities. The objective of this study was to determine the association between qualitative emphysema identified on screening CTs and risk for hospital admission.

STUDY DESIGN AND METHODS

We conducted a retrospective multicenter study from two CTLS cohorts: Lahey Hospital and Medical Center (LHMC) CTLS program, Burlington, MA and Mount Auburn Hospital (MAH) CTLS program, Cambridge, MA. CTLS exams were qualitatively scored by radiologists at time of screening for presence of emphysema. Multivariable Cox regression models were used to evaluate the association between CT qualitative emphysema and all-cause, COPD-related, and pneumonia-related hospital admission.

RESULTS

We included 4673 participants from the LHMC cohort and 915 from the MAH cohort. 57% and 51.9% of the LHMC and MAH cohorts had presence of CT emphysema, respectively. In the LHMC cohort, the presence of emphysema was associated with all-cause hospital admission (HR 1.15, CI 1.07-1.23; p < 0.001) and COPD-related admission (HR 1.64; 95% CI 1.14-2.36; p = 0.007), but not with pneumonia-related admission (HR 1.52; 95% CI 1.27-1.83; p < 0.001). In the MAH cohort, the presence of emphysema was only associated with COPD-related admission (HR 2.05; 95% CI 1.07-3.95; p = 0.031).

CONCLUSION

Qualitative CT assessment of emphysema is associated with COPD-related hospital admission in a CTLS population. Identification of emphysema on CLTS exams may provide an opportunity for prevention and early intervention to reduce admission risk.

Quantitative Pectoralis Muscle Area is Associated with the Development of Lung Cancer in a Large Lung Cancer Screening Cohort

BACKGROUND

Studies have demonstrated an inverse relationship between body mass index (BMI) and the risk of developing lung cancer. We conducted a retrospective cohort study evaluating baseline quantitative computed tomography (CT) measurements of body composition, specifically muscle and fat area in a large CT lung screening cohort (CTLS). We hypothesized that quantitative measurements of baseline body composition may aid in risk stratification for lung cancer.

METHODS

Patients who underwent baseline CTLS between January 1st, 2012 and September 30th, 2014 and who had an in-network primary care physician were included. All patients met NCCN Guidelines eligibility criteria for CTLS. Quantitative measurements of pectoralis muscle area (PMA) and subcutaneous fat area (SFA) were performed on a single axial slice of the CT above the aortic arch with the Chest Imaging Platform Workstation software. Cox multivariable proportional hazards model for cancer was adjusted for variables with a univariate p < 0.2. Data were dichotomized by sex and then combined to account for baseline differences between sexes.

RESULTS

One thousand six hundred and ninety six patients were included in this study. A total of 79 (4.7%) patients developed lung cancer. There was an association between the 25th percentile of PMA and the development of lung cancer [HR 1.71 (1.07, 2.75), p < 0.025] after adjusting for age, BMI, qualitative emphysema, qualitative coronary artery calcification, and baseline Lung-RADS® score.

CONCLUSIONS

Quantitative assessment of PMA on baseline CTLS was associated with the development of lung cancer. Quantitative PMA has the potential to be incorporated as a variable in future lung cancer risk models.

Neural networks-based regularization for large-scale medical image reconstruction

In this paper we present a generalized Deep Learning-based approach for solving ill-posed large-scale inverse problems occuring in medical image reconstruction. Recently, Deep Learning methods using iterative neural networks (NNs) and cascaded NNs have been reported to achieve state-of-the-art results with respect to various quantitative quality measures as PSNR, NRMSE and SSIM across different imaging modalities. However, the fact that these approaches employ the application of the forward and adjoint operators repeatedly in the network architecture requires the network to process the whole images or volumes at once, which for some applications is computationally infeasible. In this work, we follow a different reconstruction strategy by strictly separating the application of the NN, the regularization of the solution and the consistency with the measured data. The regularization is given in the form of an image prior obtained by the output of a previously trained NN which is used in a Tikhonov regularization framework. By doing so, more complex and sophisticated network architectures can be used for the removal of the artefacts or noise than it is usually the case in iterative NNs. Due to the large scale of the considered problems and the resulting computational complexity of the employed networks, the priors are obtained by processing the images or volumes as patches or slices. We evaluated the method for the cases of 3D cone-beam low dose CT and undersampled 2D radial cine MRI and compared it to a total variation-minimization-based reconstruction algorithm as well as to a method with regularization based on learned overcomplete dictionaries. The proposed method outperformed all the reported methods with respect to all chosen quantitative measures and further accelerates the regularization step in the reconstruction by several orders of magnitude.

NCCN Guidelines as a Model of Extended Criteria for Lung Cancer Screening

Background: This review assessed the performance of patients in NCCN high-risk group 2 in a clinical CT lung screening (CTLS) program. Methods: We retrospectively reviewed screening results for all patients from our institution undergoing clinical CTLS from January 2012 through December 2016, with follow-up through June 2017. To qualify for screening, patients had to meet the NCCN Guidelines high-risk criteria for CTLS, have a physician order for screening, be asymptomatic, be lung cancer-free for 5 years, and have no known metastatic disease. We compared demographics and screening performance of NCCN high-risk groups 1 and 2 across >4 rounds of screening. Screening metrics assessed included rates of positive and suspicious examinations, significant incidental and infectious/inflammatory findings, false negatives, and cancer detection. We also compared cancer stage and histology detected in each NCCN high-risk group. Results: A total of 2,927 individuals underwent baseline screening, of which 698 (24%) were in NCCN group 2. On average, group 2 patients were younger (60.6 vs 63.1 years), smoked less (38.8 vs 50.8 pack-years), had quit longer (18.1 vs 6.3 years), and were more often former smokers (61.4% vs 44.2%). Positive and suspicious examination rates, false negatives, and rates of infectious/inflammatory findings were equivalent in groups 1 and 2 across all rounds of screening. An increased rate of cancer detection was observed in group 2 during the second annual (T2) screening round (2.7% vs 0.5%; P=.005), with no difference in the other screening rounds: baseline (T0; 2% vs 2.3%; P=.61), first annual (T1; 1.2% vs 1.7%; P=.41), and third annual and beyond (≥T3; 1.2% vs 1.1%; P=1.00). Conclusions: CTLS appears to be equally effective in both NCCN high-risk groups.

Probabilistic Modeling of Exam Durations in Radiology Procedures

In this paper, we model the statistical properties of imaging exam durations using parametric probability distributions such as the Gaussian, Gamma, Weibull, lognormal, and log-logistic. We establish that in a majority of radiology procedures, the underlying distribution of exam durations is best modeled by a log-logistic distribution, while the Gaussian has the poorest fit among the candidates. Further, through illustrative examples, we show how business insights and workflow analytics can be significantly impacted by making the correct (log-logistic) versus incorrect (Gaussian) model choices.

Qualitative coronary artery calcium assessment on CT lung screening exam helps predict first cardiac events

Results

A total of 1,513 individuals underwent CTLS. Downstream data, pre-test cardiac risk factors and CAC scores were available for 88.3% (1,336/1,513). The average length of follow-up was 2.64 (SD ±0.72) years. There were a total of 43 events, occurring in 1.55% (6/386) of patients with mild CAC, 3.24% (11/339) of patients with moderate CAC, and 8.90% (26/292) of patients with marked CAC. There were no events among patients with no reported CAC (0/319). Using multivariable logistic modeling, the increased odds of an initial cardiac event was 2.56 (95% CI, 1.76-3.92, P<0.001) for mild CAC, 6.57 (95% CI, 3.10-15.4, P<0.001) for moderate CAC, and 16.8 (95% CI, 5.46-60.3, P<0.001) for marked CAC, as compared to individuals with no CAC. Time to event analysis showed distinct differences among the four CAC categories (P<0.001).

Conclusions

Qualitative coronary artery calcification scoring of CTLS exams may provide a novel method to help select individuals at elevated risk for an initial cardiac event.

Inpatient Complexity in Radiology-a Practical Application of the Case Mix Index Metric

With ongoing healthcare payment reforms in the USA, radiology is moving from its current state of a revenue generating department to a new reality of a cost-center. Under bundled payment methods, radiology does not get reimbursed for each and every inpatient procedure, but rather, the hospital gets reimbursed for the entire hospital stay under an applicable diagnosis-related group code. The hospital case mix index (CMI) metric, as defined by the Centers for Medicare and Medicaid Services, has a significant impact on how much hospitals get reimbursed for an inpatient stay. Oftentimes, patients with the highest disease acuity are treated in tertiary care radiology departments. Therefore, the average hospital CMI based on the entire inpatient population may not be adequate to determine department-level resource utilization, such as the number of technologists and nurses, as case length and staffing intensity gets quite high for sicker patients. In this study, we determine CMI for the overall radiology department in a tertiary care setting based on inpatients undergoing radiology procedures. Between April and September 2015, CMI for radiology was 1.93. With an average of 2.81, interventional neuroradiology had the highest CMI out of the ten radiology sections. CMI was consistently higher across seven of the radiology sections than the average hospital CMI of 1.81. Our results suggest that inpatients undergoing radiology procedures were on average more complex in this hospital setting during the time period considered. This finding is relevant for accurate calculation of labor analytics and other predictive resource utilization tools.

Adherence to Radiology Recommendations in a Clinical CT Lung Screening Program

BACKGROUND

Assess patient adherence to radiologist recommendations in a clinical CT lung cancer screening program.

METHODS

Patients undergoing CT lung cancer screening between January 12, 2012, and June 12, 2013, were included in this institutional review board-approved retrospective review. Patients referred from outside our institution were excluded. All patients met National Comprehensive Cancer Network Guidelines Lung Cancer Screening high-risk criteria. Full-time program navigators used a CT lung screening program management system to schedule patient appointments, generate patient result notification letters detailing the radiologist follow-up recommendation, and track patient and referring physician notification of missed appointments at 30, 60, and 90 days. To be considered adherent, patients could be no more than 90 days past due for their next recommended examination as of September 12, 2014. Patients who died, were diagnosed with cancer, or otherwise became ineligible for screening were considered adherent. Adherence rates were assessed across multiple variables.

RESULTS

During the study interval, 1,162 high-risk patients were screened, and 261 of 1,162 (22.5%) outside referrals were excluded. Of the remaining 901 patients, 503 (55.8%) were male, 414 (45.9%) were active smokers, 377 (41.8%) were aged 65 to 73, and >95% were white. Of the 901 patients, 772 (85.7%) were adherent. Most common reasons for nonadherence were patient refusal of follow-up exam (66.7%), inability to successfully contact the patient (20.9%), and inability to obtain the follow-up order from the referring provider (7.8%); 23 of 901 (2.6%) were discharged for other reasons.

CONCLUSIONS

High rates of adherence to radiologist recommendations are achievable for in-network patients enrolled in a clinical CT lung screening program.

A model to determine payments associated with radiology procedures

OBJECTIVE

Across the United States, there is a growing number of patients in Accountable Care Organizations and under risk contracts with commercial insurance. This is due to proliferation of new value-based payment models and care delivery reform efforts. In this context, the business model of radiology within a hospital or health system context is shifting from a primary profit-center to a cost-center with a goal of cost savings. Radiology departments need to increasingly understand how the transactional nature of the business relates to financial rewards. The main challenge with current reporting systems is that the information is presented only at an aggregated level, and often not broken down further, for instance, by type of exam. As such, the primary objective of this research is to provide better visibility into payments associated with individual radiology procedures in order to better calibrate expense/capital structure of the imaging enterprise to the actual revenue or value-add to the organization it belongs to.

MATERIALS AND METHODS

We propose a methodology that can be used to determine technical payments at a procedure level. We use a proportion based model to allocate payments to individual radiology procedures based on total charges (which also includes non-radiology related charges).

RESULTS

Using a production dataset containing 424,250 radiology exams we calculated the overall average technical charge for Radiology to be $873.08 per procedure and the corresponding average payment to be $326.43 (range: $48.27 for XR and $2750.11 for PET/CT) resulting in an average payment percentage of 37.39% across all exams.

DISCUSSION

We describe how charges associated with a procedure can be used to approximate technical payments at a more granular level with a focus on Radiology. The methodology is generalizable to approximate payment for other services as well. Understanding payments associated with each procedure can be useful during strategic practice planning.

CONCLUSIONS

Charge-to-total charge ratio can be used to approximate radiology payments at a procedure level.

Automatic Lung-RADS™ classification with a natural language processing system

Background

Our aim was to train a natural language processing (NLP) algorithm to capture imaging characteristics of lung nodules reported in a structured CT report and suggest the applicable Lung-RADS™ (LR) category.

Methods

Our study included structured, clinical reports of consecutive CT lung screening (CTLS) exams performed from 08/2014 to 08/2015 at an ACR accredited Lung Cancer Screening Center. All patients screened were at high-risk for lung cancer according to the NCCN Guidelines^®. All exams were interpreted by one of three radiologists credentialed to read CTLS exams using LR using a standard reporting template. Training and test sets consisted of consecutive exams. Lung screening exams were divided into two groups: three training sets (500, 120, and 383 reports each) and one final evaluation set (498 reports). NLP algorithm results were compared with the gold standard of LR category assigned by the radiologist.

Results

The sensitivity/specificity of the NLP algorithm to correctly assign LR categories for suspicious nodules (LR 4) and positive nodules (LR 3/4) were 74.1%/98.6% and 75.0%/98.8% respectively. The majority of mismatches occurred in cases where pulmonary findings were present not currently addressed by LR. Misclassifications also resulted from the failure to identify exams as follow-up and the failure to completely characterize part-solid nodules. In a sub-group analysis among structured reports with standardized language, the sensitivity and specificity to detect LR 4 nodules were 87.0% and 99.5%, respectively.

Conclusions

An NLP system can accurately suggest the appropriate LR category from CTLS exam findings when standardized reporting is used.

Smoking cessation results in a clinical lung cancer screening program

BACKGROUND

Lung cancer screening may provide a "teachable moment" for promoting smoking cessation. This study assessed smoking cessation and relapse rates among individuals undergoing follow-up low-dose chest computed tomography (CT) in a clinical CT lung screening program and assessed the influence of initial screening results on smoking behavior.

METHODS

Self-reported smoking status for individuals enrolled in a clinical CT lung screening program undergoing a follow-up CT lung screening exam between 1st February, 2014 and 31st March, 2015 was retrospectively reviewed and compared to self-reported smoking status using a standardized questionnaire at program entry. Point prevalence smoking cessation and relapse rates were calculated across the entire population and compared with exam results. All individuals undergoing screening fulfilled the National Comprehensive Cancer Network Clinical Practice Guidelines in Oncology: Lung Cancer Screening v1.2012(®) high-risk criteria and had an order for CT lung screening.

RESULTS

A total of 1,483 individuals underwent a follow-up CT lung screening exam during the study interval. Smoking status at time of follow-up exam was available for 1,461/1,483 (98.5%). A total of 46% (678/1,461) were active smokers at program entry. The overall point prevalence smoking cessation and relapse rates were 20.8% and 9.3%, respectively. Prior positive screening exam results were not predictive of smoking cessation (OR 1.092; 95% CI, 0.715-1.693) but were predictive of reduced relapse among former smokers who had stopped smoking for 2 years or less (OR 0.330; 95% CI, 0.143-0.710). Duration of program enrollment was predictive of smoking cessation (OR 0.647; 95% CI, 0.477-0.877).

CONCLUSIONS

Smoking cessation and relapse rates in a clinical CT lung screening program rates are more favorable than those observed in the general population. Duration of participation in the screening program correlated with increased smoking cessation rates. A positive exam result correlated with reduced relapse rates among smokers recently quit smoking.

Experience With a CT Screening Program for Individuals at High Risk for Developing Lung Cancer

PURPOSE

The aim of this study was to compare results of National Comprehensive Cancer Network (NCCN) high-risk group 2 with those of NCCN high-risk group 1 in a clinical CT lung screening program.

METHODS

The results of consecutive clinical CT lung screening examinations performed from January 2012 through December 2013 were retrospectively reviewed. All examinations were interpreted by radiologists credentialed in structured CT lung screening reporting, following the NCCN Clinical Practice Guidelines in Oncology: Lung Cancer Screening (version 1.2012). Positive results required a solid nodule ≥4 mm, a ground-glass nodule ≥5 mm, or a mediastinal or hilar lymph node >1 cm, not stable for >2 years. Significant incidental findings and findings suspicious for pulmonary infection were also recorded.

RESULTS

A total of 1,760 examinations were performed (464 in group 2, 1,296 in group 1); no clinical follow-up was available in 432 patients (28%). Positive results, clinically significant incidental findings, and suspected pulmonary infection were present in 25%, 6%, and 6% in group 2 and 28.2%, 6.2%, and 6.6% in group 1, respectively. Twenty-three cases of lung cancer were diagnosed (6 in group 2, 17 in group 1), for annualized rates of malignancy of 1.8% in group 2 and 1.6% in group 1.

CONCLUSION

NCCN group 2 results were substantively similar to those for group 1 and closely resemble those reported in the National Lung Screening Trial. Similar rates of positivity and lung cancer diagnosis in both groups suggest that thousands of additional lives may be saved each year if screening eligibility is expanded to include this particular high-risk group.

Performance of ACR Lung-RADS in a Clinical CT Lung Screening Program

PURPOSE

The aim of this study was to assess the effect of applying ACR Lung-RADS in a clinical CT lung screening program on the frequency of positive and false-negative findings.

METHODS

Consecutive, clinical CT lung screening examinations performed from January 2012 through May 2014 were retroactively reclassified using the new ACR Lung-RADS structured reporting system. All examinations had initially been interpreted by radiologists credentialed in structured CT lung screening reporting following the National Comprehensive Cancer Network's Clinical Practice Guidelines in Oncology: Lung Cancer Screening (version 1.2012), which incorporated positive thresholds modeled after those in the National Lung Screening Trial. The positive rate, number of false-negative findings, and positive predictive value were recalculated using the ACR Lung-RADS-specific positive solid/part-solid nodule diameter threshold of 6 mm and nonsolid (ground-glass) threshold of 2 cm. False negatives were defined as cases reclassified as benign under ACR Lung-RADS that were diagnosed with malignancies within 12 months of the baseline examination.

RESULTS

A total of 2,180 high-risk patients underwent baseline CT lung screening during the study interval; no clinical follow-up was available in 577 patients (26%). ACR Lung-RADS reduced the overall positive rate from 27.6% to 10.6%. No false negatives were present in the 152 patients with >12-month follow-up reclassified as benign. Applying ACR Lung-RADS increased the positive predictive value for diagnosed malignancy in 1,603 patients with follow-up from 6.9% to 17.3%.

CONCLUSIONS

The application of ACR Lung-RADS increased the positive predictive value in our CT lung screening cohort by a factor of 2.5, to 17.3%, without increasing the number of examinations with false-negative results.