Computed tomography machine learning classifier correlates with mortality in interstitial lung disease.

BACKGROUND: A machine learning classifier system, Fibresolve, was designed and validated as an adjunct to non-invasive diagnosis in idiopathic pulmonary fibrosis (IPF). The system uses a deep learning algorithm to analyze chest computed tomography (CT) imaging. We hypothesized that Fibresolve is a useful predictor of mortality in interstitial lung diseases (ILD). METHODS: Fibresolve was previously validated in a multi-site >500-patient dataset. In this analysis, we assessed the usefulness of Fibresolve to predict mortality in a subset of 228 patients with IPF and other ILDs in whom follow up data was available. We applied Cox regression analysis adjusting for the Gender, Age, and Physiology (GAP) score and for other known predictors of mortality in IPF. We also analyzed the role of Fibresolve as tertiles adjusting for GAP stages. RESULTS: During a median follow-up of 2.8 years (range 5 to 3434 days), 89 patients died. After adjusting for GAP score and other mortality risk factors, the Fibresolve score significantly predicted the risk of death (HR: 7.14; 95% CI: 1.31-38.85; p = 0.02) during the follow-up period, as did forced vital capacity and history of lung cancer. After adjusting for GAP stages and other variables, Fibresolve score split into tertiles significantly predicted the risk of death (p = 0.027 for the model; HR 1.37 for 2nd tertile; 95% CI: 0.77-2.42. HR 2.19 for 3rd tertile; 95% CI: 1.22-3.93). CONCLUSIONS: The machine learning classifier Fibresolve demonstrated to be an independent predictor of mortality in ILDs, with prognostic performance equivalent to GAP based solely on CT images.

Machine learning classifier is associated with mortality in interstitial lung disease: a retrospective validation study leveraging registry data.

BACKGROUND: Mortality prediction in interstitial lung disease (ILD) poses a significant challenge to clinicians due to heterogeneity across disease subtypes. Currently, forced vital capacity (FVC) and Gender, Age, and Physiology (GAP) score are the two most utilized metrics in prognostication. Recently, a machine learning classifier system, Fibresolve, designed to identify a variety of computed tomography (CT) patterns associated with idiopathic pulmonary fibrosis (IPF), was demonstrated to have a significant association with mortality across multiple subtypes of ILD. The purpose of this follow-up study was to retrospectively validate these findings in a large, external cohort of patients with ILD. METHODS: In this multi-center validation study, Fibresolve was applied to chest CT scans of patients with confirmed ILD that had available follow-up data. Fibresolve scores categorized by tertile were analyzed using Cox regression analysis adjusted for tobacco use and modified GAP (mGAP) score. RESULTS: Of 643 patients included, 446 (69.3%) died over a median follow-up time of 144 [1-821] weeks. The median [range] mGAP score was 5 [3-7]. In multivariable analysis, Fibresolve score categorized by tertile was significantly associated with mortality (Tertile 2 HR 1.47, 95% CI 0.82-2.37, p = 0.11; Tertile 3 HR 3.12, 95% CI 1.98-4.90, p < 0.001). Subgroup analyses revealed significant associations amongst those with non-IPF ILDs (Tertile 2 HR 1.95, 95% CI 1.28-2.97, Tertile 3 HR 4.66, 95% CI 2.94-7.38) and severe disease, defined by a FVC ≤ 75% (Tertile 2 HR 2.29, 95% CI 1.43-3.67, Tertile 3 HR 4.80, 95% CI 2.93-7.86). CONCLUSIONS: Fibresolve is independently associated with mortality in ILD, particularly amongst patients with non-IPF ILDs and in those with severe disease.

A Machine Learning System to Indicate Diagnosis of Idiopathic Pulmonary Fibrosis Non-Invasively in Challenging Cases.

Radiologic usual interstitial pneumonia (UIP) patterns and concordant clinical characteristics define a diagnosis of idiopathic pulmonary fibrosis (IPF). However, limited expert access and high inter-clinician variability challenge early and pre-invasive diagnostic sensitivity and differentiation of IPF from other interstitial lung diseases (ILDs). We investigated a machine learning-driven software system, Fibresolve, to indicate IPF diagnosis in a heterogeneous group of 300 patients with interstitial lung disease work-up in a retrospective analysis of previously and prospectively collected registry data from two US clinical sites. Fibresolve analyzed cases at the initial pre-invasive assessment. An Expert Clinical Panel (ECP) and three panels of clinicians with varying experience analyzed the cases for comparison. Ground Truth was defined by separate multi-disciplinary discussion (MDD) with the benefit of surgical pathology results and follow-up. Fibresolve met both pre-specified co-primary endpoints of sensitivity superior to ECP and significantly greater specificity (p = 0.0007) than the non-inferior boundary of 80.0%. In the key subgroup of cases with thin-slice CT and atypical UIP patterns (n = 124), Fibresolve's diagnostic yield was 53.1% [CI: 41.3-64.9] (versus 0% pre-invasive clinician diagnostic yield in this group), and its specificity was 85.9% [CI: 76.7-92.6%]. Overall, Fibresolve was found to increase the sensitivity and diagnostic yield for IPF among cases of patients undergoing ILD work-up. These results demonstrate that in combination with standard clinical assessment, Fibresolve may serve as an adjunct in the diagnosis of IPF in a pre-invasive setting.

Analysis of Validation Performance of a Machine Learning Classifier in Interstitial Lung Disease Cases Without Definite or Probable Usual Interstitial Pneumonia Pattern on CT Using Clinical and Pathology-Supported Diagnostic Labels.

We previously validated Fibresolve, a machine learning classifier system that non-invasively predicts idiopathic pulmonary fibrosis (IPF) diagnosis. The system incorporates an automated deep learning algorithm that analyzes chest computed tomography (CT) imaging to assess for features associated with idiopathic pulmonary fibrosis. Here, we assess performance in assessment of patterns beyond those that are characteristic features of usual interstitial pneumonia (UIP) pattern. The machine learning classifier was previously developed and validated using standard training, validation, and test sets, with clinical plus pathologically determined ground truth. The multi-site 295-patient validation dataset was used for focused subgroup analysis in this investigation to evaluate the classifier's performance range in cases with and without radiologic UIP and probable UIP designations. Radiologic assessment of specific features for UIP including the presence and distribution of reticulation, ground glass, bronchiectasis, and honeycombing was used for assignment of radiologic pattern. Output from the classifier was assessed within various UIP subgroups. The machine learning classifier was able to classify cases not meeting the criteria for UIP or probable UIP as IPF with estimated sensitivity of 56-65% and estimated specificity of 92-94%. Example cases demonstrated non-basilar-predominant as well as ground glass patterns that were indeterminate for UIP by subjective imaging criteria but for which the classifier system was able to correctly identify the case as IPF as confirmed by multidisciplinary discussion generally inclusive of histopathology. The machine learning classifier Fibresolve may be helpful in the diagnosis of IPF in cases without radiological UIP and probable UIP patterns.

External validation of Fibresolve, a machine-learning algorithm, to non-invasively diagnose idiopathic pulmonary fibrosis.

BACKGROUND: Previous work has shown the ability of Fibresolve, a machine learning system, to non-invasively classify idiopathic pulmonary fibrosis (IPF) with a pre-invasive sensitivity of 53% and specificity of 86% versus other types of interstitial lung disease. Further external validation for the use of Fibresolve to classify IPF in patients with non-definite usual interstitial pneumonia (UIP) is needed. The aim of this study is to assess the sensitivity for Fibresolve to positively classify IPF in an external cohort of patients with a non-definite UIP radiographic pattern. METHODS: This is a retrospective analysis of patients (n = 193) enrolled in two prospective phase two clinical trials that enrolled patients with IPF. We retrospectively identified patients with non-definite UIP on HRCT (n = 51), 47 of whom required surgical lung biopsy for diagnosis. Fibresolve was used to analyze the HRCT chest imaging which was obtained prior to invasive biopsy and sensitivity for final diagnosis of IPF was calculated. RESULTS: The sensitivity of Fibresolve for the non-invasive classification of IPF in patients with a non-definite UIP radiographic pattern by HRCT was 76.5% (95% CI 66.5-83.7). For the subgroup of 47 patients who required surgical biopsy to aid in final diagnosis of IPF, Fibresolve had a sensitivity of 74.5% (95% CI 60.5-84.7). CONCLUSION: In patients with suspected IPF with non-definite UIP on HRCT, Fibresolve can positively identify cases of IPF with high sensitivity. These results suggest that in combination with standard clinical assessment, Fibresolve has the potential to serve as an adjunct in the non-invasive diagnosis of IPF.

Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis.

RATIONALE: Non-invasive diagnosis of idiopathic pulmonary fibrosis (IPF) involves identification of usual interstitial pneumonia (UIP) pattern by computed tomography (CT) and exclusion of other known etiologies of interstitial lung disease (ILD). However, uncertainty in identification of radiologic UIP pattern leads to the continued need for invasive surgical biopsy. We thus developed and validated a machine learning algorithm using CT scans alone to augment non-invasive diagnosis of IPF. METHODS: The primary algorithm was a deep learning convolutional neural network (CNN) with model inputs of CT images only. The algorithm was trained to predict IPF among cases of ILD, with reference standard of multidisciplinary discussion (MDD) consensus diagnosis. The algorithm was trained using a multi-center dataset of more than 2000 cases of ILD. A US-based multi-site cohort (n = 295) was used for algorithm tuning, and external validation was performed with a separate dataset (n = 295) from European and South American sources. RESULTS: In the tuning set, the model achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (CI: 0.83-0.92) in differentiating IPF from other ILDs. Sensitivity and specificity were 0.67 (0.57-0.76) and 0.90 (0.83-0.95), respectively. By contrast, pre-recorded assessment prior to MDD diagnosis had sensitivity of 0.31 (0.23-0.42) and specificity of 0.92 (0.87-0.95). In the external test set, c-statistic was also 0.87 (0.83-0.91). Model performance was consistent across a variety of CT scanner manufacturers and slice thickness. CONCLUSION: The presented deep learning algorithm demonstrated consistent performance in identifying IPF among cases of ILD using CT images alone and suggests generalization across CT manufacturers.

Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software.

Background: Improvement in recognition and referral of pulmonary fibrosis (PF) is vital to improving patient outcomes within interstitial lung disease. We determined the performance metrics and processing time of an artificial intelligence triage and notification software, ScreenDx-LungFibrosis™, developed to improve detection of PF. Methods: ScreenDx-LungFibrosis™ was applied to chest computed tomography (CT) scans from multisource data. Device output (+/- PF) was compared to clinical diagnosis (+/- PF), and diagnostic performance was evaluated. Primary endpoints included device sensitivity and specificity > 80% and processing time < 4.5 min. Results: Of 3,018 patients included, PF was present in 22.9%. ScreenDx-LungFibrosis™ detected PF with a sensitivity and specificity of 91.3% (95% confidence interval (CI): 89.0-93.3%) and 95.1% (95% CI: 94.2-96.0%), respectively. Mean processing time was 27.6 s (95% CI: 26.0 - 29.1 s). Conclusions: ScreenDx-LungFibrosis™ accurately and reliably identified PF with a rapid per-case processing time, underscoring its potential for transformative improvement in PF outcomes when routinely applied to chest CTs.

Machine learning to distinguish lymphangioleiomyomatosis from other diffuse cystic lung diseases.

Patients with lymphangioleiomyomatosis (LAM) frequently experience delays in diagnosis, owing partly to the delayed characterization of imaging findings. This project aimed to develop a machine learning model to distinguish LAM from other diffuse cystic lung diseases (DCLDs). Computed tomography scans from patients with confirmed DCLDs were acquired from registry datasets and a recurrent convolutional neural network was trained for their classification. The final model provided sensitivity and specificity of 85% and 92%, respectively, for LAM, similar to the historical metrics of 88% and 97%, respectively, by experts. The proof-of-concept work holds promise as a clinically useful tool to assist in recognizing LAM.

Improving reference standards for validation of AI-based radiography.

OBJECTIVE: Demonstrate the importance of combining multiple readers' opinions, in a context-aware manner, when establishing the reference standard for validation of artificial intelligence (AI) applications for, e.g. chest radiographs. By comparing individual readers, majority vote of a panel, and panel-based discussion, we identify methods which maximize interobserver agreement and label reproducibility. METHODS: 1100 frontal chest radiographs were evaluated for 6 findings: airspace opacity, cardiomegaly, pulmonary edema, fracture, nodules, and pneumothorax. Each image was reviewed by six radiologists, first individually and then via asynchronous adjudication (web-based discussion) in two panels of three readers to resolve disagreements within each panel. We quantified the reproducibility of each method by measuring interreader agreement. RESULTS: Panel-based majority vote improved agreement relative to individual readers for all findings. Most disagreements were resolved with two rounds of adjudication, which further improved reproducibility for some findings, particularly reducing misses. Improvements varied across finding categories, with adjudication improving agreement for cardiomegaly, fractures, and pneumothorax. CONCLUSION: The likelihood of interreader agreement, even within panels of US board-certified radiologists, must be considered before reads can be used as a reference standard for validation of proposed AI tools. Agreement and, by extension, reproducibility can be improved by applying majority vote, maximum sensitivity, or asynchronous adjudication for different findings, which supports the development of higher quality clinical research. ADVANCES IN KNOWLEDGE: A panel of three experts is a common technique for establishing reference standards when ground truth is not available for use in AI validation. The manner in which differing opinions are resolved is shown to be important, and has not been previously explored.

Sharing is Caring: Exploring machine learning-enabled methods for regional medical imaging exchange using procedure metadata.

Seamless sharing between imaging facilities of medical images obtained on the same patient is crucial in providing accurate and efficient care to patients. However, the terminology used to describe semantically similar examinations can vary widely between facilities. Current practice is manual table-based mapping to a standard terminology, which has substantial potential for mislabelled and missing examinations. In this work, we establish several baseline methods for automating the mapping of radiology imaging procedure descriptions to a SNOMED CT based standard terminology. Our best performing baseline, consisting of a bag of words representation and shallow neural network, achieved 96.3% accuracy. In addition, we explore an unsupervised clustering method that explores relevancy matching without the need for an intervening standard. Lastly, we make the procedure name dataset used in this work available to encourage extension of this application.

Machine Learning for Automation of Radiology Protocols for Quality and Efficiency Improvement.

PURPOSE: The aim of this study was to enhance multispecialty CT and MRI protocol assignment quality and efficiency through development, testing, and proposed workflow design of a natural language processing (NLP)-based machine learning classifier. METHODS: NLP-based machine learning classification models were developed using order entry input data and radiologist-assigned protocols from more than 18,000 unique CT and MRI examinations obtained during routine clinical use. k-Nearest neighbor, random forest, and deep neural network classification models were evaluated at baseline and after applying class frequency and confidence thresholding techniques. To simulate performance in real-world deployment, the model was evaluated in two operating modes in combination: automation (automated assignment of the top result) and clinical decision support (CDS; top-three protocol suggestion for clinical review). Finally, model-radiologist discordance was subjectively reviewed to guide explainability and safe use. RESULTS: Baseline protocol assignment performance achieved weighted precision of 0.757 to 0.824. Simulating real-world deployment using combined thresholding techniques, the optimized deep neural network model assigned 69% of protocols in automation mode with 95% accuracy. In the remaining 31% of cases, the model achieved 92% accuracy in CDS mode. Analysis of discordance with subspecialty radiologist labels revealed both more and less appropriate model predictions. CONCLUSIONS: A multiclass NLP-based classification algorithm was designed to drive local operational improvement in CT and MR radiology protocol assignment at subspecialist quality. The results demonstrate a simulated workflow deployment enabling automated assignment of protocols in nearly 7 of 10 cases with very few errors combined with top-three CDS for remaining cases supporting a high-quality, efficient radiology workflow.

International evaluation of an AI system for breast cancer screening.

Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Chest Radiograph Interpretation with Deep Learning Models: Assessment with Radiologist-adjudicated Reference Standards and Population-adjusted Evaluation.

BackgroundDeep learning has the potential to augment the use of chest radiography in clinical radiology, but challenges include poor generalizability, spectrum bias, and difficulty comparing across studies.PurposeTo develop and evaluate deep learning models for chest radiograph interpretation by using radiologist-adjudicated reference standards.Materials and MethodsDeep learning models were developed to detect four findings (pneumothorax, opacity, nodule or mass, and fracture) on frontal chest radiographs. This retrospective study used two data sets. Data set 1 (DS1) consisted of 759 611 images from a multicity hospital network and ChestX-ray14 is a publicly available data set with 112 120 images. Natural language processing and expert review of a subset of images provided labels for 657 954 training images. Test sets consisted of 1818 and 1962 images from DS1 and ChestX-ray14, respectively. Reference standards were defined by radiologist-adjudicated image review. Performance was evaluated by area under the receiver operating characteristic curve analysis, sensitivity, specificity, and positive predictive value. Four radiologists reviewed test set images for performance comparison. Inverse probability weighting was applied to DS1 to account for positive radiograph enrichment and estimate population-level performance.ResultsIn DS1, population-adjusted areas under the receiver operating characteristic curve for pneumothorax, nodule or mass, airspace opacity, and fracture were, respectively, 0.95 (95% confidence interval [CI]: 0.91, 0.99), 0.72 (95% CI: 0.66, 0.77), 0.91 (95% CI: 0.88, 0.93), and 0.86 (95% CI: 0.79, 0.92). With ChestX-ray14, areas under the receiver operating characteristic curve were 0.94 (95% CI: 0.93, 0.96), 0.91 (95% CI: 0.89, 0.93), 0.94 (95% CI: 0.93, 0.95), and 0.81 (95% CI: 0.75, 0.86), respectively.ConclusionExpert-level models for detecting clinically relevant chest radiograph findings were developed for this study by using adjudicated reference standards and with population-level performance estimation. Radiologist-adjudicated labels for 2412 ChestX-ray14 validation set images and 1962 test set images are provided.© RSNA, 2019Online supplemental material is available for this article.See also the editorial by Chang in this issue.

Author Correction: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.

With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20-43% and is now included in US screening guidelines1-6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7-10. We propose a deep learning algorithm that uses a patient's current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide.

Increased prevalence of tracheal diverticula in cystic fibrosis patients.

OBJECTIVE: This investigation sought to evaluate the prevalence and imaging characteristics of tracheal diverticula (TD) among patients with cystic fibrosis (CF). METHODS: A total of 113 patients with CF at our institution, with a median age of 29 years, had chest CT examinations between 2002 and 2014. These imaging studies were retrospectively reviewed to assess for the presence and characteristics of TD, including quantity, size and location. The severity of the CF disease was assessed using the Bhalla CT scoring system and pulmonary function tests. RESULTS: Of the 113 cases reviewed, 20 (17.7%) patients were found to have 1 or more TD. The presence of TD was associated with more severe disease by imaging criteria, with a Bhalla CT score of 13.9 ± 4.3 in patients with TD and 11.5 ± 4.3 in patients without TD. For the pulmonary function tests, forced expiratory volume in 1 s (FEV1) and FEV1 percent predicted demonstrated a trend towards worsening function in patients with TD, although the difference was not statistically significant. CONCLUSION: The prevalence of TD in our patient population with CF based on chest CT exams was 17.7%. In addition, the presence of TD was associated with more severe CF disease by imaging criteria. ADVANCES IN KNOWLEDGE: TD appear to have a higher prevalence in patients with CF than in the general population, are associated with more severe CF pulmonary disease by CT criteria and are frequently underreported by radiologists.

Implementation of Certified EHR, Patient Portal, and "Direct" Messaging Technology in a Radiology Environment Enhances Communication of Radiology Results to Both Referring Physicians and Patients.

Since 2009, the Federal government distributed over $29 billion to providers who were adopting compliant electronic health record (EHR) technology. With a focus on radiology, we explore how EHR technology impacts interoperability with referring clinicians' EHRs and patient engagement. We also discuss the high-level details of contributing supporting frameworks, specifically Direct messaging and health information service provider (HISP) technology. We characterized Direct messaging, a secure e-mail-like protocol built to allow exchange of encrypted health information online, and the new supporting HISP infrastructure. Statistics related to both the testing and active use of this framework were obtained from DirectTrust.org, an organization whose framework supports Direct messaging use by healthcare organizations. To evaluate patient engagement, we obtained usage data from a radiology-centric patient portal between 2014 and 2015, which in some cases included access to radiology reports. Statistics from 2013 to 2015 showed a rise in issued secure Direct addresses from 8724 to 752,496; a rise in the number of participating healthcare organizations from 667 to 39,751; and a rise in the secure messages sent from 122,842 to 27,316,438. Regarding patient engagement, an average of 234,679 patients per month were provided portal access, with 86,400 patients per month given access to radiology reports. Availability of radiology reports online was strongly associated with increased system usage, with a likelihood ratio of 2.63. The use of certified EHR technology and Direct messaging in the practice of radiology allows for the communication of patient information and radiology results with referring clinicians and increases patient use of patient portal technology, supporting bidirectional radiologist-patient communication.

A prospective clinical study to evaluate the safety and performance of wireless localization of nonpalpable breast lesions using radiofrequency identification technology.

OBJECTIVE: The purpose of this study was to evaluate the safety and performance of localizing nonpalpable breast lesions using radiofrequency identification technology. SUBJECTS AND METHODS: Twenty consecutive women requiring preoperative localization of a breast lesion were recruited. Subjects underwent placement of both a hook wire and a radiofrequency identification tag immediately before surgery. The radiofrequency identification tag was the primary method used by the operating surgeon to localize each lesion during excision, with the hook wire serving as backup in case of tag migration or failed localization. Successful localization with removal of the intended lesion was the primary outcome measured. Tag migration and postoperative infection were also noted to assess safety. RESULTS: Twenty patients underwent placement of a radiofrequency identification tag, 12 under ultrasound guidance and eight with stereotactic guidance. In all cases, the radiofrequency identification tag was successfully localized by the reader at the level of the skin before incision, and the intended lesion was removed along with the radiofrequency identification tag. There were no localization failures and no postoperative infections. Tag migration did not occur before incision, but in three cases, occurred as the lesion was being retracted with fingers to make the final cut along the deep surface of the specimen. CONCLUSION: In this initial clinical study, radiofrequency tags were safe and able to successfully localize nonpalpable breast lesions. Radiofrequency identification technology may represent an alternative method to hook wire localization.

Evaluation of lossy data compression in primary interpretation for full-field digital mammography.

OBJECTIVE. For full-field digital mammography (FFDM), federal regulations prohibit lossy data compression for primary reading and archiving, unlike all other medical images, where reading physicians can apply their professional judgment in implementing lossy compression. Faster image transfer, lower costs, and greater access to expert mammographers would result from development of a safe standard for primary interpretation and archive of lossy-compressed FFDM images. This investigation explores whether JPEG 2000 80:1 lossy data compression affects clinical accuracy in digital mammography. MATERIALS AND METHODS. Randomized FFDM cases (n = 194) were interpreted by six experienced mammographers with and without JPEG 2000 80:1 lossy compression applied. A cancer-enriched population was used, with just less than half of the cases (42%) containing subtle (< 1 cm) biopsy-proven cancerous lesions, and the remaining cases were negative as proven by 2-year follow-up. Data were analyzed using the jackknife alternative free-response ROC (JAFROC) method. RESULTS. The differences in reader performance between lossy-compressed and non-lossy-compressed images using lesion localization (0.660 vs 0.671), true-positive fraction (0.879 vs 0.879), and false-positive fraction (0.283 vs 0.271) were not statistically significant. There was no difference in the JAFROC figure of merit between lossy-compressed and non-lossy-compressed images, with a mean difference of -0.01 (95% CI, -0.03 to 0.01; F1,5 = 2.30; p = 0.189). CONCLUSION. These results suggest that primary interpretation of JPEG 2000 80:1 lossy-compressed FFDM images may be viable without degradation of clinical quality. Benefits would include lower storage costs, faster telemammography, and enhanced access to expert mammographers.