Imaging Research Community Research Articles

Toward widespread use of virtual trials in medical imaging innovation and regulatory science.

The rapid advancement in the field of medical imaging presents a challenge in keeping up to date with the necessary objective evaluations and optimizations for safe and effective use in clinical settings. These evaluations are traditionally done using clinical imaging trials, which while effective, pose several limitations including high costs, ethical considerations for repetitive experiments, time constraints, and lack of ground truth. To tackle these issues, virtual trials (aka in silico trials) have emerged as a promising alternative, using computational models of human subjects and imaging devices, and observer models/analysis to carry out experiments. To facilitate the widespread use of virtual trials within the medical imaging research community, a major need is to establish a common consensus framework that all can use. Based on the ongoing efforts of an AAPM Task Group (TG387), this article provides a comprehensive overview of the requirements for establishing virtual imaging trial frameworks, paving the way toward their widespread use within the medical imaging research community. These requirements include credibility, reproducibility, and accessibility. Credibility assessment involves verification, validation, uncertainty quantification, and sensitivity analysis, ensuring the accuracy and realism of computational models. A proper credibility assessment requires a clear context of use and the questions that the study is intended to objectively answer. For reproducibility and accessibility, this article highlights the need for detailed documentation, user-friendly software packages, and standard input/output formats. Challenges in data and software sharing, including proprietary data and inconsistent file formats, are discussed. Recommended solutions to enhance accessibility include containerized environments and data-sharing hubs, along with following standards such as CDISC (Clinical Data Interchange Standards Consortium). By addressing challenges associated with credibility, reproducibility, and accessibility, virtual imaging trials can be positioned as a powerful and inclusive resource, advancing medical imaging innovation and regulatory science.

Full-color computational ghost imaging using a chromatic LED array and image interpolation

Computational ghost imaging has been an interesting topic for the imaging research community. However, low resolution and quality of image have been a major problem inhibiting the application of computational ghost imaging technique. In this work, we develop a chromatic 64 × 64 LED array which provides high-speed structured illumination up to 2.5 MHz for computational ghost imaging. Importantly, rather than using regular Cartesian arrangement which is commonly used in a digital camera’s detection array, the LED chips on chromatic LED array we propose are arranged in a special way we refer to as basket-weave sampling. The experimental results demonstrate that our proposed arrangement outperforms Cartesian arrangement for storing high-frequency information of colored pictures, with averaged root mean squared error (RMSE) reduced by 4.6%. Meanwhile, considering the physical structure of the LED array, we propose a targeted interpolation algorithm for resulting images obtained from the experiment, and results show that our algorithm has lower averaged RMSE by 2% when compared to bilinear algorithm and by 6.4% when compared to bicubic algorithm.

5K+ CT Images on Fractured Limbs: A Dataset for Medical Imaging Research.

Imaging techniques widely use Computed Tomography (CT) scans for various purposes, such as screening, diagnosis, and decision-making. Of all, it holds true for bone injuries. To build fully automated Computer-Aided Detection (CADe) and Diagnosis (CADx) tools and techniques, it requires fairly large amount of data (with gold standard). Therefore, in this paper, since state-of-the-art works relied on small dataset, we introduced a CT image dataset on limbs that is designed to understand bone injuries. Our dataset is a collection of 24 patient-specific CT cases having fractures at upper and lower limbs. From upper limbs, 8 cases were collected from bones in/around the shoulder (left and right). Similarly, from lower limbs, 16 cases were collected from knees (left and right). Altogether, 5684 CT images (upper limbs: 2057 and lower limbs: 3627) were collected. Each patient-specific CT case is composed of maximum 257 scans/slices in average. Of all, clinically approved annotations were made on every 10th slices, resulting in 1787 images. Importantly, no fractured limbs were missed in our annotation. Besides, to avoid privacy and confidential issues, patient-related information were deleted. The proposed dataset could be a promising resource for the medical imaging research community, where imaging techniques are employed for various purposes. To the best of our knowledge, this is the first time 5K+ CT images on fractured limbs are provided for research and educational purposes.

Using Deep Convolutional Neural Networks for Neonatal Brain Image Segmentation.

IntroductionDeep learning neural networks are especially potent at dealing with structured data, such as images and volumes. Both modified LiviaNET and HyperDense-Net performed well at a prior competition segmenting 6-month-old infant magnetic resonance images, but neonatal cerebral tissue type identification is challenging given its uniquely inverted tissue contrasts. The current study aims to evaluate the two architectures to segment neonatal brain tissue types at term equivalent age.MethodsBoth networks were retrained over 24 pairs of neonatal T1 and T2 data from the Developing Human Connectome Project public data set and validated on another eight pairs against ground truth. We then reported the best-performing model from training and its performance by computing the Dice similarity coefficient (DSC) for each tissue type against eight test subjects.ResultsDuring the testing phase, among the segmentation approaches tested, the dual-modality HyperDense-Net achieved the best statistically significantly test mean DSC values, obtaining 0.94/0.95/0.92 for the tissue types and took 80 h to train and 10 min to segment, including preprocessing. The single-modality LiviaNET was better at processing T2-weighted images than processing T1-weighted images across all tissue types, achieving mean DSC values of 0.90/0.90/0.88 for gray matter, white matter, and cerebrospinal fluid, respectively, while requiring 30 h to train and 8 min to segment each brain, including preprocessing.DiscussionOur evaluation demonstrates that both neural networks can segment neonatal brains, achieving previously reported performance. Both networks will be continuously retrained over an increasingly larger repertoire of neonatal brain data and be made available through the Canadian Neonatal Brain Platform to better serve the neonatal brain imaging research community.

An economic photoacoustic imaging platform using automatic laser synchronization and inverse beamforming

We present a proof-of-concept of an automatic integration of photoacoustic (PA) imaging on clinical ultrasound (US) imaging platforms. Here we tackle two critical challenges: the laser synchronization and the inaccessibility to the beamformer core embedded in commercial US imaging platform. In particular, the line trigger frequency (LTF) estimation and the asynchronous synthetic aperture inverse beamforming (ASAIB) were developed and evaluated in both k-Wave simulation and phantom experiment. The proposed method is an economical solution to enable PA imaging on a greater number of US equipment to further thrive the PA imaging research community.

Deep learning in medical image registration: a survey

The establishment of image correspondence through robust image registration is critical to many clinical tasks such as image fusion, organ atlas creation, and tumor growth monitoring, and is a very challenging problem. Since the beginning of the recent deep learning renaissance, the medical imaging research community has developed deep learning based approaches and achieved the state-of-the-art in many applications, including image registration. The rapid adoption of deep learning for image registration applications over the past few years necessitates a comprehensive summary and outlook, which is the main scope of this survey. This requires placing a focus on the different research areas as well as highlighting challenges that practitioners face. This survey, therefore, outlines the evolution of deep learning based medical image registration in the context of both research challenges and relevant innovations in the past few years. Further, this survey highlights future research directions to show how this field may be possibly moved forward to the next level.

Prostate Cancer Detection using Deep Convolutional Neural Networks

Prostate cancer is one of the most common forms of cancer and the third leading cause of cancer death in North America. As an integrated part of computer-aided detection (CAD) tools, diffusion-weighted magnetic resonance imaging (DWI) has been intensively studied for accurate detection of prostate cancer. With deep convolutional neural networks (CNNs) significant success in computer vision tasks such as object detection and segmentation, different CNN architectures are increasingly investigated in medical imaging research community as promising solutions for designing more accurate CAD tools for cancer detection. In this work, we developed and implemented an automated CNN-based pipeline for detection of clinically significant prostate cancer (PCa) for a given axial DWI image and for each patient. DWI images of 427 patients were used as the dataset, which contained 175 patients with PCa and 252 patients without PCa. To measure the performance of the proposed pipeline, a test set of 108 (out of 427) patients were set aside and not used in the training phase. The proposed pipeline achieved area under the receiver operating characteristic curve (AUC) of 0.87 (95{boldsymbol{ % }} Confidence Interval (CI): 0.84–0.90) and 0.84 (95{boldsymbol{ % }} CI: 0.76–0.91) at slice level and patient level, respectively.

PROSTATEx Challenges for computerized classification of prostate lesions from multiparametric magnetic resonance images.

Grand challenges stimulate advances within the medical imaging research community; within a competitive yet friendly environment, they allow for a direct comparison of algorithms through a well-defined, centralized infrastructure. The tasks of the two-part PROSTATEx Challenges (the PROSTATEx Challenge and the PROSTATEx-2 Challenge) are (1)the computerized classification of clinically significant prostate lesions and (2)the computerized determination of Gleason Grade Group in prostate cancer, both based on multiparametric magnetic resonance images. The challenges incorporate well-vetted cases for training and testing, a centralized performance assessment process to evaluate results, and an established infrastructure for case dissemination, communication, and result submission. In the PROSTATEx Challenge, 32 groups apply their computerized methods (71 methods total) to 208 prostate lesions in the test set. The area under the receiver operating characteristic curve for these methods in the task of differentiating between lesions that are and are not clinically significant ranged from 0.45 to 0.87; statistically significant differences in performance among the top-performing methods, however, are not observed. In the PROSTATEx-2 Challenge, 21 groups apply their computerized methods (43 methods total) to 70 prostate lesions in the test set. When compared with the reference standard, the quadratic-weighted kappa values for these methods in the task of assigning a five-point Gleason Grade Group to each lesion range from to 0.27; superiority to random guessing can be established for only two methods. When approached with a sense of commitment and scientific rigor, challenges foster interest in the designated task and encourage innovation in the field.

Developing a ‘multiPatchPET’ system in GATE for a PET system design with irregular geometries

This work modified the commonly used Monte Carlo tool package GATE by developing a new ‘multiPatchPET’ system so that GATE users can easily simulate PET systems with irregular geometries. The motivation was to design a brain PET scanner with high sensitivity. It is known that compact PET scanners with a large solid coverage angle can achieve high sensitivity with fewer scintillation detectors, and thus have the potential to provide better image quality in brain PET imaging than conventional ring PET scanners. However, considering a straightforward example with the largest possible solid angle, a spherical PET scanner is hard to manufacture. A more practical alternative would be a sphere-like polyhedral PET scanner with flat detector patches. Moreover, when monolithic scintillators are chosen to construct these flat detector modules, detection efficiency is further improved. Thus, we plan to design a sphere-like polyhedral PET scanner made up of monolithic scintillators. Unfortunately, in our design study, we found that simulating such a scanner with the latest GATE version (8.0) was not trivial, since no predefined systems could be used. In this work we introduced a ‘multiPatchPET’ system to GATE, which we and other GATE users will be able to use to develop PET scanners with any irregular geometry and any shape of patch. To validate our modification, a single block detector and an mCT scanner were simulated via both the original ‘ecat’ system and the new ‘multiPatchPET’ system. The results show no difference in terms of the detecting efficiency and reconstruction image. Then we used the ‘multiPatchPET’ system to simulate an 86 surface polyhedral brain PET scanner. Compared with two cylindrical brain scanners, the polyhedral brain scanner shows a higher sensitivity and has fewer noisy images. Thus, it was proved that our modification, which is accessible to the nuclear imaging research community, equipped GATE with a powerful and user-friendly tool to simulate complex scanners with irregular patches easily.

Review of quantitative multiscale imaging of breast cancer.

Breast cancer is the most common cancer among women worldwide and ranks second in terms of overall cancer deaths. One of the difficulties associated with treating breast cancer is that it is a heterogeneous disease with variations in benign and pathologic tissue composition, which contributes to disease development, progression, and treatment response. Many of these phenotypes are uncharacterized and their presence is difficult to detect, in part due to the sparsity of methods to correlate information between the cellular microscale and the whole-breast macroscale. Quantitative multiscale imaging of the breast is an emerging field concerned with the development of imaging technology that can characterize anatomic, functional, and molecular information across different resolutions and fields of view. It involves a diverse collection of imaging modalities, which touch large sections of the breast imaging research community. Prospective studies have shown promising results, but there are several challenges, ranging from basic physics and engineering to data processing and quantification, that must be met to bring the field to maturity. This paper presents some of the challenges that investigators face, reviews currently used multiscale imaging methods for preclinical imaging, and discusses the potential of these methods for clinical breast imaging.

Advanced optical simulation of scintillation detectors in GATE V8.0: first implementation of a reflectance model based on measured data

Typical PET detectors are composed of a scintillator coupled to a photodetector that detects scintillation photons produced when high energy gamma photons interact with the crystal. A critical performance factor is the collection efficiency of these scintillation photons, which can be optimized through simulation. Accurate modelling of photon interactions with crystal surfaces is essential in optical simulations, but the existing UNIFIED model in GATE is often inaccurate, especially for rough surfaces. Previously a new approach for modelling surface reflections based on measured surfaces was validated using custom Monte Carlo code. In this work, the LUT Davis model is implemented and validated in GATE and GEANT4, and is made accessible for all users in the nuclear imaging research community. Look-up-tables (LUTs) from various crystal surfaces are calculated based on measured surfaces obtained by atomic force microscopy. The LUTs include photon reflection probabilities and directions depending on incidence angle. We provide LUTs for rough and polished surfaces with different reflectors and coupling media. Validation parameters include light output measured at different depths of interaction in the crystal and photon track lengths, as both parameters are strongly dependent on reflector characteristics and distinguish between models. Results from the GATE/GEANT4 beta version are compared to those from our custom code and experimental data, as well as the UNIFIED model. GATE simulations with the LUT Davis model show average variations in light output of <2% from the custom code and excellent agreement for track lengths with R2 > 0.99. Experimental data agree within 9% for relative light output. The new model also simplifies surface definition, as no complex input parameters are needed. The LUT Davis model makes optical simulations for nuclear imaging detectors much more precise, especially for studies with rough crystal surfaces. It will be available in GATE V8.0.

LUNGx Challenge for computerized lung nodule classification.

The purpose of this work is to describe the LUNGx Challenge for the computerized classification of lung nodules on diagnostic computed tomography (CT) scans as benign or malignant and report the performance of participants' computerized methods along with that of six radiologists who participated in an observer study performing the same Challenge task on the same dataset. The Challenge provided sets of calibration and testing scans, established a performance assessment process, and created an infrastructure for case dissemination and result submission. Ten groups applied their own methods to 73 lung nodules (37 benign and 36 malignant) that were selected to achieve approximate size matching between the two cohorts. Area under the receiver operating characteristic curve (AUC) values for these methods ranged from 0.50 to 0.68; only three methods performed statistically better than random guessing. The radiologists' AUC values ranged from 0.70 to 0.85; three radiologists performed statistically better than the best-performing computer method. The LUNGx Challenge compared the performance of computerized methods in the task of differentiating benign from malignant lung nodules on CT scans, placed in the context of the performance of radiologists on the same task. The continued public availability of the Challenge cases will provide a valuable resource for the medical imaging research community.

Development and Investigation of Ultrastable PbS/CdS/ZnS Quantum Dots for Near‐Infrared Tumor Imaging

Achieving bright, reliable, robust, and stable probes for in vivo imaging is becoming extremely urgent for the cancer imaging research community. To date very few works have reported on elucidating in the varied and chemically complex biological milieu. The authors report detailed investigations of the synthesis of near‐infrared, water dispersive, strongly luminescent, and highly stable PbS/CdS/ZnS core/shell/shell quantum dots (QDs). These QDs are extremely stable, they could keep their initial morphology, dispersion status, and photoluminescence (PL) in phosphate buffered saline buffer for as long as 14 months. The QDs also show excellent photostability and could keep ≈80% of their initial PL intensity after 1 h continuous, strong UV illumination. More interestingly, they show negligible toxicity to cultured cells even at high QDs concentration. Given these outstanding properties, the QDs are explored for in vivo, tumor imaging in mice. With one order of magnitude lower QD concentration (0.04 mg mL–1), significantly weaker laser intensity (0.04 W cm–2 vs ≈1 W cm–2), and considerably shorter signal integration time (≤1 ms vs hundreds of ms) as compared to the best reported rare earth doped nanoparticles, the QDs show high emission intensity even at injection depth of ≈2.5 mm.

TU-AB-BRA-03: The Cancer Imaging Archive: Supporting Radiomic and Imaging Genomic Research with Open-Access Data Sets

Purpose: Lack of reproducibility in scientific research, particularly in healthcare, has become an increasing problem in recent years. This is especially important in the emerging field of radiomics/radiogenomics where large data sets and huge numbers of feature variables lead to an increased risk of spurious correlations which are not actually driven by biology. To address this problem we have developed an open-access database called The Cancer Imaging Archive (TCIA) which allows researchers to share the original image data necessary to accurately compare and validate research methods. Methods: Scalable processes for data de-identification were developed which leverage DICOM (PS 3.15 Annex E) standards to ensure compliance with HIPAA regulations. Submission software is customized for each new data set and a team of trained experts assist submitters with the upload process. Data are organized into collections related to a particular cancer type, modality, or research question. Collections may be open-access or restricted to specific users. Users may browse and download the data via their web browser or using programmatic interfaces. Digital object identifiers can be created to allow easy re-use of data or citations in related publications. A helpdesk is available to answer questions from TCIA users. Results: TCIA contains over 52 data collections (46 publicly accessible) for a total of 26.5 million images and associated data. Sixteen of the TCIA data collections support radiogenomics research by linking imaging from subjects with genomic, clinical and pathology data that are available on The Cancer Genome Atlas data portal or Gene Expression Omnibus. Approximately 3,000 users visit the site monthly. More than 90 manuscripts and 12 DOIs have been published relating to TCIA data. Conclusion: TCIA provides a wealth of high-value imaging data to the imaging research community, as well as comprehensive services required to support its user community and facilitate continued growth. Funded by NCI Contract No. HHSN261200800001E

Informatics in Radiology: Development of a Research PACS for Analysis of Functional Imaging Data in Clinical Research and Clinical Trials

Picture archiving and communication systems (PACS) provide limited flexibility for the development of novel research methods. By contrast, the research model of data access is more flexible but has vulnerabilities in numerous areas. No single monolithic application can fulfill the diverse and rapidly changing needs of the clinical imaging research community. Instead, the focus should be on the interoperability of preexisting systems. To a large extent, this can be achieved by means of a unified interface for storing and retrieving data. The concept of a research PACS combines the advantages of the clinical and research models of data access while eliminating the disadvantages. A research PACS streamlines the data management process. Instead of a single software program, it consists of a confederation of independent applications brought together by the ability to store and retrieve data in a common database. A prototype research PACS has been developed that is based on the Extensible Neuroimaging Archive Toolkit (XNAT) in association with two new in-house tools: a data selection tool and a data archiving tool. By taking as an example the comparison of regions of interest in multifunctional liver data, it was demonstrated that this framework allows a number of in-house and open-source applications originally designed to work on a stand-alone basis to be integrated into a unified workflow, with minimal redevelopment effort.

Enabling ITK-based processing and 3D Slicer MRML scene management in ParaView

This paper documents on-going work to facilitate ITK-based processing and 3D Slicer scene management in ParaView. We believe this will broaden the use of ParaView for high performance computing and visualization in the medical imaging research community. The effort is focused on developing ParaView plug-ins for managing VTK structures from 3D Slicer MRML scenes and encapsulating ITK filters for deployment in ParaView. In this paper, we present KWScene, an open source cross-platform library that is being developed to support implementation of these types of plugins. We describe the overall design of the library and provide implementation details and conclude by presenting a concrete example that demonstrates the use of the KWScene library in computational anatomy research at Johns Hopkins Center for Imaging Science.

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.

The development of computer-aided diagnostic (CAD) methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography (CT) scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute (NCI), further advanced by the Foundation for the National Institutes of Health (FNIH), and accompanied by the Food and Drug Administration (FDA) through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ("nodule > or =3 mm," "nodule <3 mm," and "non-nodule > or =3 mm"). In the subsequent unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of the three other radiologists to render a final opinion. The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. The Database contains 7371 lesions marked "nodule" by at least one radiologist. 2669 of these lesions were marked "nodule > or =3 mm" by at least one radiologist, of which 928 (34.7%) received such marks from all four radiologists. These 2669 lesions include nodule outlines and subjective nodule characteristic ratings. The LIDC/IDRI Database is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.

WE-B-201B-02: The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Public Database of CT Scans for Lung Nodule Analysis

PURPOSE: The Lung Image Database Consortium (LIDC) was created by the National Cancer Institute to create a public database of annotated thoracic computed tomography (CT) scans as a reference standard for imaging research. This effort was augmented by the Foundation for the National Institutes of Health through the Image Database Resource Initiative (IDRI). The LIDC/IDRI Database is intended to facilitate computer-aided diagnosis (CAD) research for lung nodule detection, classification, and quantitative assessment. METHOD/MATERIALS: The LIDC/IDRI Database contains 1018 CT scans collected retrospectively from the clinical archives of seven academic institutions. Each scan was reviewed asynchronously by four thoracic radiologists through a two-phase process. During the first “blinded read” phase, each radiologist independently reviewed the scans and marked lesions they identified according to one of three categories: “nodule ≥ 3 mm,” “nodule < 3 mm,” and “non-nodule ≥ 3 mm.” The second “unblinded read” phase allowed each radiologist to review the marks of all other radiologists and confirm or modify their own marks. For any lesion that a radiologist marked as a “nodule ≥ 3 mm,” that radiologist constructed nodule outlines in every CT section in which the nodule appeared and provided subjective ratings of nodule characteristics such as subtlety, spiculation, solidity, and margin. The Database contains all images and radiologist marks for use by investigators. RESULTS: The Database contains 7371 lesions marked by at least one radiologist as either a “nodule ≥ 3 mm” or a “nodule < 3 mm.” 2669 lesions were marked by at least one radiologist as a “nodule ≥ 3 mm,” of which 777 (29.1%) were assigned such a mark by only a single radiologist, and 928 (34.8%) received such marks from all four radiologists. CONCLUSIONS: The LIDC/IDRI Database is expected to become a powerful resource as a reference standard for the medical imaging research community.

Efficient registration of multitemporal and multisensor aerial images based on alignment of nonparametric edge features

The topic of aerial image registration attracts considerable interest within the imaging research community due to its significance for several applications, including change detection, sensor fusion, and topographic mapping. Our interest is focused on finding the optimal transformation between two aerial images that depict the same visual scene in the presence of pronounced spatial, temporal, and sensor variations. We first introduce a stochastic edge estimation process suitable for geometric shape-based registration, which we also compare to intensity-based registration. Furthermore, we propose an objective function that weights the L2 distances of the edge estimates by the feature points' energy, which we denote by sum of normalized squared differences and compare to standard objective functions, such as mutual information and the sum of absolute centered differences. In the optimization stage, we employ a genetic algorithm scheme in a multiscale image representation scheme to enhance the registration accuracy and reduce the computational load. Our experimental tests, measuring registration accuracy, rate of convergence, and statistical properties of registration errors, suggest that the proposed edge-based representation and objective function in conjunction with genetic algorithm optimization are capable of addressing several forms of imaging variations and producing encouraging registration results.

Lung image database consortium: developing a resource for the medical imaging research community.

To stimulate the advancement of computer-aided diagnostic (CAD) research for lung nodules in thoracic computed tomography (CT), the National Cancer Institute launched a cooperative effort known as the Lung Image Database Consortium (LIDC). The LIDC is composed of five academic institutions from across the United States that are working together to develop an image database that will serve as an international research resource for the development, training, and evaluation of CAD methods in the detection of lung nodules on CT scans. Prior to the collection of CT images and associated patient data, the LIDC has been engaged in a consensus process to identify, address, and resolve a host of challenging technical and clinical issues to provide a solid foundation for a scientifically robust database. These issues include the establishment of (a) a governing mission statement, (b) criteria to determine whether a CT scan is eligible for inclusion in the database, (c) an appropriate definition of the term qualifying nodule, (d) an appropriate definition of "truth" requirements, (e) a process model through which the database will be populated, and (f) a statistical framework to guide the application of assessment methods by users of the database. Through a consensus process in which careful planning and proper consideration of fundamental issues have been emphasized, the LIDC database is expected to provide a powerful resource for the medical imaging research community. This article is intended to share with the community the breadth and depth of these key issues.