Inter-algorithm lesion volumetry comparison of real and 3D simulated lung lesions in CT

Robins, Marthony; Solomon, Justin; Hoye, Jocelyn; Smith, Taylor J.; Ebner, Lukas; Samei, Ehsan

doi:10.1117/12.2254219

Cited by 3 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both methods reported less than 3% difference in shape and less than 5% difference in volume, relative to baseline. Fourth, a study conducted in the context of actual patient data indicated that three commercial segmentation algorithms performed similarly on simulated lesions vs real lesions for volume measurement . The average percent bias (±standard error) was −9.2 ± 3.2% for real lesions vs −6.7 ± 1.2% for virtual lesions with algorithm A, 3.9 ± 2.5% vs 5.0 ± 0.9% for algorithm B, and 5.3 ± 2.3% vs 1.8 ± 0.8% for algorithm C, respectively.…”

Section: Acquisition Methodsmentioning

confidence: 96%

“…These masks were exported and used to create CT data volumes of interest (VOIs), from which lesion models were simulated using the Duke Lesion Tool (DLT, Duke University). The process of database creation is fully described by Robins et al . and depicted in Fig.…”

Section: Acquisition Methodsmentioning

confidence: 99%

“…This approach allows us to surpass the capabilities of clinical studies and model a myriad of realistic disease conditions without sample size limitations or the need for repetitive patient image acquisitions. We have previously demonstrated the use of hybrid datasets in quantitative CT applications, and in reader and technology evaluation tasks . This reference database can allow for investigations of new applications and software tools.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Validation of lesion simulations in clinical CT data for anonymized chest and abdominal CT databases

et al. 2019

Self Cite

View full text Add to dashboard Cite

Purpose: To make available to the medical imaging community a computed tomography (CT) image database composed of hybrid datasets (patient CT images with digitally inserted anthropomorphic lesions) where lesion ground truth is known a priori. It is envisioned that such a dataset could be a resource for the assessment of CT image quality, machine learning, and imaging technologies [e.g., computer aided detection (CAD) and segmentation algorithms]. Acquisition and validation methods: This HIPPA compliant, IRB waiver of approval study consisted of utilizing 120 chest and 100 abdominal clinically acquired adult CT exams. One image series per patient exam was utilized based on coverage of the anatomical region of interest (either the thorax or abdomen). All image series were de-identified. Simulated lesions were derived from a library of anatomically informed digital lesions (93 lung and 50 liver lesions) where six and four digital lesions with nominal diameters ranging from 4 to 20 mm were inserted into lung and liver image series, respectively. Locations for lesion insertion were randomly chosen. A previously validated lesion simulation and virtual insertion technique were utilized. The resulting hybrid images were reviewed by three experienced radiologists to assure similarity with routine clinical imaging in a diverse adult population. Data format and usage notes: The database is composed of four datasets that contain 100 patient cases each, for a total of 400 image series accompanied by Matlab.mat tables that provide descriptive information about the virtually inserted lesions (i.e., size, shape, opacity, and insertion location in physical (world) coordinates and voxel indices). All image and metadata are stored in DICOM format on the Quantitative Imaging Data Warehouse (https://qidw.rsna.org/#collection/57d463471cac0a4ec 8ff8f46/folder/5b23dceb1cac0a4ec800a770?dialog=login), in two sets: (a) QIBA CT Hybrid Dataset I which contains Lung I and Liver I datasets, and (b) QIBA CT Hybrid Dataset II which contains Lung II and Liver II datasets. The QIDW is supported by the Radiological Society of North America (RSNA). Registration is required upon initial log in. Potential applications: By simulating lesion opacity (full solid, part solid and ground glass), size, and texture, the relationship between lesion morphology and segmentation or CAD algorithm performance can be investigated without the need for repetitive patient exams. This database can also serve as a reference standard for device and reader performance studies.

show abstract

Section: Acquisition Methodsmentioning

confidence: 96%

Section: Acquisition Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Validation of lesion simulations in clinical CT data for anonymized chest and abdominal CT databases

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hybrid datasets, created by virtually inserting simulated lesions into real patient CT datasets, can potentially meet these goals. They can provide study design flexibility at low cost with proven utility demonstrated in multiple prior studies (22,23). However, claiming equivalency of hybrid datasets to real clinical data, especially as a basis for a broad compliance standard, cannot be made if they are not compared across a wide range of segmentation algorithms.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Simulated Lesions as Surrogates to Clinical Lesions for Thoracic CT Volumetry: The Results of an International Challenge

et al. 2019

Self Cite

View full text Add to dashboard Cite

Hybrid datasets yielded conclusions similar to real computed tomography datasets where phantom QIBA compliant was also compliant for hybrid datasets. Some groups deemed compliant for simulated methods, not for physical lesion measurements. The magnitude of this difference was small (<5.4%). While technical performance is not equivalent, they correlate, such that, volumetrically simulated lesions could potentially serve as practical proxies.

show abstract

“…This approach is more practical, less expensive, and offers the advantage of known ground truth. Hybrid datasets can offer a viable alternative to answer a range of clinically relevant research questions, [5][6][7][8][9][10][11] including eye tracking and decision-making processes in radiologist's detection of lung nodules, 8 taskspecific image quality and detection of liver tumors, 9 and validation of breast mass simulation algorithms. 10 While simulated lesions have proven useful for many applications, their utility for quantification of tumor volume needs to be established and further verified against real lesions.…”

Section: Introductionmentioning

confidence: 99%

Interchangeability between real and three-dimensional simulated lung tumors in computed tomography: an interalgorithm volumetry study

et al. 2018

Self Cite

View full text Add to dashboard Cite

Using hybrid datasets consisting of patient-derived computed tomography (CT) images with digitally inserted computational tumors, we establish volumetric interchangeability between real and computational lung tumors in CT. Pathologically-confirmed malignancies from 30 thoracic patient cases from the RIDER database were modeled. Tumors were either isolated or attached to lung structures. Patient images were acquired on one of two CT scanner models (Lightspeed 16 or VCT; GE Healthcare) using standard chest protocol. Real tumors were segmented and used to inform the size and shape of simulated tumors. Simulated tumors developed in Duke Lesion Tool (Duke University) were inserted using a validated image-domain insertion program. Four readers performed volume measurements using three commercial segmentation tools. We compared the volume estimation performance of segmentation tools between real tumors in actual patient CT images and corresponding simulated tumors virtually inserted into the same patient images (i.e., hybrid datasets). Comparisons involved (1) direct assessment of measured volumes and the standard deviation between simulated and real tumors across readers and tools, respectively, (2) multivariate analysis, involving segmentation tools, readers, tumor shape, and attachment, and (3) effect of local tumor environment on volume measurement. Volume comparison showed consistent trends (9% volumetric difference) between real and simulated tumors across all segmentation tools, readers, shapes, and attachments. Across all cases, readers, and segmentation tools, an intraclass correlation coefficient = 0.99 indicates that simulated tumors correlated strongly with real tumors (p ¼ 0.95). In addition, the impact of the local tumor environment on tumor volume measurement was found to have a segmentation tool-related influence. Strong agreement between simulated tumors modeled in this study compared to their real counterparts suggests a high degree of similarity. This indicates that, volumetrically, simulated tumors embedded into patient CT data can serve as reasonable surrogates to real patient data.

show abstract

Inter-algorithm lesion volumetry comparison of real and 3D simulated lung lesions in CT

Cited by 3 publications

References 0 publications

Validation of lesion simulations in clinical CT data for anonymized chest and abdominal CT databases

Validation of lesion simulations in clinical CT data for anonymized chest and abdominal CT databases

Evaluation of Simulated Lesions as Surrogates to Clinical Lesions for Thoracic CT Volumetry: The Results of an International Challenge

Interchangeability between real and three-dimensional simulated lung tumors in computed tomography: an interalgorithm volumetry study

Contact Info

Product

Resources

About