Insertion of virtual pulmonary nodules in CT data of the chest: development of a software tool

Shin, Hoen‐oh; Blietz, Matthias; Frericks, Bernd; Baus, Stefan; Savellano, Dagmar Högemann; Galanski, Michael

doi:10.1007/s00330-006-0254-x

Cited by 20 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms have been developed and have been integrated into software tools for automated assessment of nodule volume. Initial studies have shown the value of the volumetry in different settings [14][15][16][17][18][19][20][21][22][23][24]. To our knowledge to date none of the algorithms has been tested on datasets acquired at different MSCT scanners from different vendors.…”

Section: Introductionmentioning

confidence: 99%

Accuracy of automated volumetry of pulmonary nodules across different multislice CT scanners

et al. 2007

View full text Add to dashboard Cite

The purpose of this study was to compare the accuracy of an automated volumetry software for phantom pulmonary nodules across various 16-slice multislice spiral CT (MSCT) scanners from different vendors. A lung phantom containing five different nodule categories (intraparenchymal, around a vessel, vessel attached, pleural, and attached to the pleura), with each category comprised of 7-9 nodules (total, n = 40) of varying sizes (diameter 3-10 mm; volume 6.62 mm(3)-525 mm(3)), was scanned with four different 16-slice MSCT scanners (Siemens, GE, Philips, Toshiba). Routine and low-dose chest protocols with thin and thick collimations were applied. The data from all scanners were used for further analysis using a dedicated prototype volumetry software. Absolute percentage volume errors (APE) were calculated and compared. The mean APE for all nodules was 8.4% (+/-7.7%) for data acquired with the 16-slice Siemens scanner, 14.3% (+/-11.1%) for the GE scanner, 9.7% (+/-9.6%) for the Philips scanner and 7.5% (+/-7.2%) for the Toshiba scanner, respectively. The lowest APEs were found within the diameter size range of 5-10 mm and volumes >66 mm(3). Nodule volumetry is accurate with a reasonable volume error in data from different scanner vendors. This may have an important impact for intraindividual follow-up studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Accuracy of automated volumetry of pulmonary nodules across different multislice CT scanners

et al. 2007

View full text Add to dashboard Cite

show abstract

“…A major issue with these approaches to simulated dataset construction is that they lack sufficient biological motivation for their simulated nodule 3-D geometries. Some approaches have involved modeling simulated nodule shapes after real lung nodule data [18][19] , however the goal in these studies has been to create simulated nodules that emulate the characteristics of real nodules, not necessarily the re-construction of the 3-D morphologies of the individual real lung nodules such that they can then be thoroughly manipulated and inserted into new medical images as the simulated nodules. Furthermore, it is important in creating simulated nodule datasets for lung nodules to include a representative proportion of vascularized and juxtapleural nodules that historically have provided the greatest challenge for CAD systems and human readers alike 10,20 .…”

Section: Introductionmentioning

confidence: 99%

Realistic simulated lung nodule dataset for testing CAD detection and sizing

Ambrosini¹,

O’Dell²

2010

SPIE Proceedings

View full text Add to dashboard Cite

The development of computer-aided diagnosis (CAD) methods for the processing of CT lung scans continues to become increasingly popular due to the potential of these algorithms to reduce image reading time, errors caused by user fatigue, and user subjectivity when screening for the presence of malignant lesions. This study seeks to address the critical need for a realistic simulated lung nodule CT image dataset based on real tumor morphologies that can be used for the quantitative evaluation and comparison of these CAD algorithms. The manual contouring of 17 different lung metastases was performed and reconstruction of the full 3-D surface of each tumor was achieved through the utilization of an analytical equation comprised of a spherical harmonics series. 2-D nodule slice representations were then computed based on these analytical equations to produce realistic simulated nodules that can be inserted into CT datasets with well-circumscribed, vascularized, or juxtapleural borders and also be scaled to represent nodule growth. The 3-D shape and intensity profile of each simulated nodule created from the spherical harmonics reconstruction was compared to the real patient CT lung metastasis from which its contour points were derived through the calculation of a 3-D correlation coefficient, producing an average value of 0.8897 (±0.0609). This database of realistic simulated nodules can fulfill the need for a reproducible and reliable gold standard for CAD algorithms with regards to nodule detection and sizing, especially given its virtually unlimited capacity for expansion to other nodule shape variants, organ systems, and imaging modalities.

show abstract

“…These lesions are subsequently inserted into the raw projection data or reconstructed clinical images. A few examples of this approach can be found in [17], [18], [19] for lung nodules, in [20], [21] for mammography, and in [22] for digital breast tomosynthesis (DBT). An important factor when using a simulated lesion generated based on mathematical models (rather than biologically inspired models) is to assure the realism of the characteristics of the artificial samples.…”

Section: Introductionmentioning

confidence: 99%

Seamless Lesion Insertion for Data Augmentation in CAD Training

Pezeshk

Petrick

Chen

et al. 2017

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

The performance of a classifier is largely dependent on the size and representativeness of data used for its training. In circumstances where accumulation and/or labeling of training samples is difficult or expensive, such as medical applications, data augmentation can potentially be used to alleviate the limitations of small datasets. We have previously developed an image blending tool that allows users to modify or supplement an existing CT or mammography dataset by seamlessly inserting a lesion extracted from a source image into a target image. This tool also provides the option to apply various types of transformations to different properties of the lesion prior to its insertion into a new location. In this study, we used this tool to create synthetic samples that appear realistic in chest CT. We then augmented different size training sets with these artificial samples, and investigated the effect of the augmentation on training various classifiers for the detection of lung nodules. Our results indicate that the proposed lesion insertion method can improve classifier performance for small training datasets, and thereby help reduce the need to acquire and label actual patient data.

show abstract

Insertion of virtual pulmonary nodules in CT data of the chest: development of a software tool

Cited by 20 publications

References 22 publications

Accuracy of automated volumetry of pulmonary nodules across different multislice CT scanners

Accuracy of automated volumetry of pulmonary nodules across different multislice CT scanners

Realistic simulated lung nodule dataset for testing CAD detection and sizing

Seamless Lesion Insertion for Data Augmentation in CAD Training

Contact Info

Product

Resources

About