The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation

McNitt‐Gray, Michael F.; Armato, Samuel G.; Meyer, Charles R.; Reeves, Anthony P.; McLennan, G; Pais, Richard; Freymann, John; Brown, Marianne; Engelmann, Roger; Bland, Peyton H.; Laderach, Gary E.; Piker, Chris; Guo, Junfeng; Qing, David; Yankelevitz, David F.; Aberle, Denise R.; Beek, Edwin Jacques Rudolph van; MacMahon, Heber; Kazerooni, Ella A.; Croft, Barbara Y.; Clarke, Laurence P.

doi:10.1117/12.713754

Cited by 29 publications

(33 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subtlety indicates the difficulty in nodule detection which refers to the contrast between the lung nodule and its surroundings, while margin describes how welldefined the margins of the defining nodule [48]. The model we used here is the classification model of − MC CNN 1 64 and the evaluation method is also the five-fold cross validation.…”

Section: Nodule Subtlety and Margin Predictionmentioning

confidence: 99%

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

Shen

Zhou

Yang

et al. 2017

Pattern Recognition

526

365

View full text Add to dashboard Cite

Section: Nodule Subtlety and Margin Predictionmentioning

confidence: 99%

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

Shen

Zhou

Yang

et al. 2017

Pattern Recognition

526

365

View full text Add to dashboard Cite

“…The database is a collection of clinical information initiated by the Lung Imaging Database Consortium (LIDC) to screen patients with lung cancer (11,12). Each patient data set is provided with up to four radiologist annotations (13). The database used for this project consisted of 29 data sets with an in-depth (along the z axis) resolution of <2 mm and nine data sets with an in-depth resolution of 2 to 5 mm.…”

Section: Databasementioning

confidence: 99%

“…On the basis of previous experience (13,19), a total of 11 features were used; the careful selection was based on two categories. The first category involved the image characteristics (shape, size, intensity, and texture), and the second category was based on dimensionality (two and three dimensions).…”

Section: Nodule Characteristicsmentioning

confidence: 99%

A Novel Approach to Nodule Feature Optimization on Thin Section Thoracic CT

Samala¹,

Moreno²,

You³

et al. 2009

Academic Radiology

View full text Add to dashboard Cite

“…3 Various information is stored for each data set in addition to the actual image data including technical scan parameters, patient information, and nodule features. 4 The ground truth assessment of lesion boundaries is based on manual outlining performed by expert radiologists.…”

Section: Introductionmentioning

confidence: 99%

A software assistant for the design of realistic software phantoms

2008

View full text Add to dashboard Cite

Segmentation and quantification of medical image data are difficult problems in image analysis. Especially, an accurate and robust assessment of quantitative parameters is a key issue in many fields, and can have a direct impact on diagnosis and treatment planning. To this end, physical and software phantom data sets have become an integral tool during the design, implementation, and optimization of new algorithms. Unfortunately, a common research resource has not been established until now for many applications.In this work we propose a software assistant for the development of realistic software phantoms. Our aim is an easy-to-use tool with an intuitive user interface. Furthermore, we provide a software for researchers including a common basis of reference data, which facilitates a standardized and objective validation of performance and limitations of own developments, as well as the comparison of different methods. The fundamental phantom design focuses on objects that can be incorporated into a given background. This can either be a homogeneous artificial background, or a volunteer or patient data set. For each phantom the exact ground truth of the investigated object is available, which provides us with an excellent tool for the generation of realistic data sets. Several experiments are carried out for a number of different applications including software phantoms of small, hyperintense brain lesions, as well as software phantoms of liver metastases.

show abstract

The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation

Cited by 29 publications

References 5 publications

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

Multi-crop Convolutional Neural Networks for lung nodule malignancy suspiciousness classification

A Novel Approach to Nodule Feature Optimization on Thin Section Thoracic CT

A software assistant for the design of realistic software phantoms

Contact Info

Product

Resources

About