Literature DB >> 29359462

Automatic detection of multisize pulmonary nodules in CT images: Large-scale validation of the false-positive reduction step.

Anindya Gupta1, Tonis Saar2, Olev Martens1, Yannick Le Moullec1.   

Abstract

PURPOSE: Currently reported computer-aided detection (CAD) approaches face difficulties in identifying the diverse pulmonary nodules in thoracic computed tomography (CT) images, especially in heterogeneous datasets. We present a novel CAD system specifically designed to identify multisize nodule candidates in multiple heterogeneous datasets.
METHODS: The proposed CAD scheme is divided into two phases: primary phase and final phase. The primary phase started with the lung segmentation algorithm and the segmented lungs were further refined using morphological closing process to include the pleural nodules. Next, we empirically formulated three subalgorithms modules to detect different sizes of nodule candidates (≥3 and <6 mm; ≥6 and <10 mm; and ≥10 mm). Each subalgorithm module included a multistage flow of rule-based thresholding and morphological processes. In the final phase, the nodule candidates were augmented to boost the performance of the classifier. The CAD system was trained using a total number of nodule candidates = 201,654 (after augmentation) and nonnodule candidates = 731,486. A rich set of 515 features based on cluster, texture, and voxel-based intensity features were utilized to train a neural network classifier. The proposed method was trained on 899 scans from the Lung Image Database Consortium/Image Database Resource Initiative (LIDC-IDRI). The CAD system was also independently tested on 153 CT scans taken from the AAPM-SPIE-LungX Dataset and two subsets from the Early Lung Cancer Action Project (ELCAP and PCF).
RESULTS: For the LIDC-IDRI training set, the proposed CAD scheme yielded an overall sensitivity of 85.6% (1189/1390) and 83.5% (1161/1390) at 8 FP/scan and 1 FP/scan, respectively. For the three independent test sets, the CAD system achieved an average sensitivity of 68.4% at 8 FP/scan.
CONCLUSION: The authors conclude that the proposed CAD system can identify dissimilar nodule candidates in the multiple heterogeneous datasets. It could be considered as a useful tool to support radiologists during screening trials.
© 2018 American Association of Physicists in Medicine.

Entities:  

Keywords:  AAPM-SPIE-LungX challenge; LIDC−IDRI, pulmonary nodules; computed tomography (CT); computer-aided detection (CAD)

Mesh:

Year:  2018        PMID: 29359462     DOI: 10.1002/mp.12746

Source DB:  PubMed          Journal:  Med Phys        ISSN: 0094-2405            Impact factor:   4.071


  11 in total

1.  Computer-Aided Detection of Pulmonary Nodules in Computed Tomography Using ClearReadCT.

Authors:  Anne-Kathrin Wagner; Arno Hapich; Marios Nikos Psychogios; Ulf Teichgräber; Ansgar Malich; Ismini Papageorgiou
Journal:  J Med Syst       Date:  2019-01-31       Impact factor: 4.460

2.  Lung Nodule Detection based on Ensemble of Hand Crafted and Deep Features.

Authors:  Tanzila Saba; Ahmed Sameh; Fatima Khan; Shafqat Ali Shad; Muhammad Sharif
Journal:  J Med Syst       Date:  2019-11-08       Impact factor: 4.460

Review 3.  Evolving the pulmonary nodules diagnosis from classical approaches to deep learning-aided decision support: three decades' development course and future prospect.

Authors:  Bo Liu; Wenhao Chi; Xinran Li; Peng Li; Wenhua Liang; Haiping Liu; Wei Wang; Jianxing He
Journal:  J Cancer Res Clin Oncol       Date:  2019-11-30       Impact factor: 4.553

4.  Optical Flow Methods for Lung Nodule Segmentation on LIDC-IDRI Images.

Authors:  R Jenkin Suji; Sarita Singh Bhadouria; Joydip Dhar; W Wilfred Godfrey
Journal:  J Digit Imaging       Date:  2020-10       Impact factor: 4.056

5.  Consistency of radiologists in identifying pulmonary nodules based on low-dose computed tomography.

Authors:  Shuai Ming; Wei Yang; Si-Jia Cui; Shuai Huang; Xiang-Yang Gong
Journal:  J Thorac Dis       Date:  2019-07       Impact factor: 2.895

6.  Evaluation of an AI-Powered Lung Nodule Algorithm for Detection and 3D Segmentation of Primary Lung Tumors.

Authors:  Thomas Weikert; Tugba Akinci D'Antonoli; Jens Bremerich; Bram Stieltjes; Gregor Sommer; Alexander W Sauter
Journal:  Contrast Media Mol Imaging       Date:  2019-07-01       Impact factor: 3.161

7.  Tumor burden of lung metastases at initial staging in breast cancer patients detected by artificial intelligence as a prognostic tool for precision medicine.

Authors:  Madison R Kocher; Jordan Chamberlin; Jeffrey Waltz; Madalyn Snoddy; Natalie Stringer; Joseph Stephenson; Jacob Kahn; Megan Mercer; Dhiraj Baruah; Gilberto Aquino; Ismail Kabakus; Philipp Hoelzer; Pooyan Sahbaee; U Joseph Schoepf; Jeremy R Burt
Journal:  Heliyon       Date:  2022-02-15

Review 8.  Noninvasive biomarkers for lung cancer diagnosis, where do we stand?

Authors:  Michael N Kammer; Pierre P Massion
Journal:  J Thorac Dis       Date:  2020-06       Impact factor: 3.005

9.  CNN models discriminating between pulmonary micro-nodules and non-nodules from CT images.

Authors:  Patrice Monkam; Shouliang Qi; Mingjie Xu; Fangfang Han; Xinzhuo Zhao; Wei Qian
Journal:  Biomed Eng Online       Date:  2018-07-16       Impact factor: 2.819

10.  Development and clinical application of deep learning model for lung nodules screening on CT images.

Authors:  Sijia Cui; Shuai Ming; Yi Lin; Fanghong Chen; Qiang Shen; Hui Li; Gen Chen; Xiangyang Gong; Haochu Wang
Journal:  Sci Rep       Date:  2020-08-12       Impact factor: 4.379

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.