Computer-aided lung cancer screening with CT: A clinically usable nodule detection and assessment system.

7562 Background: The National Lung Screening Trial (NLST) recently demonstrated that lung cancer screening with low-dose CT reduces mortality. Current protocols use 4–8 mm nodules as positive screens. While there are some computer-aided nodule detection (CAD) systems currently available, they are rarely used in clinical practice because they generate too many false positives and lack reliable measurement tools. The purpose of this work is to develop a new CAD system to overcome these limitations and evaluate it against an expert panel of radiologists. Methods: The CAD system developed for lung nodule detection and measurement incorporates computer vision techniques including intensity thresholding, Euclidean Distance Transformation, and watershed segmentation. Rules pertaining to volume and shape were applied to automatically discriminate between nodules and bronchovascular anatomy. CAD system performance was assessed using 108 consecutive cases from the publically available Lung Imaging Database Consortium (LIDC), in which four radiologists reviewed each case. CT slice thickness ranged from 0.6–3.0 mm. Nodules were included that were: (a) ≥ 4mm, and (b) marked by a majority of the LIDC readers, and (c) ≥ 4 x CT slice thickness (to ensure adequate spatial resolution). Results: 44 of 108 subjects had one or more nodules meeting criteria. Median CAD sensitivity per subject for these 44 cases is reported for all nodules ≥ 4mm and the subset of nodules ≥ 8mm. The false positive (FP) rate per subject is reported for all 108 cases. The overall concordance correlation coefficient (CCC) between the CAD volume of each nodule and the LIDC reference volume was measured. Conclusions: Based on clinical CT screening protocols, a CAD system has been developed with high nodule sensitivity and a much lower false positive rate than previously reported systems. Automated volume measurements show strong agreement with the reference standard, providing a comprehensive detection and assessment workflow for lung cancer screening. [Table: see text]

Download Full-text

Validation of a deep learning-based computer-aided system for lung nodule detection in a Chinese lung cancer screening program

10.1183/13993003.congress-2020.4168 ◽

2020 ◽

Author(s):

Xiaonan Cui ◽

Sunyi Zheng ◽

Marjolein Heuvelmans ◽

Yihui Du ◽

Grigory Sidorenkov ◽

...

Keyword(s):

Lung Cancer ◽

Deep Learning ◽

Screening Program ◽

Lung Nodule ◽

Lung Cancer Screening ◽

Lung Nodule Detection ◽

Cancer Screening Program ◽

Nodule Detection ◽

Computer Aided ◽

Lung Cancer Screening Program

Download Full-text

Computer-Aided Diagnosis of Lung Nodules: Systems for Estimation of Lung Cancer Probability and False-Positive Reduction of Lung Nodule Detection

Lung Imaging and CADx ◽

10.1201/9780429055959-6 ◽

2019 ◽

pp. 107-132

Author(s):

Mizuho Nishio

Keyword(s):

Lung Cancer ◽

False Positive ◽

Lung Nodule ◽

Computer Aided Diagnosis ◽

Lung Nodules ◽

Lung Nodule Detection ◽

False Positive Reduction ◽

Nodule Detection ◽

Computer Aided ◽

Aided Diagnosis

Download Full-text

Performance of a computer-aided diagnosis (CAD) system for the detection of pulmonary nodules at multidetector CT data in low dose lung cancer screening

Clinical Imaging ◽

10.1016/j.clinimag.2005.04.012 ◽

2005 ◽

Vol 29 (4) ◽

pp. 300

Keyword(s):

Lung Cancer ◽

Cancer Screening ◽

Low Dose ◽

Multidetector Ct ◽

Pulmonary Nodules ◽

Lung Cancer Screening ◽

Cad System ◽

Computer Aided ◽

Ct Data ◽

Aided Diagnosis

Download Full-text

Comparison of sensitivity of lung nodule detection between radiologists and technologists on low-dose CT lung cancer screening images

British Journal of Radiology ◽

10.1259/bjr/75768386 ◽

2012 ◽

Vol 85 (1017) ◽

pp. e603-e608 ◽

Cited By ~ 12

Author(s):

R Kakinuma ◽

K Ashizawa ◽

T Kobayashi ◽

A Fukushima ◽

H Hayashi ◽

...

Keyword(s):

Lung Cancer ◽

Cancer Screening ◽

Low Dose ◽

Lung Nodule ◽

Lung Cancer Screening ◽

Low Dose Ct ◽

Lung Nodule Detection ◽

Nodule Detection

Download Full-text

Evaluation of automated lung nodule detection on low-dose computed tomography scans from a lung cancer screening program1

Academic Radiology ◽

10.1016/j.acra.2004.10.061 ◽

2005 ◽

Vol 12 (3) ◽

pp. 337-346 ◽

Cited By ~ 24

Author(s):

Samuel G. Armato ◽

Arunabha S. Roy ◽

Heber MacMahon ◽

Feng Li ◽

Kunio Doi ◽

...

Keyword(s):

Computed Tomography ◽

Lung Cancer ◽

Cancer Screening ◽

Low Dose ◽

Lung Nodule ◽

Lung Cancer Screening ◽

Lung Nodule Detection ◽

Nodule Detection ◽

Computed Tomography Scans ◽

Low Dose Computed Tomography

Download Full-text

High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels

BMC Medical Imaging ◽

10.1186/s12880-021-00594-4 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Yeshwant Reddy Chillakuru ◽

Kyle Kranen ◽

Vishnu Doppalapudi ◽

Zhangyuan Xiong ◽

Letian Fu ◽

...

Keyword(s):

Lung Cancer ◽

Cancer Screening ◽

Object Detection ◽

High Precision ◽

False Positive ◽

False Positive Rate ◽

Lung Nodule ◽

Lung Cancer Screening ◽

Radiology Reports ◽

Axial Slice

Abstract Background Reidentification of prior nodules for temporal comparison is an important but time-consuming step in lung cancer screening. We develop and evaluate an automated nodule detector that utilizes the axial-slice number of nodules found in radiology reports to generate high precision nodule predictions. Methods 888 CTs from Lung Nodule Analysis were used to train a 2-dimensional (2D) object detection neural network. A pipeline of 2D object detection, 3D unsupervised clustering, false positive reduction, and axial-slice numbers were used to generate nodule candidates. 47 CTs from the National Lung Cancer Screening Trial (NLST) were used for model evaluation. Results Our nodule detector achieved a precision of 0.962 at a recall of 0.573 on the NLST test set for any nodule. When adjusting for unintended nodule predictions, we achieved a precision of 0.931 at a recall 0.561, which corresponds to 0.06 false positives per CT. Error analysis revealed better detection of nodules with soft tissue attenuation compared to ground glass and undeterminable attenuation. Nodule margins, size, location, and patient demographics did not differ between correct and incorrect predictions. Conclusions Utilization of axial-slice numbers from radiology reports allowed for development of a lung nodule detector with a low false positive rate compared to prior feature-engineering and machine learning approaches. This high precision nodule detector can reduce time spent on reidentification of prior nodules during lung cancer screening and can rapidly develop new institutional datasets to explore novel applications of computer vision in lung cancer imaging.

Download Full-text

Development of CAD System for Automatic Lung Nodule Detection: A Review

BIO Web of Conferences ◽

10.1051/bioconf/20214104001 ◽

2021 ◽

Vol 41 ◽

pp. 04001

Author(s):

Sekar Sari ◽

Indah Soesanti ◽

Noor Akhmad Setiawan

Keyword(s):

Lung Cancer ◽

Feature Extraction ◽

Cancer Detection ◽

False Positive ◽

Lung Nodule ◽

Cad Systems ◽

Cad System ◽

Lung Nodule Detection ◽

Nodule Detection ◽

Lung Cancer Detection

Lung cancer is a type of cancer that spreads rapidly and is the leading cause of mortality globally. The Computer-Aided Detection (CAD) system for automatic lung cancer detection has a significant influence on human survival. In this article, we report the summary of relevant literature on CAD systems for lung cancer detection. The CAD system includes preprocessing techniques, segmentation, lung nodule detection, and false-positive reduction with feature extraction. In evaluating some of the work on this topic, we used a search of selected literature, the dataset used for method validation, the number of cases, the image size, several techniques in nodule detection, feature extraction, sensitivity, and false-positive rates. The best performance CAD systems of our analysis results show the sensitivity value is high with low false positives and other parameters for lung nodule detection. Furthermore, it also uses a large dataset, so the further systems have improved accuracy and precision in detection. CNN is the best lung nodule detection method and need to develop, it is preferable because this method has witnessed various growth in recent years and has yielded impressive outcomes. We hope this article will help professional researchers and radiologists in developing CAD systems for lung cancer detection.

Download Full-text