Limits...
A new method of detecting pulmonary nodules with PET/CT based on an improved watershed algorithm.

Zhao J, Ji G, Qiang Y, Han X, Pei B, Shi Z - PLoS ONE (2015)

Bottom Line: Then, an improved watershed method was used to mark suspicious areas on the CT image.Next, the support vector machine (SVM) method was used to classify SPNs based on textural features of CT images and metabolic features of PET images to validate the proposed method.Our proposed method was more efficient than traditional methods and methods based on the CT or PET features alone (sensitivity 95.6%; average of 2.9 false positives per scan).

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, China.

ABSTRACT

Background: Integrated 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) is widely performed for staging solitary pulmonary nodules (SPNs). However, the diagnostic efficacy of SPNs based on PET/CT is not optimal. Here, we propose a method of detection based on PET/CT that can differentiate malignant and benign SPNs with few false-positives.

Method: Our proposed method combines the features of positron-emission tomography (PET) and computed tomography (CT). A dynamic threshold segmentation method was used to identify lung parenchyma in CT images and suspicious areas in PET images. Then, an improved watershed method was used to mark suspicious areas on the CT image. Next, the support vector machine (SVM) method was used to classify SPNs based on textural features of CT images and metabolic features of PET images to validate the proposed method.

Results: Our proposed method was more efficient than traditional methods and methods based on the CT or PET features alone (sensitivity 95.6%; average of 2.9 false positives per scan).

No MeSH data available.


Related in: MedlinePlus

Low-contrast nodules detected by the proposed method.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4390287&req=5

pone.0123694.g007: Low-contrast nodules detected by the proposed method.

Mentions: Table 1 depicts traditional and proposed method sensitivity and false positives. Figs 7 and 8 show examples of the nodules and non-nodules detected based on the proposed methods and these were better than nodule detection depicted in Table 1. Sensitivity can be improved by 2.6% (from 93% based on the Choi method), and the rate of false positives was relatively low. In this paper, traditional methods were based on CT image features images, which affected low contrast nodule detection accuracy. Low contrast nodules are shown in Fig 7. Methods based solely on CT features always failed to detect them. Because CT features of those nodules were ambiguous, gray level-based traditional methods could hardly detect them. PET images depict tumor metabolic features, so our proposed methods can account for nodular metabolic features (SUVmax) that reflect tumor traits.


A new method of detecting pulmonary nodules with PET/CT based on an improved watershed algorithm.

Zhao J, Ji G, Qiang Y, Han X, Pei B, Shi Z - PLoS ONE (2015)

Low-contrast nodules detected by the proposed method.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4390287&req=5

pone.0123694.g007: Low-contrast nodules detected by the proposed method.
Mentions: Table 1 depicts traditional and proposed method sensitivity and false positives. Figs 7 and 8 show examples of the nodules and non-nodules detected based on the proposed methods and these were better than nodule detection depicted in Table 1. Sensitivity can be improved by 2.6% (from 93% based on the Choi method), and the rate of false positives was relatively low. In this paper, traditional methods were based on CT image features images, which affected low contrast nodule detection accuracy. Low contrast nodules are shown in Fig 7. Methods based solely on CT features always failed to detect them. Because CT features of those nodules were ambiguous, gray level-based traditional methods could hardly detect them. PET images depict tumor metabolic features, so our proposed methods can account for nodular metabolic features (SUVmax) that reflect tumor traits.

Bottom Line: Then, an improved watershed method was used to mark suspicious areas on the CT image.Next, the support vector machine (SVM) method was used to classify SPNs based on textural features of CT images and metabolic features of PET images to validate the proposed method.Our proposed method was more efficient than traditional methods and methods based on the CT or PET features alone (sensitivity 95.6%; average of 2.9 false positives per scan).

View Article: PubMed Central - PubMed

Affiliation: College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, China.

ABSTRACT

Background: Integrated 18F-fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) is widely performed for staging solitary pulmonary nodules (SPNs). However, the diagnostic efficacy of SPNs based on PET/CT is not optimal. Here, we propose a method of detection based on PET/CT that can differentiate malignant and benign SPNs with few false-positives.

Method: Our proposed method combines the features of positron-emission tomography (PET) and computed tomography (CT). A dynamic threshold segmentation method was used to identify lung parenchyma in CT images and suspicious areas in PET images. Then, an improved watershed method was used to mark suspicious areas on the CT image. Next, the support vector machine (SVM) method was used to classify SPNs based on textural features of CT images and metabolic features of PET images to validate the proposed method.

Results: Our proposed method was more efficient than traditional methods and methods based on the CT or PET features alone (sensitivity 95.6%; average of 2.9 false positives per scan).

No MeSH data available.


Related in: MedlinePlus