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

Segmentation results of suspicious nodules in CT images.(a-1, -2, and 3) suspicious nodule areas; (b-1, -2, and 3) suspicious nodules evaluated by a dynamic threshold segmentation method; (c-1, -2, and 3) show the resulting outer rectangle templates; (d-1, -2, and 3) show the suspicious nodules with the outer rectangles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0123694.g006: Segmentation results of suspicious nodules in CT images.(a-1, -2, and 3) suspicious nodule areas; (b-1, -2, and 3) suspicious nodules evaluated by a dynamic threshold segmentation method; (c-1, -2, and 3) show the resulting outer rectangle templates; (d-1, -2, and 3) show the suspicious nodules with the outer rectangles.

Mentions: Fig 6 shows segmentation results of suspicious nodules in CT images. To evaluate the performance of our proposed SPN segmentation, current traditional methods were compared to segmentation results of our proposed method with manual segmentation methods. Table 2 depicts these data and indicates that our proposed method offers good segmentation performance. The last column of Table 2 depicts segmentation results that confirm greater accuracy for segmentation than a method based on a growing region and dynamic threshold.


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)

Segmentation results of suspicious nodules in CT images.(a-1, -2, and 3) suspicious nodule areas; (b-1, -2, and 3) suspicious nodules evaluated by a dynamic threshold segmentation method; (c-1, -2, and 3) show the resulting outer rectangle templates; (d-1, -2, and 3) show the suspicious nodules with the outer rectangles.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0123694.g006: Segmentation results of suspicious nodules in CT images.(a-1, -2, and 3) suspicious nodule areas; (b-1, -2, and 3) suspicious nodules evaluated by a dynamic threshold segmentation method; (c-1, -2, and 3) show the resulting outer rectangle templates; (d-1, -2, and 3) show the suspicious nodules with the outer rectangles.
Mentions: Fig 6 shows segmentation results of suspicious nodules in CT images. To evaluate the performance of our proposed SPN segmentation, current traditional methods were compared to segmentation results of our proposed method with manual segmentation methods. Table 2 depicts these data and indicates that our proposed method offers good segmentation performance. The last column of Table 2 depicts segmentation results that confirm greater accuracy for segmentation than a method based on a growing region and dynamic threshold.

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