A New Method of Detecting Pulmonary Nodules with PET/CT Based on an Improved Watershed Algorithm

Zhao, Juanjuan; Ji, Guohua; Qiang, Yong; Han, Xiaoqing; Peng, Bo; Shi, Zhiping

doi:10.1371/journal.pone.0123694

Cited by 44 publications

(26 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The watershed technique was applied, which can be classified as a region-based segmentation approach [ 30 , 31 ]. This step computes a complete partition of the image into basins.…”

Section: Methodsmentioning

confidence: 99%

Computed tomography-based volumetric tool for standardized measurement of the maxillary sinus

et al. 2018

View full text Add to dashboard Cite

Volume measurements of maxillary sinus may be useful to identify diseases affecting paranasal sinuses. However, literature shows a lack of consensus in studies measuring the volume. This may be attributable to different computed tomography data acquisition techniques, segmentation methods, focuses of investigation, among other reasons. Furthermore, methods for volumetrically quantifying the maxillary sinus are commonly manual or semiautomated, which require substantial user expertise and are time-consuming. The purpose of the present study was to develop an automated tool for quantifying the total and air-free volume of the maxillary sinus based on computed tomography images. The quantification tool seeks to standardize maxillary sinus volume measurements, thus allowing better comparisons and determinations of factors that influence maxillary sinus size. The automated tool utilized image processing techniques (watershed, threshold, and morphological operators). The maxillary sinus volume was quantified in 30 patients. To evaluate the accuracy of the automated tool, the results were compared with manual segmentation that was performed by an experienced radiologist using a standard procedure. The mean percent differences between the automated and manual methods were 7.19% ± 5.83% and 6.93% ± 4.29% for total and air-free maxillary sinus volume, respectively. Linear regression and Bland-Altman statistics showed good agreement and low dispersion between both methods. The present automated tool for maxillary sinus volume assessment was rapid, reliable, robust, accurate, and reproducible and may be applied in clinical practice. The tool may be used to standardize measurements of maxillary volume. Such standardization is extremely important for allowing comparisons between studies, providing a better understanding of the role of the maxillary sinus, and determining the factors that influence maxillary sinus size under normal and pathological conditions.

show abstract

“…The watershed technique was applied, which can be classified as a region-based segmentation approach [ 30 , 31 ]. This step computes a complete partition of the image into basins.…”

Section: Methodsmentioning

confidence: 99%

Computed tomography-based volumetric tool for standardized measurement of the maxillary sinus

et al. 2018

View full text Add to dashboard Cite

show abstract

“…In recent work, Bagci et al [4] proposed a method to simultaneously delineate ROIs in PET, PET-CT, PET-MR imaging, and fused MR-PET-CT images using a random walk segmentation algorithm with an automated similarity-based seed selection process. Zhao et al [14] combined dynamic thresholding, watershed segmentation, and support vector machine (SVM) classification to classify solitary pulmonary nodules on the basis of CT texture features and PET metabolic features. Similarly, Lartizien et al [15] used texture feature selection and SVM classification for staging of lymphoma patients based on their PET-CT imaging data.…”

Section: Related Workmentioning

confidence: 99%

Co-Learning Feature Fusion Maps From PET-CT Images of Lung Cancer

Kumar

Fulham

Feng

et al. 2020

IEEE Trans. Med. Imaging

175

View full text Add to dashboard Cite

The analysis of multi-modality positron emission tomography and computed tomography (PET-CT) images requires combining the sensitivity of PET to detect abnormal regions with anatomical localization from CT. However, current methods for PET-CT image analysis either process the modalities separately or fuse information from each modality based on knowledge about the image analysis task. These methods generally do not consider the spatially varying visual characteristics that encode different information across the different modalities, which have different priorities at different locations. For example, a high abnormal PET uptake in the lungs is more meaningful for tumor detection than physiological PET uptake in the heart. Our aim is to improve fusion of the complementary information in multi-modality PET-CT with a new supervised convolutional neural network (CNN) that learns to fuse complementary information for multi-modality medical image analysis. Our CNN first encodes modality-specific features and then uses them to derive a spatially varying fusion map that quantifies the relative importance of each modality's features across different spatial locations. These fusion maps are then multiplied with the modality-specific feature maps to obtain a representation of the complementary multi-modality information at different locations, which can then be used for image analysis, e.g. region detection. We evaluated our CNN on a region detection problem using a dataset of PET-CT images of lung cancer. We compared our method to baseline techniques for multi-modality image analysis (pre-fused inputs, multi-branch techniques, multichannel techniques) and demonstrated that our approach had a significantly higher accuracy (p < 0.05) than the baselines.

show abstract

“…Good features can help physicians to distinguish lung nodules efficiently [17–19]. To facilitate analysis and research on lung lesions, we extract lung nodule features based on grayscale, morphology, and texture.…”

Section: Description Of the Retrieval Framework And Pruning Algorithmmentioning

confidence: 99%

Rapid Retrieval of Lung Nodule CT Images Based on Hashing and Pruning Methods

Pan

Qiang

Yuan

et al. 2016

BioMed Research International

Self Cite

View full text Add to dashboard Cite

The similarity-based retrieval of lung nodule computed tomography (CT) images is an important task in the computer-aided diagnosis of lung lesions. It can provide similar clinical cases for physicians and help them make reliable clinical diagnostic decisions. However, when handling large-scale lung images with a general-purpose computer, traditional image retrieval methods may not be efficient. In this paper, a new retrieval framework based on a hashing method for lung nodule CT images is proposed. This method can translate high-dimensional image features into a compact hash code, so the retrieval time and required memory space can be reduced greatly. Moreover, a pruning algorithm is presented to further improve the retrieval speed, and a pruning-based decision rule is presented to improve the retrieval precision. Finally, the proposed retrieval method is validated on 2,450 lung nodule CT images selected from the public Lung Image Database Consortium (LIDC) database. The experimental results show that the proposed pruning algorithm effectively reduces the retrieval time of lung nodule CT images and improves the retrieval precision. In addition, the retrieval framework is evaluated by differentiating benign and malignant nodules, and the classification accuracy can reach 86.62%, outperforming other commonly used classification methods.

show abstract

A New Method of Detecting Pulmonary Nodules with PET/CT Based on an Improved Watershed Algorithm

Cited by 44 publications

References 27 publications

Computed tomography-based volumetric tool for standardized measurement of the maxillary sinus

Computed tomography-based volumetric tool for standardized measurement of the maxillary sinus

Co-Learning Feature Fusion Maps From PET-CT Images of Lung Cancer

Rapid Retrieval of Lung Nodule CT Images Based on Hashing and Pruning Methods

Contact Info

Product

Resources

About