Lung nodule detection using multi-resolution analysis

Assefa, Maregu; Faye, Ibrahima; Malik, Aamir Saeed; Shoaib, Muhammad

doi:10.1109/iccme.2013.6548290

Cited by 23 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Template matching methods to segment the SPNs were used by [47] [48] that could detect the circular /semicircular nodules. [49] developed both circular and semicircular templates to detect nodules residing inside and on the boundaries of lung region. This circular, spherical hypothesis is not enough to portray the actual geometry of nodules.…”

Section: Template Matchingmentioning

confidence: 99%

“…Voxel (Volumetric pixel) based false positive reduction methods were used by [62] [63]. [49] extracted intensity based and multi resolution based features such as mean, energy, entropy etc. to reduce the false positive cases.…”

Section: False Positive Reductionmentioning

confidence: 99%

“…[50] exercised nine similarity measures for categorization. [49] extracted intensity based and multi resolution based features to reduce the false positive cases. A mathematical model proposed by [39] which used the estimation of growth rate and volume doubling time to classify the nodules appropriately.…”

Section: Feature Based Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Techniques for Detection of Solitary Pulmonary Nodules in Human Lung and Their Classifications -A Survey

Bhavanishankar¹,

M.V²

2015

IJCI

View full text Add to dashboard Cite

Lung cancer is proving to be a catastrophic threat to the mankind and is main cause of deaths among other cancer related casualties. The presence of solitary pulmonary nodules in human lungs in the form of benign or malignant determines the gravity of lung ailment. This survey focusses on different techniques used to detect and classify the lung nodules which in turn will assist the domain experts for better diagnosis. Among many imaging modalities Computed Tomography (CT) being the most sought after because of its high resolution, isotropic acquisition which helps in locating the lung lesions. Since the volume of the CT scans are very large, Computer Aided Detection/Diagnosis (CAD/x) has more advantages in addition to manual interpretation with respect to speed and accuracy. This paper attempts to summarize various methods that have been proposed by several authors over the years of their research.

show abstract

Section: Template Matchingmentioning

confidence: 99%

Section: False Positive Reductionmentioning

confidence: 99%

See 1 more Smart Citation

Techniques for Detection of Solitary Pulmonary Nodules in Human Lung and Their Classifications -A Survey

Bhavanishankar¹,

M.V²

2015

IJCI

View full text Add to dashboard Cite

show abstract

“…Moreover, system does not provide any information regarding the type of nodules in consideration. Assefa et al 37 proposed a method based on template matching and multiresolution for lung nodule detection. Seven statistical and two intensity based features were extracted for the false positive reduction stage.…”

Section: Introductionmentioning

confidence: 99%

Fully automatic detection of lung nodules in CT images using a hybrid feature set

et al. 2017

View full text Add to dashboard Cite

Purpose The aim of this study was to develop a novel technique for lung nodule detection using an optimized feature set. This feature set has been achieved after rigorous experimentation, which has helped in reducing the false positives significantly. Method The proposed method starts with preprocessing, removing any present noise from input images, followed by lung segmentation using optimal thresholding. Then the image is enhanced using multiscale dot enhancement filtering prior to nodule detection and feature extraction. Finally, classification of lung nodules is achieved using Support Vector Machine (SVM) classifier. The feature set consists of intensity, shape (2D and 3D) and texture features, which have been selected to optimize the sensitivity and reduce false positives. In addition to SVM, some other supervised classifiers like K‐Nearest‐Neighbor (KNN), Decision Tree and Linear Discriminant Analysis (LDA) have also been used for performance comparison. The extracted features have also been compared class‐wise to determine the most relevant features for lung nodule detection. The proposed system has been evaluated using 850 scans from Lung Image Database Consortium (LIDC) dataset and k‐fold cross‐validation scheme. Results The overall sensitivity has been improved compared to the previous methods and false positives per scan have been reduced significantly. The achieved sensitivities at detection and classification stages are 94.20% and 98.15%, respectively, with only 2.19 false positives per scan. Conclusions It is very difficult to achieve high performance metrics using only a single feature class therefore hybrid approach in feature selection remains a better choice. Choosing right set of features can improve the overall accuracy of the system by improving the sensitivity and reducing false positives.

show abstract

“…lung segmentation and enhancement, feature extraction and classification. In [8], the research work aims to develop a CAD system to detect pulmonary lung nodules from Low Dose CT (LDCT) scan images using template matching algorithm integrated with multi-resolution feature analysis technique in order to enhance the false positive detection rate. 134 out of 165 nodules were correctly detected by the proposed scheme with a detection rate of 81.212%.…”

Section: Literature Surveymentioning

confidence: 99%

Lung Nodule Segmentation in Computed Tomography Images for Preoperative Planning and Diagnosis Purposes

2015

Icrbit - 2015

View full text Add to dashboard Cite

Abstract-The precise segmentation of lung nodule is of great significance to identify tumors for the diagnosis of the lung cancer. Computed tomography (CT) is powerful evaluation technique for producing 2D cross sectional images of the organs under test by providing characteristics of the internal structure of an organ. Here, Segmentation concept is used to analyze the nodule in the CT lung image. In this proposed work, the lung CT image is segmented from which nodule is isolated and then classified as either benign or malignant. Segmentation is done using optimal threshold technique which is followed by Region of Interest (ROI) extraction. Then texture features of this ROI have been extracted using Gray Level Co-occurrence Matrix (GLCM) and classification is performed on these features. Experiments have been conducted to classify nodule as benign or malignant. and obtained above 95% of accuracy. CT images required for the work are collected from the diagnostic center.-CT images; Segmentation; lung nodules (key words)

show abstract

Lung nodule detection using multi-resolution analysis

Cited by 23 publications

References 13 publications

Techniques for Detection of Solitary Pulmonary Nodules in Human Lung and Their Classifications -A Survey

Techniques for Detection of Solitary Pulmonary Nodules in Human Lung and Their Classifications -A Survey

Fully automatic detection of lung nodules in CT images using a hybrid feature set

Lung Nodule Segmentation in Computed Tomography Images for Preoperative Planning and Diagnosis Purposes

Contact Info

Product

Resources

About