Automatic lung nodules detection in computed tomography images using nodule filtering and neural networks

Talebpour, Alireza; Hemmati, Hamidreza; Hosseinian, M. Zarif

doi:10.1109/iraniancee.2014.6999847

Cited by 10 publications

(10 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tan-sigmoid is an internal function that is present in every neuron. The proposed method was put to the test using the LIDC-IDRI database, and the results showed that it had a sensitivity of 90% on an FP/scan of 10 [104]. Kuruvilla and Gunavathi [65] carried out yet another study, this time making use of the back propagation neural network.…”

Section: Classification: False Positive Reductionmentioning

confidence: 99%

“…Tariq et al [55] employ neurofuzzy to identify nodules, and they extract characteristics using vector and intensity. Back propagation neural network (BPNN) was utilized by Talebpour et al for the purpose of detecting nodules, in conjunction with geometric and textural feature extraction [104]. However, machine learning algorithms for detecting nodules and extracting features have difficulty with the work of defining and selecting the characteristics of a particular picture, which also causes the task to become more time-consuming.…”

Section: Cnn-based Computer-aided Lung Nodule Detection Systemmentioning

confidence: 99%

See 1 more Smart Citation

A review of convolutional neural network-based computer-aided lung nodule detection system

Sari

Sutikno²,

Soesanti³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

Worldwide, lung cancer is the leading cause of mortality and rapidly spreads. Lung tissue that is benign does not grow significantly, but lung tissue that is malignant grows rapidly and attacks the body, posing a grave threat to one's health. This paper provides a literature review of computer-aided detection (CAD) systems for lung cancer diagnosis. Preprocessing, segmentation, detection, and classification are the stages of the CAD system. This review divides the preprocessing into three stages: image smoothing, edge sharpening, and noise removal. Additionally, lung segmentation is divided into three stages: histogram-based thresholding, linked component analysis, and lung extraction. The detecting phase aids in decreasing the workload. Several techniques are briefly described, including random forest, support vector machine (SVM), naive bayes, K-nearest neighbor (KNN), and convolutional neural network (CNN). Classification is the final stage; the image is then identified as containing or not possessing nodules. The prospect of incorporating CNN-based deep learning techniques into the CAD system is discussed. This paper is superior to other review studies on this topic due to its comprehensive examination of pertinent literature and structured presentation. We anticipate that our study may aid professional researchers and radiologists in developing more effective CAD systems for detecting lung cancer.

show abstract

Section: Classification: False Positive Reductionmentioning

confidence: 99%

Section: Cnn-based Computer-aided Lung Nodule Detection Systemmentioning

confidence: 99%

A review of convolutional neural network-based computer-aided lung nodule detection system

Sari

Sutikno²,

Soesanti³

et al. 2023

IJ-AI

View full text Add to dashboard Cite

show abstract

“…In image processing methods, different algorithms are used to determine normality and abnormality of an image from the final result of segmentation. The area, perimeter, eccentricity, and average intensity are main features help to form the classification of cancer region that is extracted in feature extraction technique [5,15,16]. 5) Classification: Subsequently, the structure is analyzed; each and every region is identified and evaluated individually for the probability of a True Positive (TP).…”

Section: Ii)mentioning

confidence: 99%

“…b) Image Enhancement: For human viewers, image enhancement, improves the interpretability and perception of data in images and for other automated image processing techniques, it provides better and accurate input. Different techniques such as Median filter, Gabor filter, and histogram equalization are also used for image pre-processing[5,7,8].…”

mentioning

confidence: 99%

Lung Cancer Nodule Detection: A Survey

Patankar¹

2019

IJRASET

View full text Add to dashboard Cite

In the world, out of 100 different types of cancers observed in the human body. Lung cancer is a third leading type of cancer that may cause death of a person. Early detection and diagnosis of the disease is essential to prolong the life of the patients affected with this scourge. For determining the cancer cells from medical images, various image processing and soft computing techniques can be used. CT-images are most commonly used for image processing. CT-image has properties like high resolution, better clarity, low noise and low distortion and etc. It is the best technique of image for detection of small nodules. This paper does focus on various techniques which have been proposed for detection of lung cancer modules. This survey attempt to summarize techniques such as pre-processing, segmentation, feature extraction, classification used in the lung cancer detection systems.

show abstract

“…The most common malignancy that results in death is this one. The diagnosis of lung cancer occurs in too many cases and at too late a stage for effective therapy in 70% of cases [2]. The patient's likelihood of surviving five years might increase to 70% if the disease is discovered when it is still in the early stages.…”

Section: Introductionmentioning

confidence: 99%

Involuntary Lung Nodules Recognition in Computed Tomography Images using 3D features Mining and Neural System

Bansal¹,

Srivastava²

2023

IJFMR

View full text Add to dashboard Cite

The best precise imaging method for determining the presence and stage of lung cancer is considered to be computed tomography (CT). On a chest X-ray, nodules are a legitimately frequent abnormality: one out of every 500 chest X-rays reveals newly diagnosed nodules. From helical CT scans, we suggested a computer-aided diagnostic (CAD) method to detect small-size lung knots, which range in size from 1 mm to 6 mm. An insignificant, curving (parenchymal knot) or caterpillar-shaped (juxta pleural nodule) wound in the lungs is known as a pulmonic knot. Because they each have a higher radio-density than the lung parenchyma, they appear snowy in images. Lung knots may indicate a lung cancer, and identifying them early on improves patient survival rates. The best precise imaging technique for finding knots is thought to be CT. However, because there is so much data in each study, analysis becomes difficult. This suggests that a human radiologist could have missed a knot. The proposed CAD method aims to reduce omissions and shorten the time needed for radiologist review of the picture. Our method classifies nodule items from non-nodule objects using a three-layer Feed Forward Neural Network with directed knowledge based on back-propagation technique and CLAHE, an alternative to Histogram Equalization that reduces the noise amplification. The technique was tested on Windows after being built in Matlab. Simple graphic user interface is supplied for convenient control.

show abstract

Automatic lung nodules detection in computed tomography images using nodule filtering and neural networks

Cited by 10 publications

References 12 publications

A review of convolutional neural network-based computer-aided lung nodule detection system

A review of convolutional neural network-based computer-aided lung nodule detection system

Lung Cancer Nodule Detection: A Survey

Involuntary Lung Nodules Recognition in Computed Tomography Images using 3D features Mining and Neural System

Contact Info

Product

Resources

About