scholarly journals Segmentation of Lung Cancer using Deep learning

2019 ◽  
Vol 8 (2) ◽  
pp. 1188-1192
Keyword(s):  
Lung Cancer ◽  
Image Segmentation ◽  
Lung Tumor ◽  
Public Health Problem ◽  
Image Database ◽  
Advanced Technology ◽  
Tumor Segmentation ◽  
Major Public Health Problem ◽  
Magnetic Resonance Imaging Mri ◽  
Time Required

Lung cancer is one among the deadliest and dangerous widespread diseases that create a major public health problem. The main aim of this paper is to basically segment the image or to identify the nodule present in the image and provide the accuracy of that segmented image. In this concern, proper segmentation of lung tumor present in the X-ray scans or Magnetic Resonance Imaging (MRI) or Computed Tomography (CT scan) is the first stone towards achieving completely automated diagnosis system for lung cancer detection of the patient. With the advanced technology and availability of dataset, the time required for a radiologist can be saved using CAD tools for tumor segmentation. In this work, we use an approach called data driven for lung tumor segmentation from CT scans by using UNet . In our approach we will train the network by using CT image with tumor having the slices of size (512 × 512 × 1). Our model has been trained and tested on the LUNA16 dataset considering 10 patients, provided by or used by Lung image database consortium (LIDC) and the image database resources initiative (IDRI). In this dataset, our proposed technique will achieve an average dice score of 0.8507. This can further be analyzed or used for other medical images to find the nodule or with other applications such as in brain image segmentation and liver image segmentation.

Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network

2021 ◽  
pp. 20210038
Author(s):  
Wutian Gan ◽  
Hao Wang ◽  
Hengle Gu ◽  
Yanhua Duan ◽  
Yan Shao ◽  
...  
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Lung Tumor ◽  
Ct Images ◽  
Hybrid Network ◽  
Evaluation Metrics ◽  
Tumor Segmentation ◽  
Tumor Delineation ◽  
3D Cnn ◽  
The Individual

Objective: A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning. Methods: In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder–decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored. Results: The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (p < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable. Conclusions: The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images. Advances in knowledge: The hybrid CNN has valuable prospect with the ability to segment lung tumor.

Abstract 368: A Cardiac Arrest Simulation-Based Feasibility Cadaver Study Investigating Time for Semi Surgical Cut Down Procedure Followed by Insertion of a Novel REBOA Catheter

Circulation ◽  
2019 ◽  
Vol 140 (Suppl_2) ◽  
Author(s):  
Helene Duhem ◽  
Lionel Lamhaut ◽  
Alice Hutin ◽  
Alexandre Bellier ◽  
Stephane Tanguy ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Median Time ◽  
Life Support ◽  
Advanced Life Support ◽  
Public Health Problem ◽  
Balloon Occlusion ◽  
Major Public Health Problem ◽  
Introducer Sheath ◽  
Human Cadavers ◽  
Time Required

Aim: Non-traumatic cardiac arrest is a major public health problem that carries an extremely high mortality rate. The Resuscitative endovascular balloon occlusion of the aorta (REBOA) procedure is currently being discussed as a possible technique to be used during Advanced Life Support (ALS) in humans with Cardiac arrest (CA). The aim of this study was to assess the training of emergency physicians in the procedures related to insertion of a novel REBOA catheter. Methods: We developed a training program using a simulated CA model on human cadavers. CPR was performed using the LUCAS device (Stryker/Jolife AB, Lund, Sweden). All cadavers were hemodynamically monitored. The Neurescue REBOA catheter (Neurescue REBOA device, Neurescue ApS, Copenhagen, Denmark) was inserted using a semi-surgical cut-down and sheath placement technique. Time needed to perform the procedures was measured. The procedures were instructed by 2 experts using video, procedural simulation on manikin and full-scale training on cadavers. Results: Six human cadavers were enrolled and a total of 12 procedures were performed by 2 expert investigators and 10 novice investigators. Eight semi-surgical cut-down producers including placements of the introducer sheath were performed on the first attempt and 4 required a second attempt. The median time required for the semi-surgical cutdown procedure and sheath placement by the novice investigators was: 6 min 48 sec (Min: 3 min 45 sec and Max: 26 min 25 sec). The median time required for the insertion and occlusion of the REBOA catheter by the novice investigators was: 3 min 22 sec (Min: 1 min 22 sec and Max: 7 min 5 sec). The median time required for full insertion for the novice investigators was: 11 min 14 sec (Min: 6 min 49 sec and Max: 28 min 15 sec). The mean aortic pressure during compression was: 31.9 mmHg (±17.0). Conclusions: Semi surgical cut-down and introducer sheath placement were performed in 1 or two 2 attempts for all novice investigators with an insertion time compatible with ALS during refractory CA. Simulation training on cadavers brings clinical realism and could be an important addition to the use of manikin or animal training models.

A Novel Approach of Lung Tumor Segmentation Using a 3D Deep Convolutional Neural Network

2022 ◽  
pp. 1-16
Author(s):  
Shweta Tyagi ◽  
Sanjay N. Talbar ◽  
Abhishek Mahajan
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Convolutional Neural Network ◽  
Lung Tumor ◽  
Early Stage ◽  
Tumor Segmentation ◽  
Lung Tumour ◽  
Dice Coefficient ◽  
Tumour Segmentation ◽  
Diagnosis Of Lung Cancer

Cancer is one of the most life-threatening diseases in the world, and lung cancer is the leading cause of death worldwide. If not detected at an early stage, the survival rate of lung cancer patients can be very low. To treat patients in later stages, one needs to analyze the tumour region. For accurate diagnosis of lung cancer, the first step is to detect and segment the tumor. In this chapter, an approach for segmentation of a lung tumour is presented. For pre-processing of lung CT images, simple image processing like morphological operations is used, and for tumour segmentation task, a 3D convolutional neural network (CNN) is used. The CNN architecture consists of a 3D encoder block followed by 3D decoder block just like U-Net but with deformable convolution blocks. For this study, two datasets have been used; one is the online-available NSCLC Radiomics dataset, and the other is collected from an Indian local hospital. The approach proposed in this chapter is evaluated in terms of dice coefficient. This approach is able to give significant results with a dice coefficient of 77.23%.

scholarly journals An image segmentation framework for extracting tumors from breast magnetic resonance images

2018 ◽  
Vol 11 (04) ◽  
pp. 1850014 ◽  
Author(s):  
Le Sun ◽  
Jinyuan He ◽  
Xiaoxia Yin ◽  
Yanchun Zhang ◽  
Jeon-Hor Chen ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Magnetic Resonance ◽  
Breast Cancer Diagnosis ◽  
Vital Role ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Breast Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri ◽  
Tumor Extraction ◽  
Disease Analysis

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get sufficient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods.

scholarly journals A Deep Learning Framework for Segmenting Brain Tumors Using MRI and Synthetically Generated CT Images

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 523
Author(s):  
Kh Tohidul Islam ◽  
Sudanthi Wijewickrema ◽  
Stephen O’Leary
Keyword(s):  
Image Segmentation ◽  
Three Dimensional ◽  
Disease Diagnosis ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Learning Framework ◽  
Guided Surgery ◽  
Magnetic Resonance Imaging Mri

Multi-modal three-dimensional (3-D) image segmentation is used in many medical applications, such as disease diagnosis, treatment planning, and image-guided surgery. Although multi-modal images provide information that no single image modality alone can provide, integrating such information to be used in segmentation is a challenging task. Numerous methods have been introduced to solve the problem of multi-modal medical image segmentation in recent years. In this paper, we propose a solution for the task of brain tumor segmentation. To this end, we first introduce a method of enhancing an existing magnetic resonance imaging (MRI) dataset by generating synthetic computed tomography (CT) images. Then, we discuss a process of systematic optimization of a convolutional neural network (CNN) architecture that uses this enhanced dataset, in order to customize it for our task. Using publicly available datasets, we show that the proposed method outperforms similar existing methods.

scholarly journals Lung tumor segmentation methods: Impact on the uncertainty of radiomics features for non-small cell lung cancer

PLoS ONE ◽  
2018 ◽  
Vol 13 (10) ◽  
pp. e0205003 ◽  
Author(s):  
Constance A. Owens ◽  
Christine B. Peterson ◽  
Chad Tang ◽  
Eugene J. Koay ◽  
Wen Yu ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cell Lung Cancer ◽  
Lung Tumor ◽  
Small Cell ◽  
Tumor Segmentation ◽  
Small Cell Lung ◽  
Segmentation Methods

scholarly journals Automatic Lung Tumor Segmentation on PET/CT Images Using Fuzzy Markov Random Field Model

2014 ◽  
Vol 2014 ◽  
pp. 1-6 ◽  
Author(s):  
Yu Guo ◽  
Yuanming Feng ◽  
Jian Sun ◽  
Ning Zhang ◽  
Wang Lin ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Random Field ◽  
Markov Random Field ◽  
Lung Tumor ◽  
Ct Images ◽  
Tumor Segmentation ◽  
Posterior Probability Distribution ◽  
Markov Random ◽  
Positron Emission ◽  
Pet Ct

The combination of positron emission tomography (PET) and CT images provides complementary functional and anatomical information of human tissues and it has been used for better tumor volume definition of lung cancer. This paper proposed a robust method for automatic lung tumor segmentation on PET/CT images. The new method is based on fuzzy Markov random field (MRF) model. The combination of PET and CT image information is achieved by using a proper joint posterior probability distribution of observed features in the fuzzy MRF model which performs better than the commonly used Gaussian joint distribution. In this study, the PET and CT simulation images of 7 non-small cell lung cancer (NSCLC) patients were used to evaluate the proposed method. Tumor segmentations with the proposed method and manual method by an experienced radiation oncologist on the fused images were performed, respectively. Segmentation results obtained with the two methods were similar and Dice’s similarity coefficient (DSC) was 0.85 ± 0.013. It has been shown that effective and automatic segmentations can be achieved with this method for lung tumors which locate near other organs with similar intensities in PET and CT images, such as when the tumors extend into chest wall or mediastinum.

scholarly journals The significance of colorectal cancer in the morbidity and mortality of the adult population of the South Banat District in the period from 2010 to 2019

2020 ◽  
Vol 49 (4) ◽  
pp. 1-16
Author(s):  
Aleksandra Perović ◽  
Jasmina Pavlović-Stojanović ◽  
Ljiljana Lazić ◽  
Dragana Antonijević-Đorđević ◽  
Magdalena Bjelica ◽  
...  
Keyword(s):  
Colorectal Cancer ◽  
Lung Cancer ◽  
Health Problem ◽  
Average Length ◽  
Adult Population ◽  
Public Health Problem ◽  
Hospital Treatment ◽  
Major Public Health Problem ◽  
The South ◽  
Major Health Problem

Introduction/Aim: According to the GLOBOCAN data, colorectal cancer (CRC) is a major public health problem in the world, because in 2018, 1,849,518 new cases and 880,792 deaths were registered. In Serbia, CRC is the second leading cause of the occurrence of disease in men (after lung cancer), and the third in women (after breast and lung cancer). The aim of this paper is to analyze the trends of outpatient morbidity, hospitalization and death from CRC in the South Banat District in the period 2010-2019. Methods: A descriptive statistical method was used. Data from routine health statistics were analyzed for the period 2010-2019. The indicators of outpatient illness, hospital treatment and death from CRC of the adult population of the South Banat District were monitored. Results: Outpatient and inpatient morbidity rates from CRC in the South Banat District are on the rise. At the annual level, 214 patients were hospitalized in the hospitals Vršac and Pančevo due to CRC. The average age was 66.8 years and the average length of treatment was 8.4 days. Most of the hospitalized people were aged between 60 and 69. Both hospitals had a higher hospitalization rate for men than for women. About 110 people a year in the district lose their lives due to CRC, and the average age of people who died is 75.7 years. The majority of men who died were aged between 70 and 79 (32.7%), while women were aged 80 and more (31.8%). Among the leading causes of death in men, CRC is in the ninth place, while in women in the thirteenth place, and the mortality rate is higher in males. Conclusion: Due to its significant participation in the occurrence of disease and death, CRC represents a major health problem in the population of the South Banat District. In order to improve the health of the population, it is necessary to conduct organized screening for the early detection of CRC in the target population, with more intensive promotion of health and healthy lifestyles to reduce exposure to factors associated with CRC.

scholarly journals Water Cycle Bat Algorithm and Dictionary-Based Deformable Model for Lung Tumor Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Mamtha V. Shetty ◽  
D. Jayadevappa ◽  
G. N. Veena
Keyword(s):  
Lung Cancer ◽  
Water Cycle ◽  
Lung Tumor ◽  
Median Filter ◽  
Bat Algorithm ◽  
Input Image ◽  
Deformable Model ◽  
Tumor Segmentation ◽  
Lung Lobe ◽  
Bayesian Fuzzy Clustering

Among the different types of cancers, lung cancer is one of the widespread diseases which causes the highest number of deaths every year. The early detection of lung cancer is very essential for increasing the survival rate in patients. Although computed tomography (CT) is the preferred choice for lungs imaging, sometimes CT images may produce less tumor visibility regions and unconstructive rates in tumor portions. Hence, the development of an efficient segmentation technique is necessary. In this paper, water cycle bat algorithm- (WCBA-) based deformable model approach is proposed for lung tumor segmentation. In the preprocessing stage, a median filter is used to remove the noise from the input image and to segment the lung lobe regions, and Bayesian fuzzy clustering is applied. In the proposed method, deformable model is modified by the dictionary-based algorithm to segment the lung tumor accurately. In the dictionary-based algorithm, the update equation is modified by the proposed WCBA and is designed by integrating water cycle algorithm (WCA) and bat algorithm (BA).

Sign in / Sign up

Export Citation Format

Share Document