scholarly journals Integrated System for Classification of Pulmonary Nodules on CT Images

2019 ◽  
Vol 8 (4) ◽  
pp. 10893-10901
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Probabilistic Neural Network ◽  
Research Work ◽  
Pulmonary Nodules ◽  
Integrated System ◽  
Lung Nodules ◽  
Dimension Vector ◽  
Hybrid Features

Mortality rate of lung cancer is increasing very day all over the world. Early stage lung nodules detection and proper treatment is solution to reduce the deaths due to lung cancer. In this research work proposed integrated CADe/CADx system segments and classifies lung nodules into benign or malignant. CADe phase segments Well Circumscribed Nodules (WCN), Juxta Vascular Nodules (JVN) and Juxta Pleural Nodules (JPN) of different size in diameter. This part uses algorithms proposed in our previous WCN, JVN and JPN lung nodules segmentation work. CADx performance classification of segmented WCNs, JVNs and JPNs nodules into benign or malignant. In first part of CADx system hybrid features of segmented lung nodules are extracted and features dimension vector is reduced with Linear Discrimination Analysis. Finally, Probabilistic Neural Network uses reduced hybrid features of segmented nodules to classify segmented nodules as benign or malignant. Proposed integrated system achieved high classification accuracy of 94.85 for WCNs, 97.65 for JVNs and 97.96 for JPNs of different size in diameter (nodules diameter< 10mm, nodules diameter >10mm and < 30mm, nodules diameter >30mm and <70mm). For small nodules achieved classification performance values are, accuracy of 94.85, sensitivity of 90 and specificity of 95.85. And nodules of size 10mm to 30mm obtained accuracy, sensitivity and specificity are 97.85, 97.65 and 94.15 respectively.

scholarly journals Classification of Pulmonary Nodules by Using Hybrid Features

2013 ◽  
Vol 2013 ◽  
pp. 1-11 ◽  
Author(s):  
Ahmet Tartar ◽  
Niyazi Kilic ◽  
Aydin Akan
Keyword(s):  
Lung Cancer ◽  
Early Detection ◽  
Classification Accuracy ◽  
Pulmonary Nodules ◽  
Detection Performance ◽  
Diagnosis And Treatment ◽  
New Classification ◽  
Hybrid Features ◽  
Classification Approach

Early detection of pulmonary nodules is extremely important for the diagnosis and treatment of lung cancer. In this study, a new classification approach for pulmonary nodules from CT imagery is presented by using hybrid features. Four different methods are introduced for the proposed system. The overall detection performance is evaluated using various classifiers. The results are compared to similar techniques in the literature by using standard measures. The proposed approach with the hybrid features results in 90.7% classification accuracy (89.6% sensitivity and 87.5% specificity).

scholarly journals Generative augmentation to improve lung nodules detection in resource-limited settings

2020 ◽  
pp. 60-69
Author(s):  
Nataliya Gusarova ◽  
Artem Lobantsev ◽  
Aleksandra Vatian ◽  
Anton Klochrov ◽  
Maxim Kabyshev ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Resource Constraints ◽  
Pulmonary Nodules ◽  
Lung Nodules ◽  
Resource Limited ◽  
Initial Dataset ◽  
Unbalanced Dataset ◽  
Expert Assessments ◽  
Computational Resources

Introduction: Lung cancer is one of the most formidable cancers. The use of neural networks technologies in its diagnostics is promising, but the datasets collected from real clinical practice cannot cover a variety of lung cancer manifestations.  Purpose: Assessment of the possibility of improving the classification of pulmonary nodules by means of generative augmentation of available datasets under resource constraints. Methods: We used part of LIDC-IDRI dataset,  the StyleGAN architecture for generating artificial lung nodules and the VGG11 model as a classifier. We generated pulmonary nodules using the proposed pipeline and invited four  experts to visually evaluate them. We formed four experimental datasets with different types of augmentation, including use of synthesized data, and we compared the effectiveness of the classification performed by the VGG11 network when training for each dataset. Results: 10 generated nodules in each group of characteristics were presented for assessment. In all cases, positive expert assessments were obtained with a Fleiss's kappa coefficient k = 0.6–0.9. We got the best values of ROCAUC=0.9604 and PRAUC=0.9625 with the proposed approach of a generative augmentation. Discussion: The obtained efficience metrics are superior to the baseline  results obtained using comparably small training datasets, and slightly less than the best results achieved using much more powerful computational resources. So, we have shown that one can effectively use for augmenting an unbalanced dataset a combination of StyleGAN and VGG11, which does not require large computing resources as well as a large initial dataset for training.

scholarly journals Novel CADe/CADx System for Lung Nodules Segmentation and Classification on Computed Tomography Images

2019 ◽  
Vol 9 (2S) ◽  
pp. 165-173
Keyword(s):  
Area Under Curve ◽  
Research Work ◽  
Decision Fusion ◽  
Lung Nodules ◽  
Hybrid Features ◽  
Malignancy Rate ◽  
Computed Tomography Images ◽  
Level 3 ◽  
Nodule Classification

Detection and classification of different types lung nodules poses major challenges in medical diagnosis routine. Classification of segmented nodules based on extracted hybrid features of segmented nodules have shown remarkable performance. Recently deep features alone and also with combination of hybrid features have improved nodules classification. In this research work new CADe/CADx system is proposed for detection and classification of Well Circumscribed Nodules, Juxta Vascular Nodules and Juxta Pleural Nodules. In nodules detection part, algorithms proposed in our previous work were used. Classifiers decision fusion based new nodules classification system is proposed. Four set of hybrid features and deep features using Convolution Neural Network are considered from segmented nodules. Hybrid features set consist of twenty four shape features, six GLCM features in four direction with a distance of two, six First Order Statistic features and twelve energy features. Five individually trained Probabilistic Neural Networks by all five set features separately used in nodule classification. In classification process all five classifiers decisions are fused at 2-level, 3-level, 4-level and 5-level. The proposed system achieved highest performance with 5-level fusion compared with other level fusions. System was evaluated on CT images of LIDC database with consideration of 2669 lung nodules of malignancy rate 1 to 5. Based on malignancy rate 2669 nodules are grouped as dataset 1 and dataset 2 with nodules of malignancy rate 1, 2, 3 and 3, 4,5 respectively. The 5-level decision fusion achieved highest accuracy of 95.72, sensitivity of 95.52, specificity of 95.79 and Area Under Curve of 96.21 for dataset 1 and accuracy of 92.54, sensitivity of 90.48, specificity of 94.63 and Area Under Curve of 92.69 for dataset 2.

scholarly journals Using Deep Learning for Classification of Early Lung Nodules on Computed Tomography Images

2018 ◽  
Author(s):  
Lucas Lima ◽  
Marcelo Oliveira
Keyword(s):  
Lung Cancer ◽  
Deep Learning ◽  
Pulmonary Nodules ◽  
Lung Nodules ◽  
Lung Cancer Patients ◽  
Early Stages ◽  
Computed Tomography Images ◽  
Area Under Roc Curve ◽  
Small Pulmonary Nodules

Lung cancer is the leading cause of cancer mortality, accounting for approximately 20% of all cancer-related deaths. Nevertheless, despite the development of new therapeutic agents and technologies, only 16% of lung cancer patients are diagnosed at early stages. Therefore, to diagnose in early stages, when the nodules are very small, is a complex task for specialists and presents some challenges. To assist the specialists, the main purpose of this work is to propose the use of Deep Learning to classify 25,200 small pulmonary nodules balanced with diameter 5-10mm. The result was of 0.992 (+/- 0.001) of area under ROC curve using 10-fold cross validation. The proposed method showed to be promising to assist the specialists in classification of small lung nodules.

scholarly journals Effect of a pulmonary nodule fact sheet on patient anxiety and knowledge: a quality improvement initiative

2018 ◽  
Vol 7 (3) ◽  
pp. e000437 ◽  
Author(s):  
Matthew T Koroscil ◽  
Mitchell H Bowman ◽  
Michael J Morris ◽  
Andrew J Skabelund ◽  
Andrew M Hersh
Keyword(s):  
Lung Cancer ◽  
Quality Improvement ◽  
Pulmonary Nodule ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
Low Risk ◽  
Quality Improvement Initiative ◽  
Patient Anxiety ◽  
Patient Understanding ◽  
Fact Sheet

IntroductionThe utilisation of chest CT for the evaluation of pulmonary disorders, including low-dose CT for lung cancer screening, is increasing in the USA. As a result, the discovery of both screening-detected and incidental pulmonary nodules has become more frequent. Despite an overall low risk of malignancy, pulmonary nodules are a common cause of emotional distress among adult patients.MethodsWe conducted a multi-institutional quality improvement (QI) initiative involving 101 participants to determine the effect of a pulmonary nodule fact sheet on patient knowledge and anxiety. Males and females aged 35 years or older, who had a history of either screening-detected or incidental solid pulmonary nodule(s) sized 3–8 mm, were included. Prior to an internal medicine or pulmonary medicine clinic visit, participants were given a packet containing a pre-fact sheet survey, a pulmonary nodule fact sheet and a post-fact sheet survey.ResultsOf 101 patients, 61 (60.4%) worried about their pulmonary nodule at least once per month with 18 (17.8%) worrying daily. The majority 67/101 (66.3%) selected chemotherapy, chemotherapy and radiation, or radiation as the best method to cure early-stage lung cancer. Despite ongoing radiographic surveillance, 16/101 (15.8%) stated they would not be interested in an intervention if lung cancer was diagnosed. Following review of the pulmonary nodule fact sheet, 84/101 (83.2%) reported improved anxiety and 96/101 (95.0%) reported an improved understanding of their health situation. Patient understanding significantly improved from 4.2/10.0 to 8.1/10.0 (p<0.01).ConclusionThe incorporation of a standardised fact sheet for subcentimeter solid pulmonary nodules improves patient understanding and alleviates anxiety. We plan to implement pulmonary nodule fact sheets into the care of our patients with low-risk subcentimeter pulmonary nodules.

scholarly journals Reducing False-Positives in Lung Nodules Detection Using Balanced Datasets

2021 ◽  
Vol 9 ◽  
Author(s):  
Jinglun Liang ◽  
Guoliang Ye ◽  
Jianwen Guo ◽  
Qifan Huang ◽  
Shaohui Zhang
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
Ct Images ◽  
False Positives ◽  
Classification Systems ◽  
Cad System ◽  
Nodule Detection ◽  
Diagnosis Of Lung Cancer ◽  
Lung Ct

Malignant pulmonary nodules are one of the main manifestations of lung cancer in early CT image screening. Since lung cancer may have no early obvious symptoms, it is important to develop a computer-aided detection (CAD) system to assist doctors to detect the malignant pulmonary nodules in the early stage of lung cancer CT diagnosis. Due to the recent successful applications of deep learning in image processing, more and more researchers have been trying to apply it to the diagnosis of pulmonary nodules. However, due to the ratio of nodules and non-nodules samples used in the training and testing datasets usually being different from the practical ratio of lung cancer, the CAD classification systems may easily produce higher false-positives while using this imbalanced dataset. This work introduces a filtering step to remove the irrelevant images from the dataset, and the results show that the false-positives can be reduced and the accuracy can be above 98%. There are two steps in nodule detection. Firstly, the images with pulmonary nodules are screened from the whole lung CT images of the patients. Secondly, the exact locations of pulmonary nodules will be detected using Faster R-CNN. Final results show that this method can effectively detect the pulmonary nodules in the CT images and hence potentially assist doctors in the early diagnosis of lung cancer.

Non-surgical management of early-stage lung cancer

2017 ◽  
Author(s):  
Jim Brown ◽  
Neal Navani
Keyword(s):  
Lung Cancer ◽  
Early Stage ◽  
Pulmonary Nodules ◽  
The Elderly ◽  
Multidisciplinary Teams ◽  
Solitary Pulmonary Nodules ◽  
Early Stage Lung Cancer ◽  
Mortality And Morbidity ◽  
Inoperable Patient ◽  
Ablative Techniques

As low-dose computed tomography screening of ‘high-risk’ smokers is occurring with increasing frequency, the incidental discovery of solitary pulmonary nodules is becoming more frequent, and lung cancer multidisciplinary teams are now often faced with balancing risk and benefit when making decisions regarding the radical treatment of patients with a clinical diagnosis of early lung cancer but borderline fitness. Surgery offers the best prospect of cure but is associated with significant mortality and morbidity; the elderly and frail experience more toxicity and a greater impact on the quality of life. This chapter reviews the criteria for assessing surgical fitness and examines the evidence for minimally invasive and ablative techniques for the treatment of early peripheral lung cancer in the medically inoperable patient.

scholarly journals Diagnosis and outcome of resected solitary pulmonary nodules after liver transplantation

2019 ◽  
Author(s):  
Mari Tone ◽  
Nobuyasu Awano ◽  
Takehiro Izumo ◽  
Hanako Yoshimura ◽  
Tatsunori Jo ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Liver Transplantation ◽  
Early Stage ◽  
Lung Resection ◽  
Invasive Pulmonary Aspergillosis ◽  
Primary Lung Cancer ◽  
Pulmonary Nodules ◽  
Solitary Pulmonary Nodules ◽  
Computed Tomography Scans

Abstract Objective Solitary pulmonary nodules after liver transplantation are challenging clinical problems. Herein, we report the causes and clinical courses of resected solitary pulmonary nodules in patients who underwent liver transplantation. Methods We retrospectively obtained medical records of 68 patients who underwent liver transplantation between March 2009 and June 2016. This study mainly focused on patients with solitary pulmonary nodules observed on computed tomography scans during follow-ups that were conducted until their deaths or February 2019. Results Computed tomography scans revealed solitary pulmonary nodules in 7 of the 68 patients. Definitive diagnoses were obtained using video-assisted lung resection in all seven patients. None experienced major postoperative complications. The final pathologic diagnoses were primary lung cancer in three patients, pulmonary metastases from hepatocellular carcinoma in one patient, invasive pulmonary aspergillosis in one patient, post-transplant lymphoproliferative disorder in one patient, and hemorrhagic infarction in one patient. The three patients with lung cancer were subsequently treated with standard curative resection. Conclusions Solitary pulmonary nodules present in several serious but potentially curable diseases, such as early-stage lung cancer. Patients who present with solitary pulmonary nodules after liver transplantation should be evaluated by standard diagnostic procedures, including surgical biopsy if necessary.

scholarly journals Detection and Classification of Early Stage Lesions in Diabetic Retinopathy using Color Fundus Images

2019 ◽  
Vol 8 (3) ◽  
pp. 4476-4480
Keyword(s):  
Diabetic Retinopathy ◽  
Clustering Algorithm ◽  
Early Stage ◽  
High Sensitivity ◽  
Morphological Operations ◽  
Hybrid Features ◽  
Speeded Up Robust Features ◽  
Fuzzy C Means Clustering ◽  
Color Fundus Images

Detection of lesions and classification of Diabetic Retinopathy (DR) play an important role in day-to-day life. In this proposed system, colour fundus image is pre-processed using morphological operations to recover from noises and it is converted into HSV colorspace. Fuzzy C-Means Clustering algorithm (FCMC) is used for segmenting the early stage lesions such as Microaneurysms (Ma), Haemorrhages (HE) and Exudates. Hybrid features such as colour correlogram and speeded up robust features (surf) are extracted to train the classifier. Cascaded Rotation Forest (CRF) classifier is used for classification of diabetic retinopathy. The proposed system increases the accuracy of detection and it has got high sensitivity.

Sign in / Sign up

Export Citation Format

Share Document