Background and Objective: Early detection of the pulmonary nodule from physical examination low-dose computer tomography (LDCT) images is an effective measure to reduce the mortality rate of lung cancer. Although ther...
详细信息
Background and Objective: Early detection of the pulmonary nodule from physical examination low-dose computer tomography (LDCT) images is an effective measure to reduce the mortality rate of lung cancer. Although there are many computeraided diagnosis (CAD) methods used for detecting pulmonary nodules, there are few CAD systems for small pulmonary nodule detection with a large amount of physical examination LDCT images. Methods: In this work, we designed a CAD system called Pulmonary Nodules detection Assistant Platform for early pulmonary nodules detection and classification based on the physical examination LDCT images. Based on the preprocessed physical examination CT images, the three-dimensional (3D) CNN-based model is presented to detect candidate pulmonary nodules and output detection results with quantitative parameters, the 3D ResNet is used to classify the detected nodules into intrapulmonary nodules and pleural nodules to reduce the physician workloads, and the Fully Connected Neural Network (FCNN) is used to classify ground-glass opacity (GGO) nodules and non-GGO nodules to help doctor pay more attention to those suspected early lung cancer nodules. Results: Experiments are performed on our 10 0 0 samples of physical examinations (LNPE10 0 0) with an average diameter of 5.3 mm and LUNA16 dataset with an average diameter of 8.31 mm, which show that the designed CAD system is automatic and efficient for detecting smaller and larger nodules from different datasets, especially for the detection of smaller nodules with diameter between 3 mm and 6 mm in physical examinations. The accuracy of pulmonary nodule detection reaches 0.879 with an average of 1 false positive per CT in LNPE10 0 0 dataset, which is comparable to the experienced physicians. The classification accuracy reaches 0.911 between intrapulmonary and pleural nodules, and 0.950 between GGO and non-GGO nodules, respectively. Conclusion: Experimental results show that the proposed pulmonary nodule
In this paper, an intelligent method is developed for improving the performance of the computer-aideddetection (CAD) system. The research objective is to improve the performance of the CAD system in Breast Cancer (BC...
详细信息
In this paper, an intelligent method is developed for improving the performance of the computer-aideddetection (CAD) system. The research objective is to improve the performance of the CAD system in Breast Cancer (BC) detection with high accuracy using thermal images. The research strategy is efficient using feature extraction, feature selection, classification and artificial intelligence methods. In the developed method, the features in the Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) are extracted from images. The features are selected using the firefly feature selection algorithm. These selected features are observed to be relevant for the abnormality detection in healthy and unhealthy breasts. The k-Nearest Neighbors (kNN), Support Vector Machine (SVM), and Decision-Tree (D-Tree) classifiers are then applied to these features for the detection of malignancy in the breast. The breast thermograms of 200 subjects available at the Database for Mastology Research for breast research using InfraRed images, DMR-IR database, are considered for evaluation of our intelligent method. The results demonstrate that the accuracy is 98.8%, 81.5%, and 95%, the sensitivity is 99%, 83.15%, and 95.91%, and the specificity is 98.2%, 80%, and 94.11% when using SVM, kNN, and D-Tree classifier algorithm, respectively. This reveals the effectiveness of our intelligent method to improve the accuracy of the CAD system in the BC detection.
Osteoarthritis and rheumatoid are most common form of arthritis disorder, affecting millions of people worldwide. This article presents a computer aided detection system (CAD) for early knee osteoarthritis and rheumat...
详细信息
Osteoarthritis and rheumatoid are most common form of arthritis disorder, affecting millions of people worldwide. This article presents a computer aided detection system (CAD) for early knee osteoarthritis and rheumatoid detection using X-ray images and machine learning classifiers. This work also proposed a novel feature extractor from X-ray images of knee to assist in detection and classification, called explainable Renyi entropic segmentation with Internet of Things (IoT) framework. The proposed method later utilizes model agnostic algorithm using post hoc explainability for extracting relevant information from prediction of knee joint segmentation. CAD system is integrated with an IoT framework and can be used remotely to assist medical practitioners in treatments of knee arthritis. The presented results show commendable improvement over different existing feature extractors in combination with different classifiers. The best result of proposed extractor method was obtained when combined with random forest classifier having Euclidean hyperparameter that gave an accuracy of 95.23%, among all the evaluators. The obtained results show the effectiveness of proposed feature extractor model to determine relevant features from knee and describe the suitable knee disorders.
Lung cancer is a malignant lung tumor characterized by controlled cell growth in tissues of the lung. Lung cancer is the most common cancer diagnosed worldwide. More deaths happen due to lung cancer than any other typ...
详细信息
ISBN:
(纸本)9781509065936
Lung cancer is a malignant lung tumor characterized by controlled cell growth in tissues of the lung. Lung cancer is the most common cancer diagnosed worldwide. More deaths happen due to lung cancer than any other type of cancer. For survival of cancer patient, early detection and treatment is very helpful and effective. For determining the cancer cells from medical images, various image processing and soft computing techniques can be used. CT-image has properties like high resolution, better clarity, low noise and low distortion. Because of this CT-images are most commonly used for image processing. It is the best technique of image for detection of small nodules. Because of early detection of lung cancer, chances of patient's survival are more. For this reason, CAD systems for lung cancer have been proposed. Basically CAD system involves three steps. Those steps are as: Pre-processing, segmentation of the lung and classification of the nodule candidates. In this paper, we proposed a method for segmentation of extracted lung region from human chest CT. That method is Artificial Neural Network classifier model. For enhancing the edge detection of lung region lobes, combination of bit-planes of each pixels are used.
Lung cancer has a five-year survival rate of 17.7% which increases to 54.4% when it is diagnosed at early stages. Automated detection techniques have been developed to detect and diagnose nodules at early stages in co...
详细信息
Lung cancer has a five-year survival rate of 17.7% which increases to 54.4% when it is diagnosed at early stages. Automated detection techniques have been developed to detect and diagnose nodules at early stages in computer tomography (CT) images. This paper presents a systematic analysis of the recent nodules detection techniques with the goal to summerize current trends and future challenges. The relevant papers are selected from IEEEXplore, science direct, PubMed, and web of science databases. Each paper is critically reviewed in order to summarize its methodology and results for further analysis. Our analyses reveal that several methods show potential progress in the field but still require an improvement to overcome many challenges like, high sensitivity with low false positive (FP) rate, detection of different nodules based on their size, shape, and positions, integration with electronic medical record (EMR) and picture archiving and communication system (PACS), and providing robust techniques that are successful across different databases. To overcome these challenges and developing a robust computeraideddetection (CADe) system, it is believed that collaborative work is required among the developers, clinicians and other relating parties in order to understand particular issues and needs of a CADe system and develop automatic techniques to overcome these challenges with high processing speed, low cost of implementation and with software security assurance. (C) 2017 Elsevier Ltd. All rights reserved.
暂无评论