A Hierarchical Classification Method for Breast Tumor Detection
01 Dec 2016-Iranian Journal of Medical Physics (Mashhad University of Medical Sciences)-Vol. 13, Iss: 4, pp 261-268
TL;DR: A hierarchical classification method for breast cancer detection is developed by including two Adaptive Boosting classifiers, the first classifier is devoted to separate normal and tumorous cases and the second layer is designed to detect tumor type.
Abstract: Introduction Breast cancer is the second cause of mortality among women. Early detection of it can enhance the chance of survival. Screening systems such as mammography cannot perfectly differentiate between patients and healthy individuals. Computer-aided diagnosis can help physicians make a more accurate diagnosis. Materials and Methods Regarding the importance of separating normal and abnormal cases in screening systems, a hierarchical classification system is defined in this paper. The proposed system is including two Adaptive Boosting (AdaBoost) classifiers, the first classifier separates the candidate images into two groups of normal and abnormal. The second classifier is applied on the abnormal group of the previous stage and divides them into benign and malignant categories. The proposed algorithm is evaluated by applying it on publicly available Mammographic Image Analysis Society (MIAS) dataset. 288 images of the database are used, including 208 normal and 80 abnormal images. 47 images of the abnormal images showed benign lesion and 33 of them had malignant lesion. Results Applying the proposed algorithm on MIAS database indicates its advantage compared to previous methods. A major improvement occurred in the first classification stage. Specificity, sensitivity, and accuracy of the first classifier are obtained as 100%, 95.83%, and 97.91%, respectively. These values are calculated as 75% in the second stage Conclusion A hierarchical classification method for breast cancer detection is developed in this paper. Regarding the importance of separating normal and abnormal cases in screening systems, the first classifier is devoted to separate normal and tumorous cases. Experimental results on available database shown that the performance of this step is adequately high (100% specificity). The second layer is designed to detect tumor type. The accuracy in the second layer is obtained 75%.
Citations
More filters
Posted Content•
TL;DR: A complete survey of studies on the application of DL techniques for COVID-19 diagnostic and automated segmentation of lungs is discussed, concentrating on works that used X-Ray and CT images.
Abstract: Coronavirus, or COVID-19, is a hazardous disease that has endangered the health of many people around the world by directly affecting the lungs. COVID-19 is a medium-sized, coated virus with a single-stranded RNA. This virus has one of the largest RNA genomes and is approximately 120 nm. The X-Ray and computed tomography (CT) imaging modalities are widely used to obtain a fast and accurate medical diagnosis. Identifying COVID-19 from these medical images is extremely challenging as it is time-consuming, demanding, and prone to human errors. Hence, artificial intelligence (AI) methodologies can be used to obtain consistent high performance. Among the AI methodologies, deep learning (DL) networks have gained much popularity compared to traditional machine learning (ML) methods. Unlike ML techniques, all stages of feature extraction, feature selection, and classification are accomplished automatically in DL models. In this paper, a complete survey of studies on the application of DL techniques for COVID-19 diagnostic and automated segmentation of lungs is discussed, concentrating on works that used X-Ray and CT images. Additionally, a review of papers on the forecasting of coronavirus prevalence in different parts of the world with DL techniques is presented. Lastly, the challenges faced in the automated detection of COVID-19 using DL techniques and directions for future research are discussed.
156 citations
Cites background from "A Hierarchical Classification Metho..."
...In recent years, applications of artificial intelligence in medicine have led to a variety of studies aiming to diagnose varied diseases, including brain tumors from MR images [16], [17], multiple types of brain disorders such from EEG [18], [19], breast cancer from mammographic images [20], [21] and pulmonary diseases such as Covid-19 from X-Ray [22] and CT-Scan [23]....
[...]
TL;DR: A comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented in this article, where rehabilitation systems developed for epileptic seizures using DL have been analyzed, and a summary is provided.
Abstract: A variety of screening approaches have been proposed to diagnose epileptic seizures, using electroencephalography (EEG) and magnetic resonance imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning (DL). Before the rise of DL, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in DL, the extraction of features and classification are entirely automated. The advent of these techniques in many areas of medicine, such as in the diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented. Various methods proposed to diagnose epileptic seizures automatically using EEG and MRI modalities are described. In addition, rehabilitation systems developed for epileptic seizures using DL have been analyzed, and a summary is provided. The rehabilitation tools include cloud computing techniques and hardware required for implementation of DL algorithms. The important challenges in accurate detection of automated epileptic seizures using DL with EEG and MRI modalities are discussed. The advantages and limitations in employing DL-based techniques for epileptic seizures diagnosis are presented. Finally, the most promising DL models proposed and possible future works on automated epileptic seizure detection are delineated.
132 citations
Posted Content•
TL;DR: A comprehensive overview of works focused on automated epileptic seizure detection using DL techniques and neuroimaging modalities is presented and the most promising DL models proposed and possible future works on automated epilepsy seizure detection are delineated.
Abstract: A variety of screening approaches have been proposed to diagnose epileptic seizures, using Electroencephalography (EEG) and Magnetic Resonance Imaging (MRI) modalities. Artificial intelligence encompasses a variety of areas, and one of its branches is deep learning. Before the rise of deep learning, conventional machine learning algorithms involving feature extraction were performed. This limited their performance to the ability of those handcrafting the features. However, in deep learning, the extraction of features and classification is entirely automated. The advent of these techniques in many areas of medicine such as diagnosis of epileptic seizures, has made significant advances. In this study, a comprehensive overview of the types of deep learning methods exploited to diagnose epileptic seizures from various modalities has been studied. Additionally, hardware implementation and cloud-based works are discussed as they are most suited for applied medicine.
109 citations
Cites methods from "A Hierarchical Classification Metho..."
...In conventional machine learning techniques, the selection of features and classifiers is done by trial-and-error method [25,26]....
[...]
Posted Content•
TL;DR: Key studies conducted with the aid of DL networks to distinguish ASD are investigated and important challenges in the automated detection and rehabilitation of ASD are presented and proposed.
Abstract: Accurate diagnosis of Autism Spectrum Disorder (ASD) is essential for its management and rehabilitation Neuroimaging techniques that are non-invasive are disease markers and may be leveraged to aid ASD diagnosis Structural and functional neuroimaging techniques provide physicians substantial information about the structure (anatomy and structural connectivity) and function (activity and functional connectivity) of the brain Due to the intricate structure and function of the brain, diagnosing ASD with neuroimaging data without exploiting artificial intelligence (AI) techniques is extremely challenging AI techniques comprise traditional machine learning (ML) approaches and deep learning (DL) techniques Conventional ML methods employ various feature extraction and classification techniques, but in DL, the process of feature extraction and classification is accomplished intelligently and integrally In this paper, studies conducted with the aid of DL networks to distinguish ASD were investigated Rehabilitation tools provided by supporting ASD patients utilizing DL networks were also assessed Finally, we presented important challenges in this automated detection and rehabilitation of ASD
87 citations
TL;DR: A complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided in this paper, where the important preprocessing techniques employed in various works are analyzed.
79 citations
References
More filters
AT&T1
TL;DR: This short overview paper introduces the boosting algorithm AdaBoost, and explains the underlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting as well as boosting’s relationship to support-vector machines.
Abstract: Boosting is a general method for improving the accuracy of any given learning algorithm. This short overview paper introduces the boosting algorithm AdaBoost, and explains the underlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting as well as boosting’s relationship to support-vector machines. Some examples of recent applications of boosting are also described.
3,212 citations
"A Hierarchical Classification Metho..." refers methods in this paper
...A weak AdaBoost was the first practical boosting algorithm and remains one of the most widely used [15, 16]....
[...]
TL;DR: A new algorithm is proposed that naturally extends the original AdaBoost algorithm to the multiclass case without reducing it to multiple two-class problems and is extremely easy to implement and is highly competitive with the best currently available multi-class classification methods.
Abstract: Boosting has been a very successful technique for solving the two-class classification problem. In going from two-class to multi-class classification, most algorithms have been restricted to reducing the multi-class classification problem to multiple two-class problems. In this paper, we propose a new algorithm that naturally extends the original AdaBoost algorithm to the multiclass case without reducing it to multiple two-class problems. Similar to AdaBoost in the twoclass case, this new algorithm combines weak classifiers and only requires the performance of each weak classifier be better than random guessing (rather than 1/2). We further provide a statistical justification for the new algorithm using a novel multi-class exponential loss function and forward stage-wise additive modeling. As shown in the paper, the new algorithm is extremely easy to implement and is highly competitive with the best currently available multi-class classification methods.
1,572 citations
TL;DR: An experimental study on learning from crowds that handles data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet), which gives valuable insights into the functionality of deep CNN learning from crowd annotations and proves the necessity of data aggregation integration.
Abstract: The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration.
512 citations
"A Hierarchical Classification Metho..." refers background or methods in this paper
...suggested applying deep learning to generate a ground-truth from nonexpert annotations in the biomedical context [7]....
[...]
...Computer-aided diagnosis (CAD) techniques were presented in recent years to help physicians, reduce false positive rate (FPR), and perform diagnosis action faster, more accurately, and more easily [2-9, 13, 14]....
[...]
TL;DR: Two automated methods to diagnose mass types of benign and malignant in mammograms are presented and different classifiers (such as random forest, naive Bayes, SVM, and KNN) are used to evaluate the performance of the proposed methods.
Abstract: CNN templates are generated using a genetic algorithm to segment mammograms.An adaptive threshold is computed in region growing process by using ANN and intensity features.In tumor classification, CNN produces better results than region growing.MLP produces the highest classification accuracy among other classifiers.Results on DDSM images are more appropriate than those of MIAS. Breast cancer is regarded as one of the most frequent mortality causes among women. As early detection of breast cancer increases the survival chance, creation of a system to diagnose suspicious masses in mammograms is important. In this paper, two automated methods are presented to diagnose mass types of benign and malignant in mammograms. In the first proposed method, segmentation is done using an automated region growing whose threshold is obtained by a trained artificial neural network (ANN). In the second proposed method, segmentation is performed by a cellular neural network (CNN) whose parameters are determined by a genetic algorithm (GA). Intensity, textural, and shape features are extracted from segmented tumors. GA is used to select appropriate features from the set of extracted features. In the next stage, ANNs are used to classify the mammograms as benign or malignant. To evaluate the performance of the proposed methods different classifiers (such as random forest, naive Bayes, SVM, and KNN) are used. Results of the proposed techniques performed on MIAS and DDSM databases are promising. The obtained sensitivity, specificity, and accuracy rates are 96.87%, 95.94%, and 96.47%, respectively.
323 citations
"A Hierarchical Classification Metho..." refers background or methods in this paper
...[2] 2015 MIAS Intensity histogram, shape, and texture Multi-layer neural network (MLP) 92....
[...]
...16%, respectively, by applying their technique on MIAS database [2]....
[...]
...Computer-aided diagnosis (CAD) techniques were presented in recent years to help physicians, reduce false positive rate (FPR), and perform diagnosis action faster, more accurately, and more easily [2-9, 13, 14]....
[...]
...There are sets of automatic or semi-automatic tools to help radiologists with detection and classification of breast abnormalities [2]....
[...]
TL;DR: The development of a novel Computer-aided Diagnosis (CADx) system for the diagnosis of breast masses is directed towards intensifying the performance of CADx algorithms as well as reducing the FNR by utilizing Zernike moments as descriptors of shape and margin characteristics.
226 citations