Computer-aided diagnosis: the emerging of three CAD systems induced by Japanese health care needs

The aim of this paper is to describe three emerging computer-aided diagnosis (CAD) systems induced by Japanese health care needs. CAD has been developing fast in the last two decades. The idea of using a computer to help in medical image diagnosis is not new. Some pioneer studies are dated back to the 1960s. In 1998, the first U.S. FDA (Food and Drug Administration) approved commercial CAD system, a film-digitized mammography system, was launched by R2 Technologies, Inc. The success was quickly repeated by a number of companies. The approval of Medicare CAD reimbursement in the U.S. in 2001 further boosted the industry. Today, CAD has its significance in the economy of the medical industry. FDA approved CAD products in the field of breast imaging (mammography, ultrasonography and breast MRI) and chest imaging (radiography and CT) can be seen. In Japan, as part of the "Knowledge Cluster Initiative" of the government, three computer-aided diagnosis (CAD) projects are hosted at the Gifu University since 2004. These projects are regarding the development of CAD systems for the early detection of (1) cerebrovascular diseases using brain MRI and MRA images by detecting lacunar infarcts, unruptured aneurysms, and arterial occlusions; (2) ocular diseases such as glaucoma, diabetic retinopathy, and hypertensive retinopathy using retinal fundus images; and (3) breast cancers using ultrasound 3-D volumetric whole breast data by detecting the breast masses. The projects are entering their final development stage. Preliminary results are presented in this paper. Clinical examinations will be started soon, and commercialized CAD systems for the above subjects will appear by the completion of this project.     

A study on the effect of morphological filters on computer-aided medical image diagnosis

We have developed several morphological image filters that can be useful for computer-aided medical image diagnosis. Several computer-aided diagnosis (CAD) systems for lung cancer and breast cancer have been developed to assist the radiologist’s diagnostic work. The CAD systems for lung cancer can automatically detect pathological changes (pulmonary nodules) with a high true-positive rate (TP) even under low false-positive rate (FP) conditions. On the other hand, the conventional CAD systems for breast cancer can automatically detect some pathological changes (calcifications and masses), but the TP for other changes, such as architectural distortion, is still very low. Motivated by the radiologist’s cognitive processes to increase TP for breast cancer, we propose new methods to extract novel morphological features from X-ray mammography. Simulation results demonstrate the effectiveness of the morphological methods for detecting tumor shadows.     

乳腺MRI图像肿块分割的分段比较与方法研究

计算机辅助诊断通过对乳腺磁共振成像( MRI)中肿块区域的自动分割和测量为医生提供定量的诊断依据。对分割过程中不同阶段的多种算法进行实验对比,以此探索更具稳定性和准确性的分割方案：空间模糊C均值( sFCM)聚类算法在肿块的初始定位中具有抗噪声能力和稳定性强的优点,而GVF snake模型在精细分割中对局部轮廓具有较好的收敛性;结合两种算法,并运用MRI序列帧间灰度分布相似、肿块位置/形状相近的原理,最终提高整个序列的分割精度与稳定性。     

Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm

Computer-aided detection/diagnosis (CAD) systems can enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. The objective of this paper is to review the recent published segmentation and classification techniques and their state-of-the-art for the human brain magnetic resonance images (MRI). The review reveals the CAD systems of human brain MRI images are still an open problem. In the light of this review we proposed a hybrid intelligent machine learning technique for computer-aided detection system for automatic detection of brain tumor through magnetic resonance images. The proposed technique is based on the following computational methods; the feedback pulse-coupled neural network for image segmentation, the discrete wavelet transform for features extraction, the principal component analysis for reducing the dimensionality of the wavelet coefficients, and the feed forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 101 images consisting of 14 normal and 87 abnormal (malignant and benign tumors) from a real human brain MRI dataset. The classification accuracy on both training and test images is 99% which was significantly good. Moreover, the proposed technique demonstrates its effectiveness compared with the other machine learning recently published techniques. The results revealed that the proposed hybrid approach is accurate and fast and robust. Finally, possible future directions are suggested.     

Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines

This study presents a computer-aided diagnosis (CAD) system with textural features for classifying benign and malignant breast tumors on medical ultrasound systems. A series of pathologically proven breast tumors were evaluated using the support vector machine (SVM) in the differential diagnosis of breast tumors. The proposed CAD system utilized facile textural features, i.e., block difference of inverse probabilities, block variation of local correlation coefficients and auto-covariance matrix, to identify breast tumor. An SVM classifier using the textual features classified the tumor as benign or malignant. The proposed system identifies breast tumors with a comparatively high accuracy. This can help inexperienced physicians avoid misdiagnosis. The main advantage of the proposed system is that the training and diagnosis procedure of SVM are faster and more stable than that of multilayer perception neural networks. With the expansion of the database, new cases can easily be gathered and used as references. This study dramatically reduces the training and diagnosis time. The SVM is a reliable choice for the proposed CAD system because it is fast and excellent in ultrasound image classification.     

医学CAD系统中降低假阳性率的解决方案

如何提高乳腺癌计算机辅助诊断系统（CAD）中的灵敏度一直是众多学者研究的热点,特别是针对亚洲女性及年轻妇女的致密组织图像的检测。尽管之前已经提出了针对该类图像的解决方法,实验也表明,该方法可以提高系统的灵敏度（真阳性率TP）,但人们发现随着TP的提高也伴随了假阳性率（FP）的增长。所以,本文的研究目的是在前续研究的基础上,即保证CAD系统的灵敏度的同时尽可能地降低假阳性率。     

A new breast tumor ultrasonography CAD system based on decision tree and BI-RADS features

In this paper, we present a novel computer-aided diagnostic (CAD) system based on the Breast Imaging Reporting and Data System (BI-RADS) terminology scores of screening ultrasonography (US). The decision tree algorithm is adopted to analyze the BI-RADS information to differentiate between the malignant and benign breast tumors. Although many ultrasonography CAD systems have been developed for decades, there are still some problems in clinical practice. Previous CAD systems are opaque for clinicians and cannot process the ultrasound image from different ultrasound machines. This study proposes a novel CAD system utilizing BI-RADS scoring standard and Classification and Regression Tree (CART) algorithm to overcome the two problems. The original dataset consists of 1300 ultrasound breast images. Three well-experienced clinicians evaluated all of the images according to the BI-RADS feature scoring standard. Subsequently, each image could be transformed into a 25?×?1 vector. The CART algorithm was finally used to classify these vectors. In the experiments, we used the oversampling method to balance the number of malignant samples and benign samples. The 5-fold cross validation was employed to evaluate the performance of the system. The accuracy reached 94.58%, the specificity was 98.84%, the sensitivity was 90.80%, the positive predictive value (PPV) was 98.91% and the negative predictive value (NVP) was 90.56%. The experiment results show that the proposed system can obtain a sufficient performance in the breast diagnosis and can effectively recognize the benign breast tumors in BI-RADS 3.     

Automatic nipple detection in breast thermograms

Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reduction in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decades, several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of interest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the analysis of medical images because it can be used in several applications, such as image registration and modality fusion. This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human body segmentation, determination of nipple candidates using adaptive thresholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.     

应用于CT图像肺结节检测的深度学习方法综述

肺癌是世界上死亡率最高的癌症，通过胸部CT影像检测肺结节对肺癌早期诊断和治疗意义重大。为了减轻放射科医生的工作量以及同时减少误诊率和漏诊率，研究人员提出了计算机辅助检测（CAD）系统辅助放射科医生检测和诊断肺结节。目前，研究人员正在尝试不同的深度学习技术，以提高计算机辅助诊断系统在基于CT图像的肺癌筛查中的性能。这项工作回顾了作为肺癌检测的CAD系统目前典型的深度学习的算法和框架，主要从数据集介绍、2D深度学习方法、3D深度学习方法、数据不平衡问题的处理、模型训练方法以及模型可解释性这六个方面进行介绍。最后，对各个方法的主要特点和算法性能进行了综合比较分析，并对如何提高结节检测性能进行了展望。     

Deep feature extraction and classification of breast ultrasound images

Controlled despeckling (structure/edges/feature preservation with smoothing the homogeneous areas) is a desired pre-processing step for the design of computer-aided diagnostic (CAD) systems using ultrasound images as the presence of speckle noise masks diagnostically important information making interpretation difficult even for experienced radiologist. For efficiently classifying the breast tumors, the conventional CAD system designs use hand-crafted features. However, these features are not robust to the variations in size, shape and orientation of the tumors resulting in lower sensitivity. Thus deep feature extraction and classification of breast ultrasound images have recently gained attention from research community. The deep networks come with an advantage of directly learning the representative features from the images. However, these networks are difficult to train from scratch if the representative training data is small in size. Therefore transfer learning approach for deep feature extraction and classification of medical images has been widely used. In the present work the performance of four pre-trained convolutional neural networks VGG-19, SqueezeNet, ResNet-18 and GoogLeNet has been evaluated for differentiating between benign and malignant tumor types. From the results of the experiments, it is noted that CAD system design using GoogLeNet architecture for deep feature extraction followed by correlation based feature selection and fuzzy feature selection using ANFC-LH yields highest accuracy of 98.0% with individual class accuracy value of 100% and 96% for benign and malignant classes respectively. For differentiating between the breast tumors, the proposed CAD system design can be utilized in routine clinical environment.

     

Sensitivity improvement of automatic pulmonary nodules detection in chest X-ray CT images

In this article, we develop an automatic detection method for non-isolated pulmonary nodules as part of a computer-aided diagnosis (CAD) system for lung cancers in chest X-ray computed tomography (CT) images. An essential core of the method is to separate non-isolated nodules from connecting structures such as the chest wall and blood vessels. The isolated nodules can be detected more easily by the CAD systems developed previously. To this end, we propose a preprocessing technique for nodule candidate detection by using double-threshold binarization. We evaluate the performance using the receiver operating characteristic (ROC) analysis in clinical chest CT images. The results suggest that the detection rate for non-isolated nodules by the proposed method is superior to that by the conventional preprocessing methods.     

Multiresolution-Based Segmentation of Calcifications for the Early Detection of Breast Cancer

Clusters of microcalcifications in a mammogram may be an early indication of breast cancer. Unfortunately, due to size, shape and limited contrast from surrounding normal tissue, microcalcifications can occasionally be hard to detect in computer-aided detection (CAD) systems. These CAD systems can also be slow compared to a radiologist's performance when reviewing film-screen mammography. The research described here investigates a rapid, multiresolution-based approach combined with wavelet analysis to provide an accurate segmentation of potential calcifications. An initial multiresolution approach to fuzzy c -means (FCM) segmentation is employed to rapidly distinguish medically significant tissues. Tissue areas chosen for high-resolution analysis are broken into multiple windows. Within each window, wavelet analysis is used to generate a contrast image, and a local FCM segmentation generates an estimate of local intensity. A simple two-rule fuzzy system then combines intensity and contrast information to derive fuzzy memberships of pixels in the high-contrast, bright pixel class. A double threshold is finally applied to this fuzzy membership to detect and segment calcifications. This sequence of steps is shown to approach detection rates of conventional classifier designs and may therefore be useful as a pre-processing module for these systems to improve speed. Results are reported for 25 images obtained from the Digital Database for Screening Mammography (DDSM).     

Generic integration of content-based image retrieval in computer-aided diagnosis

Content-based image retrieval (CBIR) offers approved benefits for computer-aided diagnosis (CAD), but is still not well established in radiological routine yet. An essential factor is the integration gap between CBIR systems and clinical information systems. The international initiative Integrating the Healthcare Enterprise (IHE) aims at improving interoperability of medical computer systems. We took into account deficiencies in IHE compliance of current picture archiving and communication systems (PACS), and developed an intermediate integration scheme based on the IHE post-processing workflow integration profile (PWF) adapted to CBIR in CAD. The Image Retrieval in Medical Applications (IRMA) framework was used to apply our integration scheme exemplarily, resulting in the application called IRMAcon. The novel IRMAcon scheme provides a generic, convenient and reliable integration of CBIR systems into clinical systems and workflows. Based on the IHE PWF and designed to grow at a pace with the IHE compliance of the particular PACS, it provides sustainability and fosters CBIR in CAD.     

A CAD system design to diagnosize alzheimers disease from MRI brain images using optimal deep neural network

Memory related issues in brain are mainly caused by Alzheimer disease (AD) which is the most common form of dementia. This disease must be diagnosed in its prodromal stage known as Mild Cognitive Impairment (MCI) also it needs an accurate detection and classification technique. In this paper, a computer-aided diagnosis (CAD) system is implemented on Magnetic resonance imaging (MRI) data from ADNI database. This disease highly affects the Hippocampus and cerebrum regions which are normally found in the grey matter region of brain. At first, MNI/ICBM atlas space of every three dimensional MRI images are constructed using normalization procedure, then grey matter region of brain is extracted. Subsequently, feature extraction is done by two dimensional Gabor filter in three scales and eight orientations. Then, the proposed optimal Deep Neural Network (DNN) classifier is used to classify the images as Cognitive normal (CN), Alzheimer disease (AD), and Mild Cognitive Impairment (MCI). Here, DNN classifier is optimized by selecting optimal weight parameter using Enhanced Squirrel Search Algorithm. The experimental results prove an efficiency of the proposed method using MR images. The proposed algorithm beats existing techniques in terms of accuracy, sensitivity, and specificity.

     

Detection of mitotic cells in breast cancer histopathological images using deep versus handcrafted features

One of the most important processes in the diagnosis of breast cancer, which is the leading mortality rate in women, is the detection of the mitosis stage at the cellular level. In literature, many studies have been proposed on the computer-aided diagnosis (CAD) system for detecting mitotic cells in breast cancer histopathological images. In this study, comparative evaluation of conventional and deep learning based feature extraction methods for automatic detection of mitosis in histopathological images are focused. While various handcrafted features are extracted with textural/spatial, statistical and shape-based methods in conventional approach, the convolutional neural network structure proposed on the deep learning approach aims to create an architecture that extracts the features of small cellular structures such as mitotic cells. Mitosis detection/counting is an important process that helps us assess how aggressive or malignant the cancer’s spread is. In the proposed study, approximately 180,000 non-mitotic and 748 mitotic cells are extracted for the evaluations. It is obvious that the classification stage cannot be performed properly due to the imbalanced numbers of mitotic and non-mitotic cells extracted from histopathological images. Hence, the random under-sampling boosting (RUSBoost) method is exploited to overcome this problem. The proposed framework is tested on mitosis detection in breast cancer histopathological images dataset provided from the International Conference on Pattern Recognition (ICPR) 2014 contest. In the results obtained with the deep learning approach, 79.42% recall, 96.78% precision and 86.97% F-measure values are achieved more successfully than handcrafted methods. A client/server-based framework has also been developed as a secondary decision support system for use by pathologists in hospitals. Thus, it is aimed that pathologists will be able to detect mitotic cells in various histopathological images more easily through necessary interfaces.

     

致密组织图像的图像增强算法

近年来乳腺癌有年轻化的趋势,年轻妇女的乳腺组织结构以致密组织为主,由于致密组织在乳腺X光片中也呈现出高亮度,所以致密组织很容易被误解为微钙化。文章主要针对这些图像,提出一种新的图像增强算法。试验证明,该算法可以改进CAD系统性能,并能更好地在致密乳腺组织图像中检测微钙化点。     

Performance evaluation of automated brain tumor detection systems with expert delineations and interobserver variability analysis in diseased patients on magnetic resonance imaging

ABSTRACT

Intervention by human expert has turned out to be essential for computerized analysis systems desiring to be approved by medical regulatory bodies. Further, to validate the performance of automated diagnosis systems, interobserver variability analysis is critically important. The purpose of this article is twofold: (i) firstly to perform interobserver variability analysis of two experienced Radiologists interpreting lesion boundary in brain magnetic resonance images; (ii) secondly, to evaluate the performance of recently proposed automated lesion segmentation model with that of the two experienced Radiologists who performed manual delineations of lesion boundary. Experiments were conducted on the database consisting of 80 real-time brain images with glioma tumor acquired using magnetic resonance imaging (MRI). Extensive statistical analysis such as the two tailed T-test, analysis of variance (ANOVA) test, Mann-Whitney U test, regression and correlation tests, etc. are performed to compare the lesions detected manually by experts and that by the automated method. Furthermore, three quantitative measures namely, dice similarity index, Jaccard coefficient, and Hausdorff distance are used to evaluate the automated lesion detection method. The experimental results show that the lesion boundaries detected by the automated method are very close to the manual delineations provided by the expert Radiologists. It is concluded that the automated systems for brain lesion detection can be utilized as a part of routine clinical practice to help the medical professionals in determining the exact location and area of lesions in brain MRI images.     

Breast cancer image assessment using an adaptative network-based fuzzy inference system

In Brazil breast cancer is the foremost cause of fatality by cancer for women. Given that the causes are unidentified, it cannot be prevented. Mammography is one of the most reliable exams for breast cancer detection and it is based on image analysis by radiologists. Early detection is the key issue for breast cancer control and computer-aided diagnosis system can help ra diologists in detection and diagnosing breast abnormalities. Hybrid neuro-fuzzy systems are suitable for pattern recognition tasks and therefore useful for medical diagnosis support through pattern identification in mammographic images. This study presents an Adaptative Network-based Fuzzy Inference System (ANFIS) that classifies the mammographic images calcification region of interest as benign or malign and provides an important tool for breast cancer image assessment. The ANFIS model, utilized in the mammogram region of interest’s classification phase, reached a maximum accuracy rate of 99.75%.     

Integrating radiologist feedback with computer aided diagnostic systems for breast cancer risk prediction in ultrasonic images: An experimental investigation in machine learning paradigm

With advancements in machine learning algorithms and computer aided diagnostic (CAD) systems, the performance of automated analysis of radiological images has improved substantially in recent times. However, the lack of integration between the radiologist and CAD systems restrains the rate of progress as well as the reach of such advancements in clinical use. This article aims to improve the clinical efficiency of ultrasound based CAD systems for classification of breast lesions by integrating back-propagation artificial neural network (BPANN), support vector machine (SVM) and radiologist feedback. The acquired breast ultrasound images were subjected to wavelet based filtering in order to reduce speckle noise followed by feature extraction, feature selection and classification. Experiments on a database of 178 ultrasound images of breast anomalies (88 benign and 90 malignant) show that the proposed methodology achieves classification accuracy of 98.621% and 98.276%, respectively, when all 457 and 19 most relevant features selected by multi-criteria feature selection method were used for classification. The accuracy achieved is significantly higher than that using conventional classifiers based on BPANN and SVM. Further, it is found that integrating expert opinion in CAD systems improves its overall performance. The quantitative results obtained are discussed in light of some recently reported studies.     

乳腺X线图像计算机辅助诊断技术综述

近年来,乳腺癌严重威胁全球女性的身体健康,乳腺X线摄影是乳腺癌筛查的有效影像检查手段.乳腺X线图像计算机辅助诊断(computer aided diagnosis,CAD)运用计算机视觉、图像处理、机器学习等人工智能先进技术,自动分析处理乳腺X线图像,可为医生在临床中提供重要的诊断参考.主要面向肿块和微钙化病变检测、分...