Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography

In this study, we investigated a pattern-recognition technique based on an artificial neural network (ANN), which is called a massive training artificial neural network (MTANN), for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography (CT) images. The MTANN consists of a modified multilayer ANN, which is capable of operating on image data directly. The MTANN is trained by use of a large number of subregions extracted from input images together with the teacher images containing the distribution for the "likelihood of being a nodule." The output image is obtained by scanning an input image with the MTANN. The distinction between a nodule and a non-nodule is made by use of a score which is defined from the output image of the trained MTANN. In order to eliminate various types of non-nodules, we extended the capability of a single MTANN, and developed a multiple MTANN (Multi-MTANN). The Multi-MTANN consists of plural MTANNs that are arranged in parallel. Each MTANN is trained by using the same nodules, but with a different type of non-nodule. Each MTANN acts as an expert for a specific type of non-nodule, e.g., five different MTANNs were trained to distinguish nodules from various-sized vessels; four other MTANNs were applied to eliminate some other opacities. The outputs of the MTANNs were combined by using the logical AND operation such that each of the trained MTANNs eliminated none of the nodules, but removed the specific type of non-nodule with which the MTANN was trained, and thus removed various types of non-nodules. The Multi-MTANN consisting of nine MTANNs was trained with 10 typical nodules and 10 non-nodules representing each of nine different non-nodule types (90 training non-nodules overall) in a training set. The trained Multi-MTANN was applied to the reduction of false positives reported by our current computerized scheme for lung nodule detection based on a database of 63 low-dose CT scans (1765 sections), which contained 71 confirmed nodules including 66 biopsy-confirmed primary cancers, from a lung cancer screening program. The Multi-MTANN was applied to 58 true positives (nodules from 54 patients) and 1726 false positives (non-nodules) reported by our current scheme in a validation test; these were different from the training set. The results indicated that 83% (1424/1726) of non-nodules were removed with a reduction of one true positive (nodule), i.e., a classification sensitivity of 98.3% (57 of 58 nodules). By using the Multi-MTANN, the false-positive rate of our current scheme was improved from 0.98 to 0.18 false positives per section (from 27.4 to 4.8 per patient) at an overall sensitivity of 80.3% (57/71).     

Computer-aided diagnostic scheme for lung nodule detection in digital chest radiographs by use of a multiple-template matching technique.

We have been developing a computer-aided diagnostic (CAD) scheme to assist radiologists in improving the detection of pulmonary nodules in chest radiographs, because radiologists can miss as many as 30% of pulmonary nodules in routine clinical practice. A key to the successful clinical application of a CAD scheme is to ensure that there are only a small number of false positives that are incorrectly reported as nodules by the scheme. In order to significantly reduce the number of false positives in our CAD scheme, we developed, in this study, a multiple-template matching technique, in which a test candidate can be identified as a false positive and thus eliminated, if its largest cross-correlation value with non-nodule templates is larger than that with nodule templates. We describe the technique for determination of cross-correlation values for test candidates with nodule templates and non-nodule templates, the technique for creation of a large number of nodule templates and non-nodule templates, and the technique for removal of nodulelike non-nodule templates and non-nodulelike nodule templates, in order to achieve a good performance. In our study, a large number of false positives (44.3%) were removed with reduction of a very small number of true positives (2.3%) by use of the multiple-template matching technique. We believe that this technique can be used to significantly improve the performance of CAD schemes for lung nodule detection in chest radiographs.     

Lung nodule detection on thoracic computed tomography images: preliminary evaluation of a computer-aided diagnosis system

We are developing a computer-aided diagnosis (CAD) system for lung nodule detection on thoracic helical computed tomography (CT) images. In the first stage of this CAD system, lung regions are identified by a k-means clustering technique. Each lung slice is classified as belonging to the upper, middle, or the lower part of the lung volume. Within each lung region, structures are segmented again using weighted k-means clustering. These structures may include true lung nodules and normal structures consisting mainly of blood vessels. Rule-based classifiers are designed to distinguish nodules and normal structures using 2D and 3D features. After rule-based classification, linear discriminant analysis (LDA) is used to further reduce the number of false positive (FP) objects. We performed a preliminary study using 1454 CT slices from 34 patients with 63 lung nodules. When only LDA classification was applied to the segmented objects, the sensitivity was 84% (53/63) with 5.48 (7961/1454) FP objects per slice. When rule-based classification was used before LDA, the free response receiver operating characteristic (FROC) curve improved over the entire sensitivity and specificity ranges of interest. In particular, the FP rate decreased to 1.74 (2530/1454) objects per slice at the same sensitivity. Thus, compared to FP reduction with LDA alone, the inclusion of rule-based classification lead to an improvement in detection accuracy for the CAD system. These preliminary results demonstrate the feasibility of our approach to lung nodule detection and FP reduction on CT images.     

Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification

We developed an advanced computer-aided diagnostic (CAD) scheme for the detection of various types of lung nodules on chest radiographs intended for implementation in clinical situations. We used 924 digitized chest images (992 noncalcified nodules) which had a 500 x 500 matrix size with a 1024 gray scale. The images were divided randomly into two sets which were used for training and testing of the computerized scheme. In this scheme, the lung field was first segmented by use of a ribcage detection technique, and then a large search area (448 x 448 matrix size) within the chest image was automatically determined by taking into account the locations of a midline and a top edge of the segmented ribcage. In order to detect lung nodule candidates based on a localized search method, we divided the entire search area into 7 x 7 regions of interest (ROIs: 64 x 64 matrix size). In the next step, each ROI was classified anatomically into apical, peripheral, hilar, and diaphragm/heart regions by use of its image features. Identification of lung nodule candidates and extraction of image features were applied for each localized region (128 x 128 matrix size), each having its central part (64 x 64 matrix size) located at a position corresponding to a ROI that was classified anatomically in the previous step. Initial candidates were identified by use of the nodule-enhanced image obtained with the average radial-gradient filtering technique, in which the filter size was varied adaptively depending on the location and the anatomical classification of the ROI. We extracted 57 image features from the original and nodule-enhanced images based on geometric, gray-level, background structure, and edge-gradient features. In addition, 14 image features were obtained from the corresponding locations in the contralateral subtraction image. A total of 71 image features were employed for three sequential artificial neural networks (ANNs) in order to reduce the number of false-positive candidates. All parameters for ANNs, i.e., the number of iterations, slope of sigmoid functions, learning rate, and threshold values for removing the false positives, were determined automatically by use of a bootstrap technique with training cases. We employed four different combinations of training and test image data sets which was selected randomly from the 924 cases. By use of our localized search method based on anatomical classification, the average sensitivity was increased to 92.5% with 59.3 false positives per image at the level of initial detection for four different sets of test cases, whereas our previous technique achieved an 82.8% of sensitivity with 56.8 false positives per image. The computer performance in the final step obtained from four different data sets indicated that the average sensitivity in detecting lung nodules was 70.1% with 5.0 false positives per image for testing cases and 70.4% sensitivity with 4.2 false positives per image for training cases. The advanced CAD scheme involving the localized search method with anatomical classification provided improved detection of pulmonary nodules on chest radiographs for 924 lung nodule cases.     

Detection of the Optic Nerve Head in Fundus Images of the Retina with Gabor Filters and Phase Portrait Analysis

We propose a method using Gabor filters and phase portraits to automatically locate the optic nerve head (ONH) in fundus images of the retina. Because the center of the ONH is at or near the focal point of convergence of the retinal vessels, the method includes detection of the vessels using Gabor filters, detection of peaks in the node map obtained via phase portrait analysis, and an intensity-based condition. The method was tested on 40 images from the Digital Retinal Images for Vessel Extraction (DRIVE) database and 81 images from the Structured Analysis of the Retina (STARE) database. An ophthalmologist independently marked the center of the ONH for evaluation of the results. The evaluation of the results includes free-response receiver operating characteristics (FROC) and a measure of distance between the manually marked and detected centers. With the DRIVE database, the centers of the ONH were detected with an average distance of 0.36 mm (18 pixels) to the corresponding centers marked by the ophthalmologist. FROC analysis indicated a sensitivity of 100% at 2.7 false positives per image. With the STARE database, FROC analysis indicated a sensitivity of 88.9% at 4.6 false positives per image.     

A model-based framework for the detection of spiculated masses on mammography

The detection of lesions on mammography is a repetitive and fatiguing task. Thus, computer-aided detection systems have been developed to aid radiologists. The detection accuracy of current systems is much higher for clusters of microcalcifications than for spiculated masses. In this article, the authors present a new model-based framework for the detection of spiculated masses. The authors have invented a new class of linear filters, spiculated lesion filters, for the detection of converging lines or spiculations. These filters are highly specific narrowband filters, which are designed to match the expected structures of spiculated masses. As a part of this algorithm, the authors have also invented a novel technique to enhance spicules on mammograms. This entails filtering in the radon domain. They have also developed models to reduce the false positives due to normal linear structures. A key contribution of this work is that the parameters of the detection algorithm are based on measurements of physical properties of spiculated masses. The results of the detection algorithm are presented in the form of free-response receiver operating characteristic curves on images from the Mammographic Image Analysis Society and Digital Database for Screening Mammography databases.     

Lung nodule detection in low-dose and thin-slice computed tomography

A computer-aided detection (CAD) system for the identification of small pulmonary nodules in low-dose and thin-slice CT scans has been developed. The automated procedure for selecting the nodule candidates is mainly based on a filter enhancing spherical-shaped objects. A neural approach based on the classification of each single voxel of a nodule candidate has been purposely developed and implemented to reduce the amount of false-positive findings per scan. The CAD system has been trained to be sensitive to small internal and sub-pleural pulmonary nodules collected in a database of low-dose and thin-slice CT scans. The system performance has been evaluated on a data set of 39 CT containing 75 internal and 27 sub-pleural nodules. The FROC curve obtained on this data set shows high values of sensitivity to lung nodules (80-85% range) at an acceptable level of false positive findings per patient (10-13 FP/scan).     

非对称卷积核YOLO V2网络的CT影像肺结节检测

肺癌一直是严重威胁人类健康的疾病之一,肺结节作为早期肺癌的一个重要征象,在肺癌的早期诊断与治疗中具有重要的意义。传统的CT影像肺结节检测方法不仅步骤繁琐、处理速度慢,而且对于结节的检出率及定位精度都亟待提高。提出一种基于非对称卷积核YOLO V2网络的CT影像肺结节检测方法:首先将连续的CT序列叠加构造为伪彩色数据集,以增强病变和健康组织的差异;然后将含有非对称卷积核的inception V3模块引入到YOLO V2网络中,构造出一种适用于肺结节检测的深度网络,一方面利用YOLO V2网络在目标检测上的优势,另一方面通过inception V3模块在网络的宽度与深度上进行扩增,以提取更加丰富的特征;为进一步提高结节的定位精度,对损失函数的设计与计算方法也进行一定的改进。为验证所提检测模型的性能,从LIDC-IDRI数据集中选取1 010个病例的CT图像用于训练和测试,在大于3 mm的肺结节中,检测敏感度为94.25%,假阳性率为8.50%。实验表明,所提出的肺结节检测方法不仅可以简化肺部CT图像的处理过程,而且在结节检测率及定位精度方面均优于传统方法,可为肺结节检测提供一种新思路。     

A Segmentation Framework of Pulmonary Nodules in Lung CT Images

Accurate segmentation of pulmonary nodules is a prerequisite for acceptable performance of computer-aided detection (CAD) system designed for diagnosis of lung cancer from lung CT images. Accurate segmentation helps to improve the quality of machine level features which could improve the performance of the CAD system. The well-circumscribed solid nodules can be segmented using thresholding, but segmentation becomes difficult for part-solid, non-solid, and solid nodules attached with pleura or vessels. We proposed a segmentation framework for all types of pulmonary nodules based on internal texture (solid/part-solid and non-solid) and external attachment (juxta-pleural and juxta-vascular). In the proposed framework, first pulmonary nodules are categorized into solid/part-solid and non-solid category by analyzing intensity distribution in the core of the nodule. Two separate segmentation methods are developed for solid/part-solid and non-solid nodules, respectively. After determining the category of nodule, the particular algorithm is set to remove attached pleural surface and vessels from the nodule body. The result of segmentation is evaluated in terms of four contour-based metrics and six region-based metrics for 891 pulmonary nodules from Lung Image Database Consortium and Image Database Resource Initiative (LIDC/IDRI) public database. The experimental result shows that the proposed segmentation framework is reliable for segmentation of various types of pulmonary nodules with improved accuracy compared to existing segmentation methods.     

Automated segmentation and quantification of inflammatory tissue of the hand in rheumatoid arthritis patients using magnetic resonance imaging data

OBJECTIVES: The aim of this paper is the development of an automated method for the segmentation and quantification of inflammatory tissue of the hand in patients suffering form rheumatoid arthritis using contrast enhanced T1-weighted magnetic resonance images. METHODS AND MATERIALS: The proposed automatic method consists of four stages: (a) preprocessing of images, (b) identification of the number of clusters, by minimizing the appropriate validity index, (c) segmentation using the fuzzy C-means algorithm employing four features which are related to intensity and the location of pixels and (d) postprocessing, where defuzzification is performed and small objects and vessels are eliminated and quantification takes place. RESULTS: The proposed method is evaluated using a dataset of image sequences obtained from 25 patients suffering from rheumatoid arthritis. For 17 of them we have obtained follow-up images after 1 year treatment. The obtained sensitivity and positive predictive rate is 97.71% and 83.35%, respectively. In addition, quantification of inflammation before and after treatment, as well as, comparison with manual segmentation is carried out. CONCLUSIONS: The proposed method performs very well and results in high detection and quantification accuracy. However, the reduction of false positives and the identification of old inflammation must be addressed.     

Automated detection of lung nodules in CT scans: false-positive reduction with the radial-gradient index

We present a number of approaches based on the radial gradient index (RGI) to achieve false-positive reduction in automated CT lung nodule detection. A database of 38 cases was used that contained a total of 82 lung nodules. For each CT section, a complementary image known as an "RGI map" was constructed to enhance regions of high circularity and thus improve the contrast between nodules and normal anatomy. Thresholds on three RGI parameters were varied to construct RGI filters that sensitively eliminated false-positive structures. In a consistency approach, RGI filtering eliminated 36% of the false-positive structures detected by the automated method without the loss of any true positives. Use of an RGI filter prior to a linear discriminant classifier yielded notable improvements in performance, with the false-positive rate at a sensitivity of 70% being reduced from 0.5 to 0.28 per section. Finally, the performance of the linear discriminant classifier was evaluated with RGI-based features. RGI-based features achieved a substantial improvement in overall performance, with a 94.8% reduction in the false-positive rate at a fixed sensitivity of 70%. These results demonstrate the potential role of RGI analysis in an automated lung nodule detection method.     

Preliminary Evaluation of Biplane Correlation (BCI) Stereographic Imaging for Lung Nodule Detection

A biplane correlation (BCI) imaging system obtains images that can be viewed in stereo, thereby minimizing overlapping structures. This study investigated whether using stereoscopic visualization provides superior lung nodule detection compared to standard postero-anterior (PA) image display. Images were acquired at two oblique views of ±3° as well as at a standard PA position from 60 patients. Images were processed using optimal parameters and displayed on a stereoscopic display. The PA image was viewed in the standard format, while the oblique views were paired to provide a stereoscopic view of the subject. A preliminary observer study was performed with four radiologists who viewed and scored the PA image then viewed and scored the BCI stereoscopic image. The BCI stereoscopic viewing of lung nodules resulted in 71 % sensitivity and 0.31 positive predictive value (PPV) index compared to PA results of 86 % sensitivity and 0.26 PPV index. The sensitivity for lung nodule detection with the BCI stereoscopic system was reduced by 15 %; however, the total number of false positives reported was reduced by 35 % resulting in an improved PPV index of 20 %. The preliminary results indicate observer dependency in terms of relative advantage of either system in the detection of lung nodules, but overall equivalency of the two methods with promising potential for BCI as an adjunct diagnostic technique.     

Automatic identification of metaphase spreads and nuclei using neural networks

The mitotic index (MI) is an important measure in cell proliferation studies. Determination of the MI is usually made by light-microscope analysis of slide preparations. The analyst identifies and counts thousands of cells and reports the percentage of mitotic shapes found among the interphase nuclei. Full automation of this process is an ambitious task, because there can exist very few mitotic shapes among hundreds of nuclei and thousands of artifacts, resulting in a high probability of false positives, i.e. objects erroneously identified as mitosis or nuclei. A semi-automated approach for MI calculation is reported, based on the development of a neural network (NN) for automatic identification of metaphase spreads and stimulated nuclei in digital images of microscope preparations at 10X magnification. After segmentation of the objects on each image, ten different morphometrical, photometrical and textural features are measured on each segmented object. An NN is used to classify the feature vectors into three classes: metaphases, nuclei and artifacts. The system has been able to classify correctly approximately 91% of the objects in each class, in a test set of 191 mitosis, 331 nuclei and 387 artifacts, obtained from 30 different microscope slides. Manual editing of false positives from the metaphase classification results allows the calculation of the MI with an error of 6.5%.     

基于VTK的医学图像网格化建模系统开发

开发了一套基于VTK的集医学图像处理、三维重建、有限元网格生成功能为一体的软件系统,实现了从医学图像到有限元网格解剖真实的几何建模.系统通过读取医学切片图像,在图像预处理、分割、表面重建、平滑与简化后生成解剖真实的几何模型和有限元网格.系统可输出CAD、RP/RM、有限元体网格文件,为基于医学图像的生物力学仿真、基于数值模拟的外科手术规划、快速成型与制造服务.     

Computerized Breast Mass Detection Using Multi-Scale Hessian-Based Analysis for Dynamic Contrast-Enhanced MRI

This study aimed to investigate a computer-aided system for detecting breast masses using dynamic contrast-enhanced magnetic resonance imaging for clinical use. Detection performance of the system was analyzed on 61 biopsy-confirmed lesions (21 benign and 40 malignant lesions) in 34 women. The breast region was determined using the demons deformable algorithm. After the suspicious tissues were identified by kinetic feature (area under the curve) and the fuzzy c-means clustering method, all breast masses were detected based on the rotation-invariant and multi-scale blob characteristics. Subsequently, the masses were further distinguished from other detected non-tumor regions (false positives). Free-response operating characteristics (FROC) curve and detection rate were used to evaluate the detection performance. Using the combined features, including blob, enhancement, morphologic, and texture features with 10-fold cross validation, the mass detection rate was 100 % (61/61) with 15.15 false positives per case and 91.80 % (56/61) with 4.56 false positives per case. In conclusion, the proposed computer-aided detection system can help radiologists reduce inter-observer variability and the cost associated with detection of suspicious lesions from a large number of images. Our results illustrated that breast masses can be efficiently detected and that enhancement and morphologic characteristics were useful for reducing non-tumor regions.     

基于改进YOLO V3的肺结节检测方法

针对肺结节占CT图像比例小、形状不规则及直接应用YOLO V3算法进行肺结节检测效果不佳的问题,提出基于 改进YOLO V3的肺结节检测方法。首先进行重采样和肺实质分割等预处理操作。然后修改YOLO V3的基础网络结构, 调整骨干网络和检测网络的结构单元数量;使用Mish激活函数替换Leaky ReLU激活函数,引入含有空洞卷积的感受野 模块层;修改损失函数。最后使用改进的YOLO V3方法进行肺结节检测,完成对比实验。在LIDC-IDRI数据集上得到了 88.89%的准确率和94.73%的高敏感度,实验结果表明该方法能够有效检测肺结节。     

眼底数码图像血管分割预处理关键技术研究

目的本文以眼底图像为研究对象,针对眼底图像血管分割的预处理关键技术进行了深入的研究和探讨。方法首先通过RGB通道选择,显示出较为清晰的血管图像,并通过自适应直方图均衡化增强图像对比度。其次,利用灰度倒置和灰度增强,使细小血管更加清晰,并采用空域滤波对血管轮廓边缘进行增强。最后进行图像填充,去除背景中的噪声干扰。结果通过MATLAB仿真实验,获得了血管脉络清晰的眼底数码图像。结论本研究为血管的自动分割以及血管成分的定性和定量分析奠定了基础。