Yoshikazu Uchiyama

Development of an Automated Method for the Detection of Chronic Lacunar Infarct Regions in Brain MR Images

The purpose of our study is to develop an algorithm that would enable the automated detection of lacunar infarct on T1-and T2-weighted magnetic resonance (MR) images. Automated identification of the lacunar infarct regions is not only useful in assisting radiologists to detect lacunar infarcts as a computer-aided detection (CAD) system but is also beneficial in preventing the occurrence of cerebral apoplexy in high-risk patients. The lacunar infarct regions are classified into the following two types for detection: “isolated lacunar infarct regions” and “lacunar infarct regions adjacent to hyperintensive structures.” The detection of isolated lacunar infarct regions was based on the multiple-phase binarization (MPB) method. Moreover, to detect lacunar infarct regions adjacent to hyperintensive structures, we used a morphological opening processing and a subtraction technique between images produced using two types of circular structuring elements. Thereafter, candidate regions were selected based on three features — area, circularity, and gravity center. Two methods were applied to the detected candidates for eliminating false positives (FPs). The first method involved eliminating FPs that occurred along the periphery of the brain using the region-growing technique. The second method, the multi-circular regions difference method (MCRDM), was based on the comparison between the mean pixel values in a series of double circles on a T1-weighted image. A training dataset comprising 20 lacunar infarct cases was used to adjust the parameters. In addition, 673 MR images from 80 cases were used for testing the performance of our method; the sensitivity and specificity were 90.1% and 30.0% with 1.7 FPs per image, respectively. The results indicated that our CAD system for the automatic detection of lacunar infarct on MR images was effective.

Modulation transfer function measurement of CT images by use of a circular edge method with a logistic curve-fitting technique

We propose a method for measuring the modulation transfer function (MTF) of a computed tomography (CT) system by use of a circular edge method with a logistic curve-fitting technique. An American College of Radiology (ACR) phantom was scanned by a Philips Brilliance system, and axial images were reconstructed by the filtered back projection algorithm with a standard reconstruction filter. The radial MTF was measured from a disk image of a rod or cylinder in the ACR phantom by use of the circular edge method. In this study, we applied a logistic curve-fitting technique to an edge-spread function (ESF) to eliminate noise because the edge method is very susceptible to noise in the ESF in a CT image. The circular edge method with the logistic curve-fitting technique provided the MTF without fluctuations due to noise for the entire spatial frequency range. The MTF was not affected by the tube current, the slice thickness, or the disk contrast, which were factors related to the amount of noise in the CT image. However, the MTF was affected by the location of the disk and by the disk size, depending on the average distance from the isocenter to the disk edge. Our results indicated that the MTF measured by the circular edge method with the logistic curve-fitting technique was not susceptible to noise in CT images. Therefore, this method is useful for MTF measurement for not only high-contrast objects, but also low-contrast objects with a large amount of noise.

Automated Classification of Cerebral Arteries in MRA Images and Its Application to Maximum Intensity Projection

Detection of unruptured aneurysms is a major task in magnetic resonance angiography (MRA). However, it is difficult for radiologists to detect small aneurysms on the maximum intensity projection (MIP) images because adjacent vessels may overlap with the aneurysms. Therefore, we proposed a method for making a new MIP image, the SelMIP image, with the interested vessels only, as opposed to all vessels, by manually selecting a cerebral artery from a list of cerebral arteries recognized automatically. By using our new SelMIP viewing technique, the selected vessel regions can also be observed from various directions and would further facilitate the radiologists in detecting small aneurysms. For automated classification of cerebral arteries, two 3D images, a target image and a reference image, are compared. Image registration is performed using the global matching and feature correspondence techniques. Segmentation of vessels in the target image is performed using the thresholding and region growing techniques. The segmented vessel regions were classified into eight cerebral arteries by calculating the Euclidean distance between a voxel in the target image and each of the voxels in the labeled eight vessel regions in the reference image. In applying the automated cerebral arteries recognization algorithm to thirteen MRA studies, results of 10 MRA studies were evaluated as clinically acceptable. Our new viewing technique would be useful in assisting radiologists for detection of aneurysms and for reducing the interpretation time

Computer-aided diagnosis scheme for classification of lacunar infarcts and enlarged Virchow-Robin spaces in brain MR images

The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images is important because their presence indicates an increased risk of severe cerebral infarction. However, accurate identification of lacunar infarcts on MR images is often hard for radiologists because of the difficulty in distinguishing lacunar infarcts and enlarged Virchow-Robin spaces. Therefore, we developed a computer-aided diagnosis (CAD) scheme for the classification of lacunar infarcts and enlarged Virchow-Robin spaces. Our database consisted of T1- and T2- weighted images obtained from 109 patients. The locations of lacunar infarcts and enlarged Virchow-Robin spaces were determined by an experienced neuroradiologist. It included 89 lacunar infarcts and 20 enlarged Virchow-Robin spaces. We first enhanced the lesions in T2-weighted image by using the white top-hat transformation. A gray-level thresholding was then applied to the enhanced image for the segmentation of lesions. From the segmented lesions, we determined image features, such as size, shape, location, and signal intensities in T1- and T2- weighted images. A neural network was then employed for distinguishing between lacunar infarcts and enlarged Virchow-Robin spaces. Our computerized method was evaluated by using a leave-one-out method. The result indicated that the area under the ROC curve was 0.945. Therefore, our CAD scheme would be useful in assisting radiologists for diagnosis of silent cerebral infarctions in MR images.

Improvement of Automated Detection Method of Lacunar Infarcts in Brain MR Images

The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images are important tasks for radiologists to ensure the prevention of severe cerebral infarction. However, their accurate identification is often difficult task. Therefore, the purpose of this study is to develop a computer- aided diagnosis scheme for the detection of lacunar infarcts. Our database consisted of 1,143 T1- and 1,143 T2-weighted images obtained from 132 patients. We first segmented the cerebral region in the Tl- weighted image by using a region growing technique. For identifying the initial lacunar infarcts candidates, white top-hat transform and multiple-phase binarization were then applied to the T2- weighted image. For eliminating false positives (FPs), we determined 12 features, i.e., the locations x and y, density differences in the Tl- and T2-weighted images, nodular components (NC), and nodular & linear components (NLC) from a scale 1 to 4. The NCs and NLCs were obtained using filter bank technique. The rule-based scheme and a neural network with 12 features were employed as the first step for eliminating FPs. The modular classifier was then used for eliminating three typical sources of FPs. As a result, the sensitivity of the detection of lacunar infarcts was 96.8% with 0.30 FP per image. Our computerized scheme would assist radiologists in identifying lacunar infarcts on MR images.

Application of targeted enrichment to next-generation sequencing of retroviruses integrated into the host human genome

The recent development and advancement of next-generation sequencing (NGS) technologies have enabled the characterization of the human genome at extremely high resolution. In the retrovirology field, NGS technologies have been applied to integration-site analysis and deep sequencing of viral genomes in combination with PCR amplification using virus-specific primers. However, virus-specific primers are not available for some epigenetic analyses, like chromatin immunoprecipitation sequencing (ChIP-seq) assays. Viral sequences are poorly detected without specific PCR amplification because proviral DNA is very scarce compared to human genomic DNA. Here, we have developed and evaluated the use of biotinylated DNA probes for the capture of viral genetic fragments from a library prepared for NGS. Our results demonstrated that viral sequence detection was hundreds or thousands of times more sensitive after enrichment, enabling us to reduce the economic burden that arises when attempting to analyze the epigenetic landscape of proviruses by NGS. In addition, the method is versatile enough to analyze proviruses that have mismatches compared to the DNA probes. Taken together, we propose that this approach is a powerful tool to clarify the mechanisms of transcriptional and epigenetic regulation of retroviral proviruses that have, until now, remained elusive.

Computerized scheme for detection of arterial occlusion in brain MRA images

Magnetic resonance angiography (MRA) is routinely employed in the diagnosis of cerebrovascular disease. Unruptured aneurysms and arterial occlusions can be detected in examinations using MRA. This paper describes a computerized detection method of arterial occlusion in MRA studies. Our database consists of 100 MRA studies, including 85 normal cases and 15 abnormal cases with arterial occlusion. Detection of abnormality is based on comparison with a reference (normal) MRA study with all the vessel known. Vessel regions in a 3D target MRA study is first segmented by using thresholding and region growing techniques. Image registration is then performed so as to maximize the overlapping of the vessel regions in the target image and the reference image. The segmented vessel regions are then classified into eight arteries based on comparison of the target image and the reference image. Relative lengths of the eight arteries are used as eight features in classifying the normal and arterial occlusion cases. Classifier based on the distance of a case from the center of distribution of normal cases is employed for distinguishing between normal cases and abnormal cases. The sensitivity and specificity for the detection of abnormal cases with arterial occlusion is 80.0% (12/15) and 95.3% (81/85), respectively. The potential of our proposed method in detecting arterial occlusion is demonstrated.

CAD Scheme for differential diagnosis of lacunar infarcts and normal Virchow-Robin spaces on brain MR images

The detection of asymptomatic lacunar infarcts on magnetic resonance (MR) images is important because their presence indicates an increased risk of severe cerebral infarction. However, accurate identification of lacunar infarcts on MR images is often hard for radiologists because of the difficulty in distinguishing lacunar infarcts and enlarged Virchow-Robin (VR) spaces. The purpose of this study was to develop a computer-aided diagnosis (CAD) scheme for the detection of lacunar infarcts on MR images. Our database consisted of T1- and T2- weighted images acquired using 1.5 T MR scanner. These images were obtained from 109 patients. Another database consisted of T1- and T2-weighted images and MRA images acquired using 3.0 T MR scanner. These images were obtained from 8 patients. We first developed a method for classification of lacunar infarcts and enlarged VR spaces by using the former database. The lesion was segmented using white top-hat transform and thresholding techniques. Image features, such as size, shape, and signal intensity, were determined from the segmented lesion. A neural network with image features was employed for distinguishing between lacunar infarcts and enlarged VR spaces. The result indicated that the area under the ROC curve was 0.945. We also developed a method for making a fusion image of T2-weighted image and MRA by using the latter database. Image registration was used to achieve a matching between T2-weighted image and MRA. Thresholding and region growing techniques were used for segmenting vessel regions in MRA. The blood flow obtained from MRA was superimposed on the lesion in T2-weighted image. Blood flow on the lesion was a crucial piece of information for the diagnosis of VR spaces. Our CAD schemes would be useful in assisting radiologists for the detection of lacunar infarcts in MR images.

Automatic segmentation of different-sized leukoaraiosis regions in brain MR images

Cerebrovascular diseases are the third leading cause of death in Japan. Therefore, a screening system for the early detection of asymptomatic brain diseases is widely used. In this screening system, leukoaraiosis is often detected in magnetic resonance (MR) images. The quantitative analysis of leukoaraiosis is important because its presence and extension is associated with an increased risk of severe stroke. However, thus far, the diagnosis of leukoaraiosis has generally been limited to subjective judgments by radiologists. Therefore, the purpose of this study was to develop a computerized method for the segmentation of leukoaraiosis, and provide an objective measurement of the lesion volume. Our database comprised of T1- and T2-weighted images obtained from 73 patients. The locations of leukoaraiosis regions were determined by an experienced neuroradiologist. We first segment cerebral parenchymal regions in T1-weighted images by using a region growing technique. For determining the initial candidate regions for leukoaraiosis, the k-means clustering of pixel values in the T1- and T2-weighted images was applied to the segmented cerebral region. For the elimination of false positives (FPs), we determined features such as the location, size, and circularity from each of the initial candidates. Finally, rule-based schemes and a quadratic discriminant analysis with these features were employed for distinguishing between the leukoaraiosis regions and the FPs. The results indicated that the sensitivity for the detection of leukoaraiosis was 100% with 5.84 FPs per image. Our computerized scheme can be useful in assisting radiologists for the quantitative analysis of leukoaraiosis in T1- and T2-weighted images.

Morphology filter bank for extracting nodular and linear patterns in medical images

PurposeUsing image processing to extract nodular or linear shadows is a key technique of computer-aided diagnosis schemes. This study proposes a new method for extracting nodular and linear patterns of various sizes in medical images.MethodsWe have developed a morphology filter bank that creates multiresolution representations of an image. Analysis bank of this filter bank produces nodular and linear patterns at each resolution level. Synthesis bank can then be used to perfectly reconstruct the original image from these decomposed patterns.ResultsOur proposed method shows better performance based on a quantitative evaluation using a synthesized image compared with a conventional method based on a Hessian matrix, often used to enhance nodular and linear patterns. In addition, experiments show that our method can be applied to the followings: (1) microcalcifications of various sizes in mammograms can be extracted, (2) blood vessels of various sizes in retinal fundus images can be extracted, and (3) thoracic CT images can be reconstructed while removing normal vessels.ConclusionsOur proposed method is useful for extracting nodular and linear shadows or removing normal structures in medical images.