Seiichi Murakami

Optimal beam quality for chest computed radiography

RATIONALE AND OBJECTIVES Optimal x-ray beam quality for chest computed radiography (CR) has not been determined. To investigate the optimal beam quality for chest CR, the authors measured the radiographic contrasts and compared the image quality of chest CR and screen-film (SF) radiographs using various x-ray tube voltages. METHODS Chest CR and SF radiographs were obtained on a phantom lung and human volunteers with or without a variety of simulated lung opacities using various x-ray tube voltage levels. Exposures were set to maintain identical patient exposure doses for all images. The contrast between peripheral lung and rib or heart was measured on these images and the differences were compared. The quality of the images of each simulated opacity was evaluated by five radiologists using a five-point grading scale. RESULTS Contrast between peripheral lung and rib or heart increased on CR images obtained by lowering the tube voltage from 140 to 80 kV, but the degree of increase was less than half the increase on SF images. The CR images of the simulated opacities obtained using a lower tube voltage were judged to be superior to those obtained with a higher tube voltage. Scattered radiation was reduced on CR images with a lower tube voltage. CONCLUSION The image quality of chest CR was improved by using a lower tube voltage than that used for conventional SF chest radiography. Considering the problem of tube loading in clinical applications, a tube voltage of 100 kV is recommended for chest CR.

Detection of Lung Nodule on Temporal Subtraction Images Based on Artificial Neural Network

The temporal subtraction technique as one of computer aided diagnosis has been introduced in medical fields to enhance the interval changes such as formation of new lesions and changes in existing abnormalities on deference image. With the temporal subtraction technique radiologists can easily detect lung nodules on visual screening. Until now, two-dimensional temporal subtraction imaging technique has been introduced for the clinical test. We have developed new temporal subtraction method to remove the subtraction artifacts which is caused by mis-registration on temporal subtraction images of lungs on MDCT images. In this paper, we propose a new computer aided diagnosis scheme for automatic enhancing the lung nodules from the temporal subtraction of thoracic MDCT images. At first, the candidates regions included nodules are detected by the multiple threshold technique in terms of the pixel value on the temporal subtraction images. Then, a rule-base method and artificial neural networks is utilized to remove the false positives of nodule candidates which is obtained temporal subtraction images. We have applied our detection of lung nodules to 30 thoracic MDCT image sets including lung nodules. With the detection method, satisfactory experimental results are obtained. Some experimental results are shown with discussion.

Detection of abnormal candidate regions on temporal subtraction images based on DCNN

Cancer is a leading cause of death both in Japan and worldwide. Detection of cancer region in CT images is the most important task to early detection. Recently, visual screening based on CT images become useful tools for cancer detection. However, due to the large number of images and the complexity of the image processing algorithms, image processing technique is still required a high screening quality. To overcome this problem, some computer aided diagnosis (CAD) algorithms are proposed. In this paper, we have designed and developed a framework combining machine learning based on deep convolutional neural networks (DCNN) and temporal subtraction techniques based on non-rigid image registration algorithm. Our main classification method can be built into three main steps; i) pre-processing for image segmentation, ii) image matching for registration, and iii) classification of abnormal regions based on machine learning algorithms. We performed our proposed technique to 25 thoracic MDCT sets and obtained true positive rates of 92.31 [%], false positive rates of 6.32 [/case] were obtained.

Automatic segmentation of phalanges regions on MR images based on MSGVF snakes

In recent years, medical imaging is important in medical diagnosis for early detection of lesions. However, a large number of images increases the stress to the radiologist. Therefore, CAD (Computer Aided Diagnosis) system is expected to reduce such burden. In diagnostic imaging of phalanges, X-ray photographs, CT (Computed Tomography) are used to evaluate the value of phalanges destruction. Whereby, the MRI (Magnetic Resonance Imaging) that is used mainly to diagnose the lesion in the soft tissue is more effective in a certain case, which is one of the important CAD systems to develop. However, studies on CAD system using MR images are not as much as the studies using CT. In this paper, we propose an automatic segmentation algorithm of phalanges regions on MR images. Although it has three dimensional information, this is the method for two dimensional algorithm. In other words, we propose for each slice of MR Images. Firstly, phalanges regions in MR images are segmented for coarse regions mainly by watershed algorithm. Next, the segmented results from the previous phase are set as the initial contour. Ultimately, the accurate segmentation of the phalanges on MR images are acquired based on MSGVF snakes.

Automatic segmentation of phalanges regions on CR images based on MSGVF Snakes

Rheumatoid arthritis and osteoporosis are two common orthopedic diseases. Rheumatoid arthritis is a disease that inflammation occurs in the joint, which always causes the joints are able to move freely. Osteoporosis is a disease that bone mineral content is reduced and risk of fragility fracture increases. As one of the diagnostic methods, medical imaging by photographed CR equipment has been widely accepted. However, some problems such as mass screening data sets and mis-diagnosis are still remained in visual screening. In order to solve these problems and reduce the burden to physicians, needs of an automatic diagnosis system capable of performing quantitative analysis is anticipated. In this paper, we carry out the development of a segmentation method of phalanges regions from CR images of the hand to perform a quantitative evaluation of rheumatoid arthritis and osteoporosis. The proposed method is carried out crude segmentation of phalanges regions from CR images of the hand, and extracts the detailed phalanges regions by Multi Scale Gradient Vector Flow Snakes (MSGVF) method. In our study, we performed Snakes algorithm to give an initial control points on MSGVF algorithm. We applied our method on three pairs of CR temporal images of phalanges regions, which are called as the previous images and the current images. We got the segmentation results of 5.95 [%] of false-positive rate and 92.9 [%] of true-positive rate.

Nonrigid image registration method for thoracic CT images using vessel structure information

Temporal Subtraction Technique is one of effective tools for diagnosis of lung cancer from thoracic CT images. By comparing two images of the same subject but shot at different time, the detection of temporal changing becomes facilitated. To acquire a more accurate subtraction image, the registration of these two images is critical. However it is not easy as the influence of the slight structures such as lung blood vessel. In this paper, a novel nonrigid image registration method based on vessel structure information is proposed. The similarity of the vessels structure is defined by means of the likelihood function of vessels structure and their direction. We combine this similarity of vessels with the intensity information of images. And the metrics are used as similarity measure in registration procedure. The proposed method has been applied to thoracic MDCT images, and the improvement of registration accuracy was investigated. The efficiency of our proposed method was indicated.

Segmentation method for phalanges in CR image by use of DCT

In this paper, we propose a CAD (Computer aided diagnosis) system to analyze the RA (rheumatoid arthritis) and osteoporosis by using image processing techniques from the CR images. To analyze the RA, we develop a segmentation method for phalanges in CR Image by use of DCT (Discrete Cosine Transform) for detection of temporal change. The temporal change is detected using the difference image between previous image and current one. The DCT is performed to emphasize the edge of the difference image. Finally, the phalanges are extracted by performing Snakes. The primary objective of this study is to segment phalanges by making temporal subtraction images. We apply our proposed technique to eight cases of CR images and satisfactory segmentation results are achieved. A new index that diagnoses the progress level of the disease of phalanges can be offered as a second opinion.

Automatic identification of bone erosions in rheumatoid arthritis from hand radiographs based on deep convolutional neural network

Although radiographic assessment of joint damage is essential in characterizing disease progression and prognosis in patients with rheumatoid arthritis (RA), it is often difficult even for trained radiologists to find radiographic changes on hand and foot radiographs because lesion changes are often subtle. This paper proposes a novel quantitative method for automatically detecting bone erosion on hand radiographs to assist radiologists. First, the proposed method performs with the crude segmentation of phalanges regions from hand radiograph and extracts the detailed phalanges regions by the multiscale gradient vector flow (MSGVF) Snakes method. Subsequently, the region of interest (ROI; 40 × 40 pixels) is automatically set on the contour line of the segmented phalanges by the MSVGF algorithm. Finally, these selected ROIs are identified by the presence or absence of bone erosion using a deep convolutional neural network classifier. This proposed method is applied to the hand radiographs of 30 cases with RA. The true-positive rate and the false-positive rate of the proposed method are 80.5% and 0.84%, respectively. The number of false-positive ROIs is 3.3 per case. We believe that the proposed method is useful for supporting radiologists in imaging diagnosis of RA.

Extraction of GGO Candidate Regions on Thoracic CT Images using SuperVoxel-Based Graph Cuts for Healthcare Systems

In this paper, we propose a method to reduce artifacts on temporal difference images by improving the conventional method using a non-rigid registration method for ground glass opacification (GGO), which is light in concentration and difficult to detect early. In this method, global matching, local matching, and 3D elastic matching are performed on the current image and past image, and an initial temporal difference image is generated. After that, we use an Iris filter, which is the gradient vector concentration degree filter, to determine the initial GGO candidate regions and perform segmentation using SuperVoxel and Graph Cuts in which a superpixel is extended to three dimensions for each region of interest. For each extracted region, a support vector machine (SVM) is used to reduce the over-segmentation. Finally, in the method that greatly reduces artifacts other than the remaining GGO candidate regions, Voxel Matching is applied to generate the final temporal difference image, emphasizing the GGO regions while reducing the artifact. The resulting ratio of artifacts to lung volume is 0.101 with an FWHM of 28.3, which is an improvement over the conventional method and shows the proposed method’s effectiveness.

Detection of lung carcinoma with predominant ground-glass opacity on CT using temporal subtraction method

PurposeTo evaluate the usefulness of the CT temporal subtraction (TS) method for the detection of the lung cancer with predominant ground-glass opacity (LC-pGGO).Materials and methodsTwenty-five pairs of CT and their TS images in patients with LC-pGGO (31 lesions) and 25 pairs of those in patients without nodules were used for an observer performance study. Eight radiologists participated and the statistical significance of differences with and without the CT-TS was assessed by JAFROC analysis.ResultsThe average figure-of-merit (FOM) values for all radiologists increased to a statistically significant degree, from 0.861 without CT-TS to 0.912 with CT-TS (p < .001). The average sensitivity for detecting the actionable lesions improved from 73.4 % to 85.9 % using CT-TS. The reading time with CT-TS was not significantly different from that without.ConclusionThe use of CT-TS improves the observer performance for the detection of LC-pGGO.Key Points• CT temporal subtraction can improve the detection accuracy of lung cancer.• Reading time with temporal subtraction is not different from that without.• CT temporal subtraction improves observer performance for ground-glass/subsolid nodule detection.