Swallowing phases are defined on the basis of the positions and moving directions of bodies of hyoid bones (BHBs) in videofluorography (VF). In this report, we propose an automatic tracking method of BHBs by use of Support Vector Machine (SVM). First, the movable prediction areas of BHBs are determined by applying discriminant analysis, morphology operations, and Random Sample Consensus techniques to frame images in VF. Then, a patchbased SVM is applied to the movable prediction areas to extract the candidate regions of BHBs. In general, several candidate regions are extracted in each frame. The false positives are eliminated by considering the continuity of the candidate regions between frame images. The proposed method was applied to actual twenty cases, and the tracking accuracy was evaluated on the basis of (1) distances between the extracted and truth regions, and (2) the correlation coefficients of x and y coordinates of these regions. The mean distance was approximately 2.9 mm, and the correlation coefficients were 0.906 and 0.958 in the x and y coordinates, respectively.

Recently, endovascular thrombectomy for acute ischemic stroke is gaining increasing attention. Identifying hypoattenuation of early ischemic changes on computerized tomography (CT) images is crucial for diagnosis. However, it is difficult to identify early ischemic changes with certainty. We present an atlas-based computerized method using a convolutional neural network (CNN) to identify early ischemic changes in the lentiform nucleus. The algorithm for this method consisted of anatomic standardization, setting of regions, creation of input images for classification, training on the CNN and classification of early ischemic changes. The method was applied to 50 patients with early ischemic change of acute stroke (<4.5 h) in the lentiform nucleus and 28 normal controls. As a result, we obtained a sensitivity of 90.0%, a specificity of 100％ and an accuracy of 93.6% for identifying early ischemic changes in the lentiform nucleus. These results indicate that this new method has the potential to accurately identify early ischemic changes in the lentiform nucleus in patients with acute ischemic stroke on CT images.

We have ever proposed pulmonary nodule clarity method in chest radiographs by controlling the pulmonary vessel (or its en face view) which is frequently extracted as false-positives. However, insufficient suppression of the clavicle, rib and peripheral pulmonary vessel shadows made difficult to detect true lung nodules. In this study, density alteration of the clavicle, rib and peripheral pulmonary vessel shadows was defined as back ground noise. We propose a new method to control back ground noise and further clarify pulmonary nodules by applying wavelet analysis and error diffusion method to our previous proposed pulmonary nodule clarity method. A radiologist evaluated the new images obtained by the proposed technique in a point of suppression of the back ground noise and visibility of the pulmonary nodules. In this evaluation of 117 images excluding "extremely subtle" and "obvious" from 154 images with nodules in the JSRT database, the back ground noise was sufficiently suppressed in 80.2％. The visibility of the pulmonary nodules was well improved in 88.0％, comparing with the previous pulmonary nodule clarity images. It became easy to find true lung nodules by suppression of the back ground noise. The proposed method is expected to be useful for detection of lung cancer nodules.

Autosomal dominant polycystic kidney disease (ADPKD) is a disease in which multiple cysts are continuously developed and enlarged in the renal parenchyma over the lifetime. It is important and yet challenging to provide a useful index to predict a prognostic pattern for renal dysfunction at the early stage of the disease. This study aimed to propose a 3D skeletonization algorithm so as to extract the morphological features of the 3D shape of the renal cysts. Ten sets of T2-weighted abdominal MR images were processed and the cumulative relative frequency of the extracted skeletonsʼ length was compared with a conventional renal functional index: eGFR. The skeletons could quantify the distribution of the size of renal cysts, and the relative frequency of short skeleton (≤3 voxels) corresponded to the eGFR. The proposed method would be valuable to assess a progression pattern in the growth and occurrence of the renal cysts in patients with ADPKD.

There are 700,000 of Rheumatoid Arthritis (RA) patients in Japan, and the number of patients is increased by 30,000 annually. Early treatment is effective to improve patientʼs prognosis. However, the appropriate treatment is required according to the progress of Rheumatoid Arthritis. The modified Total Sharp (mTS) score evaluates the progression of RA on the hand or foot X-ray. The mTS score evaluation is required several times a year for the effective treatment of RA. The mTS score assessment needs very long time. The automatic mTS score calculation system is required. This paper proposes the finger joint detection method and the mTS score calculation method using Support Vector Machine. Experimental results on 90 RA patientʼs X-ray images showed that the proposed method detects finger joints with accuracy of 81.4 (％), and estimated the erosion and JSN score with accuracy of 56.1, 60.4 (％), respectively.