Texture filtering based unsupervised registration methods and its application in liver computed tomography images / 生物医学工程学杂志

Image registration is of great clinical importance in computer aided diagnosis and surgical planning of liver diseases. Deep learning-based registration methods endow liver computed tomography (CT) image registration with characteristics of real-time and high accuracy. However, existing methods in registering images with large displacement and deformation are faced with the challenge of the texture information variation of the registered image, resulting in subsequent erroneous image processing and clinical diagnosis. To this end, a novel unsupervised registration method based on the texture filtering is proposed in this paper to realize liver CT image registration. Firstly, the texture filtering algorithm based on L0 gradient minimization eliminates the texture information of liver surface in CT images, so that the registration process can only refer to the spatial structure information of two images for registration, thus solving the problem of texture variation. Then, we adopt the cascaded network to register images with large displacement and large deformation, and progressively align the fixed image with the moving one in the spatial structure. In addition, a new registration metric, the histogram correlation coefficient, is proposed to measure the degree of texture variation after registration. Experimental results show that our proposed method achieves high registration accuracy, effectively solves the problem of texture variation in the cascaded network, and improves the registration performance in terms of spatial structure correspondence and anti-folding capability. Therefore, our method helps to improve the performance of medical image registration, and make the registration safely and reliably applied in the computer-aided diagnosis and surgical planning of liver diseases.

An automatic pulmonary nodules detection algorithm with multi-scale information fusion / 生物医学工程学杂志

Lung nodules are the main manifestation of early lung cancer. So accurate detection of lung nodules is of great significance for early diagnosis and treatment of lung cancer. However, the rapid and accurate detection of pulmonary nodules is a challenging task due to the complex background, large detection range of pulmonary computed tomography (CT) images and the different sizes and shapes of pulmonary nodules. Therefore, this paper proposes a multi-scale feature fusion algorithm for the automatic detection of pulmonary nodules to achieve accurate detection of pulmonary nodules. Firstly, a three-layer modular lung nodule detection model was designed on the deep convolutional network (VGG16) for large-scale image recognition. The first-tier module of the network is used to extract the features of pulmonary nodules in CT images and roughly estimate the location of pulmonary nodules. Then the second-tier module of the network is used to fuse multi-scale image features to further enhance the details of pulmonary nodules. The third-tier module of the network was fused to analyze the features of the first-tier and the second-tier module of the network, and the candidate box of pulmonary nodules in multi-scale was obtained. Finally, the candidate box of pulmonary nodules under multi-scale was analyzed with the method of non-maximum suppression, and the final location of pulmonary nodules was obtained. The algorithm is validated by the data of pulmonary nodules on LIDC-IDRI common data set. The average detection accuracy is 90.9%.

Transmigration of the Mandibular Canine: A Report of Two Rare Cases.

When the tooth, instead of erupting in its normal position, remains impacted and crosses midline and is seen on the opposite side of the jaw, it is termed as Transmigration; e.g., right side tooth is seen on the left side and vice-versa. This phenomenon occurs without any pathology intervening cause. Canines are commonly seen unerupted and remain impacted, but rarely seen crossing the midline and migrating to the opposite side. They are usually symptomless. Here, we present two such rare cases of transmigration of the mandibular canine, one from the right side to the left side and appearing piercing the lower border of the mandible and producing a hard bulge on the left side of the lower jaw, but without any pain. The other case is of transmigration of mandibular left canine toward the right side well below the inferior alveolar canal beyond mental foramen facing toward posterior region of the mandible and causing pain symptoms in the jaw due to its close proximity to inferior alveolar canal. It is very essential to have panoramic radiograph to detect such abnormalities at an early stage to plan treatment and avoid future complications. Cone beam computed tomography images also play an important role.

Serially Sectioned Images of the Whole Body - Sixth Report: Browsing Software of the Serially Sectioned Images for Learning Sectional Anatomy / 대한해부학회지

Sectional anatomy is the course to learn anatomical structures on the sectional planes of cadaver. The purpose of this research is to make browsing software of the serially sectioned images, which is useful not only to learn sectional anatomy but also to learn magnetic resonance (MR) images and computed tomography (CT) images. One-thousand seven-hundred two sets of corresponding anatomical, MR, CT, and segmented images (intervals 1 mm) were selected from the serially sectioned images (horizontal direction) of a Korean male cadaver's whole body. We composed browsing software (file size 377 MBytes) of the images, which involved the following functions: The anatomical, MR, CT, and segmented images, which were always corresponding, were displayed; one of four images could be enlarged; images of interesting levels could be displayed in a real time conveniently either using software buttons, scroll bar, image number or using computer keyboard; names of the 13 anatomical structures, which were already segmented, could be displayed. By using this software, medical students and doctors can figure out stereoscopic anatomical structures from the anatomical images to review anatomy; they can compare MR and CT images with corresponding anatomical images to easily recognize anatomical structures in the MR and CT images.

Study some clinical characteristics, computed tomography images and the treated outcome of chronic subdural hematoma

A series of 31 patients chronic subdural hematoma (CSH) were treated at Thai nguyen general hospital from 4/2002 to 4/2004, the range of age were 41 years to 77 years, in which the group of 51- 60 years was 38.7%. There were 20 cases (64.5%) relative to prior injury. The duration from injury to admitted hospital 5-8 weeks was 51.6%. There were 1 case presented after injury 12 weeks. The clinical: group 1:15 (48.4%); group 2: 14 (45.2%). CT scanner was important in the diagnosis. The results of treatment: good outcome 83.8%, mortality 3.3%.