Publications by authors named "Tsutomu Ubagai"
We herein report a case of orbital metastasis from the breast cancer in a 58-year-old woman presenting with visual disturbance and bilateral periorbital swelling. She had undergone radical mastectomy for right breast cancer 9 years previously and been receiving hormone therapy for bone metastasis of breast cancer for the past 4 years. Computed tomography and magnetic resonance imaging revealed an ill-defined mass in the bilateral orbits, whereas an excisional biopsy confirmed metastasis of invasive lobular carcinoma (ILC) of the breast.
View Article and Find Full Text PDF[Improvement of overall performance for lung nodule detection in chest CT images].
Nihon Hoshasen Gijutsu Gakkai Zasshi
March 2008
Article Synopsis
- Developed an automated system to detect lung nodules in 3D CT images, improving on previous methods that utilized linear discriminant analysis and 53 image features.
- Enhanced false-positive reduction by implementing edge image and radial image analysis, leading to better overall performance in nodule detection.
- Evaluated the new system on 69 cases from four hospitals, achieving an average of 5.2 false positives per case with a sensitivity rate of 95.8%, aiding early lung cancer detection.
We have developed an automated computerized method for the detection of lung nodules in three-dimensional (3D) computed tomography (CT) images obtained by helical CT. In this scheme, a lung segmentation technique for the determination of the nodule search area is performed based on a gray-level thresholding technique. To enhance lung nodules, we employed the 3D cross-correlation method by using a 3D Gaussian template with zero-surrounding as a model of lung nodule.
View Article and Find Full Text PDF