• Radiation Oncology Journal
• /
• v.32 no.3
• /
• pp.125-131
• /
• 2014

Purpose: We reviewed treatment outcomes and prognostic factors for patients with salivary ductal carcinoma (SDC) treated with surgery and postoperative radiotherapy from 2005 to 2012. Materials and Methods: A total of 16 patients were identified and 15 eligible patients were included in analysis. Median age was 61 years (range, 40 to 71 years) and 12 patients (80%) were men. Twelve patients (80%) had a tumor in the parotid gland, 9 (60%) had T3 or T4 disease, and 9 (60%) had positive nodal disease. All patients underwent surgery and postoperative radiotherapy. Postoperative radiotherapy was delivered using 3-dimensional conformal radiotherapy or intensity-modulated radiotherapy. Locoregional failure-free survival (LRFFS), distant failure-free survival (DFFS), progression-free survival (PFS), and overall survival (OS) were calculated using the Kaplan-Meier method. Differences in survival based on risk factors were tested using a log-rank test. Results: Median total radiotherapy dose was 60 Gy (range, 52.5 to 63.6 Gy). Four patients received concurrent weekly chemotherapy with cisplatin. Among 10 patients who underwent surgery with neck dissection, 7 received modified radical neck dissection. With a median follow-up time of 38 months (range, 24 to 105 months), 4-year rates were 86% for LRFFS, 51% for DFFS, 46% for PFS, and 93% for OS. Local failure was observed in 2 patients (13%), and distant failure was observed in 7 (47%). The lung was the most common involved site of distant metastasis. Conclusion: Surgery and postoperative radiotherapy in SDC patients resulted in good local control, but high distant metastasis remained a major challenge.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.299-302
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of$.$10 persons show that the proposed method yields high recognition rates.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.408-410
• /
• 2009

We present an efficient and robust measurement model for visual tracking. This approach builds on and extends work on subspace representations of measurement model. Subspace-based tracking algorithms have been introduced to visual tracking literature for a decade and show considerable tracking performance due to its robustness in matching. However the measures used in their measurement models are often restricted to few approaches. We propose a novel measure of object matching using Angle In Feature Space, which aims to improve the discriminability of matching in subspace. Therefore, our tracking algorithm can distinguish target from similar background clutters which often cause erroneous drift by conventional Distance From Feature Space measure. Experiments demonstrate the effectiveness of the proposed tracking algorithm under severe cluttered background.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.822-826
• /
• 2001

The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of 10 persons show that the proposed method yields high recognition rates.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.608-611
• /
• 2004

In this paper, we propose a robust face recognition technique based on the principle of eigenfaces. The traditional eigenface recognition (EFR) method works quite well when the input test patterns are cropped fares. However, when confronted with recognizing faces embedded in arbitrary backgrounds, the EFR method fails to discriminate effectively between faces and background patterns, giving rise to many false alarms. In order to improve robustness in the presence of background, we argue in favor of loaming the distribution of background patterns. A background space is constructed from the background patterns and this space together with the face space is used for recognizing faces. The proposed method outperforms the traditional EFR technique and gives very good results even on complicated scenes.