We present large scale facial model (LSFM)-a 3D Morphable Model (3DMM) automatically constructed from 9663 distinct facial identities. To the best of our knowledge LSFM is the largest-scale Morphable Model ever constructed, containing statistical information from a huge variety of the human population. To build such a large model we introduce a novel fully automated and robust Morphable Model construction pipeline, informed by an evaluation of state-of-the-art dense correspondence techniques. The dataset that LSFM is trained on includes rich demographic information about each subject, allowing for the construction of not only a global 3DMM model but also models tailored for specific age, gender or ethnicity groups. We utilize the proposed model to perform age classification from 3D shape alone and to reconstruct noisy out-of-sample data in the low-dimensional model space. Furthermore, we perform a systematic analysis of the constructed 3DMM models that showcases their quality and descriptive power. reveal that the proposed 3DMM achieves state-of-the-art results, outperforming existing models by a large margin. Finally, for the benefit of the research community, we make publicly available the source code of the proposed automatic 3DMM construction pipeline, as well as the constructed global 3DMM and a variety of bespoke models tailored by age, gender and ethnicity.

BACKGROUND Sentinel lymph node (SLN) biopsy originally was described as a means of identifying lymph node metastases in malignant melanoma and breast carcinoma. The use of SLN biopsy in patients with oral and oropharyngeal squamous cell carcinoma and clinically N0 necks was investigated to determine whether the pathology of the SLN reflected that of the neck. METHODS Patients undergoing elective neck dissections for head and neck squamous cell carcinoma accessible to injection were enrolled into our study. Sentinel lymph node biopsy was performed after blue dye and radiocolloid injection. Preoperative lymphoscintigraphy and the perioperative use of a gamma probe identified radioactive SLNs; visualization of blue stained lymphatics identified blue SLNs. A neck dissection completed the surgical procedure, and the pathology of the SLN was compared with that of the remaining neck dissection. RESULTS Sentinel lymph node biopsy was performed on 40 cases with clinically N0 necks. Twenty were pathologically clear of tumor and 20 contained subclinical metastases. SLNs were found in 17 necks with pathologic disease and contained metastases in 16. The sentinel lymph node was the only lymph node containing tumor in 12 of 16. CONCLUSIONS The SLN, in head and neck carcinomas accessible to injection without anesthesia, is an accurate reflector of the status of the regional lymph nodes, when found in patients with early tumors. Sentinel lymph nodes may be found in clinically unpredictable sites, and SLN biopsy may aid in identifying the clinically N0 patient with early lymph node disease. If SLNs cannot be located in the neck, an elective lymph node dissection should be considered. Cancer 2001;91:2077–83. © 2001 American Cancer Society.

No abstract

No abstract

No abstract