CT of normal skulls in three categories (Female, Male, Mixed)

The data contains 300 skulls. The data is divided into three groups with 100 scans in three categories Females, Males, and Mix. The purpose of the project was to generate a machine learning algorithm to be able reconstruct missing parts of the skull for cranioplasty. Each scan was verified to ensure normal skull shape. To ensure data privacy the faces have been deblurred with an in-house developed algorithm.

本数据集共收录300例颅骨扫描样本，按类别分为女性组、男性组及混合组三类，每类各包含100份扫描样本。本项目旨在研发机器学习算法，以实现颅骨成形术（cranioplasty）中颅骨缺损区域的重建。每份扫描样本均经过核验，以确保其颅骨形态正常。为保障数据隐私，已通过自研算法对扫描图像中的面部区域实施去模糊处理。