基于深度学习的腹内脂肪分割算法DiMax

利用Active contour 算法识别腹部脂肪像素点；对识别出的腹部脂肪像素点采用多尺度块作为特征输入，通过新的深度神经网络算法自动学习分层的抽象本质特征，将这些特征输入分类算法得到初步分割结果；然后将初步分割结果转到极坐标中，利用 SAT 在极坐标下成为图像底部的特征，得到腹部脂肪分割图；最后按照梯度高低对腹部脂肪分割图中各类型脂肪比例进行计算，并通过体绘制技术直观显示计算结果。

Identify abdominal fat pixels using the Active Contour algorithm. First, take multi-scale patches of the identified abdominal fat pixels as feature inputs, and automatically learn hierarchical abstract intrinsic features via a novel deep neural network algorithm. Feed these features into a classification algorithm to obtain preliminary segmentation results. Next, transform the preliminary segmentation results into the polar coordinate system, and utilize the characteristic that SAT appears as the feature at the bottom of the image under polar coordinates to generate the abdominal fat segmentation map. Finally, calculate the proportion of each type of fat in the abdominal fat segmentation map based on gradient magnitudes, and visually display the calculation results through volume rendering technology.

搜集汇总

背景与挑战

背景概述

该数据集提供上海轨道交通站点基于联通度指标的客流分布排行，每日更新，覆盖全上海交通站点，适用于城市交通规划和治理。