1 简介
医学影像分割的基本目标是将图像分割成不同的解剖组织，从而可以从背景中提取出感兴趣区域。因为图像的低分辨率和弱对比度，实现医学影像分割是一件具有挑战的任务。而且，这个任务由于噪声和伪阴影变得更加困难，这些干扰项可能是因器材限制、重建算法和患者移动等原因造成的。目前还没有通用的医学图像分割算法，算法的优点和缺点经常根据所研究的问题而变化。将分割概念具体到颅内出血 CT 图像上，就是将颅腔中的出血病灶区别于其他组织从图像中分割出来。图像分割有两大类方法 ：一种是像素分类，另一种为追踪变化的边界。第一类分割方法假设在每个子类中像素具有几乎恒定的灰度值，这对于具有相似生理特性的解剖结构来说是合理的。这类方法可以同时检测出多个感兴趣的子类，但是该方法很容易受到环境噪声和图像不均匀性的影响。相比之下，追踪变化边界的分割方法要利用图像灰度信息和空间信息。因此，该子类必须是均匀的并且包围在一个特定的变化边界中。当应用于医学图像分割时，由于固有的噪声和伪阴影，它们都不具有普遍的适用性。
本文针对人脑CT图像的出血病灶区域,提出了一种改进的模糊C-均值(Fuzzy C-Means,FCM)算法进行颅脑内出血病灶的分割.首先对颅脑CT图像进行预分割,通过左右扫描算法和中值滤波算法将颅内结构从源CT图像中提取出来;然后对预分割而得到的颅内结构,利用在目标函数和隶属度函数中分别添加空间信息的改进FCM聚类算法进行出血病灶提取.通过对CT颅脑图像和添加椒盐噪声的CT颅脑图像进行病灶分割,结果显示本文算法对噪声不敏感,可以准确分割出出血病灶.
2 部分代码
function varargout = CT_image_KFCM(varargin)
% CT_IMAGE_KFCM MATLAB code for CT_image_KFCM.fig
% CT_IMAGE_KFCM, by itself, creates a new CT_IMAGE_KFCM or raises the existing
% singleton*.
%
% H = CT_IMAGE_KFCM returns the handle to a new CT_IMAGE_KFCM or the handle to
% the existing singleton*.
%
% CT_IMAGE_KFCM('CALLBACK',hObject,eventData,handles,...) calls the local
% function named CALLBACK in CT_IMAGE_KFCM.M with the given input arguments.
%
% CT_IMAGE_KFCM('Property','Value',...) creates a new CT_IMAGE_KFCM or raises the
% existing singleton*. Starting from the left, property value pairs are
% applied to the GUI before CT_image_KFCM_OpeningFcn gets called. An
% unrecognized property name or invalid value makes property application
% stop. All inputs are passed to CT_image_KFCM_OpeningFcn via varargin.
%
% *See GUI Options on GUIDE's Tools menu. Choose "GUI allows only one
% instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES
% Edit the above text to modify the response to help CT_image_KFCM
% Last Modified by GUIDE v2.5 14-Apr-2020 22:56:58
% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name', mfilename, ...
'gui_Singleton', gui_Singleton, ...
'gui_OpeningFcn', @CT_image_KFCM_OpeningFcn, ...
'gui_OutputFcn', @CT_image_KFCM_OutputFcn, ...
'gui_LayoutFcn', [] , ...
'gui_Callback', []);
if nargin && ischar(varargin{1})
gui_State.gui_Callback = str2func(varargin{1});
end
if nargout
[varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT
% --- Executes just before CT_image_KFCM is made visible.
function CT_image_KFCM_OpeningFcn(hObject, eventdata, handles, varargin)
% This function has no output args, see OutputFcn.
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% varargin command line arguments to CT_image_KFCM (see VARARGIN)
% Choose default command line output for CT_image_KFCM
handles.output = hObject;
% Update handles structure
guidata(hObject, handles);
% UIWAIT makes CT_image_KFCM wait for user response (see UIRESUME)
% uiwait(handles.figure1);
% --- Outputs from this function are returned to the command line.
function varargout = CT_image_KFCM_OutputFcn(hObject, eventdata, handles)
% varargout cell array for returning output args (see VARARGOUT);
% hObject handle to figure
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% Get default command line output from handles structure
varargout{1} = handles.output;
% --- Executes on button press in pushbutton1.
function pushbutton1_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton1 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global I
[filename, pathname]= ...
uigetfile({'*.*';'*.bmp';'*.tif';'*.png';'*.jpg'},'select picture');
str= [pathname filename];
I= imread(str);
axes(handles.axes1);
imshow(I);
title('原图');
% --- Executes on button press in pushbutton2.
function pushbutton2_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton2 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
% --- Executes on button press in pushbutton3.
function pushbutton3_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton3 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global I
cluster_n =4; %聚类数目
m=2; %隶属度权重参数m
iter_max=150; %最大迭代次数
e=1e-5; %停止阈值条件
delta=10; %高斯核的delta值 5~15
Vinit=KFCM_init(I,cluster_n); %聚类中心初始化
I=KFCM_Img(I,Vinit,cluster_n,m,iter_max,e,delta);
axes(handles.axes3);
imshow(I,[]);
% --- Executes on button press in pushbutton4.
function pushbutton4_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton4 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global I
axes(handles.axes4);
imshow(I==2);
% --- Executes on button press in pushbutton5.
function pushbutton5_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton5 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global I
axes(handles.axes5);
imshow(I==3);
% --- Executes on button press in pushbutton6.
function pushbutton6_Callback(hObject, eventdata, handles)
% hObject handle to pushbutton6 (see GCBO)
% eventdata reserved - to be defined in a future version of MATLAB
% handles structure with handles and user data (see GUIDATA)
global I
axes(handles.axes6);
imshow(I==4);
3 仿真结果
4 参考文献
[1]姜春雨, 刘景鑫, 钟慧湘,等. 基于改进的FCM模糊聚类的颅内出血CT图像分割研究[J]. 中国医疗设备, 2018, 33(6):5.
**部分理论引用网络文献，若有侵权联系博主删除。**
5 MATLAB代码与数据下载地址
见博客主页
