AI-医学影像分割方法与流程

AI医学影像分割方法与流程–基于低场磁共振影像的病灶识别

– 作者:coder_fang AI框架：PaddleSeg

1. 数据准备，使用MedicalLabelMe进行dcm文件标注，产生同名.json文件。
2. 编写程序生成训练集图片，包括掩码图。
3. 代码如下: def doCvt(labelDir): outdir=labelDir+"\output"; if os.path.exists(outdir): shutil.rmtree(outdir) os.makedirs(outdir+"\images") #原始图 os.makedirs(outdir + “\masks1”) #可视掩码图,只包含0,255 os.makedirs(outdir + “\masks2”) #训练掩码图，只包含0,1 start=0 files=glob.glob(labelDir+’*.json’) for f in files: fname=os.path.basename(f) jsondata = json.load(open(labelDir+"\"+ fname, encoding=“utf-8”)) imagePath = os.path.join(labelDir, jsondata.get(“image_path”)) ds = pydicom.read_file(imagePath) # 读取.dcm文件 img = ds.pixel_array # 提取图像信息 img = (img * (255/img.max())).astype(np.uint8) pathout ="{}\images\{:05d}.png".format(outdir,start) result=cv2.bilateralFilter(img,11,64,128) #对低场图片进行去噪声 cv2.imwrite(pathout, result) label_name_to_value = {’background’: 0,‘H’:1} for shape in jsondata.get(“frames”)[0].get(“shapes”): label_name = shape[’label’] if label_name in label_name_to_value: label_value = label_name_to_value[label_name] else: label_value = len(label_name_to_value) label_name_to_value[label_name] = label_value mask = np.zeros(img.shape ,dtype=np.uint8) # 假设图片是灰度图，调整dtype为np.uint8

遍历所有形状并绘制到掩码上

for shape in jsondata.get(“frames”)[0].get(“shapes”):

获取形状的类型和坐标点

shape_type = shape[‘shape_type’] points = shape[‘points’] if shape_type == ‘polygon’:

绘制多边形掩码

cv2.fillPoly(mask, [np.array(points).reshape((-1, 1, 2)).astype(np.int32)], 1) elif shape_type == ‘rectangle’:

绘制矩形掩码（转换为多边形）

x, y, w, h = points pts = np.array([[x, y], [x + w, y], [x + w, y + h], [x, y + h]]) cv2.fillPoly(mask, [pts.reshape((-1, 1, 2)).astype(np.int32)], 1)

可以根据需要添加其他形状的处理方式，如圆形等。

保存可视掩码图像（例如PNG格式）

pathout = “{}\masks1\{:05d}.png”.format(outdir, start) cv2.imwrite(pathout, (mask * 255).astype(np.uint8))

保存训练掩码图像（例如PNG格式）

pathout = “{}\masks2\{:05d}.png”.format(outdir, start) cv2.imwrite(pathout, mask.astype(np.uint8)) lbl_viz = imgviz.label2rgb( mask, img ) start+=1 效果如图: 4. 使用PaddlePaddle 2.6.2版本，单独下载PaddleSeg2.8.1版本进行编译，2.8以前版本会有问题。 5. 生成训练数据和验证数据集对应列表： def create_list(data_path): image_path = os.path.join(data_path, ‘images’) label_path = os.path.join(data_path, ‘masks2’) data_names = os.listdir(image_path) random.shuffle(data_names) # 打乱数据 with open(os.path.join(data_path, ’train_list.txt’), ‘w’) as tf: with open(os.path.join(data_path, ‘val_list.txt’), ‘w’) as vf: for idx, data_name in enumerate(data_names): img = os.path.join(‘images’, data_name) lab = os.path.join(‘masks2’, data_name) if idx % 9 == 0: # 90%的作为训练集 vf.write(img + ’ ’ + lab + ‘\n’) else: tf.write(img + ’ ’ + lab + ‘\n’) print(‘数据列表生成完成’) data_path = ‘work/output’ create_list(data_path) # 生成数据列表 6. 基于列表生成数据集并进行验证:

构建训练集

train_transforms = [ T.RandomHorizontalFlip(),#水平翻转 T.RandomVerticalFlip(), T.RandomNoise(), T.Resize(), T.Normalize() # 归一化 ] train_dataset = Dataset( transforms=train_transforms, dataset_root=‘work/output’, num_classes=2, img_channels=1, mode=‘train’, train_path=‘work/output/train_list.txt’, separator=’ ‘, )

构建验证集

val_transforms = [ T.Resize(), T.Normalize() ] val_dataset = Dataset( transforms=val_transforms, dataset_root=‘work/output’, num_classes=2, img_channels=1, mode=‘val’, val_path=‘work/output/val_list.txt’, separator=’ ‘, ) #随机抽取训练集数据进行可视化验证 import matplotlib.pyplot as plt import numpy as np plt.figure(figsize=(10,16)) for i in range(1,6,2): ,img,label,= train_dataset[random.randint(0,100)].items() print(img[1].shape) img = np.transpose(img[1], (1,2,0)) img = img*0.5 + 0.5 plt.subplot(3,2,i),plt.imshow(img,‘gray’),plt.title(‘img’),plt.xticks([]),plt.yticks([]) plt.subplot(3,2,i+1),plt.imshow(label[1],‘gray’),plt.title(’label’),plt.xticks([]),plt.yticks([]) plt.show 7. 构建训练网络并训练: #可以尝试PaddelSeg中多种分割模型，这里目前测试的BiSeNetV2均衡了效果和训练验证速度，表现还可以 model = BiSeNetV2(num_classes=2,#二分类分割 in_channels=1,#单通道 lambd=0.25, align_corners=False, pretrained=‘OutDir/best_model/model.pdparams’ ) base_lr = 0.0005 lr = paddle.optimizer.lr.PolynomialDecay(learning_rate=base_lr, decay_steps=1500, verbose=False) optimizer = paddle.optimizer.Momentum(lr, parameters=model.parameters(), momentum=0.9, weight_decay=4.0e- losses = {} losses[’types’] = [CrossEntropyLoss()] *5 losses[‘coef’] = [0.8,0.2]*5 from paddleseg.core import train train( model=model, train_dataset=train_dataset, val_dataset=val_dataset, optimizer=optimizer, save_dir=‘OutDir’, iters=3000, batch_size=8, save_interval=200, log_iters=20, num_workers=0, losses=losses, use_vdl=True)#开始训练，这里最好使用GPU训练 8. 验证数据，并将预测结果融合到原始图中 #测试结果 transforms = T.Compose([ T.Resize(target_size=(512, 512)), T.Normalize() ]) #显示图片时调整合适的窗宽窗位 def wwwl(im,window_width,window_level):

计算最大值和最小值

min_val = window_level - window_width / 2 max_val = window_level + window_width / 2 #im = ((im - min_val) / (max_val - min_val)) * 255 im=np.clip(im,min_val,max_val).astype(np.uint8) return im #加载模型 model = BiSeNetV2(num_classes=2, in_channels=1,) model_path = ‘OutDir/best_model/model.pdparams’ para_state_dict = paddle.load(model_path) model.set_dict(para_state_dict) import matplotlib.pyplot as plt import numpy as np #testimg里放置一些病灶图片，尽量不是训练集里数据 files = glob.glob(‘work/testimg/.png’) row=(int)(len(files)) plt.figure(figsize=(16,row8)) i=1; for f in files: #读取数据 im = cv2.imread(f, 0).astype(‘float32’) im=F.normalize(im,0.5,0.5) h,w = im.shape data = np.expand_dims(im,axis=0).repeat(1,axis=0) data = data[np.newaxis, …] data = paddle.to_tensor(data) predata=model(data) output = predata[0].numpy() output = np.argmax(output,axis=1) output = np.squeeze(output) #输入模型预测的时候缩放到(512,512),现在要缩放到原始数据的大小 output = cv2.resize(output, (h, w), interpolation=cv2.INTER_NEAREST) output = output.astype(np.uint8)128 #归到255 im=(im0.5+0.5)255 im=wwwl(im,128,60) max_val = np.max(im) im=im(255/max_val) imgori=cv2.cvtColor(im.astype(np.uint8), cv2.COLOR_GRAY2BGR); imgpre=cv2.cvtColor(output, cv2.COLOR_GRAY2BGR); imgpre[:,:,1]= 0 imgpre[:,:,2]= 0 mask_img=cv2.addWeighted(imgpre, 0.2, imgori, 0.5, 0) plt.subplot(row,2,i),plt.imshow(mask_img,‘gray’),plt.title(‘img’),plt.xticks([]),plt.yticks([]) i+=1 plt.show 9. 基于上述模型持续优化并训练，如需模型工程化，可使用paddleseg 中的export.py ,将模型进行转换，转换后可将其集成到python或c++工程使用，转换命令如下： python export.py –model_path OutDir/best_model/model.pdparams –input_shape 1 1 512 512 –save_dir OutDir/Saved –config work/config.yml 完！