arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.09107eess.IVcs.AIcs.LG
收藏

利用全局二值掩码进行医学图像结构分割

Leveraging Global Binary Masks for Structure Segmentation in Medical Images

the University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心);Stanford University(斯坦福大学)

Mahdieh Kazemimoghadam, Zi Yang, Lin Ma, Mingli Chen, Weiguo Lu, Xuejun Gu

AI总结:

针对医学图像分割模型泛化性差、训练数据稀缺的问题,提出利用全局二值掩码编码解剖形状位置信息的框架,可提升小样本下分割精度,增强模型泛化性。

摘要:

用于医学图像分割的深度学习(DL)模型受输入图像强度变化的影响极大,且由于推理时主要利用像素强度信息而缺乏泛化能力。获取充足的训练数据是限制模型应用的另一项挑战。我们提出利用医学图像中器官解剖形状与位置信息的一致性,引入了一个通过全局二值掩码利用反复出现的解剖模式进行器官分割的框架。本研究探讨了两种场景:1)全局二值掩码作为U-Net模型的唯一输入,强制模型仅编码器官的位置与形状信息以实现分割/定位;2)全局二值掩码作为额外通道引入,充当位置/形状线索以缓解训练数据稀缺的问题。研究使用了脑部和心脏CT图像两个带真值标注的数据集,分别按26:10:10和12:3:5的比例划分为训练集、验证集和测试集。仅使用全局二值掩码训练时,脑部和心脏结构的Dice系数分别为0.77(0.06)和0.85(0.04),相对于真值质心的平均欧氏距离分别为3.12(1.43)mm和2.5(0.93)mm。结果表明,全局二值掩码编码了出人意料的丰富位置与形状信息。在小训练数据子集上,引入全局二值掩码的模型准确率显著高于仅使用CT图像训练的模型;在脑部和心脏数据集的1-8个训练样本场景下,性能分别提升了4.3-125.3%和1.3-48.1%。这些发现表明,利用全局二值掩码有助于构建泛化性更强的模型,并可弥补训练数据不足的问题。

英文摘要:

Deep learning (DL) models for medical image segmentation are highly influenced by intensity variations of input images and lack generalization due to primarily utilizing pixels' intensity information for inference. Acquiring sufficient training data is another challenge limiting models' applications. We proposed to leverage the consistency of organs' anatomical shape and position information in medical images. We introduced a framework leveraging recurring anatomical patterns through global binary masks for organ segmentation. Two scenarios were studied.1) Global binary masks were the only model's (i.e. U-Net) input, forcing exclusively encoding organs' position and shape information for segmentation/localization.2) Global binary masks were incorporated as an additional channel functioning as position/shape clues to mitigate training data scarcity. Two datasets of the brain and heart CT images with their ground-truth were split into (26:10:10) and (12:3:5) for training, validation, and test respectively. Training exclusively on global binary masks led to Dice scores of 0.77(0.06) and 0.85(0.04), with the average Euclidian distance of 3.12(1.43)mm and 2.5(0.93)mm relative to the center of mass of the ground truth for the brain and heart structures respectively. The outcomes indicate that a surprising degree of position and shape information is encoded through global binary masks. Incorporating global binary masks led to significantly higher accuracy relative to the model trained on only CT images in small subsets of training data; the performance improved by 4.3-125.3% and 1.3-48.1% for 1-8 training cases of the brain and heart datasets respectively. The findings imply the advantages of utilizing global binary masks for building generalizable models and to compensate for training data scarcity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑