Auto-initialized cascaded level set (AI-CALS) segmentation of bladder lesions on multidetector row CT urography.
Auto-initialized cascaded level set (AI-CALS) segmentation of bladder lesions on multidetector row CT urography.
复制标题
DOI：
10.1016/j.acra.2012.08.012
复制
发表时间：
2013-02
影响因子：
4.8
通讯作者：
Zhou, Chuan
中科院分区：
文献类型：
--
作者：
Hadjiiski, Lubomir;Chan, Heang-Ping;Caoili, Elaine M.;Cohan, Richard H.;Wei, Jun;Zhou, Chuan
目的：开发一种在CT尿路造影(CTU)扫描上分割膀胱癌的计算机系统，以检测和定性膀胱癌。我们开发了一种自动初始化级联水平集(AI-CALS)方法来执行膀胱病变分割。根据初步数据集对分割性能进行评估，初步数据集包括28例获得IRB批准的患者的28次CTU扫描。膀胱部分填充静脉(IV)造影剂。病变全部或部分位于膀胱增强区或非增强区。一位经验丰富的腹部放射科医生用包围盒标记了28个病变(14个恶性病变和14个良性病变)，作为自动分割系统的输入，并对每个病变进行了难度评级(DR)，从1到5(5=最微妙)。将自动分割的等高线与放射科医生手动绘制的3D等高线进行比较。我们使用了三种性能指标进行比较。此外，由两名经验丰富的放射科医生组成的专家小组对自动分割的质量进行了评估，他们对轮廓的质量进行了从1到10(10=“优秀”)的评分。平均体积交叉率为67.2±16.9%，平均绝对体积误差为27.3±26.9%，平均测距为2.89±1.69 mm。在28个细分中，18个被给予8级或以上的质量评级。平均评分为7.9±1.5分。难度1级、2级、3级、4级的病变平均质量分级分别为8.8±0.9、7.9±1.8、7.4±0.9、6.6±1.5。我们的初步研究证明了在CTU扫描中使用3D水平集方法分割膀胱病变的可行性。
To develop a computerized system for segmentation of bladder lesions on CT urography (CTU) scans for detection and characterization of bladder cancer. We have developed an auto-initialized cascaded level set (AI-CALS) method to perform bladder lesion segmentation. The segmentation performance was evaluated on a preliminary data set including 28 CTU scans from 28 patients collected retrospectively with IRB approval. The bladders were partially filled with intravenous (IV) contrast material. The lesions were located fully or partially within the contrast-enhanced area or in the non-contrast-enhanced area of the bladder. An experienced abdominal radiologist marked 28 lesions (14 malignant and 14 benign) with bounding boxes that served as input to the automated segmentation system and assigned a difficulty rating (DR) on a scale of 1 to 5 (5=most subtle) to each lesion. The contours from automated segmentation were compared to 3D contours manually drawn by the radiologist. Three performance metric measures were used for comparison. In addition, the automated segmentation quality was assessed by an expert panel of two experienced radiologists, who provided quality ratings of the contours on a scale from 1 to 10 (10 = “excellent”). The average volume intersection ratio, the average absolute volume error, and the average distance measure were 67.2±16.9%, 27.3±26.9%, and 2.89±1.69 mm, respectively. Of the 28 segmentations, 18 were given quality ratings of 8 or above. The average rating was 7.9±1.5. The average quality ratings for lesions with difficulty ratings of 1, 2, 3, and 4 were 8.8±0.9, 7.9±1.8, 7.4±0.9, 6.6±1.5, respectively. Our preliminary study demonstrates the feasibility of using the 3D level set method for segmenting bladder lesions in CTU scans.
登录
查看更多内容
DOI：
10.1109/titb.2012.2200496
发表时间：
2012-07
期刊：
IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society
影响因子：
--
作者：
Duan C;Yuan K;Liu F;Xiao P;Lv G;Liang Z
通讯作者：
Liang Z
影响因子：
1.1
作者：
Akbar, SA;Mortele, KJ;Silverman, SG
通讯作者：
Silverman, SG
影响因子：
10.6
作者：
Sahiner, B;Petrick, N;Gurcan, MN
通讯作者：
Gurcan, MN
通过 MR 膀胱造影检测膀胱壁异常区域的基于体积的特征
DOI：
10.1109/tbme.2011.2158541
发表时间：
2011-09
期刊：
IEEE transactions on bio-medical engineering
影响因子：
--
作者：
Duan C;Yuan K;Liu F;Xiao P;Lv G;Liang Z
通讯作者：
Liang Z
影响因子：
19.7
作者：
Park, Sung Bin;Kim, Jeong Kon;Cho, Kyoung-Sik
通讯作者：
Cho, Kyoung-Sik