CN116433754A - Side crack extraction method, device, storage medium and equipment - Google Patents
Side crack extraction method, device, storage medium and equipmentDownload PDFInfo
- Publication number
- CN116433754A CN116433754ACN202310328719.7ACN202310328719ACN116433754ACN 116433754 ACN116433754 ACN 116433754ACN 202310328719 ACN202310328719 ACN 202310328719ACN 116433754 ACN116433754 ACN 116433754A
- Authority
- CN
- China
- Prior art keywords
- fissure
- sylvian
- sylvian fissure
- extraction
- extract
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本发明属于医学图像处理技术领域，具体涉及基于校正后的影像，自动化锁定最佳的脑沟分割阈值、结合侧裂解剖位置识别侧裂的方法。The invention belongs to the technical field of medical image processing, and in particular relates to a method for automatically locking the optimal brain sulcus segmentation threshold based on corrected images and identifying the Sylvian fissure in combination with the anatomical position of the Sylvian fissure.
背景技术Background technique
侧裂：Sylvian fissure。位于大脑半球外侧面中部的一条沟。起自脑底面的前穿质，在大脑半球外侧走行，其后部是额叶和颞叶的分界，内部埋藏有岛叶。侧裂沟里汇聚了大脑中动脉MCA、前穿动脉、大脑中浅静脉、大脑中深静脉。Sylvian fissure: Sylvian fissure. A groove in the middle of the lateral surface of the cerebral hemisphere. The anterior penetrating substance from the bottom of the brain runs on the outer side of the cerebral hemisphere, and the posterior part is the boundary between the frontal lobe and the temporal lobe, and the insula is buried inside. The middle cerebral artery MCA, the anterior perforating artery, the superficial middle cerebral vein, and the deep middle cerebral vein converge in the sylvian fissure.
经翼点外侧裂入路是神经外科使用最广泛的手术入路之一。外侧裂有动静脉的分支，故进行侧裂区的手术受到神经外科医生的高度重视，手术引起的血流紊乱或出血可能导致严重的后果。对专家来说此手术入路可能比较简单但对于无经验者是一个难度较高的手术入路。尤其是脑出血外科手术，血肿挤压导致脑组织移位，占据了侧裂沟的空间，从影像中已无法分辨侧裂。The transpterional Sylvian approach is one of the most widely used surgical approaches in neurosurgery. There are branches of arteries and veins in the Sylvian fissure, so neurosurgeons attach great importance to the operation in the Sylvian fissure area. The blood flow disorder or bleeding caused by the operation may lead to serious consequences. This surgical approach may be relatively simple for experts, but it is a difficult surgical approach for inexperienced people. Especially in intracerebral hemorrhage surgery, the extrusion of the hematoma causes the displacement of the brain tissue, occupying the space of the Sylvian fissure, and the Sylvian fissure can no longer be distinguished from the images.
临床上对于侧裂的识别主要是基于医生的经验，也有借助计算机技术、对侧裂进行手工标注。由于医生的水平参差不齐，对于经验不足的医生，侧裂判断失误易导致脑出血。而借助计算机技术进行影像标记需要逐层标记费时费力，且对于侧裂沟有挤压的情况无法进行标记。The clinical identification of the Sylvian fissure is mainly based on the experience of doctors, and there are also manual annotations of the Sylvian fissure with the help of computer technology. Due to the uneven level of doctors, for inexperienced doctors, misjudgment of Sylvian fissure can easily lead to cerebral hemorrhage. However, image marking with the help of computer technology requires time-consuming and labor-intensive marking layer by layer, and it cannot be marked when the lateral fissure is squeezed.
发明内容Contents of the invention
针对上述问题，本发明提供了一种在CT平扫影像上，基于校正后的影像，自动化锁定最佳的脑沟分割阈值、结合侧裂解剖位置识别侧裂的方法，对于侧裂受挤压部位，利用脑解剖结构对称性特性，拟合生成异常侧侧裂。In view of the above problems, the present invention provides a method of automatically locking the optimal brain sulcus segmentation threshold based on the corrected image on the CT plain scan image, and identifying the Sylvian fissure in combination with the anatomical position of the Sylvian fissure. Based on the symmetry of the brain anatomical structure, the abnormal Sylvian fissure was generated by fitting.
为了实现上述目的，本发明提供了如下技术方案：In order to achieve the above object, the present invention provides the following technical solutions:
本发明提供了一种侧裂提取方法，其特征在于，包括以下步骤：The invention provides a side fissure extraction method, characterized in that, comprising the following steps:
第一步，采用已有专利技术CN114266789A方法1～4步提取全脑脑外间隙、大脑皮层区域CortexROI，得到全脑脑沟脑室区域csfROI；The first step is to use the existing patented technology CN114266789A method 1 to 4 steps to extract the extracerebral space of the whole brain and the CortexROI of the cerebral cortex region to obtain the csfROI of the brain sulcus and ventricle region of the whole brain;
第二步，采用ITK刚性配准方法实现头部三维校正；The second step is to use the ITK rigid registration method to realize the three-dimensional correction of the head;
第三步，提取侧裂；The third step is to extract the side fissure;
第四步，拟合生成异常侧侧裂。The fourth step is to generate abnormal Sylvian fissure by fitting.
进一步地，所述第三步具体包括：Further, the third step specifically includes:
(1)提取z轴候选范围：提取断层切面面积最大层上下1.5cm，共3cm范围为侧裂所在z轴方向候选层(slice1、……sliceM)；(1) Extract the candidate range of the z-axis: extract 1.5cm above and below the layer with the largest section area of the fault, and a total of 3cm is the candidate layer in the z-axis direction where the Sylvian fissure is located (slice1,...sliceM);
(2)提取y轴方向候选范围：遍历(slice1、……sliceM)，计算各断层slice头骨上缘与下缘之间的距离H，H均分为4份，第2/4区域为侧裂所在区域(slice1y、……sliceMy)；(2) Extract the candidate range in the y-axis direction: traverse (slice1,...sliceM), calculate the distance H between the upper edge and lower edge of the skull of each fault slice, H is divided into 4 parts, and the 2/4 area is the lateral fissure area(slice1y , ... sliceMy );
(3)提取x轴候选范围：计算断层最左侧与最右侧之间的距离W，W均分3份，取出(slice1y、……sliceMy)两侧的区域(slice1xy、……sliceMxy)；(3) Extract the candidate range of the x-axis: calculate the distance W between the leftmost and the rightmost of the fault, W is divided into 3 parts, and the regions (slice1 xy, … sliceMxy );
(4)提取侧裂：提取(slice1xy、……sliceMxy)区域内的第一步所得csfROI中为分割得到的双侧侧裂。(4) Sylvian fissure extraction: the csfROI obtained in the first step in the region of extraction (slice1xy , ... sliceMxy ) is the bilateral sylvian fissure obtained by segmentation.
进一步地，所述第四步具体包括：Further, the fourth step specifically includes:
(1)确定病变侧：统计两侧侧裂体积，体积小的一侧为病变侧；(1) Determine the lesion side: count the volume of the sylvian fissure on both sides, and the side with the smaller volume is the lesion side;
(2)对称拟合生成：将正常侧侧裂以中轴线做镜像对称，拟合为病变侧侧裂。(2) Symmetrical fitting generation: the normal Sylvian fissure is mirror-symmetrical to the central axis, and fitted to the lesioned Sylvian fissure.
本发明还提供一种侧裂提取模型，其特征在于，通过上述任一项所述的侧裂提取方法构建得到。The present invention also provides a Sylvian fissure extraction model, which is characterized in that it is constructed by any of the Sylvian fissure extraction methods described above.
本发明还提供一种侧裂提取装置，其特征在于，包括如上所述的侧裂提取模型。The present invention also provides a Sylvian fissure extraction device, which is characterized in that it comprises the above-mentioned Sylvian fissure extraction model.
本发明还提供一种电子设备，包括存储器和处理器，所述存储器存储有可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述程序时实现上述任一项所述的侧裂提取方法中的步骤。The present invention also provides an electronic device, including a memory and a processor, the memory stores a computer program that can run on the processor, and it is characterized in that, when the processor executes the program, any of the above A step in the described Sylvian extraction method.
本发明还提供一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现上述任一项所述的侧裂提取方法。The present invention also provides a computer-readable storage medium, on which a computer program is stored, wherein, when the computer program is executed by a processor, the Sylvian fissure extraction method described in any one of the above is implemented.
与现有技术相比本发明的有益效果。Compared with the prior art, the present invention has beneficial effects.
发明人创造性的提出在阈值分割的基础上，结合侧裂的解剖位置提取候选区域，在对应的解剖区域内提取侧裂，针对有病变挤占的情况，根据正常侧分割得到的侧裂对异常侧进行拟合，得到全脑的侧裂分割结果。The inventor creatively proposes to extract candidate regions based on the threshold segmentation, combined with the anatomical location of the Sylvian fissure, and extract the Sylvian fissure in the corresponding anatomical region. Fitting is performed to obtain the Sylvian fissure segmentation result of the whole brain.
本发明适用于CT平扫影像NCCT、灌注影像CTP，且适用于多家医院、多种设备、多种脑形的批量、快速、自动化、准确识别。针对侧裂异常的薄扫影像数据，平均一套160层的NCCT数据处理时间仅为20s，且运算结果稳定，同一套数据处理多次的结果一致。The invention is applicable to NCCT of plain CT scan images and CTP of perfusion images, and is applicable to batch, fast, automatic and accurate recognition of multiple hospitals, various equipment, and various brain shapes. For the thin-scan image data with abnormal Sylvian fissure, the average processing time for a set of 160-slice NCCT data is only 20s, and the calculation results are stable, and the results of the same set of data processed multiple times are consistent.
附图说明Description of drawings
图1整体流程图。Figure 1 overall flow chart.
图2全脑脑外间隙，其中，a为原始扫描数据横断面示图；b为分割得到的全脑脑外间隙区域。Fig. 2 The extracerebral space of the whole brain, wherein, a is a cross-sectional view of the original scanning data; b is the extracerebral space area of the whole brain obtained by segmentation.
图3三维校正。Figure 3 Three-dimensional correction.
图4空间坐标轴定义。Figure 4 Definition of spatial coordinate axes.
图5Z轴方向候选范围，其中，a为侧裂候选区域矢状位示图；b为侧裂候选区域横断面示图。Fig. 5 Candidate range in the Z-axis direction, in which, a is a sagittal view of the candidate region of the Sylvian fissure; b is a cross-sectional view of the candidate region of the Sylvian fissure.
图6Y轴方向候选范围。Figure 6 Candidate ranges in the Y-axis direction.
图7X轴方向候选范围。Figure 7 X-axis direction candidate range.
图8检测出的侧裂。Figure 8 Sylvian fissure detected.
图9拟合生成的侧裂。Figure 9 Fitting generated Sylvian fissures.
图10分割的侧裂3D展示。Figure 10 Sylvian fissure segmented in 3D.
具体实施方式Detailed ways
下面通过具体实施例和附图对本发明做进一步详细说明。以下实施例仅对本发明进行进一步说明，不应理解为对本发明的限制。The present invention will be described in further detail below through specific embodiments and accompanying drawings. The following examples only further illustrate the present invention, and should not be construed as limiting the present invention.
本发明具体流程如图1所示。The specific process of the present invention is shown in Figure 1.
第一步，采用专利CN114266789A方法，得出全脑脑外间隙阈值(ThreshValue)，根据阈值对影像进行分割，得到全脑脑沟脑室(脑外间隙)区域csfROI，如图2所示。In the first step, the patent CN114266789A method is used to obtain the threshold value (ThreshValue) of the extracerebral space of the whole brain, and the image is segmented according to the threshold value to obtain the csfROI of the sulcus ventricle (extrabrain space) region of the whole brain, as shown in Figure 2.
第二步：采用ITK三维刚性配准，对影像进行校正(如图3所示)。Step 2: Use ITK 3D rigid registration to correct the image (as shown in Figure 3).
第三步：提取侧裂，具体步骤如下：The third step: Extract the lateral fissure, the specific steps are as follows:
(1)提取z轴候选范围：提取断层切面面积最大层上下1.5cm，共3cm范围为侧裂所在z轴方向候选层(slice1、……sliceM)，示意图如图4和5。(1) Extract candidate z-axis ranges: extract 1.5 cm above and below the layer with the largest section area of the fault, and a total range of 3 cm is the candidate layers in the z-axis direction (slice1, ... sliceM) where the Sylvian fissure is located. The schematic diagrams are shown in Figures 4 and 5.
(2)提取y轴方向候选范围：遍历(slice1、……sliceM)，计算各断层slice头骨上缘与下缘之间的距离H，H均分为4份，第2/4区域为侧裂所在区域(slice1y、……sliceMy)，示意图如图6。(2) Extract the candidate range in the y-axis direction: traverse (slice1,...sliceM), calculate the distance H between the upper edge and lower edge of the skull of each fault slice, H is divided into 4 parts, and the 2/4 area is the lateral fissure The area (slice1y , ... sliceMy ) is shown in Figure 6.
(3)提取x轴候选范围：计算断层最左侧与最右侧之间的距离W，W均分3份，取出(slice1y、……sliceMy)两侧的区域(slice1xy、……sliceMxy)，示意图如图7。(3) Extract the candidate range of the x-axis: calculate the distance W between the leftmost and the rightmost of the fault, W is divided into 3 parts, and the regions (slice1 xy, … sliceMxy ), the schematic diagram is shown in FIG. 7 .
(4)提取侧裂：提取(slice1xy、……sliceMxy)区域内的csfROI中(图2)为分割得到的双侧侧裂。如图8。(4) Sylvian fissure extraction: extracting the csfROI in the (slice1xy , ... sliceMxy ) region ( FIG. 2 ) is the bilateral Sylvian fissure obtained by segmentation. Figure 8.
第四步：拟合生成全脑侧裂。Step 4: Fitting to generate the whole Sylvian fissure.
(1)确定病变侧：统计两侧侧裂体积，体积小的一侧为病变侧。(1) Determine the lesion side: count the volume of both sides of the Sylvian fissure, and the side with the smaller volume is the lesion side.
(2)对称拟合生成：将正常侧侧裂以中轴线做镜像对称，拟合为病变侧侧裂(图9和10)。(2) Symmetrical fitting generation: the normal Sylvian fissure is mirror-symmetrical to the central axis, and fitted to the diseased Sylvian fissure (Figs. 9 and 10).
Claims (7)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310328719.7ACN116433754B (en) | 2023-03-30 | 2023-03-30 | Side fissure extraction method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310328719.7ACN116433754B (en) | 2023-03-30 | 2023-03-30 | Side fissure extraction method, device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116433754Atrue CN116433754A (en) | 2023-07-14 |
| CN116433754B CN116433754B (en) | 2025-08-12 |
Family
ID=87079005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310328719.7AActiveCN116433754B (en) | 2023-03-30 | 2023-03-30 | Side fissure extraction method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116433754B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060270926A1 (en)* | 2005-02-07 | 2006-11-30 | Qingmao Hu | Methods and systems to segment central sulcus and Sylvian fissure |
| CN101916443A (en)* | 2010-08-19 | 2010-12-15 | 中国科学院深圳先进技术研究院 | Processing method and system of CT image |
| CN101971213A (en)* | 2008-02-29 | 2011-02-09 | 新加坡科技研究局 | A method and system for anatomy structure segmentation and modeling in an image |
| CN109191442A (en)* | 2018-08-28 | 2019-01-11 | 深圳大学 | Ultrasound image assessment and screening technique and device |
| CN114266789A (en)* | 2021-12-28 | 2022-04-01 | 沈阳东软智能医疗科技研究院有限公司 | Method, device, equipment and medium for segmenting infarct area based on brain image |
- 2023
- 2023-03-30CNCN202310328719.7Apatent/CN116433754B/enactiveActive
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060270926A1 (en)* | 2005-02-07 | 2006-11-30 | Qingmao Hu | Methods and systems to segment central sulcus and Sylvian fissure |
| CN101971213A (en)* | 2008-02-29 | 2011-02-09 | 新加坡科技研究局 | A method and system for anatomy structure segmentation and modeling in an image |
| CN101916443A (en)* | 2010-08-19 | 2010-12-15 | 中国科学院深圳先进技术研究院 | Processing method and system of CT image |
| CN109191442A (en)* | 2018-08-28 | 2019-01-11 | 深圳大学 | Ultrasound image assessment and screening technique and device |
| CN114266789A (en)* | 2021-12-28 | 2022-04-01 | 沈阳东软智能医疗科技研究院有限公司 | Method, device, equipment and medium for segmenting infarct area based on brain image |
Non-Patent Citations (2)
| Title |
|---|
| AURICELIO BATISTA CEZAR-JUNIOR 等: ""Subarachnoid hemorrhage and COVID-19 Association or coincidence?"", 《MEDICINE (2020)》, vol. 99, no. 51, 31 December 2020 (2020-12-31), pages 1 - 7* |
| 胡福广 等: ""脑外侧裂区显微外科解剖学研究"", 中国神经精神疾病杂志, no. 05, 27 May 2010 (2010-05-27), pages 272 - 275* |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116433754B (en) | 2025-08-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110338830B (en) | Method for automatically extracting head and neck blood vessel central path in CTA image | |
| KR101120250B1 (en) | Vascular image extraction and labeling system and method | |
| JP5258694B2 (en) | Medical image processing apparatus and method, and program | |
| CN107563998B (en) | Method for processing heart image in medical image | |
| US8831328B2 (en) | Method and system for segmenting a brain image | |
| US20150141818A1 (en) | Vascular imaging method and device | |
| WO2010117573A3 (en) | Automated measurement of brain injury indices using brain ct images, injury data, and machine learning | |
| CN103985122B (en) | The dirtiest extracting method of based on heart CT image | |
| CN101238987A (en) | A Processing Method for CT Cerebral Hemorrhage Images | |
| CN113469935B (en) | Automatic detection and positioning method for posterior superior iliac spine based on CT image | |
| CN109949322A (en) | A segmentation method of cerebrovascular images based on T1-enhanced magnetic resonance images | |
| Gupta et al. | Automatic segmentation of cerebrospinal fluid, white and gray matter in unenhanced computed tomography images | |
| CN108765483A (en) | The method and system of sagittal plane in being determined in a kind of CT images from brain | |
| CN106780491A (en) | The initial profile generation method used in GVF methods segmentation CT pelvis images | |
| Liu et al. | Automatic model-guided segmentation of the human brain ventricular system from CT images | |
| Liao et al. | Automatic recognition of midline shift on brain CT images | |
| Sofian et al. | Segmentation and detection of media adventitia coronary artery boundary in medical imaging intravascular ultrasound using otsu thresholding | |
| Dos Santos et al. | Automatic detection of carotid arteries in computed tomography angiography: a proof of concept protocol | |
| Karim et al. | Left atrium segmentation for atrial fibrillation ablation | |
| CN116433754A (en) | Side crack extraction method, device, storage medium and equipment | |
| CN114869315A (en) | A three-dimensional model reconstruction and visualization method and system for pancreatic lesions | |
| CN106780492A (en) | A kind of extraction method of key frame of CT pelvises image | |
| CN114764809A (en) | Self-adaptive threshold segmentation method and device for lung CT (computed tomography) density increase shadow | |
| Memiş et al. | Computerized 2D detection of the multiform femoral heads in magnetic resonance imaging (MRI) sections with the integro-differential operator | |
| CN108154532B (en) | Method for assisting in evaluating thyroid volume of SPECT image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |