A Practical Guide to Manual and Semi-Automated Neurosurgical Brain Lesion Segmentation

被引:1
作者
Jain, Raunak [1 ]
Lee, Faith [1 ]
Luo, Nianhe [1 ]
Hyare, Harpreet [2 ]
Pandit, Anand S. [3 ,4 ]
机构
[1] UCL, UCL Med Sch, London WC1E 6DE, England
[2] Natl Hosp Neurol & Neurosurg, Lysholm Dept Neuroradiol, London WC1N 3BG, England
[3] Natl Hosp Neurol & Neurosurg, Victor Horsley Dept Neurosurg, London WC1N 3BG, England
[4] UCL, Inst Neurol, High Dimens Neurol, London WC1N 3BG, England
来源
NEUROSCI | 2024年 / 5卷 / 03期
关键词
segmentation; education; radiomics; meningioma; glioblastoma; GLIOBLASTOMA-MULTIFORME; MR-IMAGES; PRIVACY; DICOM;
D O I
10.3390/neurosci5030021
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
The purpose of the article is to provide a practical guide for manual and semi-automated image segmentation of common neurosurgical cranial lesions, namely meningioma, glioblastoma multiforme (GBM) and subarachnoid haemorrhage (SAH), for neurosurgical trainees and researchers. Materials and Methods: The medical images used were sourced from the Medical Image Computing and Computer Assisted Interventions Society (MICCAI) Multimodal Brain Tumour Segmentation Challenge (BRATS) image database and from the local Picture Archival and Communication System (PACS) record with consent. Image pre-processing was carried out using MRIcron software (v1.0.20190902). ITK-SNAP (v3.8.0) was used in this guideline due to its availability and powerful built-in segmentation tools, although others (Seg3D, Freesurfer and 3D Slicer) are available. Quality control was achieved by employing expert segmenters to review. Results: A pipeline was developed to demonstrate the pre-processing and manual and semi-automated segmentation of patient images for each cranial lesion, accompanied by image guidance and video recordings. Three sample segmentations were generated to illustrate potential challenges. Advice and solutions were provided within both text and video. Conclusions: Semi-automated segmentation methods enhance efficiency, increase reproducibility, and are suitable to be incorporated into future clinical practise. However, manual segmentation remains a highly effective technique in specific circumstances and provides initial training sets for the development of more advanced semi- and fully automated segmentation algorithms.
引用
收藏
页码:265 / 275
页数:11
相关论文
共 60 条
[1]   Radiological characteristics of glioblastoma multiforme using CT and MRI examination [J].
Abd-Elghany, Amr A. ;
Naji, Abdu Ahmed ;
Alonazi, Batil ;
Aldosary, Hassan ;
Alsufayan, Mohammed Abdluaziz ;
Alnasser, Mohammed ;
Mohammad, EbtsamA. ;
Mahmoud, Mustafa Z. .
JOURNAL OF RADIATION RESEARCH AND APPLIED SCIENCES, 2019, 12 (01) :289-293
[2]   Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging [J].
Abdel Razek, Ahmed Abdel Khalek ;
Alksas, Ahmed ;
Shehata, Mohamed ;
AbdelKhalek, Amr ;
Abdel Baky, Khaled ;
El-Baz, Ayman ;
Helmy, Eman .
INSIGHTS INTO IMAGING, 2021, 12 (01)
[3]   Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions [J].
Akkus, Zeynettin ;
Galimzianova, Alfiia ;
Hoogi, Assaf ;
Rubin, Daniel L. ;
Erickson, Bradley J. .
JOURNAL OF DIGITAL IMAGING, 2017, 30 (04) :449-459
[4]   Letter: Image Segmentation in Neurosurgery: An Undervalued Skill Set? [J].
Ann, Chu Ning ;
Luo, Nianhe ;
Pandit, Anand S. .
NEUROSURGERY, 2022, 91 (01) :E31-E32
[5]  
Atkinson D., 2022, Geometry in medical imaging: DICOM and NIfTI formats, DOI DOI 10.5281/ZENODO.6467772
[6]   HIPAA privacy and DICOM anonymization for research [J].
Avrin, David .
ACADEMIC RADIOLOGY, 2008, 15 (03) :273-273
[7]  
Baid U, 2021, Arxiv, DOI [arXiv:2107.02314, 10.48550/arXiv:2107.02314]
[8]  
Bakas S, 2019, Arxiv, DOI arXiv:1811.02629
[9]  
Bakas Spyridon, 2017, TCIA
[10]  
Bakas Spyridon, 2017, TCIA