Xianjing Zhao1,2, Kaixing Chen3, Ge Wu3, Guyue Zhang3, Xin Zhou3, Chuanfeng Lv3, Shiman Wu2, Yun Chen4, Guotong Xie3,5,6, Zhenwei Yao7,8. 1. Shanghai Institute of Medical Imaging, Shanghai, China. 2. Department of Radiology, Huashan Hospital, Fudan University, 12 Middle Urumqi Road, Jing'an District, Shanghai, 200040, China. 3. Ping An Technology (Shenzhen) Co., Ltd., Shanghai, China. 4. Department of Radiology, Xiangyang Central Hospital, Hubei University of Arts and Science, Xiangyang, China. 5. Ping An Health Cloud Company Limited, Shanghai, China. 6. Ping An International Smart City Technology Co., Ltd., Shanghai, China. 7. Shanghai Institute of Medical Imaging, Shanghai, China. zwyao@fudan.edu.cn. 8. Department of Radiology, Huashan Hospital, Fudan University, 12 Middle Urumqi Road, Jing'an District, Shanghai, 200040, China. zwyao@fudan.edu.cn.
Abstract
OBJECTIVES: To evaluate for the first time the performance of a deep learning method based on no-new-Net for fully automated segmentation and volumetric measurements of intracerebral hemorrhage (ICH), intraventricular extension of intracerebral hemorrhage (IVH), and perihematomal edema (PHE) in primary ICH on CT. METHODS: Three hundred and eighty primary ICH patients who underwent CT at hospital arrival were divided into a training cohort (n = 300) and a validation cohort (n = 80). An independent cohort with 80 patients was used for testing. Ground truth (segmentation masks) was manually generated by radiologists. Model performance on lesion segmentation and volumetric measurement of ICH, IVH, and PHE were evaluated by comparing the model results with the segmentations performed by radiologists. RESULTS: In the test cohort, the Dice scores of lesion segmentation were 0.92, 0.79, and 0.71 for ICH, IVH, and PHE, respectively. The sensitivities were 0.93 for ICH, 0.88 for IVH, and 0.81 for PHE. The positive predictive values were 0.92, 0.76, and 0.69 for ICH, IVH, and PHE, respectively. Excellent concordance (concordance correlation coefficients [CCCs] ≥ 0.98) of ICH and IVH and good concordance of PHE (CCCs ≥ 0.92) were demonstrated between manually and automatically measured volumes. The model took approximately 15 s to provide automatic segmentation and volume analysis for each patient. CONCLUSION: Our model demonstrates good reliability for automatic segmentation and volume measurement of ICH, IVH, and PHE in primary ICH, which can be useful to reduce the effort and time of doctors to calculate volumes of ICH, IVH, and PHE. KEY POINTS: • Deep learning algorithms can provide automatic and reliable assessment of intracerebral hemorrhage, intraventricular hemorrhage, and perihematomal edema on CT. • Non-contrast CT-based deep learning method can be helpful to provide efficient and accurate measurements of ICH, IVH, and PHE in primary ICH patients, thereby reducing the effort and time of doctors to segment and calculate volumes of ICH, IVH, and PHE in primary ICH patients.
OBJECTIVES: To evaluate for the first time the performance of a deep learning method based on no-new-Net for fully automated segmentation and volumetric measurements of intracerebral hemorrhage (ICH), intraventricular extension of intracerebral hemorrhage (IVH), and perihematomal edema (PHE) in primary ICH on CT. METHODS: Three hundred and eighty primary ICHpatients who underwent CT at hospital arrival were divided into a training cohort (n = 300) and a validation cohort (n = 80). An independent cohort with 80 patients was used for testing. Ground truth (segmentation masks) was manually generated by radiologists. Model performance on lesion segmentation and volumetric measurement of ICH, IVH, and PHE were evaluated by comparing the model results with the segmentations performed by radiologists. RESULTS: In the test cohort, the Dice scores of lesion segmentation were 0.92, 0.79, and 0.71 for ICH, IVH, and PHE, respectively. The sensitivities were 0.93 for ICH, 0.88 for IVH, and 0.81 for PHE. The positive predictive values were 0.92, 0.76, and 0.69 for ICH, IVH, and PHE, respectively. Excellent concordance (concordance correlation coefficients [CCCs] ≥ 0.98) of ICH and IVH and good concordance of PHE (CCCs ≥ 0.92) were demonstrated between manually and automatically measured volumes. The model took approximately 15 s to provide automatic segmentation and volume analysis for each patient. CONCLUSION: Our model demonstrates good reliability for automatic segmentation and volume measurement of ICH, IVH, and PHE in primary ICH, which can be useful to reduce the effort and time of doctors to calculate volumes of ICH, IVH, and PHE. KEY POINTS: • Deep learning algorithms can provide automatic and reliable assessment of intracerebral hemorrhage, intraventricular hemorrhage, and perihematomal edema on CT. • Non-contrast CT-based deep learning method can be helpful to provide efficient and accurate measurements of ICH, IVH, and PHE in primary ICHpatients, thereby reducing the effort and time of doctors to segment and calculate volumes of ICH, IVH, and PHE in primary ICHpatients.
Entities:
Keywords:
Cerebral hemorrhage; Deep learning; Edema; Tomography, X-ray computed
Authors: H van Voorst; P R Konduri; L M van Poppel; W van der Steen; P M van der Sluijs; E M H Slot; B J Emmer; W H van Zwam; Y B W E M Roos; C B L M Majoie; G Zaharchuk; M W A Caan; H A Marquering Journal: AJNR Am J Neuroradiol Date: 2022-07-28 Impact factor: 4.966
Authors: Matthew F Sharrock; W Andrew Mould; Meghan Hildreth; E Paul Ryu; Nathan Walborn; Issam A Awad; Daniel F Hanley; John Muschelli Journal: J Neuroimaging Date: 2022-04-17 Impact factor: 2.324