Purpose: To evaluate the 3D U‐Net model for automatic segmentation and measurement of cervical spine structures using magnetic resonance (MR) images of healthy adults.Materials and methods: MR images of the cervical spine from 160 healthy adults were collected retrospectively. A previously constructed deep‐learning model was used to automatically segment anatomical structures. Segmentation and localization results were checked by experienced radiologists. Pearson's correlation analyses were conducted to examine relationships between patient and image parameters.Results: No measurement was significantly correlated with age or sex. The mean values of the areas of the subarachnoid space and spinal cord from the C2/3 (cervical spine 2–3) to C6/7 intervertebral disc levels were 102.85–358.12 mm2 and 53.71–110.32 mm2, respectively. The ratios of the areas of the spinal cord to the subarachnoid space were 0.25–0.68. The transverse and anterior‐posterior diameters of the subarachnoid space were 14.77–26.56 mm and 7.38–17.58 mm, respectively. The transverse and anterior‐posterior diameters of the spinal cord were 9.11–16.02 mm and 5.47–10.12 mm, respectively.Conclusion: A deep learning model based on 3D U‐Net automatically segmented and performed measurements on cervical spine MR images from healthy adults, paving the way for quantitative diagnosis models for spinal cord diseases.
Background: Accurate prediction of the histological grade and Ki-67 expression of soft tissue sarcoma (STS) before surgery is essential for the subsequent diagnosis, treatment, and prognostic evaluation of patients. Purpose: To evaluate intravoxel incoherent motion (IVIM) and diffusion kurtosis imaging (DKI) in predicting the histological grade and Ki-67 expression of STS. Material and Methods: A total of 40 patients underwent 3-T MRI, including conventional sequences; IVIM and DKI parameters were obtained. All patients were divided into a low-grade (grade 1 and grade 2) group and a high-grade (grade 3) group through pathological analysis. Ki-67 expression of each lesion was calculated. Chi-square test, independent sample t-test, Mann–Whitney U test, Pearson, Spearman, and receiver operating characteristic curve analysis were performed. Results: There were 17 patients in the low-grade group and 23 in the high-grade group. Ki-67 expression was in the range of 10%–80%. D value was inversely correlated with Ki-67 expression. MK value showed a moderate positive correlation with Ki-67 expression. Regarding histological grading, only the peritumoral enhancement was statistically different between low- and high-grade STS on conventional MRI ( P=0.024). The high-grade group had significantly higher MK value and lower D and MD value than the low-grade group. MK value showed the best diagnostic performance. The combination of MK and MD yielded the highest specificity (88.24%), and the combination of D, MK, and MD yielded the best area under the curve value (0.841) and sensitivity (95.65%). Conclusion: IVIM and DKI parameters were correlated with Ki-67 expression and could help differentiate between low- and high-grade STS.
Background: Accurate identification of the histopathological grade and the Ki-67 expression level is important in clinical cases of soft tissue sarcomas (STSs). Purpose: To explore the feasibility of a radiomics model based on intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) and diffusion kurtosis imaging (DKI) MRI parameter maps in predicting the histopathological grade and Ki-67 expression level of STSs. Material and Methods: In total, 42 patients diagnosed with STSs between May 2018 and January 2020 were selected. The MADC software in Functool of GE ADW 4.7 workstation was used to obtain standard apparent diffusion coefficient (ADC), D, D*, f, mean diffusivity, and mean kurtosis (MK). The histopathological grade and Ki-67 expression level of STSs were identified. The radiomics features of IVIM and DKI parameter maps were used as the dataset. The area under the receiver operating characteristic curve (AUC) and F1-score were calculated. Results: D-SVM achieved the best diagnostic performance for histopathological grade. The AUC in the validation cohort was 0.88 (sensitivity: 0.75 [low level] and 0.83 [high level]; specificity: 0.83 [low level] and 0.75 [high level]; F1-score: 0.75 [low level] and 0.83 [high level]). MK-SVM achieved the best diagnostic performance for Ki-67 expression level. The AUC in the validation cohort was 0.83 (sensitivity: 0.83 [low level] and 0.50 [high level; specificity: 0.50 [low level] and 0.83 [high level]; F1-score: 0.77 [low level] and 0.57 [high level]). Conclusion: The proposed radiomics classifier could predict the pathological grade of STSs and the Ki-67 expression level in STSs.
30 June 2026 in Journal of Magnetic Resonance Imaging