RESUMO
Objective:To explore the feasibility of the AI intelligent reconstruction model based on knee joint magnetic resonance data developed by Nuctech Company Limited for evaluating knee cartilage injury.Methods:Thirty-three patients (a total of forty-one knees) who were hospitalized with severe knee osteoarthritis in Beijing Tsinghua Changgung Hospital from May 2021 to April 2022 were selected. All of them were planned to be performed total knee arthroplasty (TKA) for the treatment of knee osteoarthritis. Fifteen males with an average age of 71±5 years old and twenty six females with an average age of 71±9 years old were included in this study. There were 19 cases of left knee and 22 cases of right knee. Thin layer MRI examination on the patients' knee joints was performed before the surgery, and artificial intelligence model based on the thin layer MRI data of the knee joint was reconstructed. The cartilage part of the model was selected and corrected by Principal Component Analysis (PCA) in order to realize model straightening. The tibial plateau cartilage of knee joint which intercepted during operation was classified according to the International Cartilage Repair Society (ICRS). Finally the results were compared with the ICRS classification results of knee artificial intelligence reconstruction model and artificial recognition of knee joint MRI images.Results:Compared with the grade of cartilage injury intercepted during our operation which was according to the ICRS classification, the sensitivity of artificial intelligence reconstruction model for the diagnosis of cartilage injury with ICRS classification grade four was 93.1%. The specificity of artificial intelligence reconstruction model was 91.4%. The positive predictive value (PPV) of artificial intelligence reconstruction model was 92.2%. And the negative predictive value (NPV) of artificial intelligence reconstruction model was 80.3%. The area under ROC curve (AUC) was 0.92. The ICRS classification consistency between artificial intelligence model and physical inspection results was good with kappa value 0.81 ( P<0.001) . In the aspect of artificial recognition of cartilage injury grading in MRI images, the sensitivity of artificial recognition was 92.10% compared with the manual identification of cartilage injury classification in MRI images. The specificity of artificial recognition was 91.60%. The positive predictive value (PPV) of artificial recognition was 97.20% and the negative predictive value (NPV) of artificial recognition was 78.8%. The kappa value of the cartilage injury classification in MRI images consistency between artificial recognition and manual identification was 0.79 ( P<0.001). Conclusion:Based on the evaluation of cartilage injury by AI reconstruction model of knee joint, the sensitivity and specificity of the diagnosis of ICRS grade IV cartilage injury can be acceptable, but still needs to be improved.
RESUMO
Objective:To evaluate the metal artifacts reduction effect of multi-acquisition variable-resonance image combination (MAVRIC-SL) after total knee arthroplasty by comparing with two-dimensional fast spin-echo metal artifact reduction sequence (2D FSE MARS).Methods:A total of 78 patients (101 knees) who underwent total knee arthroplasty in Beijing Tsinghua Changgung Hospital from December 2018 to December 2020 were prospectively collected. All patients underwent 3.0 T MR examination within 2 weeks after surgery. The sequences included axial, sagittal, and coronal 2D FSE MARS and MAVRIC-SL. The ranges of prosthesis artifacts were measured, and the scores of the prosthesis clarity, anatomical structure clarity, and joint effusion diagnosis confidence were evaluated by Likert scale. Paired t test was used to compare the difference of artifact range between 2D FSE MARS and MAVRIC-SL. The Wilcoxon signed rank-sum test was used to compare image quality scores and joint effusion diagnosis confidence scores. Results:In 101 knees, the ranges of prosthesis artifacts in axial, sagittal, and coronal 2D FSE MARS were (63.3±8.5), (60.0±7.4) and (62.1±8.7) cm 2, while those of MAVRIC-SL were (49.5±5.8), (44.1±6.6) and (46.1±7.5) cm 2. The differences were statistically significant ( t=20.021, 21.834, 25.472, all P<0.001). The subjective scores of femoral prosthesis clarity, tibial prosthesis clarity, and anatomical structure clarity of MAVRIC-SL were significantly higher than those of 2D FSE MARS (all P<0.001). Confidence scores of 2D FSE MARS and MAVRIC-SL for diagnosing joint effusion were 2 (1, 3) and 3 (2, 3), respectively, and the difference was statistically significant ( Z=6.549, P<0.001). Conclusion:Compared with 2D FSE MARS, MAVRIC-SL can further reduce the metal artifacts in total knee arthroplasty and improve the diagnostic confidence of joint effusion.
RESUMO
Objective To assess the feasibility of quantitative measurement of subcutaneous and supraclavicular adipose tissue with iterative decomposition of water and fat with echo asymmetry and least square estimation-iron quantification sequence (IDEAL-IQ).Methods Totally 87 normal young female volunteers (20-35 years old) were recruited and divided into body mass index (BMI)＜24 kg/m2 group (n=72) and BMI≥24 kg/m2 group (n=15).Fat fraction (FF) and T2* relaxation rate (R2*) of supraclavicular adipose tissue,chest wall adipose tissue,abdominal wall adipose tissue and liver were measured,respectively.The differences of FF and R2* value of chest wall,subcutaneous and supraclavicular adipose tissue were compared between two groups,and the correlation between FF,R2* value of supraclavicular adipose tissue and BMI was respectively analyzed.Results FF of supraclavicular adipose tissue ([80.99 ± 7.73]％) was lower than that of chest wall subcutaneous adipose tissue ([93.04 ± 1.55] ％,P＜0.001).R2* of supraclavicular adipose tissue ([65.52±23.59]Hz) was higher than that of chest wall subcutaneous adipose tissue ([38.82±7.11]Hz,P＜0.001).The differences of FF and R2* values of supraclavicular adipose tissue,chest wall,abdominal wall subcutaneous adipose tissue and liver were significant between BMI＜24 kg/m2 group and BMI≥24 kg/m2 group (all P＜0.05).There was positive correlation (r=0.601,P＜0.001) between FF of supraclavicular adipose tissue and BMI and negative correlation (r=-0.409,P =0.001) between R2* of supraclavicular adipose tissue and BMI.Conclusion IDEAL-IQ technique can quantitatively assess the difference between subcutaneous and supraclavicular adipose tissue in healthy young women.FF and R2 * value has significant difference between the above mentioned positions.