High-resolution Magnetic Resonance Imaging of the Triangular Fibrocartilage Complex Using Compressed Sensing Sensitivity Encoding (SENSE)

Evaluation of the consistency of the MRI- based AI segmentation cartilage model using the natural tibial plateau cartilage

OBJECTIVE

The study aims to evaluate the accuracy of an MRI-based artificial intelligence (AI) segmentation cartilage model by comparing it to the natural tibial plateau cartilage.

METHODS

This study included 33 patients (41 knees) with severe knee osteoarthritis scheduled to undergo total knee arthroplasty (TKA). All patients had a thin-section MRI before TKA. Our study is mainly divided into two parts: (i) In order to evaluate the MRI-based AI segmentation cartilage model's 2D accuracy, the natural tibial plateau was used as gold standard. The MRI-based AI segmentation cartilage model and the natural tibial plateau were represented in binary visualization (black and white) simulated photographed images by the application of Simulation Photography Technology. Both simulated photographed images were compared to evaluate the 2D Dice similarity coefficients (DSC). (ii) In order to evaluate the MRI-based AI segmentation cartilage model's 3D accuracy. Hand-crafted cartilage model based on knee CT was established. We used these hand-crafted CT-based knee cartilage model as gold standard to evaluate 2D and 3D consistency of between the MRI-based AI segmentation cartilage model and hand-crafted CT-based cartilage model. 3D registration technology was used for both models. Correlations between the MRI-based AI knee cartilage model and CT-based knee cartilage model were also assessed with the Pearson correlation coefficient.

RESULTS

The AI segmentation cartilage model produced reasonably high two-dimensional DSC. The average 2D DSC between MRI-based AI cartilage model and the tibial plateau cartilage is 0.83. The average 2D DSC between the AI segmentation cartilage model and the CT-based cartilage model is 0.82. As for 3D consistency, the average 3D DSC between MRI-based AI cartilage model and CT-based cartilage model is 0.52. However, the quantification of cartilage segmentation with the AI and CT-based models showed excellent correlation (r = 0.725; P values < 0.05).

CONCLUSION

Our study demonstrated that our MRI-based AI cartilage model can reliably extract morphologic features such as cartilage shape and defect location of the tibial plateau cartilage. This approach could potentially benefit clinical practices such as diagnosing osteoarthritis. However, in terms of cartilage thickness and three-dimensional accuracy, MRI-based AI cartilage model underestimate the actual cartilage volume. The previous AI verification methods may not be completely accurate and should be verified with natural cartilage images. Combining multiple verification methods will improve the accuracy of the AI model.

Comparison of compressed sensing-sensitivity encoding (CS-SENSE) accelerated 3D T2W TSE sequence versus conventional 3D and 2D T2W TSE sequences in rectal cancer: a prospective study

PURPOSE

This study aimed to evaluate the image quality and diagnostic value of compressed sensing-sensitivity encoding (CS-SENSE) accelerated 3-dimensional (3D) T2-weighted turbo spin-echo (T2W TSE) sequence in patients with rectal cancer compared with conventional 3D and 2-dimensional (2D) sequences.

METHODS

A total of 54 patients who underwent the above three sequences were enrolled. Two radiologists independently reviewed the image quality using an ordinal 5-point Likert scale. The quantitative measurement was performed to calculate the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The diagnostic value was assessed using TN staging, extramural vascular invasion and mesorectal fascia status. Friedman and McNemar's tests were applied for comparative analysis.

RESULTS

Forty-two patients were successfully included. Compared with 3D and 2D sequences, the CS-SENSE 3D sequence speeded up by 39% and 23%, respectively. The edge sharpness of CS-SENSE 3D images was similar to that of 3D and 2D images. The noise of CS-SENSE 3D images was comparable to that of 3D images but higher than that of 2D images. The SNR_tumor and SNR_{rectal wall} of CS-SENSE 3D images were considerably lower than those of 3D and 2D images. The CNR of CS-SENSE 3D images was similar to that of 3D images but lower than that of 2D images. However, no considerable differences were noted in diagnostic value among the three sequences.

CONCLUSIONS

CS-SENSE 3D T2 sequence provided comparable diagnostic performance, with substantially reduced imaging time and no significant sacrifices in image quality. This technique may serve as a reliable tool for evaluating rectal cancer.