Deriving new soft tissue contrasts from conventional MR images using deep learning

Deep Learning Assisted Classification of T1ρ-MR Based Intervertebral Disc Degeneration Phases

BACKGROUND

According to the T1ρ value of nucleus pulposus, our previous study has found that intervertebral disc degeneration (IDD) can be divided into three phases based on T1ρ-MR, which is helpful for the selection of biomaterial treatment timing. However, the routine MR sequences for patients with IDD are T1- and T2-MR, T1ρ-MR is not commonly used due to long scanning time and extra expenses, which limits the application of T1ρ-MR based IDD phases.

PURPOSE

To build a deep learning model to achieve the classification of T1ρ-MR based IDD phases from routine T1-MR images.

STUDY TYPE

Retrospective.

POPULATION

Sixty (M/F: 35/25) patients with low back pain or lower limb radiculopathy are randomly divided into training (N = 50) and test (N = 10) sets.

FIELD STRENGTH/SEQUENCES

1.5 T MR scanner; T1-, T2-, and T1ρ-MR sequence (spin echo).

ASSESSMENT

The T1ρ values of the nucleus pulposus in intervertebral discs (IVDs) were measured. IVDs were divided into three phases based on the mean T1ρ value: pre-degeneration phase (mean T1ρ value >110 msec), rapid degeneration phase (mean T1ρ value: 80-110 msec), and late degeneration phase (mean T1ρ value <80 msec). After measurement, the T1ρ values, phases, and levels of IVDs were input into the model as labels.

STATISTICAL TESTS

Intraclass correlation coefficient, area under the receiver operating characteristic curve (AUC), F1-score, accuracy, precision, and recall (P < 0.05 was considered significant).

RESULTS

In the test dataset, the model achieved a mean average precision of 0.996 for detecting IVD levels. The diagnostic accuracy of the T1ρ-MR based IDD phases was 0.840 and the AUC was 0.871, the average AUC of 5-folds cross validation was 0.843.

DATA CONCLUSION

The proposed deep learning model achieved the classification of T1ρ-MR based IDD phases from routine T1-MR images, which may provide a method to facilitate the application of T1ρ-MR in IDD.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Deep Learning-Based Water-Fat Separation from Dual-Echo Chemical Shift-Encoded Imaging

Conventional water–fat separation approaches suffer long computational times and are prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual-echo water–fat separation method. With IRB approval, raw data from 68 pediatric clinically indicated dual echo scans were analyzed, corresponding to 19382 contrast-enhanced images. A densely connected hierarchical convolutional network was constructed, in which dual-echo images and corresponding echo times were used as input and water/fat images obtained using the projected power method were regarded as references. Models were trained and tested using knee images with 8-fold cross validation and validated on out-of-distribution data from the ankle, foot, and arm. Using the proposed method, the average computational time for a volumetric dataset with ~400 slices was reduced from 10 min to under one minute. High fidelity was achieved (correlation coefficient of 0.9969, l1 error of 0.0381, SSIM of 0.9740, pSNR of 58.6876) and water/fat swaps were mitigated. I is of particular interest that metal artifacts were substantially reduced, even when the training set contained no images with metallic implants. Using the models trained with only contrast-enhanced images, water/fat images were predicted from non-contrast-enhanced images with high fidelity. The proposed water–fat separation method has been demonstrated to be fast, robust, and has the added capability to compensate for metal artifacts.