Cross-Cohort Automatic Knee MRI Segmentation With Multi-Planar U-Nets

Background: Segmentation of medical image volumes is a time-consuming manual task. Automatic tools are often tailored toward specific patient cohorts, and it is unclear how they behave in other clinical settings.

Purpose: To evaluate the performance of the open-source Multi-Planar U-Net (MPUnet), the validated Knee Imaging Quantification (KIQ) framework, and a state-of-the-art two-dimensional (2D) U-Net architecture on three clinical cohorts without extensive adaptation of the algorithms.

Study type: Retrospective cohort study.

Subjects: A total of 253 subjects (146 females, 107 males, ages 57 ± 12 years) from three knee osteoarthritis (OA) studies (Center for Clinical and Basic Research [CCBR], Osteoarthritis Initiative [OAI], and Prevention of OA in Overweight Females [PROOF]) with varying demographics and OA severity (64/37/24/53/2 scans of Kellgren and Lawrence [KL] grades 0-4).

Field strength/sequence: 0.18 T, 1.0 T/1.5 T, and 3 T sagittal three-dimensional fast-spin echo T1w and dual-echo steady-state sequences.

Assessment: All models were fit without tuning to knee magnetic resonance imaging (MRI) scans with manual segmentations from three clinical cohorts. All models were evaluated across KL grades.

Statistical tests: Segmentation performance differences as measured by Dice coefficients were tested with paired, two-sided Wilcoxon signed-rank statistics with significance threshold α = 0.05.

Results: The MPUnet performed superior or equal to KIQ and 2D U-Net on all compartments across three cohorts. Mean Dice overlap was significantly higher for MPUnet compared to KIQ and U-Net on CCBR ( $0.83\pm 0.04$ vs. $0.81\pm 0.06$ and $0.82\pm 0.05$ ), significantly higher than KIQ and U-Net OAI ( $0.86\pm 0.03$ vs. $0.84\pm 0.04$ and $0.85\pm 0.03)$ , and not significantly different from KIQ while significantly higher than 2D U-Net on PROOF ( $0.78\pm 0.07$ vs. $0.77\pm 0.07$ , $P=0.10$ , and $0.73\pm 0.07)$ . The MPUnet performed significantly better on $N=22$ KL grade 3 CCBR scans with $0.78\pm 0.06$ vs. $0.75\pm 0.08$ for KIQ and $0.76\pm 0.06$ for 2D U-Net.

Data conclusion: The MPUnet matched or exceeded the performance of state-of-the-art knee MRI segmentation models across cohorts of variable sequences and patient demographics. The MPUnet required no manual tuning making it both accurate and easy-to-use.

Level of evidence: 3 TECHNICAL EFFICACY: Stage 2.