The role of input imaging combination and ADC threshold on segmentation of acute ischemic stroke lesion using U-Net.

BACKGROUND: To evaluate the effect of the weighting of input imaging combo and ADC threshold on the performance of the U-Net and to find an optimized input imaging combo and ADC threshold in segmenting acute ischemic stroke (AIS) lesion. METHODS: This study retrospectively enrolled a total of 212 patients having AIS. Four combos, including ADC-ADC-ADC (AAA), DWI-ADC-ADC (DAA), DWI-DWI-ADC (DDA), and DWI-DWI-DWI (DDD), were used as input images, respectively. Three ADC thresholds including 0.6, 0.8 and 1.8 × 10-3 mm2/s were applied. Dice similarity coefficient (DSC) was used to evaluate the segmentation performance of U-Nets. Nonparametric Kruskal-Wallis test with Tukey-Kramer post-hoc tests were used for comparison. A p < .05 was considered statistically significant. RESULTS: The DSC significantly varied among different combos of images and different ADC thresholds. Hybrid U-Nets outperformed uniform U-Nets at ADC thresholds of 0.6 × 10-3 mm2/s and 0.8 × 10-3 mm2/s (p < .001). The U-Net with imaging combo of DDD had segmentation performance similar to hybrid U-Nets at an ADC threshold of 1.8 × 10-3 mm2/s (p = .062 to 1). The U-Net using the imaging combo of DAA at the ADC threshold of 0.6 × 10-3 mm2/s achieved the highest DSC in the segmentation of AIS lesion. CONCLUSIONS: The segmentation performance of U-Net for AIS varies among the input imaging combos and ADC thresholds. The U-Net is optimized by choosing the imaging combo of DAA at an ADC threshold of 0.6 × 10-3 mm2/s in segmentating AIS lesion with highest DSC. KEY POINTS: • Segmentation performance of U-Net for AIS differs among input imaging combos. • Segmentation performance of U-Net for AIS differs among ADC thresholds. • U-Net is optimized using DAA with ADC = 0.6 × 10-3 mm2/s.

Imaging quality of PROPELLER diffusion-weighted MR imaging and its diagnostic performance in distinguishing pleomorphic adenomas from Warthin tumors of the parotid gland.

The aim of this study was to evaluate the imaging quality and diagnostic performance of fast spin echo diffusion-weighted imaging with periodically rotated overlapping parallel lines with enhanced reconstruction (FSE-PROP-DWI) in distinguishing parotid pleomorphic adenoma (PMA) from Warthin tumor (WT). This retrospective study enrolled 44 parotid gland tumors from 34 patients, including 15 PMAs and 29 WTs with waived written informed consent. All participants underwent 1.5 T diffusion-weighted imaging including FSE-PROP-DWI and single-shot echo-planar diffusion-weighted imaging (SS-EP-DWI). After imaging resizing and registration among T2WI, FSE-PROP-DWI and SS-EP-DWI, imaging distortion was quantitatively analyzed by using the Dice coefficient. Signal-to-noise ratio and contrast-to-noise ratio were qualitatively evaluated. The mean apparent diffusion coefficient (ADC) of parotid gland tumors was calculated. Wilcoxon signed-rank test was used for paired comparison between FSE-PROP-DWI versus SS-EP-DWI. Mann-Whitney U test was used for independent group comparison between PMAs versus WTs. Diagnostic performance was evaluated by receiver operating characteristics curve analysis. P < 0.05 was considered statistically significant. The Dice coefficient was statistically significantly higher on FSE-PROP-DWI than SS-EP-DWI for both tumors (P < 0.005). Mean ADC was statistically significantly higher in PMAs than WTs on both FSE-PROP-DWI and SS-EP-DWI (P < 0.005). FSE-PROP-DWI and SS-EP-DWI successfully distinguished PMAs from WTs with an AUC of 0.880 and 0.945, respectively (P < 0.05). Sensitivity, specificity, positive predictive value, negative predictive value and accuracy in diagnosing PMAs were 100%, 69.0%, 62.5%, 100% and 79.5% for FSE-PROP-DWI, and 100%, 82.8%, 75%, 100% and 88.6% for SS-EP-DWI, respectively. FSE-PROP-DWI is useful to distinguish parotid PMAs from WTs with less distortion of tumors but lower AUC than SS-EP-DWI.

Improving performance of deep learning models using 3.5D U-Net via majority voting for tooth segmentation on cone beam computed tomography.

Deep learning allows automatic segmentation of teeth on cone beam computed tomography (CBCT). However, the segmentation performance of deep learning varies among different training strategies. Our aim was to propose a 3.5D U-Net to improve the performance of the U-Net in segmenting teeth on CBCT. This study retrospectively enrolled 24 patients who received CBCT. Five U-Nets, including 2Da U-Net, 2Dc U-Net, 2Ds U-Net, 2.5Da U-Net, 3D U-Net, were trained to segment the teeth. Four additional U-Nets, including 2.5Dv U-Net, 3.5Dv5 U-Net, 3.5Dv4 U-Net, and 3.5Dv3 U-Net, were obtained using majority voting. Mathematical morphology operations including erosion and dilation (E&D) were applied to remove diminutive noise speckles. Segmentation performance was evaluated by fourfold cross validation using Dice similarity coefficient (DSC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV). Kruskal-Wallis test with post hoc analysis using Bonferroni correction was used for group comparison. P < 0.05 was considered statistically significant. Performance of U-Nets significantly varies among different training strategies for teeth segmentation on CBCT (P < 0.05). The 3.5Dv5 U-Net and 2.5Dv U-Net showed DSC and PPV significantly higher than any of five originally trained U-Nets (all P < 0.05). E&D significantly improved the DSC, accuracy, specificity, and PPV (all P < 0.005). The 3.5Dv5 U-Net achieved highest DSC and accuracy among all U-Nets. The segmentation performance of the U-Net can be improved by majority voting and E&D. Overall speaking, the 3.5Dv5 U-Net achieved the best segmentation performance among all U-Nets.