Journal: BMC Cancer

Article Title: Artificial intelligence utilization in cancer screening program across ASEAN: a scoping review

doi: 10.1186/s12885-025-14026-x

Figure Lengend Snippet: Characteristics of the reviewed studies focusing on the utilization of AI technology in the ASEAN region until May 2024

Article Snippet: Hamid et al. (2024) [ ] , Malaysia , Breast , , Application of Artificial Intelligence (AI) System in Opportunistic Screening and Diagnostic Population in a Middle-income Nation , , Retrospective cross-sectional study , Deep learning model (DL)- Lunit INSIGHT MMG (version 1.1.7.2, Lunit, South Korea) , Silent trial.

Techniques: Imaging, Genome Wide, Methylation, Modification, Diagnostic Assay

Journal: Osteology (Basel, Switzerland)

Article Title: Shoulder Bone Segmentation with DeepLab and U-Net

doi: 10.3390/osteology4020008

Figure Lengend Snippet: Architectures of (A) U-Net and (B) DeepLab used in this study. Adapted from and , respectively. Training results showing accuracy and loss values for (C) U-Net and (D) DeepLab.

Article Snippet: We have implemented two-dimensional (2D) U-Net [ ] and DeepLab v3 [ ] deep learning (DL) models in Matlab with Deep Learning Toolbox (R2021b) to perform the segmentation of shoulder ZTE MR images.

Techniques:

Journal: Osteology (Basel, Switzerland)

Article Title: Shoulder Bone Segmentation with DeepLab and U-Net

doi: 10.3390/osteology4020008

Figure Lengend Snippet: Segmentation results on test images. (A, D) Ground truth or manually segmented images of humeral bone and the remaining other tissues shown for comparison. Output segmented images of (B, C) the humeral head (E, F) and the remaining tissues after DL segmentation performed by (B,E) U-Net and (C,F) DeepLab. Qualitatively, U-Net slightly over-estimated area for humeral head while DeepLab slightly under-estimated. (G) Input ZTE MRI image is shown. (H, I) Segmented ZTE images (from the ground truth; A and D) were used to create separate 3D renderings of the (H) humerus and (I) glenoid / scapular bone.

Article Snippet: We have implemented two-dimensional (2D) U-Net [ ] and DeepLab v3 [ ] deep learning (DL) models in Matlab with Deep Learning Toolbox (R2021b) to perform the segmentation of shoulder ZTE MR images.

Techniques: Comparison

Journal: Osteology (Basel, Switzerland)

Article Title: Shoulder Bone Segmentation with DeepLab and U-Net

doi: 10.3390/osteology4020008

Figure Lengend Snippet: DL model performances compared. Boxplots of inference accuracy (Dice score, sensitivity, specificity) quantified on the humeral bone (A) and the remaining tissue (B), determined using U-Net (blue) and DeepLab (red) models. Marked differences in the accuracy metrics for the humeral bone was noted.

Article Snippet: We have implemented two-dimensional (2D) U-Net [ ] and DeepLab v3 [ ] deep learning (DL) models in Matlab with Deep Learning Toolbox (R2021b) to perform the segmentation of shoulder ZTE MR images.

Techniques:

Journal: Osteology (Basel, Switzerland)

Article Title: Shoulder Bone Segmentation with DeepLab and U-Net

doi: 10.3390/osteology4020008

Figure Lengend Snippet: Mean and standard deviation of the Dice scores, sensitivity, and specificity values. P-values from t-tests indicate statistical difference between the mean values obtained using U-Net vs. DeepLab.

Article Snippet: We have implemented two-dimensional (2D) U-Net [ ] and DeepLab v3 [ ] deep learning (DL) models in Matlab with Deep Learning Toolbox (R2021b) to perform the segmentation of shoulder ZTE MR images.

Techniques: Standard Deviation