mlsanityData to 7 Oct 2026

Segmentation of Shoulder Muscle MRI Using a New Region and Edge based Deep Auto-Encoder

arXiv 2108.11720 ↗First posted 26 Aug 2021eess.IV cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Automatic segmentation of shoulder muscle MRI is challenging due to the high variation in muscle size, shape, texture, and spatial position of tears. Manual segmentation of tear and muscle portion is hard, time-consuming, and subjective to pathological expertise. This work proposes a new Region and Edge-based Deep Auto-Encoder (RE-DAE) for shoulder muscle MRI segmentation. The proposed RE-DAE harmoniously employs average and max-pooling operation in the encoder and decoder blocks of the Convolutional Neural Network (CNN). Region-based segmentation incorporated in the Deep Auto-Encoder (DAE) encourages the network to extract smooth and homogenous regions. In contrast, edge-based segmentation tries to learn the boundary and anatomical information. These two concepts, systematically combined in a DAE, generate a discriminative and sparse hybrid feature space (exploiting both region homogeneity and boundaries). Moreover, the concept of static attention is exploited in the proposed RE-DAE that helps in effectively learning the tear region. The performances of the proposed MRI segmentation based DAE architectures have been tested using a 3D MRI shoulder muscle dataset using the hold-out cross-validation technique. The MRI data has been collected from the Korea University Anam Hospital, Seoul, South Korea. Experimental comparisons have been conducted by employing innovative custom-made and existing pre-trained CNN architectures both using transfer learning and fine-tuning. Objective evaluation on the muscle datasets using the proposed SA-RE-DAE showed a dice similarity of 85.58% and 87.07%, an accuracy of 81.57% and 95.58% for tear and muscle regions, respectively. The high visual quality and the objective result suggest that the proposed SA-RE-DAE is able to correctly segment tear and muscle regions in shoulder muscle MRI for better clinical decisions.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 17 of its 66 references that are in the map. First posted on arXiv 26 Aug 2021.

Builds on

17 of 66 references.

References · 17

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  6. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  7. 2018Attention Gated Networks: Learning to Leverage Salient Regions in Medical Imagescited by 271
  8. 2019A Survey of the Recent Architectures of Deep Convolutional Neural Networkscited by 211
  9. 2014MatConvNet - Convolutional Neural Networks for MATLABcited by 36
  10. 2015Understanding symmetries in deep networkscited by 17
  11. 2020COVID-19 Detection in Chest X-Ray Images using a New Channel Boosted CNNcited by 15
  12. 2019Automatic brain tissue segmentation in fetal MRI using convolutional neural networkscited by 14
5 more
  1. 2018U-SegNet: Fully Convolutional Neural Network based Automated Brain tissue segmentation Toolcited by 11
  2. 2020Classification and Region Analysis of COVID-19 Infection using Lung CT Images and Deep Convolutional Neural Networkscited by 11
  3. 2019Healthy versus pathological learning transferability in shoulder muscle MRI segmentation using deep convolutional encoder-decoderscited by 6
  4. 2019Transfer Learning and Meta Classification Based Deep Churn Prediction System for Telecom Industrycited by 6
  5. 2018Adaptive Transfer Learning in Deep Neural Networks: Wind Power Prediction using Knowledge Transfer from Region to Region and Between Different Task Domainscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 3; 2024: 3; 2025: 2; 2026: 2.

15 papers.

Sort:

  1. 2023A survey of the Vision Transformers and their CNN-Transformer based Variantscited by 33
  2. 2022A New Deep Hybrid Boosted and Ensemble Learning-based Brain Tumor Analysis using MRIcited by 10
  3. 2022IoT Malware Detection Architecture using a Novel Channel Boosted and Squeezed CNNcited by 10
  4. 2023MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentationcited by 8
  5. 2022Brain Tumor MRI Classification using a Novel Deep Residual and Regional CNNcited by 7
  6. 2022A New Deep Boosted CNN and Ensemble Learning based IoT Malware Detectioncited by 6
  7. 2023COVID-19 Infection Analysis Framework using Novel Boosted CNNs and Radiological Imagescited by 4
  8. 2024RS-FME-SwinT: A Novel Feature Map Enhancement Framework Integrating Customized SwinT with Residual and Spatial CNN for Monkeypox Diagnosiscited by 4
  9. 2025CE-RS-SBCIT A Novel Channel Enhanced Hybrid CNN Transformer with Residual, Spatial, and Boundary-Aware Learning for Brain Tumor MRI Analysiscited by 3
  10. 2025RS-CA-HSICT: A Residual and Spatial Channel Augmented CNN Transformer Framework for Monkeypox Detectioncited by 3
  11. 2024A Novel Feature Map Enhancement Technique Integrating Residual CNN and Transformer for Alzheimer Diseases Diagnosiscited by 2
  12. 2022Malaria Parasitic Detection using a New Deep Boosted and Ensemble Learning Frameworkcited by 1
3 more
  1. 2026A Tumor Aware DenseNet Swin Hybrid Learning with Boosted and Hierarchical Feature Spaces for Large-Scale Brain MRI Classificationcited by 1
  2. 2024A Novel Decision Ensemble Framework: Customized Attention-BiLSTM and XGBoost for Speculative Stock Price Forecastingcited by 0
  3. 2026DenseSwinV2: Channel Attentive Dual Branch CNN Transformer Learning for Cassava Leaf Disease Classificationcited by 0