CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation

Chen, Cheng; Liu, Bo; Zhou, Kangneng; He, Wanzhang; Yan, Fei; Wang, Zhiliang; Xiao, Ruoxiu

doi:10.1016/j.compbiomed.2021.104776

Cited by 27 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Ma, Zou & Liu (2021) added a context module to jump connections in the MHSU-Net network to reduce feature loss during segmentation. Chen et al (2021a) proposed cross-scale residual network (CSR-Net), which realizes the fusion of features from different layers through cross-scale residual connections and realizes the transformation between different scales and channels of the hierarchy to establish a close connection at different resolutions. Soulami et al (2021) proposed an end-to-end improved UNet model that combines residual fast and hybrid loss functions for detecting, segmenting, and classifying breast masses in one stage.…”

Section: Related Workmentioning

confidence: 99%

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation

Li,

Tian,

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

Melanoma is a malignant skin tumor that threatens human life and health. Early detection is essential for effective treatment. However, the low contrast between melanoma lesions and normal skin and the irregularity in size and shape make skin lesions difficult to detect with the naked eye in the early stages, making the task of skin lesion segmentation challenging. Traditional encoder-decoder built with U-shaped networks using convolutional neural network (CNN) networks have limitations in establishing long-term dependencies and global contextual connections, while the Transformer architecture is limited in its application to small medical datasets. To address these issues, we propose a new skin lesion segmentation network, SUTrans-NET, which combines CNN and Transformer in a parallel fashion to form a dual encoder, where both CNN and Transformer branches perform dynamic interactive fusion of image information in each layer. At the same time, we introduce our designed multi-grouping module SpatialGroupAttention (SGA) to complement the spatial and texture information of the Transformer branch, and utilize the Focus idea of YOLOV5 to construct the Patch Embedding module in the Transformer to prevent the loss of pixel accuracy. In addition, we design a decoder with full-scale information fusion capability to fully fuse shallow and deep features at different stages of the encoder. The effectiveness of our method is demonstrated on the ISIC 2016, ISIC 2017, ISIC 2018 and PH2 datasets and its advantages over existing methods are verified.

show abstract

Section: Related Workmentioning

confidence: 99%

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation

Li,

Tian,

et al. 2024

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…Finally, they removed small-sized predictions to decrease the false positive. Chen et al (2021a) proposed the cross-scale residual network (CSR-Net) to segment scaphoid fracture. This model allows a cross-scale residual connection to merge the features from different scales.…”

Section: Image Segmentationmentioning

confidence: 99%

A review of advances in image-guided orthopedic surgery

Fan¹,

Zhu²,

Tu³

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Orthopedic surgery remains technically demanding due to the complex anatomical structures and cumbersome surgical procedures. The introduction of image-guided orthopedic surgery (IGOS) has significantly decreased the surgical risk and improved the operation results. This review focuses on the application of recent advances in Artificial Intelligence (AI), Deep Learning (DL), Augmented Reality (AR) and Robotics in image-guided spine surgery, joint arthroplasty, fracture reduction and bone tumor resection. For the pre-operative stage, key technologies of AI and deep learning based medical image segmentation, 3D reconstruction and surgical planning procedures are systematically reviewed. For the intra-operative stage, the development of novel image registration, surgical tool calibration and real-time navigation are reviewed. Furthermore, the combination of the surgical navigation system with augmented reality (AR) and robotic technology is also discussed. Finally, the current issues and prospects of the IGOS system are discussed, with the goal of establishing a reference and providing guidance for surgeons, engineers, and researchers involved in the research and development of this area.

show abstract

“…The scaphoid fracture (ScaF) dataset is from Beijing Jishuitan Hospital, taken from the scaphoid fracture patients, and scanned with a TOSHIBA Aquilion PRIME equipment with 120 kV voltage and 180 mA current. We expanded this dataset to 84 cases based on our previous work (Chen et al 2021a). All CT images were cropped around the scaphoid bone to size of 128 × 128 × 128 per the guidance of clinical experts.…”

Section: Datasetsmentioning

confidence: 99%

Pairwise attention-enhanced adversarial model for automatic bone segmentation in CT images

Chen¹,

Qi²,

Zhou³

et al. 2023

Phys. Med. Biol.

Self Cite

View full text Add to dashboard Cite

Objective: Bone segmentation is a critical step in screw placement navigation. Although the deep learning methods have promoted the rapid development for bone segmentation, the local bone separation is still challenging due to irregular shapes and similar representational features. Approach: In this paper, we proposed the pairwise attention-enhanced adversarial model (Pair-SegAM) for automatic bone segmentation in CT images, which includes the two parts of the segmentation model and discriminator. Considering that the distributions of the predictions from the segmentation model contains complicated semantics, we improve the discriminator to strengthen the awareness ability of the target region, improving the parsing of semantic information features. The Pair-SegAM has a pairwise structure, which uses two calculation mechanics to set up pairwise attention maps, then we utilize the semantic fusion to filter unstable regions. Therefore, the improved discriminator provides more refinement information to capture the bone outline, thus effectively enhancing the segmentation models for bone segmentation. Main results: To test the Pair-SegAM, we selected the two bone datasets for assessment. We evaluated our method against several bone segmentation models and latest adversarial models on the both datasets. The experimental results prove that our method not only exhibits superior bone segmentation performance, but also states effective generalization. Significance: Our method provides a more efficient segmentation of specific bones and has the potential to be extended to other semantic segmentation domains.

show abstract

CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation

Cited by 27 publications

References 33 publications

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation

SUTrans-NET: a hybrid transformer approach to skin lesion segmentation

A review of advances in image-guided orthopedic surgery

Pairwise attention-enhanced adversarial model for automatic bone segmentation in CT images

Contact Info

Product

Resources

About