UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

Ji, Yuanfeng; Zhang, Ruimao; Li, Zhen; Ren, Jinchang; Zhang, Shaoting; Luo, Ping

doi:10.1007/978-3-030-59710-8_34

Cited by 16 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea is to use meta-learning to focus on pixels that have gradients closer to those of expert labels. Ji et al [22] employ a neural architecture search based method for volumetric medical image segmentation by searching for scale-wise feature aggregation strategies and blockwise operators in the encoder-decoder network in an effort to generate better feature representations.…”

Section: Related Workmentioning

confidence: 99%

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

Zunair¹,

Hamza²

2021

Preprint

View full text Add to dashboard Cite

The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low-and high-level convolutional features, resulting in not only blurred feature maps, but also overand under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

Zunair¹,

Hamza²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It also plays a vital role in designing a computer-aided detection or diagnostic system (13)(14)(15). Recently, deep learning techniques have made significant progress in medical image segmentation (16)(17)(18). The convolution neural network (CNN) has become a promising choice in breast ultrasound image segmentation (19)(20)(21)(22).…”

Section: Introductionmentioning

confidence: 99%

Application of Convolution Neural Network Algorithm Based on Multicenter ABUS Images in Breast Lesion Detection

Zhang

Tong

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

ObjectiveThis study aimed to evaluate a convolution neural network algorithm for breast lesion detection with multi-center ABUS image data developed based on ABUS image and Yolo v5.MethodsA total of 741 cases with 2,538 volume data of ABUS examinations were analyzed, which were recruited from 7 hospitals between October 2016 and December 2020. A total of 452 volume data of 413 cases were used as internal validation data, and 2,086 volume data from 328 cases were used as external validation data. There were 1,178 breast lesions in 413 patients (161 malignant and 1,017 benign) and 1,936 lesions in 328 patients (57 malignant and 1,879 benign). The efficiency and accuracy of the algorithm were analyzed in detecting lesions with different allowable false positive values and lesion sizes, and the differences were compared and analyzed, which included the various indicators in internal validation and external validation data.ResultsThe study found that the algorithm had high sensitivity for all categories of lesions, even when using internal or external validation data. The overall detection rate of the algorithm was as high as 78.1 and 71.2% in the internal and external validation sets, respectively. The algorithm could detect more lesions with increasing nodule size (87.4% in ≥10 mm lesions but less than 50% in <10 mm). The detection rate of BI-RADS 4/5 lesions was higher than that of BI-RADS 3 or 2 (96.5% vs 79.7% vs 74.7% internal, 95.8% vs 74.7% vs 88.4% external). Furthermore, the detection performance was better for malignant nodules than benign (98.1% vs 74.9% internal, 98.2% vs 70.4% external).ConclusionsThis algorithm showed good detection efficiency in the internal and external validation sets, especially for category 4/5 lesions and malignant lesions. However, there are still some deficiencies in detecting category 2 and 3 lesions and lesions smaller than 10 mm.

show abstract

“…1 (a)). The UNet [16] based encoder-decoder networks [16,24,12] merge Ping Luo is the corresponding author of this paper. In contrast to (a-c), MCTrans models pixel-wise relationships between multiple scales features, enabling more consistent and effective context encoding.…”

Section: Introductionmentioning

confidence: 99%

Multi-compound Transformer for Accurate Biomedical Image Segmentation

Zhang

Wang

et al. 2021

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

The recent vision transformer (i.e. for image classification) learns nonlocal attentive interaction of different patch tokens. However, prior arts miss learning the cross-scale dependencies of different pixels, the semantic correspondence of different labels, and the consistency of the feature representations and semantic embeddings, which are critical for biomedical segmentation. In this paper, we tackle the above issues by proposing a unified transformer network, termed Multi-Compound Transformer (MCTrans), which incorporates rich feature learning and semantic structure mining into a unified framework. Specifically, MCTrans embeds the multi-scale convolutional features as a sequence of tokens, and performs intra-and inter-scale self-attention, rather than single-scale attention in previous works. In addition, a learnable proxy embedding is also introduced to model semantic relationship and feature enhancement by using selfattention and cross-attention, respectively. MCTrans can be easily plugged into a UNet-like network, and attains a significant improvement over the state-of-theart methods in biomedical image segmentation in six standard benchmarks. For example, MCTrans outperforms UNet by 3.64%, 3.71%, 4.34%, 2.8%, 1.88%, 1.57% in Pannuke, CVC-Clinic, CVC-Colon, Etis, Kavirs, ISIC2018 dataset, respectively. Code is available at https://github.com/JiYuanFeng/MCTrans.

show abstract

UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

Cited by 16 publications

References 24 publications

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation

Application of Convolution Neural Network Algorithm Based on Multicenter ABUS Images in Breast Lesion Detection

Multi-compound Transformer for Accurate Biomedical Image Segmentation

Contact Info

Product

Resources

About