Brain tumour segmentation based on an improved U-Net

Zheng, Ping; Zhu, Xunfei; Guo, Wenbo

doi:10.1186/s12880-022-00931-1

Cited by 22 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is estimated to take 9-11 hours to segment 5-20 brain images [10]. Many proposed models based on U -net [11] have achieved state-of-the-art performances in brain segmentation, which adopt a serial encoding-decoding structure and use hybrid dilated convolution (HDC) modules. Their results are in line with a recent study in brain segmentation, which investigates concatenation between each module of two serial networks [11].…”

Section: Related Workmentioning

confidence: 99%

Two Independent Teachers are Better Role Model

Khaled

Mubarak

2023

Preprint

View full text Add to dashboard Cite

Recent deep learning models have attracted substantial attention in infant brainanalysis. These models have performed state-of-the-art performance, such as semi-supervised techniques (e.g., Temporal Ensembling, mean teacher). However, these models depend on an encoder-decoder structure with stacked local operators togather long-range information, and the local operators limit the efficiency and effectiveness. Besides, the MRI data contain different tissue properties (T P s) suchas T1 and T2. One major limitation of these models is that they use both dataas inputs to the segment process, i.e., the models are trained on the dataset once, and it requires much computational and memory requirements during inference. In this work, we address the above limitations by designing a new deep-learningmodel, called 3D-DenseUNet, which works as adaptable global aggregation blocksin down-sampling to solve the issue of spatial information loss. The self-attention module connects the down-sampling blocks to up-sampling blocks, and integrates the feature maps in three dimensions of spatial and channel, effectively improvingthe representation potential and discriminating ability of the model. Additionally, we propose a new method called Two Independent Teachers (2IT), that summarizes the model weights instead of label predictions. Each teacher model is trainedon different types of brain data, T1 and T2, respectively. Then, a fuse model is added to improve test accuracy and enable training with fewer parameters andlabels compared to the Temporal Ensembling method without modifying the network architecture. Empirical results demonstrate the effectiveness of the proposed method. The code is publicly available at: https://github.com/AfifaKhaled/Two-Independent-Teachers-are-Better-Role-Model

show abstract

Section: Related Workmentioning

confidence: 99%

Two Independent Teachers are Better Role Model

Khaled

Mubarak

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…13,39,40,43,51,52 In recent years, the technology of machine learning has made significant strides in processing images, including recognition, segmentation, and classification. 62 These technologies have been widely used and made significant contributions to the auxiliary diagnosis of organ lesions, especially in the lung, 63 breast, 64 thyroid, 65 and other organs. 62 Therefore, a number of researchers have begun also to apply traditional machine learning or deep learning technologies to identify HB in MASH and conduct quantitative analysis automatically.…”

Section: Analys Is Limitations Of E Xis Ting Hb Recog Niti On Alg Ori...mentioning

confidence: 99%

Object detection: A novel AI technology for the diagnosis of hepatocyte ballooning

Zheng,

Sha,

Deng

et al. 2023

Liver International

View full text Add to dashboard Cite

Metabolic dysfunction‐associated fatty liver disease (MAFLD) has reached epidemic proportions worldwide and is the most frequent cause of chronic liver disease in developed countries. Within the spectrum of liver disease in MAFLD, steatohepatitis is a progressive form of liver disease and hepatocyte ballooning (HB) is a cardinal pathological feature of steatohepatitis. The accurate and reproducible diagnosis of HB is therefore critical for the early detection and treatment of steatohepatitis. Currently, a diagnosis of HB relies on pathological examination by expert pathologists, which may be a time‐consuming and subjective process. Hence, there has been interest in developing automated methods for diagnosing HB. This narrative review briefly discusses the development of artificial intelligence (AI) technology for diagnosing fatty liver disease pathology over the last 30 years and provides an overview of the current research status of AI algorithms for the identification of HB, including published articles on traditional machine learning algorithms and deep learning algorithms. This narrative review also provides a summary of object detection algorithms, including the principles, historical developments, and applications in the medical image analysis. The potential benefits of object detection algorithms for HB diagnosis (specifically those combined with a transformer architecture) are discussed, along with the future directions of object detection algorithms in HB diagnosis and the potential applications of generative AI on transformer architecture in this field. In conclusion, object detection algorithms have huge potential for the identification of HB and could make the diagnosis of MAFLD more accurate and efficient in the near future.

show abstract

“…However, these brain tumour segmentation methods still face various challenges. For instance, the results of these methods may not meet the strict accuracy and detail requirements in medical applications [9]. The limited scope of CNN structures and the weakening of long-term feature dependencies with increased network depth can lead to missed detection of small targets and blurred object edge segmentation [10,11].…”

Section: Introductionmentioning

confidence: 99%

Brain tumour segmentation framework with deep nuanced reasoning and Swin‐T

Xu,

Yu,

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Tumour medical image segmentation plays a crucial role in clinical imaging diagnosis. Existing research has achieved good results, enabling the segmentation of three tumour regions in MRI brain tumour images. Existing models have limited focus on the brain tumour areas, and the long‐term dependency of features is weakened as the network depth increases, resulting in blurred edge segmentation of the targets. Additionally, considering the excellent segmentation performance of the Swin Transformer(Swin‐T) network, its network structure and parameters are relatively large. To address these limitations, this paper proposes a brain tumour segmentation framework with deep nuanced reasoning and Swin‐T. It is mainly composed of the backbone hybrid network (BHN) and the deep micro texture extraction module (DMTE). The BHN combines the Swin‐T stage with a new downsampling transition module called dual path feature reasoning (DPFR). The entire network framework is designed to extract global and local features from multi‐modal data, enabling it to capture and analyze deep texture features in multi‐modal images. It provides significant optimization over the Swin‐T network structure. Experimental results on the BraTS dataset demonstrate that the proposed method outperforms other state‐of‐the‐art models in terms of segmentation performance. The corresponding source codes are available at https://github.com/CurbUni/Brain‐Tumor‐Segmentation‐Framework‐with‐Deep‐Nuanced‐Reasoning‐and‐Swin‐T.

show abstract

Brain tumour segmentation based on an improved U-Net

Cited by 22 publications

References 22 publications

Two Independent Teachers are Better Role Model

Two Independent Teachers are Better Role Model

Object detection: A novel AI technology for the diagnosis of hepatocyte ballooning

Brain tumour segmentation framework with deep nuanced reasoning and Swin‐T

Contact Info

Product

Resources

About