Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS)

Mohsen Yaghoubi Suraki

cs.CVApr 10, 2026

Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS)

Authors: Mohsen Yaghoubi Suraki

Abstract

Glioma is a harmful brain tumor that requires early detection to ensure better health results. Early detection of this tumor is key for effective treatment and requires an automated segmentation process. However, it is a challenging task to find tumors due to tumor characteristics like location and size. A reliable method to accurately separate tumor zones from healthy tissues is deep learning models, which have shown promising results over the last few years. In this research, an Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS) is introduced. This model is an innovative combination of adaptive dual residual networks, attention mechanisms, and multiscale spatial attention. The dual adaptive residual network architecture captures high-level semantic and intricate low-level details from brain images, ensuring precise segmentation of different tumor parts, types, and hard regions. The attention gates use gating and input signals to compute attention coefficients for the input features, and multiscale spatial attention generates scaled attention maps and combines these features to hold the most significant information about the brain tumor. We trained the model for 200 epochs using the ReLU activation function on BraTS 2020 and BraTS 2019 datasets. These improvements resulted in high accuracy for tumor detection and segmentation on BraTS 2020, achieving dice scores of 0.9229 for the whole tumor, 0.8432 for the tumor core, and 0.8004 for the enhancing tumor.

Figures & tables

Figure 1.1 : Display of four brain MRI modalities (FLAIR, T1, T1ce, T2) on the left alongside the corresponding Ground Truth segmentation on the right

Figure 2.1 : Illustration of Brain Tumor Segmentation and Annotations. The left side displays MRI scans highlighting the whole tumor, tumor core, and enhancing tumor regions. The rightmost image presents a detailed annotation of tumor components, including edema/invasion, non-enhancing, enhancing, and necrosis regions as per the BraTS standards. [ 6 ]

Figure 2.2 : Comparison of neural network blocks: Standard vs. Residual. The standard block directly learns the desired mapping $f(x)$ , while the residual block learns the residual $g(x)=f(x)-x$ , facilitating easier learning of the identity function $f(x)=x$ . [ 20 ]

Figure 2.3 : Diagram of the Attention Gate Module, showing the selective focus mechanism on important input features through attention coefficients and subsequent feature refinement for enhanced model performance [ 27 ]

Figure 2.4 : The Spatial Attention Module diagram, illustrating the process where the network assigns variable importance to different areas of the input, enhancing the focus on regions with critical information by refining features through pooling and convolutional layers. [ 22 ]

Figure 4.1 : Depiction of the Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS), showcasing the integration of advanced attention features for enhancing salient features across multiple scales in 3D input data.

Figure 4.2 : Depiction of a Residual Neural Network (ResNet) with Integrated Attention Mechanisms. The schematic outlines ResNet blocks as the foundation for feature extraction, supplemented by skip connections for spatial integrity, and group normalization for consistent learning. Attention modules further refine the output by transforming the input with 3D convolutional maps and a sigmoid function to direct the model’s learning towards significant areas, resulting in a carefully weighted output prepared for the subsequent decoding phase

Figure 5.1 : Scatter plots illustrating the correlation between the size of various tumor sub-regions (NET, ED, and ET) and the overall tumor volume. The graphs indicate varying degrees of association

Figure 5.2 : Bar charts representing the distribution of key tumor features (NET, ED, and ET) across training, validation, and test datasets for each of the five folds in a cross-validation framework.

Figure 5.3 : Training and Validation Loss Trends over 200 Epochs. This graph tracks the decline in loss values for both the training and validation sets, indicating the model’s progressive learning and increasing accuracy in brain tumor segmentation over time.

Figure 5.4 : Evaluation of Segmentation Accuracy on Brain Tumors. The first column displays MRI scans, the middle column shows the Ground Truth for tumor areas, and the third column presents the model’s Predictions. The comparison across columns illustrates the model’s proficiency in segmenting different tumor regions against the established Ground Truth.

Architecture	Dice Score			HD
	WT	TC	ET	WT	TC	ET
Dual-Path attention U-Net [ 43 ]	0.8780 ±0.112	0.7790 ±0.199	0.7520 ±0.282	6.3000 ±10.03	11.0200 ±34.49	30.6500 ±96.09
3D self-ensemble ResUNet [ 44 ]	0.89	0.81	0.76	5.28	7.74	33.26
Modified 3D U-net [ 45 ]	0.90 ±0.111	0.84 ±0.0.257	0.74 ±0.0.2158	5.08 ±5.988	8.69 ±79.565	36.04 ±074.8080
TransBTS [ 46 ]	0.8900	0.8136	0.7850	6.4690	10.4680	16.7160
MENet [ 47 ]	0.8800	0.7400	0.7000	6.9500	30.1800	38.6000

Table 5.1 : Performance comparison of different architectures.

Method	Dice Score			HD			Sensitivity			Specificity
	WT	TC	ET	WT	TC	ET	WT	TC	ET	WT	TC	ET
Fold 1	0.9216	0.8506	0.8219	1.4021	2.8624	6.9510	0.9312	0.8848	0.8449	0.9191	0.8640	0.8458
Fold 2	0.9212	0.8435	0.8204	1.5128	3.0682	6.9243	0.9214	0.9013	0.8421	0.9269	0.8393	0.8500
Fold 3	0.9314	0.8386	0.7730	0.8930	3.2084	16.1447	0.9338	0.8942	0.8476	0.9320	0.8416	0.8003
Fold 4	0.9231	0.8534	0.7925	1.2530	2.8359	11.3218	0.9322	0.8903	0.8276	0.9216	0.8604	0.8391
Fold 5	0.9172	0.8284	0.7963	1.5535	3.2397	11.3021	0.9172	0.8689	0.8454	0.9270	0.8471	0.8247

Table 5.2 : Quantitative results of the proposed method on brain tumor segmentation.

Method	Dice Score			HD			Sensitivity			Specificity
	WT	TC	ET	WT	TC	ET	WT	TC	ET	WT	TC	ET
Fold 1	0.8897	0.7593	0.6994	2.3118	4.7868	17.4723	0.9109	0.8129	0.7755	0.8830	0.7931	0.7593
Fold 2	0.8947	0.7608	0.6995	1.9869	4.8476	17.6157	0.8964	0.7864	0.7690	0.9014	0.8063	0.7623
Fold 3	0.8953	0.7632	0.7105	1.8619	4.2071	13.3497	0.8994	0.8056	0.7714	0.9006	0.7841	0.7626
Fold 4	0.8968	0.7490	0.6899	2.0270	5.0622	18.0932	0.9135	0.8335	0.7876	0.8932	0.7554	0.7370
Fold 5	0.8914	0.7472	0.7090	2.2766	5.4035	17.7841	0.8997	0.7823	0.7732	0.9007	0.8036	0.7740

Table 5.3 : Quantitative results of the 3D-Unet Model (base model) on brain tumor segmentation.

Architecture	Dice Score			HD
	WT	TC	ET	WT	TC	ET
dual supervision guided attentional network [ 57 ]	0.882	0.771	0.727	8.09	10.3	6.6
heuristic approach for segmentation [ 58 ]	0.8598	0.7728	0.7153	-	-	-
RAAGR2-Net [ 59 ]	0.884	0.814	0.763	-	-	-
Swinbts [ 49 ]	0.8975 ±0.070	0.7928 ±0.232	0.7443 ±0.294	-	-	-
Cascaded 3D U-Net and 3D U-Net++ [ 60 ]	0.867	0.834	0.802	-	-	-

Table 5.4 : Comparison of the proposed model with other approaches on the BraTS 2019 dataset

Brain Tumor Segmentation

Brain tumor segmentation uses medical imaging, especially MRI, to delineate tumors and their subregions for diagnosis, treatment planning, and monitoring.

See all 76 papers

A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images
May 28, 2026Sourjya Mukherjee, Ananya Bhattacharjee, R. MuruganU-Net Medical Image Segmentation
Biomedical Imaging Laboratory, Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, Assam, India, 788010
An Explainable AI-Driven Framework for Automated Brain Tumor Segmentation Using an Attention-Enhanced U-Net
Mar 24, 2026MD Rashidul Islam, Bakary GibbaBrain Tumor Segmentation Convolutional Neural Networks
School of Computing and Informatics Albukhary International University, 05200, Alor Setar, Malaysia
ReFRM3D: A Radiomics-enhanced Fused Residual Multiparametric 3D Network with Multi-Scale Feature Fusion for Glioma Characterization
Dec 27, 2025Md. Abdur Rahman, Md Noman Hossain, Arefin Ittesafun Abian +4BraTS Medical Image Segmentation
Applied Artificial Intelligence and Intelligent Systems (AAIINS) Laboratory, Dhaka 1217, Bangladesh · Department of Computer Science and Engineering, United International University, Dhaka, 1212, Bangladesh · Department of Data Science and Artificial Intelligence, Monash University, Clayton, VIC, 3153, Australia +1

May 28, 2026J/K move · Enter open · S save

A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images

Sourjya Mukherjee, Ananya Bhattacharjee, R. Murugan

Biomedical Imaging Laboratory, Department of Electronics and Communication Engineering, National Institute of Technology Silchar, Silchar, Assam, India, 788010

U-Net Medical Image Segmentation Attention Mechanisms Brain Tumor Segmentation

Open paper AskPDF arXiv

Brain cancer's severity necessitates precise brain tumor segmentation, which is crucial for effective brain tumor diagnosis. Manual identification, burdened by high costs, labor, and error risks, highlights the need for automated methods. In this study, we introduce the Global Context-aware Squeeze and Excite Residual UNet (GCSER-UNet), which facilitates a fusion of spatial and channel-wise attention and thus enhances the model's capacity to capture intricate spatial dependencies and contextual information. GCSER-UNet efficiently extracts tumor segments from multimodal MRI slices, delivering exceptional performance. Evaluations on benchmark databases exhibit its superiority, achieving a notable 94 percent dice score on the TCGA LGG dataset, surpassing the state-of-the-art dice score of 91.8 percent. In the BraTS 2020 dataset, the proposed GCSER-UNet ensemble approach yielded dice scores of 95 percent, 92 percent, and 90 percent for the tumor regions - Whole Tumor (W), Tumor Core (T), and Enhancing Tumor (E), respectively. The current state-of-the-art dice scores were 94 percent, 93 percent, and 88 percent. These compelling outcomes highlight the efficacy of GCSER-UNet in precise brain tumor segmentation and thus can aid neurologists in effective brain cancer management and treatment planning.

Abstract

Brain Tumor Segmentation

Explore similar work

A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images

An Explainable AI-Driven Framework for Automated Brain Tumor Segmentation Using an Attention-Enhanced U-Net

ReFRM3D: A Radiomics-enhanced Fused Residual Multiparametric 3D Network with Multi-Scale Feature Fusion for Glioma Characterization