MSFR‐Net: Multi‐modality and single‐modality feature recalibration network for brain tumor segmentation

Li, Xiang; Jiang, Yuchen; Li, Minglei; Zhang, Jiusi; Yin, Shen; Luo, Hao

doi:10.1002/mp.15933

Cited by 13 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the Dice score of TC and the Hausdorff 95 of WT, the AMCA‐Net is also very competitive. For example, the MSFR‐Net 44 studied the relationship between single‐modality and its highly correlated tumor sub‐components. Its Dice scores on the WT and ET regions are lower than that of the AMCA‐Net on BraTS2018 dataset.…”

Section: Resultsmentioning

confidence: 99%

Attention‐guided multi‐scale context aggregation network for multi‐modal brain glioma segmentation

Cao

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundAccurate segmentation of brain glioma is a critical prerequisite for clinical diagnosis, surgical planning and treatment evaluation. In current clinical workflow, physicians typically perform delineation of brain tumor subregions slice‐by‐slice, which is more susceptible to variabilities in raters and also time‐consuming. Besides, even though convolutional neural networks (CNNs) are driving progress, the performance of standard models still have some room for further improvement.PurposeTo deal with these issues, this paper proposes an attention‐guided multi‐scale context aggregation network (AMCA‐Net) for the accurate segmentation of brain glioma in the magnetic resonance imaging (MRI) images with multi‐modalities.MethodsAMCA‐Net extracts the multi‐scale features from the MRI images and fuses the extracted discriminative features via a self‐attention mechanism for brain glioma segmentation. The extraction is performed via a series of down‐sampling, convolution layers, and the global context information guidance (GCIG) modules are developed to fuse the features extracted for contextual features. At the end of the down‐sampling, a multi‐scale fusion (MSF) module is designed to exploit and combine all the extracted multi‐scale features. Each of the GCIG and MSF modules contain a channel attention (CA) module that can adaptively calibrate feature responses and emphasize the most relevant features. Finally, multiple predictions with different resolutions are fused through different weightings given by a multi‐resolution adaptation (MRA) module instead of the use of averaging or max‐pooling to improve the final segmentation results.ResultsDatasets used in this paper are publicly accessible, that is, the Multimodal Brain Tumor Segmentation Challenges 2018 (BraTS2018) and 2019 (BraTS2019). BraTS2018 contains 285 patient cases and BraTS2019 contains 335 cases. Simulations show that the AMCA‐Net has better or comparable performance against that of the other state‐of‐the‐art models. In terms of the Dice score and Hausdorff 95 for the BraTS2018 dataset, 90.4% and 10.2 mm for the whole tumor region (WT), 83.9% and 7.4 mm for the tumor core region (TC), 80.2% and 4.3 mm for the enhancing tumor region (ET), whereas the Dice score and Hausdorff 95 for the BraTS2019 dataset, 91.0% and 10.7 mm for the WT, 84.2% and 8.4 mm for the TC, 80.1% and 4.8 mm for the ET. Conclusions: The proposed AMCA‐Net performs comparably well in comparison to several state‐of‐the‐art neural net models in identifying the areas involving the peritumoral edema, enhancing tumor, and necrotic and non‐enhancing tumor core of brain glioma, which has great potential for clinical practice. In future research, we will further explore the feasibility of applying AMCA‐Net to other similar segmentation tasks.

show abstract

Section: Resultsmentioning

confidence: 99%

Attention‐guided multi‐scale context aggregation network for multi‐modal brain glioma segmentation

Cao

et al. 2023

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Next we compare the CTV delineation quality of several DL models, including the proposed PPAF-net, PPF-net, the RA-CTVNet, 23 model by Rhee et al, 20 U-Net, 24 U-Net++, 25 EANet, 44 DeepLab v3+, 22 MSRF-Net, 45 TransUNet, 46 SegFormer, 47 SETR, 48 PA-Net 49 and OAU-Net. 50 The PPF-net is the PPAF-net without the attention module.…”

Section: Performance Evaluationmentioning

confidence: 99%

Delineation of clinical target volume and organs at risk in cervical cancer radiotherapy by deep learning networks

Tian,

Wang,

Liu

et al. 2023

Medical Physics

View full text Add to dashboard Cite

PurposeDelineation of the clinical target volume (CTV) and organs‐at‐risk (OARs) is important in cervical cancer radiotherapy. But it is generally labor‐intensive, time‐consuming, and subjective. This paper proposes a parallel‐path attention fusion network (PPAF‐net) to overcome these disadvantages in the delineation task.MethodsThe PPAF‐net utilizes both the texture and structure information of CTV and OARs by employing a U‐Net network to capture the high‐level texture information, and an up‐sampling and down‐sampling (USDS) network to capture the low‐level structure information to accentuate the boundaries of CTV and OARs. Multi‐level features extracted from both networks are then fused together through an attention module to generate the delineation result.ResultsThe dataset contains 276 computed tomography (CT) scans of patients with cervical cancer of staging IB‐IIA. The images are provided by the West China Hospital of Sichuan University. Simulation results demonstrate that PPAF‐net performs favorably on the delineation of the CTV and OARs (e.g., rectum, bladder and etc.) and achieves the state‐of‐the‐art delineation accuracy, respectively, for the CTV and OARs. In terms of the Dice Similarity Coefficient (DSC) and the Hausdorff Distance (HD), 88.61% and 2.25 cm for the CTV, 92.27% and 0.73 cm for the rectum, 96.74% and 0.68 cm for the bladder, 96.38% and 0.65 cm for the left kidney, 96.79% and 0.63 cm for the right kidney, 93.42% and 0.52 cm for the left femoral head, 93.69% and 0.51 cm for the right femoral head, 87.53% and 1.07 cm for the small intestine, and 91.50% and 0.84 cm for the spinal cord.ConclusionsThe proposed automatic delineation network PPAF‐net performs well on CTV and OARs segmentation tasks, which has great potential for reducing the burden of radiation oncologists and increasing the accuracy of delineation. In future, radiation oncologists from the West China Hospital of Sichuan University will further evaluate the results of network delineation, making this method helpful in clinical practice.

show abstract

“…Inspired by this work, Aboussaleh et al proposed a novel U-Net architecture, it first used three different pre-trained encoders to extract the multi-scale features from multimodal images, and then used three bi-FPN modules and fine-tuning strategy to enrich these features, fusing and passing these enriched features into a decoder can generate the final segmentation results (Aboussaleh et al 2023). Subsequently, Li et al presented a multimodal and single modal feature correction network (Li et al 2023), in which the multimodal images and single modal image were input first into two independent encoders, and then using the attentions between single modal and multimodal features to disentangle the modality-independent semantics. Although these methods can extract modality-specific features, they lack well-designed feature fusion rules, resulting in unsatisfactory segmentation results.…”

Section: Introductionmentioning

confidence: 99%

Glioma segmentation based on dense contrastive learning and multimodal features recalibration

Hu,

Wang,

Wang

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Accurate segmentation of different regions of gliomas from multimodal magnetic resonance (MR) images is crucial for glioma grading and precise diagnosis, but many existing segmentation methods are difficult to effectively utilize multimodal MR image information to recognize accurately the lesion regions with small size, low contrast and irregular shape. To address this issue, this work proposes a novel 3D glioma segmentation model DCL-MANet. DCL-MANet has an architecture of multiple encoders and one single decoder. Each encoder is used to extract MR image features of a given modality. To overcome the entangle problems of multimodal semantic features, a dense contrastive learning (DCL) strategy is presented to extract the modality-specific and common features. Following that, feature recalibration block (RFB) based on modality-wise attention is used to recalibrate the semantic features of each modality, enabling the model to focus on the features that are beneficial for glioma segmentation. These recalibrated features are input into the decoder to obtain the segmentation results. To verify the superiority of the proposed method, we compare it with several state-of-the-art (SOTA) methods in terms of Dice, ASSD, HD95 and volumetric similarity (Vs). The comparison results show that the average Dice, ASSD, HD95 and Vs of DCL-MANet on all tumor regions are improved at least by 0.66\%, 3.47\%, 8.94\% and 1.07\% respectively. For small enhance tumor (ET) region, the corresponding improvement can be up to 0.37\%, 7.83\%, 11.32\%, and 1.35\%, respectively. In addition, the ablation results demonstrate the effectiveness of the proposed DCL and RFB, combining them can significantly increase Dice (1.59\%) and Vs (1.54\%) while decrease ASSD (40.51\%) and HD95 (45.16\%) on ET region. The proposed DCL-MANet could disentangle the multimodal features and enhance the semantics of modality-dependent features, providing a potential means to accurately segment small lesion regions in gliomas.

show abstract

MSFR‐Net: Multi‐modality and single‐modality feature recalibration network for brain tumor segmentation

Cited by 13 publications

References 40 publications

Attention‐guided multi‐scale context aggregation network for multi‐modal brain glioma segmentation

Attention‐guided multi‐scale context aggregation network for multi‐modal brain glioma segmentation

Delineation of clinical target volume and organs at risk in cervical cancer radiotherapy by deep learning networks

Glioma segmentation based on dense contrastive learning and multimodal features recalibration

Contact Info

Product

Resources

About