Multi-decoder Networks with Multi-denoising Inputs for Tumor Segmentation

Vu, Minh H.; Nyholm, Tufve; Löfstedt, Tommy

doi:10.1007/978-3-030-72084-1_37

Cited by 10 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their results could be improved by refining the PatchGAN architecture and exploring an ensemble approach by training multiple Vox2Vox models using different augmentation techniques. Vu et al [56] employed a multi-decoder architecture that jointly learned three BT regions while sharing a common encoder, enabling end-to-end DL-based segmentation. Additionally, they stacked the original images with their denoised counterparts as an input enhancement technique, which led to improved performance, with DS values of 78.13%, 92.75%, and 88.34% for ET, WT, and TC, respectively.…”

Section: Deep Feature-based Methodsmentioning

confidence: 99%

“…DS Dual-path attention 3D U-Net [41] 87.8 NLCA-VNet [59] 88.50 SDV-TUNet [60] 89.20 3DUV-NetR+ [61] 82.80 DAUnet [62] 89.2 PFA-Net (proposed) 91.02 Network. DS Dual-path attention 3D U-Net [41] 91.20 Modality-pairing 3D U-Net [42] 92.40 3D SA-Net [43] 91.51 3D U-Net [44] 90.37 Triplanar U-Net [45] 93 Ensemble model [46] 85 Multiple 3D U-Net [47] 92.29 MVP U-Net [48] 79.90 nnU-Net [49] 91.87 MTAU [51] 72 Dense 3D U-Net [52] 88.20 RMU-Net [54] 91.35 U-attention Net [53] 91.90 SGEResU-Net [18] 90.48 3D-GAN [55] 91.63 Multi-decoder [56] 92.75 Dynamic DMF-Net [57] 91.36 AGSE-VNet [58] 85 NLCA-VNet [59] 90.50 SDV-TUNet [60] 90.22 3DUV-NetR+ [61] 91.95 DAUnet [62] 90.6 A comparative study of the homogeneous dataset analysis, as presented in Tables 9-11, provides valuable insights into the performance of various CAD methods. It was concluded that different CAD methods tend to excel in the diagnosis of one type of tumor, while exhibiting lower performance for other types.…”

Section: Networkmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Fractal Dimension and Segmentation of Brain Tumor with Parallel Features Aggregation Network

Sultan,

Ullah,

Hong

et al. 2024

Fractal Fract

View full text Add to dashboard Cite

The accurate recognition of a brain tumor (BT) is crucial for accurate diagnosis, intervention planning, and the evaluation of post-intervention outcomes. Conventional methods of manually identifying and delineating BTs are inefficient, prone to error, and time-consuming. Subjective methods for BT recognition are biased because of the diffuse and irregular nature of BTs, along with varying enhancement patterns and the coexistence of different tumor components. Hence, the development of an automated diagnostic system for BTs is vital for mitigating subjective bias and achieving speedy and effective BT segmentation. Recently developed deep learning (DL)-based methods have replaced subjective methods; however, these DL-based methods still have a low performance, showing room for improvement, and are limited to heterogeneous dataset analysis. Herein, we propose a DL-based parallel features aggregation network (PFA-Net) for the robust segmentation of three different regions in a BT scan, and we perform a heterogeneous dataset analysis to validate its generality. The parallel features aggregation (PFA) module exploits the local radiomic contextual spatial features of BTs at low, intermediate, and high levels for different types of tumors and aggregates them in a parallel fashion. To enhance the diagnostic capabilities of the proposed segmentation framework, we introduced the fractal dimension estimation into our system, seamlessly combined as an end-to-end task to gain insights into the complexity and irregularity of structures, thereby characterizing the intricate morphology of BTs. The proposed PFA-Net achieves the Dice scores (DSs) of 87.54%, 93.42%, and 91.02%, for the enhancing tumor region, whole tumor region, and tumor core region, respectively, with the multimodal brain tumor segmentation (BraTS)-2020 open database, surpassing the performance of existing state-of-the-art methods. Additionally, PFA-Net is validated with another open database of brain tumor progression and achieves a DS of 64.58% for heterogeneous dataset analysis, surpassing the performance of existing state-of-the-art methods.

show abstract

Section: Deep Feature-based Methodsmentioning

confidence: 99%

Section: Networkmentioning

confidence: 99%

Estimation of Fractal Dimension and Segmentation of Brain Tumor with Parallel Features Aggregation Network

Sultan,

Ullah,

Hong

et al. 2024

Fractal Fract

View full text Add to dashboard Cite

show abstract

“…4.3.8 Method-8: Team UmU (Vu et al, 2021) The method proposes a Multi-Decoder Cascaded Network to predict the probability of the three tumor entities. An uncertainty score, u r i,j,k , at voxel (i, j, k) was defined by:…”

Section: Method-3: Team Uniandes (Daza Et Al 2021)mentioning

confidence: 99%

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results

Mehta

Filos

Baid

et al. 2022

Melba

View full text Add to dashboard Cite

Deep learning (DL) models have provided the state-of-the-art performance in a wide variety of medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder the translation of DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties, could enable clinical review of the most uncertain regions, thereby building trust and paving the way towards clinical translation. Recently, a number of uncertainty estimation methods have been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019-2020 task on uncertainty quantification (QU-BraTS), and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions, and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentages of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, and hence highlight the need for uncertainty quantification in medical image analyses. Our evaluation code is made publicly available at <a href='https://github.com/RagMeh11/QU-BraTS'>https://github.com/RagMeh11/QU-BraTS</a>

show abstract

“…The function L DSC in (1) denotes the soft DSC loss, which is defined as [17], [15], [18], [19], [20]…”

Section: A Data-adaptive Loss Functionmentioning

confidence: 99%

A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation

Norman

Nyholm

et al. 2022

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

In the last years, deep learning has dramatically improved the performances in a variety of medical image analysis applications. Among different types of deep learning models, convolutional neural networks have been among the most successful and they have been used in many applications in medical imaging.Training deep convolutional neural networks often requires large amounts of image data to generalize well to new unseen images. It is often time-consuming and expensive to collect large amounts of data in the medical image domain due to expensive imaging systems, and the need for experts to manually make ground truth annotations. A potential problem arises if new structures are added when a decision support system is already deployed and in use. Since the field of radiation therapy is constantly developing, the new structures would also have to be covered by the decision support system.In the present work, we propose a novel loss function to solve multiple problems: imbalanced datasets, partiallylabeled data, and incremental learning. The proposed loss function adapts to the available data in order to utilize all available data, even when some have missing annotations. We demonstrate that the proposed loss function also works well in an incremental learning setting, where an existing model is easily adapted to semi-automatically incorporate delineations of new organs when they appear. Experiments on a large in-house dataset show that the proposed method performs on par with baseline models, while greatly reducing the training time and eliminating the hassle of maintaining multiple models in practice.

show abstract

Multi-decoder Networks with Multi-denoising Inputs for Tumor Segmentation

Cited by 10 publications

References 13 publications

Estimation of Fractal Dimension and Segmentation of Brain Tumor with Parallel Features Aggregation Network

Estimation of Fractal Dimension and Segmentation of Brain Tumor with Parallel Features Aggregation Network

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation – Analysis of Ranking Scores and Benchmarking Results

A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation

Contact Info

Product

Resources

About