Deep learning techniques for tumor segmentation: a review

Jiang, Huiyan; Diao, Zhaoshuo; Yao, Yu-Dong

doi:10.1007/s11227-021-03901-6

Cited by 37 publications

(20 citation statements)

References 173 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although U-Net overcomes the challenge of preserving the original information during FCN upsampling via skip-connection, the boundary cannot achieve a reasonable segmentation result due to the blurring of the border and internal pixels. This uncertainty arises because convolution operators might provide comparable values in the voxel feature map at the tumor boundary, even in the first convolution layer [ 88 ]. Shen et al [ 89 ] proposed a boundary segmentation technique based on a Boundary-Aware FCN network.…”

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

“…After multiplying the image by the original, it is delivered to the second U-Net network. The output result is the segmentation result in its entirety [ 88 ].…”

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

“…Preprocessing is grouped into four categories: approach based on image attributes, data augmentations, noise removal, and edge improvement. They have essentially agreed that if the image is placed directly into the deep neural network without preprocessing, the effect is considerably reduced, and in some cases, proper preprocessing is critical to the model’s performance [ 88 , 104 ]. Among the different bias field correction strategies are the non-parametric non-uniform normalization (N3) approach [ 105 ].…”

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

“…Flip, Rotation, Shift, Shear, Zoom, Brightness, and Elastic distortion are all common strategies for increasing the number of datasets [ 110 ]. To emphasize that when dealing with a limited data collection, the advantage of data augmentation is equivalent to the benefit of model update [ 88 ]. However, it is easy to implement.…”

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

See 3 more Smart Citations

Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art

Abdelrahman

Viriri

2022

J. Imaging

View full text Add to dashboard Cite

Cure rates for kidney cancer vary according to stage and grade; hence, accurate diagnostic procedures for early detection and diagnosis are crucial. Some difficulties with manual segmentation have necessitated the use of deep learning models to assist clinicians in effectively recognizing and segmenting tumors. Deep learning (DL), particularly convolutional neural networks, has produced outstanding success in classifying and segmenting images. Simultaneously, researchers in the field of medical image segmentation employ DL approaches to solve problems such as tumor segmentation, cell segmentation, and organ segmentation. Segmentation of tumors semantically is critical in radiation and therapeutic practice. This article discusses current advances in kidney tumor segmentation systems based on DL. We discuss the various types of medical images and segmentation techniques and the assessment criteria for segmentation outcomes in kidney tumor segmentation, highlighting their building blocks and various strategies.

show abstract

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

“…After multiplying the image by the original, it is delivered to the second U-Net network. The output result is the segmentation result in its entirety [ 88 ].…”

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

Section: Overview Of Deep Learning (Dl) Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art

Abdelrahman

Viriri

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Since convolutional neural networks (CNN) [ 18 ] has proved to be a precise and efficient method of semantic image segmentation since it is end-to-end and able to capture contextual semantics through computing high-level feature maps, SegNet [ 19 ] referring to a fully convolutional network (FCN) [ 20 ] as the encoder stage was first proposed. Then Olaf Ronneberger proposed U-Net [ 7 ], one of the most successful networks based on FCN structure, which has been a baseline network architecture in medical image segmentation due to its powerful effect and few training parameters [ 21 ]. Many of other network architectures are its modifications such as 3D U-Net [ 22 ], V-Net [ 23 ], U-Net 3+ [ 24 ] etc.…”

Section: Related Workmentioning

confidence: 99%

DCNet: Densely Connected Deep Convolutional Encoder–Decoder Network for Nasopharyngeal Carcinoma Segmentation

Yang

Han

Liu

2021

Sensors

View full text Add to dashboard Cite

Nasopharyngeal Carcinoma segmentation in magnetic resonance imagery (MRI) is vital to radiotherapy. Exact dose delivery hinges on an accurate delineation of the gross tumor volume (GTV). However, the large-scale variation in tumor volume is intractable, and the performance of current models is mostly unsatisfactory with indistinguishable and blurred boundaries of segmentation results of tiny tumor volume. To address the problem, we propose a densely connected deep convolutional network consisting of an encoder network and a corresponding decoder network, which extracts high-level semantic features from different levels and uses low-level spatial features concurrently to obtain fine-grained segmented masks. Skip-connection architecture is involved and modified to propagate spatial information to the decoder network. Preliminary experiments are conducted on 30 patients. Experimental results show our model outperforms all baseline models, with improvements of 4.17%. An ablation study is performed, and the effectiveness of the novel loss function is validated.

show abstract

A prior‐information‐based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer

Wang,

Chang,

Pei

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

ObjectiveAdaptive planning to accommodate anatomic changes during treatment often requires repeated segmentation. In this study, prior patient‐specific data was integrateda into a registration‐guided multi‐channel multi‐path (Rg‐MCMP) segmentation framework to improve the accuracy of repeated clinical target volume (CTV) segmentation.MethodsThis study was based on CT image datasets for a total of 90 cervical cancer patients who received two courses of radiotherapy. A total of 15 patients were selected randomly as the test set. In the Rg‐MCMP segmentation framework, the first‐course CT images (CT1) were registered to second‐course CT images (CT2) to yield aligned CT images (aCT1), and the CTV in the first course (CTV1) was propagated to yield aligned CTV contours (aCTV1). Then, aCT1, aCTV1, and CT2 were combined as the inputs for 3D U‐Net consisting of a channel‐based multi‐path feature extraction network. The performance of the Rg‐MCMP segmentation framework was evaluated and compared with the single‐channel single‐path model (SCSP), the standalone registration methods, and the registration‐guided multi‐channel single‐path (Rg‐MCSP) model. The Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), and average surface distance (ASD) were used as the metrics.ResultsThe average DSC of CTV for the deformable image DIR‐MCMP model was found to be 0.892, greater than that of the standalone DIR (0.856), SCSP (0.837), and DIR‐MCSP (0.877), which were improvements of 4.2%, 6.6%, and 1.7%, respectively. Similarly, the rigid body DIR‐MCMP model yielded an average DSC of 0.875, which exceeded standalone RB (0.787), SCSP (0.837), and registration‐guided multi‐channel single‐path (0.848), which were improvements of 11.2%, 4.5%, and 3.2%, respectively. These improvements in DSC were statistically significant (p < 0.05).ConclusionThe proposed Rg‐MCMP framework achieved excellent accuracy in CTV segmentation as part of the adaptive radiotherapy workflow.

show abstract

Deep learning techniques for tumor segmentation: a review

Cited by 37 publications

References 173 publications

Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art

Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art

DCNet: Densely Connected Deep Convolutional Encoder–Decoder Network for Nasopharyngeal Carcinoma Segmentation

A prior‐information‐based automatic segmentation method for the clinical target volume in adaptive radiotherapy of cervical cancer

Contact Info

Product

Resources

About