The predictive value of segmentation metrics on dosimetry in organs at risk of the brain

Poel, Robert; Rüfenacht, Elias; Hermann, Evelyn; Scheib, Stefan; Manser, Peter; Aebersold, Daniel M.

doi:10.1016/j.media.2021.102161

Cited by 17 publications

(19 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research is conducted using different tools, including DL, a science that has been very popular in recent years in the radiological field. For example, so far in 2021, DL research related to brain cancer can be found, such as Radiation therapy planning of head and neck cancer patients [28], automatic diagnosis of brain tumors [29], detection and classification of brain tumors [30]- [33], diagnostic feasibility assessment with DL networks [34], detection of brain metastases [35], prediction of survival in patients with infiltrating gliomas [36], the prognosis of glioblastoma multiforme [37], analysis for diagnostic biomarkers of glioma [38], segmentation of brain tumors [39]- [42], segmentation in dosimetry in organs at risk [43], and denoising to improve quality in subjective imaging [44].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data Augmentation and Transfer Learning for Brain Tumor Detection in Magnetic Resonance Imaging

Anaya-Isaza

Mera-Jiménez

2022

IEEE Access

View full text Add to dashboard Cite

The exponential growth of deep learning networks has allowed us to tackle complex tasks, even in fields as complicated as medicine. However, using these models requires a large corpus of data for the networks to be highly generalizable and with high performance. In this sense, data augmentation methods are widely used strategies to train networks with small data sets, being vital in medicine due to the limited access to data. A clear example of this is magnetic resonance imaging in pathology scans associated with cancer. In this vein, we compare the effect of several conventional data augmentation schemes on the ResNet50 network for brain tumor detection. In addition, we included our strategy based on principal component analysis. The training was performed with the network trained from zeros and transfer-learning, obtained from the ImageNet dataset. The investigation allowed us to achieve an F1 detection score of 92.34%. The score was achieved with the ResNet50 network through the proposed method and implementing the learning transfer. In addition, it was also concluded that the proposed method is different from the other conventional methods with a significance level of 0.05 through the Kruskal Wallis test statistic.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In general, most authors performed the applications with a small data set; however, they did not implement any data augmentation strategy or learning transfer. Examples of these are: Menze, Al-Saffar, Khairandish, Islam, Song, Poel, Yan, and Wong et al [29], [31], [32], [36]- [38], [43], [44].…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation and Transfer Learning for Brain Tumor Detection in Magnetic Resonance Imaging

Anaya-Isaza

Mera-Jiménez

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Currently, various medical testing and surgical instruments, such as magnetic resonance imaging (MRI), electroencephalogram (ECG), and computed tomography imaging, are the embodiment of technological applications. In order to form medical images, these images must have high resolution and clarity to describe the pathology of various parts of a patient's body and help doctors make a diagnosis [ 3 , 4 ]. The relative complexity of the brain structure makes the tumor images have more details, variable morphology, and uneven grayscale [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Segmentation for Multimodal Brain Tumor Images Using Dual-Tree Complex Wavelet Transform and Deep Reinforcement Learning

Liu

Cai³

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Image segmentation is an effective tool for computer-aided medical treatment, to retain the detailed features and edges of the segmented image and improve the segmentation accuracy. Therefore, a segmentation algorithm using deep reinforcement learning (DRL) and dual-tree complex wavelet transform (DTCWT) for multimodal brain tumor images is proposed. First, the bivariate concept in DTCWT is used to determine whether the image noise points belong to the real or imaginary region, and the noise probability is checked after calculation; second, the wavelet coefficients corresponding to the region where the noise is located are selected to transform the noise into normal pixel points by bivariate; then, the conditional probability of occurrence of marker points in the edge and center regions of the image is calculated with the target points, and the initial segmentation of the image is achieved by the known wavelet coefficients; finally, the segmentation framework is constructed using DRL, and the network is trained by loss function to optimize the segmentation results and achieve accurate image segmentation. The experiment was evaluated on BraTS2018 dataset, CQ500 dataset, and a hospital brain tumor dataset. The results show that the algorithm in this paper can effectively remove multimodal brain tumor image noise, and the segmented image has good retention of detail features and edges, and the segmented image has high similarity with the original image. The highest information loss index of the segmentation results is only 0.18, the image boundary error is only about 0.3, and F-value is high, which indicates that the proposed algorithm is accurate and can operate efficiently, and has practical applicability.

show abstract

“…Recently, with the development of deep learning algorithms, especially the convolutional neural network (CNN), medical image analysis has made significant progress in a range of applications such as lesion detection and classification [ 4 , 5 ], image registration and enhancement [ 6 , 7 ], organs segmentation [ 8 , 9 ], and dose calculation in radiotherapy [ 10 – 12 ]. This also led to the development of several deep neural networks based approaches for the translation of medical images [ 13 – 18 ].…”

Section: Introductionmentioning

confidence: 99%

Multimodal image translation via deep learning inference model trained in video domain

et al. 2022

View full text Add to dashboard Cite

Background Current medical image translation is implemented in the image domain. Considering the medical image acquisition is essentially a temporally continuous process, we attempt to develop a novel image translation framework via deep learning trained in video domain for generating synthesized computed tomography (CT) images from cone-beam computed tomography (CBCT) images. Methods For a proof-of-concept demonstration, CBCT and CT images from 100 patients were collected to demonstrate the feasibility and reliability of the proposed framework. The CBCT and CT images were further registered as paired samples and used as the input data for the supervised model training. A vid2vid framework based on the conditional GAN network, with carefully-designed generators, discriminators and a new spatio-temporal learning objective, was applied to realize the CBCT–CT image translation in the video domain. Four evaluation metrics, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and structural similarity (SSIM), were calculated on all the real and synthetic CT images from 10 new testing patients to illustrate the model performance. Results The average values for four evaluation metrics, including MAE, PSNR, NCC, and SSIM, are 23.27 ± 5.53, 32.67 ± 1.98, 0.99 ± 0.0059, and 0.97 ± 0.028, respectively. Most of the pixel-wise hounsfield units value differences between real and synthetic CT images are within 50. The synthetic CT images have great agreement with the real CT images and the image quality is improved with lower noise and artifacts compared with CBCT images. Conclusions We developed a deep-learning-based approach to perform the medical image translation problem in the video domain. Although the feasibility and reliability of the proposed framework were demonstrated by CBCT–CT image translation, it can be easily extended to other types of medical images. The current results illustrate that it is a very promising method that may pave a new path for medical image translation research.

show abstract

The predictive value of segmentation metrics on dosimetry in organs at risk of the brain

Cited by 17 publications

References 32 publications

Data Augmentation and Transfer Learning for Brain Tumor Detection in Magnetic Resonance Imaging

Data Augmentation and Transfer Learning for Brain Tumor Detection in Magnetic Resonance Imaging

Segmentation for Multimodal Brain Tumor Images Using Dual-Tree Complex Wavelet Transform and Deep Reinforcement Learning

Multimodal image translation via deep learning inference model trained in video domain

Contact Info

Product

Resources

About