Diagnostics

Research

Jump to: Review

21 pages, 4832 KiB

Open AccessArticle

Bridged-U-Net-ASPP-EVO and Deep Learning Optimization for Brain Tumor Segmentation

by Rammah Yousef, Shakir Khan, Gaurav Gupta, Bader M. Albahlal, Saad Abdullah Alajlan and Aleem Ali

Diagnostics 2023, 13(16), 2633; https://doi.org/10.3390/diagnostics13162633 - 9 Aug 2023

Cited by 13 | Viewed by 2896

Abstract

Brain tumor segmentation from Magnetic Resonance Images (MRI) is considered a big challenge due to the complexity of brain tumor tissues, and segmenting these tissues from the healthy tissues is an even more tedious challenge when manual segmentation is undertaken by radiologists. In [...] Read more.

Brain tumor segmentation from Magnetic Resonance Images (MRI) is considered a big challenge due to the complexity of brain tumor tissues, and segmenting these tissues from the healthy tissues is an even more tedious challenge when manual segmentation is undertaken by radiologists. In this paper, we have presented an experimental approach to emphasize the impact and effectiveness of deep learning elements like optimizers and loss functions towards a deep learning optimal solution for brain tumor segmentation. We evaluated our performance results on the most popular brain tumor datasets (MICCAI BraTS 2020 and RSNA-ASNR-MICCAI BraTS 2021). Furthermore, a new Bridged U-Net-ASPP-EVO was introduced that exploits Atrous Spatial Pyramid Pooling to enhance capturing multi-scale information to help in segmenting different tumor sizes, Evolving Normalization layers, squeeze and excitation residual blocks, and the max-average pooling for down sampling. Two variants of this architecture were constructed (Bridged U-Net_ASPP_EVO v1 and Bridged U-Net_ASPP_EVO v2). The best results were achieved using these two models when compared with other state-of-the-art models; we have achieved average segmentation dice scores of 0.84, 0.85, and 0.91 from variant1, and 0.83, 0.86, and 0.92 from v2 for the Enhanced Tumor (ET), Tumor Core (TC), and Whole Tumor (WT) tumor sub-regions, respectively, in the BraTS 2021validation dataset. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

14 pages, 1952 KiB

Open AccessArticle

A Semi-Supervised Graph Convolutional Network for Early Prediction of Motor Abnormalities in Very Preterm Infants

by Hailong Li, Zhiyuan Li, Kevin Du, Yu Zhu, Nehal A. Parikh and Lili He

Diagnostics 2023, 13(8), 1508; https://doi.org/10.3390/diagnostics13081508 - 21 Apr 2023

Cited by 2 | Viewed by 1634

Abstract

Approximately 32–42% of very preterm infants develop minor motor abnormalities. Earlier diagnosis soon after birth is urgently needed because the first two years of life represent a critical window of opportunity for early neuroplasticity in infants. In this study, we developed a semi-supervised [...] Read more.

Approximately 32–42% of very preterm infants develop minor motor abnormalities. Earlier diagnosis soon after birth is urgently needed because the first two years of life represent a critical window of opportunity for early neuroplasticity in infants. In this study, we developed a semi-supervised graph convolutional network (GCN) model that is able to simultaneously learn the neuroimaging features of subjects and consider the pairwise similarity between them. The semi-supervised GCN model also allows us to combine labeled data with additional unlabeled data to facilitate model training. We conducted our experiments on a multisite regional cohort of 224 preterm infants (119 labeled subjects and 105 unlabeled subjects) who were born at 32 weeks or earlier from the Cincinnati Infant Neurodevelopment Early Prediction Study. A weighted loss function was applied to mitigate the impact of an imbalanced positive:negative (~1:2) subject ratio in our cohort. With only labeled data, our GCN model achieved an accuracy of 66.4% and an AUC of 0.67 in the early prediction of motor abnormalities, outperforming prior supervised learning models. By taking advantage of additional unlabeled data, the GCN model had significantly better accuracy (68.0%, p = 0.016) and a higher AUC (0.69, p = 0.029). This pilot work suggests that the semi-supervised GCN model can be utilized to aid early prediction of neurodevelopmental deficits in preterm infants. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

18 pages, 3375 KiB

Open AccessArticle

A Hybrid Residual Attention Convolutional Neural Network for Compressed Sensing Magnetic Resonance Image Reconstruction

by Md. Biddut Hossain, Ki-Chul Kwon, Rupali Kiran Shinde, Shariar Md Imtiaz and Nam Kim

Diagnostics 2023, 13(7), 1306; https://doi.org/10.3390/diagnostics13071306 - 30 Mar 2023

Cited by 2 | Viewed by 2507

Abstract

We propose a dual-domain deep learning technique for accelerating compressed sensing magnetic resonance image reconstruction. An advanced convolutional neural network with residual connectivity and an attention mechanism was developed for frequency and image domains. First, the sensor domain subnetwork estimates the unmeasured frequencies [...] Read more.

We propose a dual-domain deep learning technique for accelerating compressed sensing magnetic resonance image reconstruction. An advanced convolutional neural network with residual connectivity and an attention mechanism was developed for frequency and image domains. First, the sensor domain subnetwork estimates the unmeasured frequencies of k-space to reduce aliasing artifacts. Second, the image domain subnetwork performs a pixel-wise operation to remove blur and noisy artifacts. The skip connections efficiently concatenate the feature maps to alleviate the vanishing gradient problem. An attention gate in each decoder layer enhances network generalizability and speeds up image reconstruction by eliminating irrelevant activations. The proposed technique reconstructs real-valued clinical images from sparsely sampled k-spaces that are identical to the reference images. The performance of this novel approach was compared with state-of-the-art direct mapping, single-domain, and multi-domain methods. With acceleration factors (AFs) of 4 and 5, our method improved the mean peak signal-to-noise ratio (PSNR) to 8.67 and 9.23, respectively, compared with the single-domain Unet model; similarly, our approach increased the average PSNR to 3.72 and 4.61, respectively, compared with the multi-domain W-net. Remarkably, using an AF of 6, it enhanced the PSNR by 9.87 ± 1.55 and 6.60 ± 0.38 compared with Unet and W-net, respectively. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

19 pages, 6374 KiB

Open AccessArticle

Efficient U-Net Architecture with Multiple Encoders and Attention Mechanism Decoders for Brain Tumor Segmentation

by Ilyasse Aboussaleh, Jamal Riffi, Khalid El Fazazy, Mohamed Adnane Mahraz and Hamid Tairi

Diagnostics 2023, 13(5), 872; https://doi.org/10.3390/diagnostics13050872 - 24 Feb 2023

Cited by 19 | Viewed by 4314

Abstract

The brain is the center of human control and communication. Hence, it is very important to protect it and provide ideal conditions for it to function. Brain cancer remains one of the leading causes of death in the world, and the detection of [...] Read more.

The brain is the center of human control and communication. Hence, it is very important to protect it and provide ideal conditions for it to function. Brain cancer remains one of the leading causes of death in the world, and the detection of malignant brain tumors is a priority in medical image segmentation. The brain tumor segmentation task aims to identify the pixels that belong to the abnormal areas when compared to normal tissue. Deep learning has shown in recent years its power to solve this problem, especially the U-Net-like architectures. In this paper, we proposed an efficient U-Net architecture with three different encoders: VGG-19, ResNet50, and MobileNetV2. This is based on transfer learning followed by a bidirectional features pyramid network applied to each encoder to obtain more spatial pertinent features. Then, we fused the feature maps extracted from the output of each network and merged them into our decoder with an attention mechanism. The method was evaluated on the BraTS 2020 dataset to segment the different types of tumors and the results show a good performance in terms of dice similarity, with coefficients of 0.8741, 0.8069, and 0.7033 for the whole tumor, core tumor, and enhancing tumor, respectively. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

16 pages, 4516 KiB

Open AccessArticle

Refined Automatic Brain Tumor Classification Using Hybrid Convolutional Neural Networks for MRI Scans

by Fatma E. AlTahhan, Ghada A. Khouqeer, Sarmad Saadi, Ahmed Elgarayhi and Mohammed Sallah

Diagnostics 2023, 13(5), 864; https://doi.org/10.3390/diagnostics13050864 - 23 Feb 2023

Cited by 9 | Viewed by 2665

Abstract

Refined hybrid convolutional neural networks are proposed in this work for classifying brain tumor classes based on MRI scans. A dataset of 2880 T1-weighted contrast-enhanced MRI brain scans are used. The dataset contains three main classes of brain tumors: gliomas, meningiomas, and pituitary [...] Read more.

Refined hybrid convolutional neural networks are proposed in this work for classifying brain tumor classes based on MRI scans. A dataset of 2880 T1-weighted contrast-enhanced MRI brain scans are used. The dataset contains three main classes of brain tumors: gliomas, meningiomas, and pituitary tumors, as well as a class of no tumors. Firstly, two pre-trained, fine-tuned convolutional neural networks, GoogleNet and AlexNet, were used for classification process, with validation and classification accuracy being 91.5% and 90.21%, respectively. Then, to improving the performance of the fine-tuning AlexNet, two hybrid networks (AlexNet-SVM and AlexNet-KNN) were applied. These hybrid networks achieved 96.9% and 98.6% validation and accuracy, respectively. Thus, the hybrid network AlexNet-KNN was shown to be able to apply the classification process of the present data with high accuracy. After exporting these networks, a selected dataset was employed for testing process, yielding accuracies of 88%, 85%, 95%, and 97% for the fine-tuned GoogleNet, the fine-tuned AlexNet, AlexNet-SVM, and AlexNet-KNN, respectively. The proposed system would help for automatic detection and classification of the brain tumor from the MRI scans and safe the time for the clinical diagnosis. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

13 pages, 4274 KiB

Open AccessArticle

Conventional and Deep-Learning-Based Image Reconstructions of Undersampled K-Space Data of the Lumbar Spine Using Compressed Sensing in MRI: A Comparative Study on 20 Subjects

by Philipp Fervers, Charlotte Zaeske, Philip Rauen, Andra-Iza Iuga, Jonathan Kottlors, Thorsten Persigehl, Kristina Sonnabend, Kilian Weiss and Grischa Bratke

Diagnostics 2023, 13(3), 418; https://doi.org/10.3390/diagnostics13030418 - 23 Jan 2023

Cited by 13 | Viewed by 2678

Abstract

Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive undersampling impairs image quality when using conventional reconstruction techniques. Deep-learning-based reconstruction methods might allow for stronger undersampling and thus faster MRI scans without loss of crucial image quality. [...] Read more.

Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive undersampling impairs image quality when using conventional reconstruction techniques. Deep-learning-based reconstruction methods might allow for stronger undersampling and thus faster MRI scans without loss of crucial image quality. We compared imaging approaches using parallel imaging (SENSE), a combination of parallel imaging and compressed sensing (COMPRESSED SENSE, CS), and a combination of CS and a deep-learning-based reconstruction (CS AI) on raw k-space data acquired at different undersampling factors. 3D T2-weighted images of the lumbar spine were obtained from 20 volunteers, including a 3D sequence (standard SENSE), as provided by the manufacturer, as well as accelerated 3D sequences (undersampling factors 4.5, 8, and 11) reconstructed with CS and CS AI. Subjective rating was performed using a 5-point Likert scale to evaluate anatomical structures and overall image impression. Objective rating was performed using apparent signal-to-noise and contrast-to-noise ratio (aSNR and aCNR) as well as root mean square error (RMSE) and structural-similarity index (SSIM). The CS AI 4.5 sequence was subjectively rated better than the standard in several categories and deep-learning-based reconstructions were subjectively rated better than conventional reconstructions in several categories for acceleration factors 8 and 11. In the objective rating, only aSNR of the bone showed a significant tendency towards better results of the deep-learning-based reconstructions. We conclude that CS in combination with deep-learning-based image reconstruction allows for stronger undersampling of k-space data without loss of image quality, and thus has potential for further scan time reduction. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

11 pages, 1998 KiB

Open AccessArticle

Native T1 Mapping-Based Radiomics for Noninvasive Prediction of the Therapeutic Effect of Pulmonary Arterial Hypertension

by Yue Wang, Lu Lin, Xiao Li, Jian Cao, Jian Wang, Zhi-Cheng Jing, Sen Li, Hao Liu, Xin Wang, Zheng-Yu Jin and Yi-Ning Wang

Diagnostics 2022, 12(10), 2492; https://doi.org/10.3390/diagnostics12102492 - 14 Oct 2022

Cited by 2 | Viewed by 1869

Abstract

(1) Background: Novel markers for predicting the short-term therapeutic effect of pulmonary arterial hypertension (PAH) to assist in the prompt initiation of tailored treatment strategies are greatly needed and highly desirable. The aim of the study was to investigate the role of cardiac [...] Read more.

(1) Background: Novel markers for predicting the short-term therapeutic effect of pulmonary arterial hypertension (PAH) to assist in the prompt initiation of tailored treatment strategies are greatly needed and highly desirable. The aim of the study was to investigate the role of cardiac magnetic resonance (CMR) native T1 mapping radiomics in predicting the short-term therapeutic effect in PAH patients; (2) Methods: Fifty-five PAH patients who received targeted therapy were retrospectively included. Patients were subdivided into an effective group and an ineffective group by assessing the therapeutic effect after ≥3 months of treatment. All patients underwent CMR examinations prior to the beginning of the therapy. Radiomics features from native T1 mapping images were extracted. A radiomics model was constructed using the support vector machine (SVM) algorithm for predicting the therapeutic effect; (3) Results: The SVM radiomics model revealed favorable performance for predicting the therapeutic effect with areas under the receiver operating characteristic curve of 0.955 in the training cohort and 0.893 in the test cohort, respectively. With the optimal cutoff value, the radiomics model showed accuracies of 0.909 and 0.818 in the training and test cohorts, respectively; (4) Conclusions: The CMR native T1 mapping-based radiomics model holds promise for predicting the therapeutic effect in PAH patients. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

15 pages, 2348 KiB

Open AccessArticle

Deep Convolutional Neural Network for Nasopharyngeal Carcinoma Discrimination on MRI by Comparison of Hierarchical and Simple Layered Convolutional Neural Networks

by Li Ji, Rongzhi Mao, Jian Wu, Cheng Ge, Feng Xiao, Xiaojun Xu, Liangxu Xie and Xiaofeng Gu

Diagnostics 2022, 12(10), 2478; https://doi.org/10.3390/diagnostics12102478 - 13 Oct 2022

Cited by 8 | Viewed by 2416

Abstract

Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To [...] Read more.

Nasopharyngeal carcinoma (NPC) is one of the most common head and neck cancers. Early diagnosis plays a critical role in the treatment of NPC. To aid diagnosis, deep learning methods can provide interpretable clues for identifying NPC from magnetic resonance images (MRI). To identify the optimal models, we compared the discrimination performance of hierarchical and simple layered convolutional neural networks (CNN). Retrospectively, we collected the MRI images of patients and manually built the tailored NPC image dataset. We examined the performance of the representative CNN models including shallow CNN, ResNet50, ResNet101, and EfficientNet-B7. By fine-tuning, shallow CNN, ResNet50, ResNet101, and EfficientNet-B7 achieved the precision of 72.2%, 94.4%, 92.6%, and 88.4%, displaying the superiority of deep hierarchical neural networks. Among the examined models, ResNet50 with pre-trained weights demonstrated the best classification performance over other types of CNN with accuracy, precision, and an F1-score of 0.93, 0.94, and 0.93, respectively. The fine-tuned ResNet50 achieved the highest prediction performance and can be used as a potential tool for aiding the diagnosis of NPC tumors. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

11 pages, 7078 KiB

Open AccessArticle

Application of a Deep Learning Algorithm for Combined Super-Resolution and Partial Fourier Reconstruction Including Time Reduction in T1-Weighted Precontrast and Postcontrast Gradient Echo Imaging of Abdominopelvic MR Imaging

by Daniel Wessling, Judith Herrmann, Saif Afat, Dominik Nickel, Haidara Almansour, Gabriel Keller, Ahmed E. Othman, Andreas S. Brendlin and Sebastian Gassenmaier

Diagnostics 2022, 12(10), 2370; https://doi.org/10.3390/diagnostics12102370 - 29 Sep 2022

Cited by 10 | Viewed by 1894

Abstract

Purpose: The purpose of this study was to test the technical feasibility and the impact on the image quality of a deep learning-based super-resolution reconstruction algorithm in 1.5 T abdominopelvic MR imaging. Methods: 44 patients who underwent abdominopelvic MRI were retrospectively included, of [...] Read more.

Purpose: The purpose of this study was to test the technical feasibility and the impact on the image quality of a deep learning-based super-resolution reconstruction algorithm in 1.5 T abdominopelvic MR imaging. Methods: 44 patients who underwent abdominopelvic MRI were retrospectively included, of which 4 had to be subsequently excluded. After the acquisition of the conventional volume interpolated breath-hold examination (VIBE_Std), images underwent postprocessing, using a deep learning-based iterative denoising super-resolution reconstruction algorithm for partial Fourier acquisitions (VIBE_SR). Image analysis of 40 patients with a mean age of 56 years (range 18–84 years) was performed qualitatively by two radiologists independently using a Likert scale ranging from 1 to 5, where 5 was considered the best rating. Results: Image analysis showed an improvement of image quality, noise, sharpness of the organs and lymph nodes, and sharpness of the intestine for pre- and postcontrast images in VIBE_SR compared to VIBE_Std (each p < 0.001). Lesion detectability was better for VIBE_SR (p < 0.001), while there were no differences concerning the number of lesions. Average acquisition time was 16 s (±1) for the upper abdomen and 15 s (±1) for the pelvis for VIBE_Std, and 15 s (±1) for the upper abdomen and 14 s (±1) for the pelvis for VIBE_SR. Conclusion: This study demonstrated the technical feasibility of a deep learning-based super-resolution algorithm including partial Fourier technique in abdominopelvic MR images and illustrated a significant improvement of image quality, noise, and sharpness while reducing TA. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

Review

Jump to: Research

21 pages, 1530 KiB

Open AccessReview

Recent Advances in Explainable Artificial Intelligence for Magnetic Resonance Imaging

by Jinzhao Qian, Hailong Li, Junqi Wang and Lili He

Diagnostics 2023, 13(9), 1571; https://doi.org/10.3390/diagnostics13091571 - 27 Apr 2023

Cited by 12 | Viewed by 4659

Abstract

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as “black boxes”. There is an unmet need to demystify DL [...] Read more.

Advances in artificial intelligence (AI), especially deep learning (DL), have facilitated magnetic resonance imaging (MRI) data analysis, enabling AI-assisted medical image diagnoses and prognoses. However, most of the DL models are considered as “black boxes”. There is an unmet need to demystify DL models so domain experts can trust these high-performance DL models. This has resulted in a sub-domain of AI research called explainable artificial intelligence (XAI). In the last decade, many experts have dedicated their efforts to developing novel XAI methods that are competent at visualizing and explaining the logic behind data-driven DL models. However, XAI techniques are still in their infancy for medical MRI image analysis. This study aims to outline the XAI applications that are able to interpret DL models for MRI data analysis. We first introduce several common MRI data modalities. Then, a brief history of DL models is discussed. Next, we highlight XAI frameworks and elaborate on the principles of multiple popular XAI methods. Moreover, studies on XAI applications in MRI image analysis are reviewed across the tissues/organs of the human body. A quantitative analysis is conducted to reveal the insights of MRI researchers on these XAI techniques. Finally, evaluations of XAI methods are discussed. This survey presents recent advances in the XAI domain for explaining the DL models that have been utilized in MRI applications. Full article

(This article belongs to the Special Issue Artificial Intelligence for Magnetic Resonance Imaging)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence for Magnetic Resonance Imaging

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (10 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI