Convolutional neural network MRI segmentation for fast and robust optimization of transcranial electrical current stimulation of the human brain

AbstractThe segmentation of structural MRI data is an essential step for deriving geometrical information about brain tissues. One important application is in transcranial electrical stimulation (e.g., tDCS), a non-invasive neuromodulatory technique where head modeling is required to determine the electric field (E-field) generated in the cortex to predict and optimize its effects. Here we propose a deep learning-based model (StarNEt) to automatize white matter (WM) and gray matter (GM) segmentation and compare its performance with FreeSurfer, an established tool. Since good definition of sulci and gyri in the cortical surface is an important requirement for E-field calculation, StarNEt is specifically designed to output masks at a higher resolution than that of the original input T1w-MRI. StarNEt uses a residual network as the encoder (ResNet) and a fully convolutional neural network with U-net skip connections as the decoder to segment an MRI slice by slice. Slice vertical location is provided as an extra input. The model was trained on scans from 425 patients in the open-access ADNI+IXI datasets, and using FreeSurfer segmentation as ground truth. Model performance was evaluated using the Dice Coefficient (DC) in a separate subset (N=105) of ADNI+IXI and in two extra testing sets not involved in training. In addition, FreeSurfer and StarNEt were compared to manual segmentations of the MRBrainS18 dataset, also unseen by the model. To study performance in real use cases, first, we created electrical head models derived from the FreeSurfer and StarNEt segmentations and used them for montage optimization with a common target region using a standard algorithm (Stimweaver) and second, we used StarNEt to successfully segment the brains of minimally conscious state (MCS) patients having suffered from brain trauma, a scenario where FreeSurfer typically fails. Our results indicate that StarNEt matches FreeSurfer performance on the trained tasks while reducing computation time from several hours to a few seconds, and with the potential to evolve into an effective technique even when patients present large brain abnormalities.

Download Full-text

Posteriori Reconstruction and Denoising for Path Tracing

10.26686/wgtn.17136407 ◽

2021 ◽

Author(s):

◽

Ping Liu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Missing Values ◽

Early Stage ◽

Computation Time ◽

Ground Truth ◽

Low Rank ◽

Tensor Structure ◽

Path Tracing ◽

Block Toeplitz Structure

<p>Path tracing is a well-established technique for photo-realistic rendering to simulate light path transport. This method has been widely adopted in visual effects industries to generate high quality synthetic images requiring a large number of samples and a long computation time. Due to the high cost to produce the final output, intermediate previsualization of path tracing is in high demand from production artists to detect errors in the early stage of rendering. But visualizing intermediate results of path tracing is also challenging since the synthesized image with limited samples or improper sampling usually suffers from distracting noise. The ideal solution would be to provide a highly plausible intermediate result in the early stages of rendering, using a small fraction of samples, and apply a posteriori manner to approximate the ground truth. In this thesis, this issue is addressed by providing several efficient posteriori reconstructions and denoising technique for previsualization of pa-th tracing. Firstly, we address the problem for the recovery of the missing values to construct low rank matrices for incomplete images including missing pixel, missing sub-pixel, and multi-frame scenarios. A novel approach utilizing a convolutional neural network which provides fast precompletion for initializing missing values, and subsequent weighted nuclear norm minimization with a parameter adjustment strategy efficiently recovers missing values even in high frequency details. The result shows better visual quality compared to the recent methods including compressed sensing based reconstruction. Furthermore, to mitigate the computation budgets of our new approac-h, we extend our method by applying a block Toeplitz structure forming a low-rank matrix for pixel recovery, and tensor structure for multi-frame recovery. In this manner, the reconstruction time can be significantly reduced. Besides that, by exploiting temporal coherence of multi-frame with a tensor structure, we demonstrate an improvement in the overall recovery quality compared to our previous approach. Our recovery methods provide satisfying solution but still require plen-ty of rendering time at prior stage compared with denoising solutions. Finally, we introduce a novel filter for denoising based on convolutional neural network, to address the problem as conventional denoising approach for rendered images. Unlike a plain CNN that applies fixed kernel size in each layer, we propose a multi-scale residual network with various auxiliary scene features to leverage a new efficient denoising filter for path tracing. Our experimental results show on par or better denoising quality compare to state-of-the-art path tracing denoiser.</p>

Download Full-text

Posteriori Reconstruction and Denoising for Path Tracing

10.26686/wgtn.17136407.v1 ◽

2021 ◽

Author(s):

◽

Ping Liu

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Missing Values ◽

Early Stage ◽

Computation Time ◽

Ground Truth ◽

Low Rank ◽

Tensor Structure ◽

Path Tracing ◽

Block Toeplitz Structure

Download Full-text

Carpal Bone Segmentation Using Fully Convolutional Neural Network

Current Medical Imaging Formerly Current Medical Imaging Reviews ◽

10.2174/1573405615666190724101600 ◽

2019 ◽

Vol 15 (10) ◽

pp. 983-989

Author(s):

Liang Kim Meng ◽

Azira Khalil ◽

Muhamad Hanif Ahmad Nizar ◽

Maryam Kamarun Nisham ◽

Belinda Pingguan-Murphy ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Automatic Segmentation ◽

Ground Truth ◽

Bone Age ◽

Image Feature ◽

Qualitative Assessment ◽

Carpal Bone ◽

Radiographic Images ◽

Accurate Quantitative Analysis

Background: Bone Age Assessment (BAA) refers to a clinical procedure that aims to identify a discrepancy between biological and chronological age of an individual by assessing the bone age growth. Currently, there are two main methods of executing BAA which are known as Greulich-Pyle and Tanner-Whitehouse techniques. Both techniques involve a manual and qualitative assessment of hand and wrist radiographs, resulting in intra and inter-operator variability accuracy and time-consuming. An automatic segmentation can be applied to the radiographs, providing the physician with more accurate delineation of the carpal bone and accurate quantitative analysis. Methods: In this study, we proposed an image feature extraction technique based on image segmentation with the fully convolutional neural network with eight stride pixel (FCN-8). A total of 290 radiographic images including both female and the male subject of age ranging from 0 to 18 were manually segmented and trained using FCN-8. Results and Conclusion: The results exhibit a high training accuracy value of 99.68% and a loss rate of 0.008619 for 50 epochs of training. The experiments compared 58 images against the gold standard ground truth images. The accuracy of our fully automated segmentation technique is 0.78 ± 0.06, 1.56 ±0.30 mm and 98.02% in terms of Dice Coefficient, Hausdorff Distance, and overall qualitative carpal recognition accuracy, respectively.

Download Full-text

Geometric property-based convolutional neural network for indoor object detection

International Journal of Advanced Robotic Systems ◽

10.1177/1729881421993323 ◽

2021 ◽

Vol 18 (1) ◽

pp. 172988142199332

Author(s):

Xintao Ding ◽

Boquan Li ◽

Jinbao Wang

Keyword(s):

Neural Network ◽

Object Detection ◽

Convolutional Neural Network ◽

Geometric Property ◽

Ground Truth ◽

Geometric Constraints ◽

Depth Information ◽

Training Set ◽

Object Knowledge ◽

The Mean

Indoor object detection is a very demanding and important task for robot applications. Object knowledge, such as two-dimensional (2D) shape and depth information, may be helpful for detection. In this article, we focus on region-based convolutional neural network (CNN) detector and propose a geometric property-based Faster R-CNN method (GP-Faster) for indoor object detection. GP-Faster incorporates geometric property in Faster R-CNN to improve the detection performance. In detail, we first use mesh grids that are the intersections of direct and inverse proportion functions to generate appropriate anchors for indoor objects. After the anchors are regressed to the regions of interest produced by a region proposal network (RPN-RoIs), we then use 2D geometric constraints to refine the RPN-RoIs, in which the 2D constraint of every classification is a convex hull region enclosing the width and height coordinates of the ground-truth boxes on the training set. Comparison experiments are implemented on two indoor datasets SUN2012 and NYUv2. Since the depth information is available in NYUv2, we involve depth constraints in GP-Faster and propose 3D geometric property-based Faster R-CNN (DGP-Faster) on NYUv2. The experimental results show that both GP-Faster and DGP-Faster increase the performance of the mean average precision.

Download Full-text

Effectiveness of transfer learning for enhancing tumor classification with a convolutional neural network on frozen sections

Scientific Reports ◽

10.1038/s41598-020-78129-0 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Young-Gon Kim ◽

Sungchul Kim ◽

Cristina Eunbee Cho ◽

In Hye Song ◽

Hee Jin Lee ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Transfer Learning ◽

Frozen Section ◽

Medical Center ◽

External Validation ◽

Model Performance ◽

Classification Model ◽

Training Dataset

AbstractFast and accurate confirmation of metastasis on the frozen tissue section of intraoperative sentinel lymph node biopsy is an essential tool for critical surgical decisions. However, accurate diagnosis by pathologists is difficult within the time limitations. Training a robust and accurate deep learning model is also difficult owing to the limited number of frozen datasets with high quality labels. To overcome these issues, we validated the effectiveness of transfer learning from CAMELYON16 to improve performance of the convolutional neural network (CNN)-based classification model on our frozen dataset (N = 297) from Asan Medical Center (AMC). Among the 297 whole slide images (WSIs), 157 and 40 WSIs were used to train deep learning models with different dataset ratios at 2, 4, 8, 20, 40, and 100%. The remaining, i.e., 100 WSIs, were used to validate model performance in terms of patch- and slide-level classification. An additional 228 WSIs from Seoul National University Bundang Hospital (SNUBH) were used as an external validation. Three initial weights, i.e., scratch-based (random initialization), ImageNet-based, and CAMELYON16-based models were used to validate their effectiveness in external validation. In the patch-level classification results on the AMC dataset, CAMELYON16-based models trained with a small dataset (up to 40%, i.e., 62 WSIs) showed a significantly higher area under the curve (AUC) of 0.929 than those of the scratch- and ImageNet-based models at 0.897 and 0.919, respectively, while CAMELYON16-based and ImageNet-based models trained with 100% of the training dataset showed comparable AUCs at 0.944 and 0.943, respectively. For the external validation, CAMELYON16-based models showed higher AUCs than those of the scratch- and ImageNet-based models. Model performance for slide feasibility of the transfer learning to enhance model performance was validated in the case of frozen section datasets with limited numbers.

Download Full-text

Nodule Detection with Convolutional Neural Network Using Apache Spark and GPU Frameworks

Applied Sciences ◽

10.3390/app11062838 ◽

2021 ◽

Vol 11 (6) ◽

pp. 2838

Author(s):

Nikitha Johnsirani Venkatesan ◽

Dong Ryeol Shin ◽

Choon Sung Nam

Keyword(s):

Neural Network ◽

Radiation Dose ◽

Convolutional Neural Network ◽

Model Performance ◽

Performance Comparison ◽

Apache Spark ◽

Training Time ◽

Learning Framework ◽

Proposed Model

In the pharmaceutical field, early detection of lung nodules is indispensable for increasing patient survival. We can enhance the quality of the medical images by intensifying the radiation dose. High radiation dose provokes cancer, which forces experts to use limited radiation. Using abrupt radiation generates noise in CT scans. We propose an optimal Convolutional Neural Network model in which Gaussian noise is removed for better classification and increased training accuracy. Experimental demonstration on the LUNA16 dataset of size 160 GB shows that our proposed method exhibit superior results. Classification accuracy, specificity, sensitivity, Precision, Recall, F1 measurement, and area under the ROC curve (AUC) of the model performance are taken as evaluation metrics. We conducted a performance comparison of our proposed model on numerous platforms, like Apache Spark, GPU, and CPU, to depreciate the training time without compromising the accuracy percentage. Our results show that Apache Spark, integrated with a deep learning framework, is suitable for parallel training computation with high accuracy.

Download Full-text

Classification of Cattle Behaviours Using Neck-Mounted Accelerometer-Equipped Collars and Convolutional Neural Networks

Sensors ◽

10.3390/s21124050 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4050

Author(s):

Dejan Pavlovic ◽

Christopher Davison ◽

Andrew Hamilton ◽

Oskar Marko ◽

Robert Atkinson ◽

...

Keyword(s):

Neural Network ◽

Model Performance ◽

Ground Truth ◽

Practical Implementation ◽

Ground Truth Data ◽

Battery Lifetime ◽

Implementation Challenges ◽

Memory Footprint ◽

Commercial Farms ◽

Using Data

Monitoring cattle behaviour is core to the early detection of health and welfare issues and to optimise the fertility of large herds. Accelerometer-based sensor systems that provide activity profiles are now used extensively on commercial farms and have evolved to identify behaviours such as the time spent ruminating and eating at an individual animal level. Acquiring this information at scale is central to informing on-farm management decisions. The paper presents the development of a Convolutional Neural Network (CNN) that classifies cattle behavioural states (`rumination’, `eating’ and `other’) using data generated from neck-mounted accelerometer collars. During three farm trials in the United Kingdom (Easter Howgate Farm, Edinburgh, UK), 18 steers were monitored to provide raw acceleration measurements, with ground truth data provided by muzzle-mounted pressure sensor halters. A range of neural network architectures are explored and rigorous hyper-parameter searches are performed to optimise the network. The computational complexity and memory footprint of CNN models are not readily compatible with deployment on low-power processors which are both memory and energy constrained. Thus, progressive reductions of the CNN were executed with minimal loss of performance in order to address the practical implementation challenges, defining the trade-off between model performance versus computation complexity and memory footprint to permit deployment on micro-controller architectures. The proposed methodology achieves a compression of 14.30 compared to the unpruned architecture but is nevertheless able to accurately classify cattle behaviours with an overall F1 score of 0.82 for both FP32 and FP16 precision while achieving a reasonable battery lifetime in excess of 5.7 years.

Download Full-text

Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence

Communications Biology ◽

10.1038/s42003-021-01697-y ◽

2021 ◽

Vol 4 (1) ◽

Author(s):

Peter M. Maloca ◽

Philipp L. Müller ◽

Aaron Y. Lee ◽

Adnan Tufail ◽

Konstantinos Balaskas ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Optical Coherence Tomography ◽

Image Segmentation ◽

Convolutional Neural Network ◽

Learning Algorithm ◽

Ground Truth ◽

Optical Coherence Tomography Image ◽

Optical Coherence ◽

Tomography Image

AbstractMachine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization (‘neural recording’). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.

Download Full-text

Performance Evaluation of Deep CNN-Based Crack Detection and Localization Techniques for Concrete Structures

Sensors ◽

10.3390/s21051688 ◽

2021 ◽

Vol 21 (5) ◽

pp. 1688

Author(s):

Luqman Ali ◽

Fady Alnajjar ◽

Hamad Al Jassmi ◽

Munkhjargal Gochoo ◽

Wasif Khan ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Crack Detection ◽

Concrete Structures ◽

Model Performance ◽

Training Data ◽

Computational Time ◽

Data Heterogeneity ◽

Public Datasets ◽

Detection And Localization

This paper proposes a customized convolutional neural network for crack detection in concrete structures. The proposed method is compared to four existing deep learning methods based on training data size, data heterogeneity, network complexity, and the number of epochs. The performance of the proposed convolutional neural network (CNN) model is evaluated and compared to pretrained networks, i.e., the VGG-16, VGG-19, ResNet-50, and Inception V3 models, on eight datasets of different sizes, created from two public datasets. For each model, the evaluation considered computational time, crack localization results, and classification measures, e.g., accuracy, precision, recall, and F1-score. Experimental results demonstrated that training data size and heterogeneity among data samples significantly affect model performance. All models demonstrated promising performance on a limited number of diverse training data; however, increasing the training data size and reducing diversity reduced generalization performance, and led to overfitting. The proposed customized CNN and VGG-16 models outperformed the other methods in terms of classification, localization, and computational time on a small amount of data, and the results indicate that these two models demonstrate superior crack detection and localization for concrete structures.

Download Full-text

Systematic review of research design and reporting of imaging studies applying convolutional neural networks for radiological cancer diagnosis

European Radiology ◽

10.1007/s00330-021-07881-2 ◽

2021 ◽

Author(s):

Robert J. O’Shea ◽

Amy Rose Sharkey ◽

Gary J. R. Cook ◽

Vicky Goh

Keyword(s):

Neural Network ◽

Systematic Review ◽

Convolutional Neural Network ◽

Cancer Diagnosis ◽

Model Performance ◽

Network Models ◽

Imaging Studies ◽

Neural Network Models ◽

Eligibility Criteria ◽

Data Partitions

Abstract Objectives To perform a systematic review of design and reporting of imaging studies applying convolutional neural network models for radiological cancer diagnosis. Methods A comprehensive search of PUBMED, EMBASE, MEDLINE and SCOPUS was performed for published studies applying convolutional neural network models to radiological cancer diagnosis from January 1, 2016, to August 1, 2020. Two independent reviewers measured compliance with the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Compliance was defined as the proportion of applicable CLAIM items satisfied. Results One hundred eighty-six of 655 screened studies were included. Many studies did not meet the criteria for current design and reporting guidelines. Twenty-seven percent of studies documented eligibility criteria for their data (50/186, 95% CI 21–34%), 31% reported demographics for their study population (58/186, 95% CI 25–39%) and 49% of studies assessed model performance on test data partitions (91/186, 95% CI 42–57%). Median CLAIM compliance was 0.40 (IQR 0.33–0.49). Compliance correlated positively with publication year (ρ = 0.15, p = .04) and journal H-index (ρ = 0.27, p < .001). Clinical journals demonstrated higher mean compliance than technical journals (0.44 vs. 0.37, p < .001). Conclusions Our findings highlight opportunities for improved design and reporting of convolutional neural network research for radiological cancer diagnosis. Key Points • Imaging studies applying convolutional neural networks (CNNs) for cancer diagnosis frequently omit key clinical information including eligibility criteria and population demographics. • Fewer than half of imaging studies assessed model performance on explicitly unobserved test data partitions. • Design and reporting standards have improved in CNN research for radiological cancer diagnosis, though many opportunities remain for further progress.

Download Full-text