U-net is an image segmentation technique developed primarily for image segmentation tasks. These traits provide U-net with a high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in nearly all major image modalities, from CT scans and MRI to X-rays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. Given that U-net’s potential is still increasing, this narrative literature review examines the numerous developments and breakthroughs in the U-net architecture and provides observations on recent trends. We also discuss the many innovations that have advanced in deep learning and discuss how these tools facilitate U-net. In addition, we review the different image modalities and application areas that have been enhanced by U-net.

U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications

Research in artificial intelligence for radiology and radiotherapy has recently become increasingly reliant on the use of deep learning-based algorithms. While the performance of the models which these algorithms produce can significantly outperform more traditional machine learning methods, they do rely on larger datasets being available for training. To address this issue, data augmentation has become a popular method for increasing the size of a training dataset, particularly in fields where large datasets aren't typically available, which is often the case when working with medical images. Data augmentation aims to generate additional data which is used to train the model and has been shown to improve performance when validated on a separate unseen dataset. This approach has become commonplace so to help understand the types of data augmentation techniques used in state-of-the-art deep learning models, we conducted a systematic review of the literature where data augmentation was utilised on medical images (limited to CT and MRI) to train a deep learning model. Articles were categorised into basic, deformable, deep learning or other data augmentation techniques. As artificial intelligence models trained using augmented data make their way into the clinic, this review aims to give an insight to these techniques and confidence in the validity of the models produced.

A review of medical image data augmentation techniques for deep learning applications.

Deep learning-based automatic segmentation of images in cardiac radiography: A promising challenge

In computer-aided analysis of cardiac MRI data, segmentations of the left ventricle (LV) and myocardium are performed to quantify LV ejection fraction and LV mass, and they are performed after the identification of a short axis slice coverage, where automatic classification of the slice range of interest is preferable. Standard cardiac image post-processing guidelines indicate the importance of the correct identification of a short axis slice range for accurate quantification. We investigated the feasibility of applying transfer learning of deep convolutional neural networks (CNNs) as a means to automatically classify the short axis slice range, as transfer learning is well suited to medical image data where labeled data is scarce and expensive to obtain. The short axis slice images were classified into out-of-apical, apical-to-basal, and out-of-basal, on the basis of short axis slice location in the LV. We developed a custom user interface to conveniently label image slices into one of the three categories for the generation of training data and evaluated the performance of transfer learning in nine popular deep CNNs. Evaluation with unseen test data indicated that among the CNNs the fine-tuned VGG16 produced the highest values in all evaluation categories considered and appeared to be the most appropriate choice for the cardiac slice range classification.

Evaluation of transfer learning in deep convolutional neural network models for cardiac short axis slice classification

Automatic myocardial segmentation in dynamic contrast enhanced perfusion MRI using Monte Carlo dropout in an encoder-decoder convolutional neural network

EVCMR: A tool for the quantitative evaluation and visualization of cardiac MRI data

This article proposes Bayesian optimization augmented factoring self-scheduling (BO FSS), a new parallel loop scheduling strategy. BO FSS is an automatic tuning variant of the factoring self-scheduling (FSS) algorithm and is based on Bayesian optimization (BO), a black-box optimization algorithm. Its core idea is to automatically tune the internal parameter of FSS by solving an optimization problem using BO. The tuning procedure only requires online execution time measurement of the target loop. In order to apply BO, we model the execution time using two Gaussian process (GP) probabilistic machine learning models. Notably, we propose a locality-aware GP model, which assumes that the temporal locality effect resembles an exponentially decreasing function. By accurately modeling the temporal locality effect, our locality-aware GP model accelerates the convergence of BO. We implemented BO FSS on the GCC implementation of the OpenMP standard and evaluated its performance against other scheduling algorithms. Also, to quantify our method’s performance variation on different workloads, or workload-robustness in our terms, we measure the minimax regret . According to the minimax regret, BO FSS shows more consistent performance than other algorithms. Within the considered workloads, BO FSS improves the execution time of FSS by as much as 22% and 5% on average.

A Probabilistic Machine Learning Approach to Scheduling Parallel Loops With Bayesian Optimization

This paper proposes Hermes, a container-based preemptive GPU scheduling framework for accelerating hyper-parameter optimization in deep learning (DL) clusters. Hermes accelerates hyper-parameter optimization by time-sharing between DL jobs and prioritizing jobs with more promising hyper-parameter combinations. Hermes’s scheduling policy is grounded on the observation that good hyper-parameter combinations converge quickly in the early phases of training. By giving higher priority to fast-converging containers, Hermes’s GPU preemption mechanism can accelerate training. This enables users to find optimal hyper-parameters faster without losing the progress of a container. We have implemented Hermes over Kubernetes and compared its performance against existing scheduling frameworks. Experiments show that Hermes reduces the time for hyper-parameter optimization up to 4.04 times against previously proposed scheduling policies such as FIFO, round-robin (RR), and SLAQ, with minimal time-sharing overhead.

https://www.mdpi.com/2079-9292/10/3/350/pdf

A GPU Scheduling Framework to Accelerate Hyper-Parameter Optimization in Deep Learning Clusters

The purpose of this study was to develop a software tool and evaluate different T1 map calculation methods in terms of computation time in cardiac magnetic resonance imaging. The modified Look-Locker inversion recovery (MOLLI) sequence was used to acquire multiple inversion time (TI) images for pre- and post-contrast T1 mapping. The T1 map calculation involved pixel-wise curve fitting based on the T1 relaxation model. A variety of methods were evaluated using data from 30 subjects for computational efficiency: MRmap, python Levenberg–Marquardt (LM), python reduced-dimension (RD) non-linear least square, C++ single- and multi-core LM, and C++ single- and multi-core RD. Median (interquartile range) computation time was 126 s (98–141) for the publicly available software MRmap, 261 s (249–282) for python LM, 77 s (74–80) for python RD, 3.4 s (3.1–3.6) for C++ multi-core LM, and 1.9 s (1.9–2.0) for C++ multi-core RD. The fastest C++ multi-core RD and the publicly available MRmap showed good agreement of myocardial T1 values, resulting in 95% Bland–Altman limits of agreement of (− 0.83 to 0.58 ms) and (− 6.57 to 7.36 ms) with mean differences of − 0.13 ms and 0.39 ms, for the pre- and post-contrast, respectively. The C++ multi-core RD was the fastest method on a regular eight-core personal computer for pre- or post-contrast T1 map calculation. The presented software tool (fT1fit) facilitated rapid T1 map and extracellular volume fraction map calculations.

/pdf/fast-calculation-software-for-modified-look-locker-inversion-4p5df5477e.pdf

Khu Rai Kim

Papers

Automatic myocardial segmentation in dynamic contrast enhanced perfusion MRI using Monte Carlo dropout in an encoder-decoder convolutional neural network

EVCMR: A tool for the quantitative evaluation and visualization of cardiac MRI data

A Probabilistic Machine Learning Approach to Scheduling Parallel Loops With Bayesian Optimization

A GPU Scheduling Framework to Accelerate Hyper-Parameter Optimization in Deep Learning Clusters

Fast calculation software for modified Look-Locker inversion recovery (MOLLI) T1 mapping