arXiv subjects

Tian Liu

Publications and source records attributed to Tian Liu.

At least 91 records · Page 5Linked to original sources

arXiv2020

Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review

This paper reviewed the deep learning-based studies for medical imaging synthesis and its clinical application. Specifically, we summarized the recent developments of deep learning-based methods in inter- and intra-modality image synthesis by listing and highlighting the proposed methods, study designs and reported performances with related clinical applications on representative studies. The challenges among the reviewed studies were summarized in the discussion part.

physics.med-ph↗

arXiv2020

Artificial Intelligence in Quantitative Ultrasound Imaging: A Review

Quantitative ultrasound (QUS) imaging is a reliable, fast and inexpensive technique to extract physically descriptive parameters for assessing pathologies. Despite its safety and efficacy, QUS suffers from several major drawbacks: poor imaging quality, inter- and intra-observer variability which hampers the reproducibility of measurements. Therefore, it is in great need to develop automatic method to improve the imaging quality and aid in measurements in QUS. In recent years, there has been an increasing interest in artificial intelligence (AI) applications in ultrasound imaging. However, no research has been found that surveyed the AI use in QUS. The purpose of this paper is to review recent research into the AI applications in QUS. This review first introduces the AI workflow, and then discusses the various AI applications in QUS. Finally, challenges and future potential AI applications in QUS are discussed.

physics.med-ph↗

arXiv2020

Learning-Based Stopping Power Mapping on Dual Energy CT for Proton Radiation Therapy

Purpose: Dual-energy CT (DECT) has been used to derive relative stopping power (RSP) map by obtaining the energy dependence of photon interactions. The DECT-derived RSP maps could potentially be compromised by image noise levels and the severity of artifacts when using physics-based mapping techniques, which would affect subsequent clinical applications. This work presents a noise-robust learning-based method to predict RSP maps from DECT for proton radiation therapy. Methods: The proposed method uses a residual attention cycle-consistent generative adversarial (CycleGAN) network. CycleGAN were used to let the DECT-to-RSP mapping be close to a one-to-one mapping by introducing an inverse RSP-to-DECT mapping. We retrospectively investigated 20 head-and-neck cancer patients with DECT scans in proton radiation therapy simulation. Ground truth RSP values were assigned by calculation based on chemical compositions, and acted as learning targets in the training process for DECT datasets, and were evaluated against results from the proposed method using a leave-one-out cross-validation strategy. Results: The predicted RSP maps showed an average normalized mean square error (NMSE) of 2.83% across the whole body volume, and average mean error (ME) less than 3% in all volumes of interest (VOIs). With additional simulated noise added in DECT datasets, the proposed method still maintained a comparable performance, while the physics-based stoichiometric method suffered degraded inaccuracy from increased noise level. The average differences in DVH metrics for clinical target volumes (CTVs) were less than 0.2 Gy for D95% and Dmax with no statistical significance. Conclusion: These results strongly indicate the high accuracy of RSP maps predicted by our machine-learning-based method and show its potential feasibility for proton treatment planning and dose calculation.

physics.med-ph↗

arXiv2020

Deep Learning in Multi-organ Segmentation

This paper presents a review of deep learning (DL) in multi-organ segmentation. We summarized the latest DL-based methods for medical image segmentation and applications. These methods were classified into six categories according to their network design. For each category, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review of each category, we briefly discussed its achievements, shortcomings and future potentials. We provided a comprehensive comparison among DL-based methods for thoracic and head & neck multiorgan segmentation using benchmark datasets, including the 2017 AAPM Thoracic Auto-segmentation Challenge datasets and 2015 MICCAI Head Neck Auto-Segmentation Challenge datasets.

eess.IV↗

arXiv2020

Machine Learning in Quantitative PET Imaging

This paper reviewed the machine learning-based studies for quantitative positron emission tomography (PET). Specifically, we summarized the recent developments of machine learning-based methods in PET attenuation correction and low-count PET reconstruction by listing and comparing the proposed methods, study designs and reported performances of the current published studies with brief discussion on representative studies. The contributions and challenges among the reviewed studies were summarized and highlighted in the discussion part followed by.

eess.IV↗

arXiv2019

Deep Learning in Medical Image Registration: A Review

This paper presents a review of deep learning (DL) based medical image registration methods. We summarized the latest developments and applications of DL-based registration methods in the medical field. These methods were classified into seven categories according to their methods, functions and popularity. A detailed review of each category was presented, highlighting important contributions and identifying specific challenges. A short assessment was presented following the detailed review of each category to summarize its achievements and future potentials. We provided a comprehensive comparison among DL-based methods for lung and brain deformable registration using benchmark datasets. Lastly, we analyzed the statistics of all the cited works from various aspects, revealing the popularity and future trend of development in medical image registration using deep learning.

eess.IV↗

arXiv2019

Feature Fusion Use Unsupervised Prior Knowledge to Let Small Object Represent

Fusing low level and high level features is a widely used strategy to provide details that might be missing during convolution and pooling. Different from previous works, we propose a new fusion mechanism called FillIn which takes advantage of prior knowledge described with superpixel segmentation. According to the prior knowledge, the FillIn chooses small region on low level feature map to fill into high level feature map. By using the proposed fusion mechanism, the low level features have equal channels for some tiny region as high level features, which makes the low level features have relatively independent power to decide final semantic label. We demonstrate the effectiveness of our model on PASCAL VOC 2012, it achieves competitive test result based on DeepLabv3+ backbone and visualizations of predictions prove our fusion can let small objects represent and low level features have potential for segmenting small objects.

cs.CV↗

arXiv2019

Radiomics in Cancer Radiotherapy: a Review

Radiomics is a nascent field in quantitative imaging that uses advanced algorithms and considerable computing power to describe tumor phenotypes, monitor treatment response, and assess normal tissue toxicity quantifiably. Remarkable interest has been drawn to the field due to its noninvasive nature and potential for diagnosing and predicting patient prognosis. This review will attempt to comprehensively and critically discuss the various aspects of radiomics including its workflow, applications to different modalities, potential applications in cancer radiotherapy, and limitations.

physics.med-ph↗

arXiv2019

Air, bone and soft-tissue Segmentation on 3D brain MRI Using Semantic Classification Random Forest with Auto-Context Model

As bone and air produce weak signals with conventional MR sequences, segmentation of these tissues particularly difficult in MRI. We propose to integrate patch-based anatomical signatures and an auto-context model into a machine learning framework to iteratively segment MRI into air, bone and soft tissue. The proposed semantic classification random forest (SCRF) method consists of a training stage and a segmentation stage. During training stage, patch-based anatomical features were extracted from registered MRI-CT training images, and the most informative features were identified to train a series of classification forests with auto-context model. During segmentation stage, we extracted selected features from MRI and fed them into the well-trained forests for MRI segmentation. The DSC for air, bone and soft tissue obtained with proposed SCRF were 0.976, 0.819 and 0.932, compared to 0.916, 0.673 and 0.830 with RF, 0.942, 0.791 and 0.917 with U-Net. SCRF also demonstrated superior segmentation performances for sensitivity and specificity over RF and U-Net for all three structure types. The proposed segmentation technique could be a useful tool to segment bone, air and soft tissue, and have the potential to be applied to attenuation correction of PET/MRI system, MRI-only radiation treatment planning and MR-guided focused ultrasound surgery.

physics.med-ph↗

arXiv2019

Machine-learning-based Classification of Lower-grade gliomas and High-grade gliomas using Radiomic Features in Multi-parametric MRI

Objectives: Glioblastomas are the most aggressive brain and central nervous system (CNS) tumors with poor prognosis in adults. The purpose of this study is to develop a machine-learning based classification method using radio-mic features of multi-parametric MRI to classify high-grade gliomas (HGG) and low-grade gliomas (LGG). Methods: Multi-parametric MRI of 80 patients, 40 HGG and 40 LGG, with gliomas from the MICCAI BRATs 2015 training database were used in this study. Each patient's T1, contrast-enhanced T1, T2, and Fluid Attenuated Inversion Recovery (FLAIR) MRIs as well as the tumor contours were provided in the database. Using the given contours, radiomic features from all four multi-parametric MRIs were extracted. Of these features, a feature selection process using two-sample T-test and least absolute shrinkage, selection operator (LASSO), and a feature correlation threshold was applied to various combinations of T1, contrast-enhanced T1, T2, and FLAIR MRIs separately. These selected features were then used to train, test, and cross-validate a random forest to differentiate HGG and LGG. Finally, the classification accuracy and area under the curve (AUC) were used to evaluate the classification method. Results: Optimized parameters showed that on average, the overall accuracy of our classification method was 0.913 or 73 out of 80 correct classifications, 36/40 for HGG and 37/40 for LGG, with an AUC of 0.956 based on the combination with FLAIR, T1, T1c and T2 MRIs. Conclusion: This study shows that radio-mic features derived from multi-parametric MRI could be used to accurately classify high and lower grade gliomas. The radio-mic features from multi-parametric MRI in combination with even more advanced machine learning methods may further elucidate the underlying tumor biology and response to therapy.

physics.med-ph↗

arXiv2019

A preliminary study on a multi-resolution-level inverse planning algorithm for Gamma Knife radiosurgery

Manual forward planning for GK radiosurgery is complicated and time-consuming, particularly for cases with large or irregularly shaped targets. Inverse planning eases GK planning by solving an optimization problem. However, due to the vast search space, most inverse planning algorithms have to decouple the planning process to isocenter preselection and sector duration optimization. This sequential scheme does not necessarily lead to optimal isocenter locations and hence optimal plans. In this study, we attempt to optimize the isocenter positions, beam shapes and durations simultaneously by proposing a multi-resolution-level (MRL) strategy to handle the large-scale GK optimization problem. In our approach, several rounds of optimizations were performed with a progressively increased spatial resolution for isocenter candidate selection. The isocenters selected from last round and their neighbors on a finer resolution were used as new isocenter candidates for next round of optimization. After plan optimization, shot sequencing was performed to group the optimized sectors to deliverable shots supported by GK treatment units. We have tested our algorithm on 6 GK cases previously treated in our institution (2 meningioma cases, 3 cases with single metastasis and 1 case with 6 metastases). Compared with manual planning, achieving same coverage and similar selectivity, our algorithm improved the gradient index averagely from 3.1 to 2.9 and reduced the maximum dose of brainstem from 8.0Gy to 5.6Gy. The average beam-on time was also reduced by from 103.8 mins to 87.4 mins. Our method was also compared with the inverse planning algorithm provided in Leksell GammaPlan planning system, and outperformed it with better plan quality for all the 6 cases.This preliminary study has demonstrated the effectiveness and feasibility of our MRL inverse planning approach for GK radiosurgery.

physics.med-ph↗

arXiv2019

Adversarial FDI Attack against AC State Estimation with ANN

Artificial neural network (ANN) provides superior accuracy for nonlinear alternating current (AC) state estimation (SE) in smart grid over traditional methods. However, research has discovered that ANN could be easily fooled by adversarial examples. In this paper, we initiate a new study of adversarial false data injection (FDI) attack against AC SE with ANN: by injecting a deliberate attack vector into measurements, the attacker can degrade the accuracy of ANN SE while remaining undetected. We propose a population-based algorithm and a gradient-based algorithm to generate attack vectors. The performance of these algorithms is evaluated through simulations on IEEE 9-bus, 14-bus and 30-bus systems under various attack scenarios. Simulation results show that DE is more effective than SLSQP on all simulation cases. The attack examples generated by DE algorithm successfully degrade the ANN SE accuracy with high probability.

cs.LG↗

arXiv2019

ColCOS$Φ$: A Multiple Pheromone Communication System for Swarm Robotics and Social Insects Research

In the last few decades we have witnessed how the pheromone of social insect has become a rich inspiration source of swarm robotics. By utilising the virtual pheromone in physical swarm robot system to coordinate individuals and realise direct/indirect inter-robot communications like the social insect, stigmergic behaviour has emerged. However, many studies only take one single pheromone into account in solving swarm problems, which is not the case in real insects. In the real social insect world, diverse behaviours, complex collective performances and flexible transition from one state to another are guided by different kinds of pheromones and their interactions. Therefore, whether multiple pheromone based strategy can inspire swarm robotics research, and inversely how the performances of swarm robots controlled by multiple pheromones bring inspirations to explain the social insects' behaviours will become an interesting question. Thus, to provide a reliable system to undertake the multiple pheromone study, in this paper, we specifically proposed and realised a multiple pheromone communication system called ColCOS$Φ$. This system consists of a virtual pheromone sub-system wherein the multiple pheromone is represented by a colour image displayed on a screen, and the micro-robots platform designed for swarm robotics applications. Two case studies are undertaken to verify the effectiveness of this system: one is the multiple pheromone based on an ant's forage and another is the interactions of aggregation and alarm pheromones. The experimental results demonstrate the feasibility of ColCOS$Φ$ and its great potential in directing swarm robotics and social insects research.

cs.RO↗

arXiv2017

Smart materials and structures for energy harvesters

Vibrational energy harvesters capture mechanical energy from ambient vibrations and convert the mechanical energy into electrical energy to power wireless electronic systems. Challenges exist in the process of capturing mechanical energy from ambient vibrations. For example, resonant harvesters may be used to improve power output near their resonance, but their narrow bandwidth makes them less suitable for applications with varying vibrational frequencies. Higher operating frequencies can increase harvesters power output, but many vibrational sources are characterized by lower frequencies, such as human motions. This paper provides a thorough review of state of the art energy harvesters based on various energy sources such as solar, thermal, electromagnetic and mechanical energy, as well as smart materials including piezoelectric materials and carbon nanotubes. The paper will then focus on vibrational energy harvesters to review harvesters using typical transduction mechanisms and various techniques to address the challenges in capturing mechanical energy and delivering it to the transducers.

physics.app-ph↗

arXiv2017

A $(1.4 + ε)$-approximation algorithm for the $2$-Max-Duo problem

The maximum duo-preservation string mapping (Max-Duo) problem is the complement of the well studied minimum common string partition (MCSP) problem, both of which have applications in many fields including text compression and bioinformatics. $k$-Max-Duo is the restricted version of Max-Duo, where every letter of the alphabet occurs at most $k$ times in each of the strings, which is readily reduced into the well known maximum independent set (MIS) problem on a graph of maximum degree $Δ\le 6(k-1)$. In particular, $2$-Max-Duo can then be approximated arbitrarily close to $1.8$ using the state-of-the-art approximation algorithm for the MIS problem. $2$-Max-Duo was proved APX-hard and very recently a $(1.6 + ε)$-approximation was claimed, for any $ε> 0$. In this paper, we present a vertex-degree reduction technique, based on which, we show that $2$-Max-Duo can be approximated arbitrarily close to $1.4$.

cs.DS↗

arXiv2017

A New Probabilistic Algorithm for Approximate Model Counting

Constrained counting is important in domains ranging from artificial intelligence to software analysis. There are already a few approaches for counting models over various types of constraints. Recently, hashing-based approaches achieve both theoretical guarantees and scalability, but still rely on solution enumeration. In this paper, a new probabilistic polynomial time approximate model counter is proposed, which is also a hashing-based universal framework, but with only satisfiability queries. A variant with a dynamic stopping criterion is also presented. Empirical evaluation over benchmarks on propositional logic formulas and SMT(BV) formulas shows that the approach is promising.

cs.AI↗

arXiv2015

Solution space structure of random constraint satisfaction problems with growing domains

In this paper we study the solution space structure of model RB, a standard prototype of Constraint Satisfaction Problem (CSPs) with growing domains. Using rigorous the first and the second moment method, we show that in the solvable phase close to the satisfiability transition, solutions are clustered into exponential number of well-separated clusters, with each cluster contains sub-exponential number of solutions. As a consequence, the system has a clustering (dynamical) transition but no condensation transition. This picture of phase diagram is different from other classic random CSPs with fixed domain size, such as random K-Satisfiability (K-SAT) and graph coloring problems, where condensation transition exists and is distinct from satisfiability transition. Our result verifies the non-rigorous results obtained using cavity method from spin glass theory, and sheds light on the structures of solution spaces of problems with a large number of states.

cond-mat.dis-nn↗

arXiv2013

Algorithms for Cut Problems on Trees

We study the {\sc multicut on trees} and the {\sc generalized multiway Cut on trees} problems. For the {\sc multicut on trees} problem, we present a parameterized algorithm that runs in time $O^{*}(ρ^k)$, where $ρ= \sqrt{\sqrt{2} + 1} \approx 1.555$ is the positive root of the polynomial $x^4-2x^2-1$. This improves the current-best algorithm of Chen et al. that runs in time $O^{*}(1.619^k)$. For the {\sc generalized multiway cut on trees} problem, we show that this problem is solvable in polynomial time if the number of terminal sets is fixed; this answers an open question posed in a recent paper by Liu and Zhang. By reducing the {\sc generalized multiway cut on trees} problem to the {\sc multicut on trees} problem, our results give a parameterized algorithm that solves the {\sc generalized multiway cut on trees} problem in time $O^{*}(ρ^k)$, where $ρ= \sqrt{\sqrt{2} + 1} \approx 1.555$ time.

cs.DS↗