arXiv subjects

Tian Liu

Publications and source records attributed to Tian Liu.

At least 73 records · Page 4Linked to original sources

arXiv2022

Reinforcement Learning in Medical Image Analysis: Concepts, Applications, Challenges, and Future Directions

Motivation: Medical image analysis involves tasks to assist physicians in qualitative and quantitative analysis of lesions or anatomical structures, significantly improving the accuracy and reliability of diagnosis and prognosis. Traditionally, these tasks are finished by physicians or medical physicists and lead to two major problems: (i) low efficiency; (ii) biased by personal experience. In the past decade, many machine learning methods have been applied to accelerate and automate the image analysis process. Compared to the enormous deployments of supervised and unsupervised learning models, attempts to use reinforcement learning in medical image analysis are scarce. This review article could serve as the stepping-stone for related research. Significance: From our observation, though reinforcement learning has gradually gained momentum in recent years, many researchers in the medical analysis field find it hard to understand and deploy in clinics. One cause is lacking well-organized review articles targeting readers lacking professional computer science backgrounds. Rather than providing a comprehensive list of all reinforcement learning models in medical image analysis, this paper may help the readers to learn how to formulate and solve their medical image analysis research as reinforcement learning problems. Approach & Results: We selected published articles from Google Scholar and PubMed. Considering the scarcity of related articles, we also included some outstanding newest preprints. The papers are carefully reviewed and categorized according to the type of image analysis task. We first review the basic concepts and popular models of reinforcement learning. Then we explore the applications of reinforcement learning models in landmark detection. Finally, we conclude the article by discussing the reviewed reinforcement learning approaches' limitations and possible improvements.

cs.CV↗

arXiv2022

Efficient Federated Learning for AIoT Applications Using Knowledge Distillation

As a promising distributed machine learning paradigm, Federated Learning (FL) trains a central model with decentralized data without compromising user privacy, which has made it widely used by Artificial Intelligence Internet of Things (AIoT) applications. However, the traditional FL suffers from model inaccuracy since it trains local models using hard labels of data and ignores useful information of incorrect predictions with small probabilities. Although various solutions try to tackle the bottleneck of the traditional FL, most of them introduce significant communication and memory overhead, making the deployment of large-scale AIoT devices a great challenge. To address the above problem, this paper presents a novel Distillation-based Federated Learning (DFL) architecture that enables efficient and accurate FL for AIoT applications. Inspired by Knowledge Distillation (KD) that can increase the model accuracy, our approach adds the soft targets used by KD to the FL model training, which occupies negligible network resources. The soft targets are generated by local sample predictions of each AIoT device after each round of local training and used for the next round of model training. During the local training of DFL, both soft targets and hard labels are used as approximation objectives of model predictions to improve model accuracy by supplementing the knowledge of soft targets. To further improve the performance of our DFL model, we design a dynamic adjustment strategy for tuning the ratio of two loss functions used in KD, which can maximize the use of both soft targets and hard labels. Comprehensive experimental results on well-known benchmarks show that our approach can significantly improve the model accuracy of FL with both Independent and Identically Distributed (IID) and non-IID data.

cs.LG↗

arXiv2022

FedCAT: Towards Accurate Federated Learning via Device Concatenation

As a promising distributed machine learning paradigm, Federated Learning (FL) enables all the involved devices to train a global model collaboratively without exposing their local data privacy. However, for non-IID scenarios, the classification accuracy of FL models decreases drastically due to the weight divergence caused by data heterogeneity. Although various FL variants have been studied to improve model accuracy, most of them still suffer from the problem of non-negligible communication and computation overhead. In this paper, we introduce a novel FL approach named Fed-Cat that can achieve high model accuracy based on our proposed device selection strategy and device concatenation-based local training method. Unlike conventional FL methods that aggregate local models trained on individual devices, FedCat periodically aggregates local models after their traversals through a series of logically concatenated devices, which can effectively alleviate the model weight divergence problem. Comprehensive experimental results on four well-known benchmarks show that our approach can significantly improve the model accuracy of state-of-the-art FL methods without causing extra communication overhead.

cs.LG↗

arXiv2022

Towards Fast and Accurate Federated Learning with non-IID Data for Cloud-Based IoT Applications

As a promising method of central model training on decentralized device data while securing user privacy, Federated Learning (FL)is becoming popular in Internet of Things (IoT) design. However, when the data collected by IoT devices are highly skewed in a non-independent and identically distributed (non-IID) manner, the accuracy of vanilla FL method cannot be guaranteed. Although there exist various solutions that try to address the bottleneck of FL with non-IID data, most of them suffer from extra intolerable communication overhead and low model accuracy. To enable fast and accurate FL, this paper proposes a novel data-based device grouping approach that can effectively reduce the disadvantages of weight divergence during the training of non-IID data. However, since our grouping method is based on the similarity of extracted feature maps from IoT devices, it may incur additional risks of privacy exposure. To solve this problem, we propose an improved version by exploiting similarity information using the Locality-Sensitive Hashing (LSH) algorithm without exposing extracted feature maps. Comprehensive experimental results on well-known benchmarks show that our approach can not only accelerate the convergence rate, but also improve the prediction accuracy for FL with non-IID data.

cs.LG↗

arXiv2021

Automatic Inverse Treatment Planning for Gamma Knife Radiosurgery via Deep Reinforcement Learning

Purpose: Several inverse planning algorithms have been developed for Gamma Knife (GK) radiosurgery to determine a large number of plan parameters via solving an optimization problem, which typically consists of multiple objectives. The priorities among these objectives need to be repetitively adjusted to achieve a clinically good plan for each patient. This study aimed to achieve automatic and intelligent priority-tuning, by developing a deep reinforcement learning (DRL) based method to model the tuning behaviors of human planners. Methods: We built a priority-tuning policy network using deep convolutional neural networks. Its input was a vector composed of the plan metrics that were used in our institution for GK plan evaluation. The network can determine which tuning action to take, based on the observed quality of the intermediate plan. We trained the network using an end-to-end DRL framework to approximate the optimal action-value function. A scoring function was designed to measure the plan quality. Results: Vestibular schwannoma was chosen as the test bed in this study. The number of training, validation and testing cases were 5, 5, and 16, respectively. For these three datasets, the average plan scores with initial priorities were 3.63 $\pm$ 1.34, 3.83 $\pm$ 0.86 and 4.20 $\pm$ 0.78, respectively, while can be improved to 5.28 $\pm$ 0.23, 4.97 $\pm$ 0.44 and 5.22 $\pm$ 0.26 through manual priority tuning by human expert planners. Our network achieved competitive results with 5.42 $\pm$ 0.11, 5.10 $\pm$ 0. 42, 5.28 $\pm$ 0.20, respectively. Conclusions: Our network can generate GK plans of comparable or slightly higher quality comparing with the plans generated by human planners via manual priority tuning. The network can potentially be incorporated into the clinical workflow to improve GK planning efficiency.

physics.med-ph↗

arXiv2021

Deep Learning Based Antenna-time Domain Channel Extrapolation for Hybrid mmWave Massive MIMO

In a time-varying massive multiple-input multipleoutput (MIMO) system, the acquisition of the downlink channel state information at the base station (BS) is a very challenging task due to the prohibitively high overheads associated with downlink training and uplink feedback. In this paper, we consider the hybrid precoding structure at BS and examine the antennatime domain channel extrapolation. We design a latent ordinary differential equation (ODE)-based network under the variational auto-encoder (VAE) framework to learn the mapping function from the partial uplink channels to the full downlink ones at the BS side. Specifically, the gated recurrent unit is adopted for the encoder and the fully-connected neural network is used for the decoder. The end-to-end learning is utilized to optimize the network parameters. Simulation results show that the designed network can efficiently infer the full downlink channels from the partial uplink ones, which can significantly reduce the channel training overhead.

cs.IT↗

arXiv2021

Profiling Visual Dynamic Complexity Using a Bio-Robotic Approach

Visual dynamic complexity is a ubiquitous, hidden attribute of the visual world that every dynamic vision system is faced with. However, it is implicit and intractable which has never been quantitatively described due to the difficulty in defending temporal features correlated to spatial image complexity. To fill this vacancy, we propose a novel bio-robotic approach to profile visual dynamic complexity which can be used as a new metric. Here we apply a state-of-the-art brain-inspired motion detection neural network model to explicitly profile such complexity associated with spatial-temporal frequency (SF-TF) of visual scene. This model is for the first time implemented in an autonomous micro-mobile robot which navigates freely in an arena with visual walls displaying moving sine-wave grating or cluttered natural scene. The neural dynamic response can make reasonable prediction on surrounding complexity since it can be mapped monotonically to varying SF-TF of visual scene. The experiments show this approach is flexible to different visual scenes for profiling the dynamic complexity. We also use this metric as a predictor to investigate the boundary of another collision detection visual system performing in changing environment with increasing dynamic complexity. This research demonstrates a new paradigm of using biologically plausible visual processing scheme to estimate dynamic complexity of visual scene from both spatial and temporal perspectives, which could be beneficial to predicting input complexity when evaluating dynamic vision systems.

cs.RO↗

arXiv2021

Artificial Intelligence in Tumor Subregion Analysis Based on Medical Imaging: A Review

Medical imaging is widely used in cancer diagnosis and treatment, and artificial intelligence (AI) has achieved tremendous success in various tasks of medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential AI applications in tumor subregion analysis are discussed.

eess.IV↗

arXiv2020

Generative Adversarial Network for Image Synthesis

This chapter reviews recent developments of generative adversarial networks (GAN)-based methods for medical and biomedical image synthesis tasks. These methods are classified into conditional GAN and Cycle-GAN according to the network architecture designs. For each category, a literature survey is given, which covers discussions of the network architecture designs, highlights important contributions and identifies specific challenges.

physics.med-ph↗

arXiv2020

Synthetic MRI-aided Head-and-Neck Organs-at-Risk Auto-Delineation for CBCT-guided Adaptive Radiotherapy

Purpose: Organ-at-risk (OAR) delineation is a key step for cone-beam CT (CBCT) based adaptive radiotherapy planning that can be a time-consuming, labor-intensive, and subject-to-variability process. We aim to develop a fully automated approach aided by synthetic MRI for rapid and accurate CBCT multi-organ contouring in head-and-neck (HN) cancer patients. MRI has superb soft-tissue contrasts, while CBCT offers bony-structure contrasts. Using the complementary information provided by MRI and CBCT is expected to enable accurate multi-organ segmentation in HN cancer patients. In our proposed method, MR images are firstly synthesized using a pre-trained cycle-consistent generative adversarial network given CBCT. The features of CBCT and synthetic MRI are then extracted using dual pyramid networks for final delineation of organs. CBCT images and their corresponding manual contours were used as pairs to train and test the proposed model. Quantitative metrics including Dice similarity coefficient (DSC) were used to evaluate the proposed method. The proposed method was evaluated on a cohort of 65 HN cancer patients. CBCT images were collected from those patients who received proton therapy. Overall, DSC values of 0.87, 0.79/0.79, 0.89/0.89, 0.90, 0.75/0.77, 0.86, 0.66, 0.78/0.77, 0.96, 0.89/0.89, 0.832, and 0.84 for commonly used OARs for treatment planning including brain stem, left/right cochlea, left/right eye, larynx, left/right lens, mandible, optic chiasm, left/right optic nerve, oral cavity, left/right parotid, pharynx, and spinal cord, respectively, were achieved. In this study, we developed a synthetic MRI-aided HN CBCT auto-segmentation method based on deep learning. It provides a rapid and accurate OAR auto-delineation approach, which can be used for adaptive radiation therapy.

physics.med-ph↗

arXiv2020

Knowledge-based Radiation Treatment Planning: A Data-driven Method Survey

This paper surveys the data-driven dose prediction approaches introduced for knowledge-based planning (KBP) in the last decade. These methods were classified into two major categories according to their methods and techniques of utilizing previous knowledge: traditional KBP methods and deep-learning-based methods. Previous studies that required geometric or anatomical features to either find the best matched case(s) from repository of previously delivered treatment plans or build prediction models were included in traditional methods category, whereas deep-learning-based methods included studies that trained neural networks to make dose prediction. A comprehensive review of each category is presented, highlighting key parameters, methods, and their outlooks in terms of dose prediction over the years. We separated the cited works according to the framework and cancer site in each category. Finally, we briefly discuss the performance of both traditional KBP methods and deep-learning-based methods, and future trends of both data-driven KBP approaches.

physics.med-ph↗

arXiv2020

A plan quality control method of treatment planning for Gamma Knife radiosurgery

With many variables to adjust, conventional manual forward planning for Gamma Knife (GK) radiosurgery is very complicated and cumbersome. The resulting plan quality heavily depends on planners skills, experiences and devoted efforts, and varies significantly among cases, planners, and institutions. Quality control for GK planning is desired to consistently provide high-quality plan to each patient. In this study, we proposed a quality control method for GK planning by building a database of high-quality GK plans. Patient anatomy was described by target volume, target shape complexity, and spatial relationship between target and nearby organs, which determine GK planning difficulty level. Plan quality was evaluated using target coverage, selectivity, intermediate dose spillage, maximum dose to 0.1 cc of brainstem, mean dose of ipsilateral cochlea, and beam-on time. When a new plan is created, a high-quality plan that has the most similar target volume size and shape complexity will be identified from the database. A model has also been built to predict the dose to brainstem and cochlea based on their overlap volume histograms. The identified reference plan and the predicted organ dose will help planners to make quality control decisions accordingly. To validate this method, we have built a database for vestibular schwannoma, which are considered to be challenging for GK planning due to the irregularly-shaped target and its proximity to brainstem and cochlea. Five cases were tested, among which one case was considered to be of high quality and four cases had a lower plan quality than prediction. These four cases were replanned and got substantially improved. Our results have demonstrated the efficacy of our proposed quality control method. This method may also be used as a plan quality prediction method to facilitate the development of automatic treatment planning for GK radiosurgery.

physics.med-ph↗

arXiv2020

An institutional study on plan quality and variation of manual forward planning for Gamma Knife radiosurgery for vestibular schwannoma

Due to the complexity and cumbersomeness of Gamma Knife (GK) manual forward planning, the quality of the resulting treatment plans heavily depends on the planners skill, experience and the amount of effort devoted to plan development. Hence, GK plan quality may vary significantly among institutions and planners, and even for a same planner at different cases. This is particularly a concern for challenging cases with complicated geometry, such as vestibular schwannoma cases. The purpose of this retrospective study is to investigate the plan quality and variation in the manually forward planned, clinically acceptable GK treatment plans of 22 previous vestibular schwannoma cases. Considering the impacts of different patient geometry and different trade-offs among the planning objectives in GK planning, it is difficult to objectively assess the plan quality across different cases. To reduce these confounding factors on plan quality assessment, we employed our recently developed multiresolution-level inverse planning algorithm to generate a golden plan for each case, which is expected to be on or close to the pareto surface with a similar trade-off as used in the manual plan. The plan quality of the manual plan is then quantified in terms of its deviation from the golden plan. A scoring criterion between 0-100 was designed to calculate a final score for each manual plan to simplify our analysis. Large quality variation was observed in these 22 cases, with two cases having a score lower than 75, three cases scoring between 80 and 85, two cases between 85 and 90, eight cases between 90 and 95, and seven cases higher than 95. Inter- and intra- planner variability was also observed in our study. This large variation in GK manual planning deserves high attention, and merits further investigation on how to reduce the variation in GK treatment plan quality.

physics.med-ph↗

arXiv2020

FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications

Along with the proliferation of Artificial Intelligence (AI) and Internet of Things (IoT) techniques, various kinds of adversarial attacks are increasingly emerging to fool Deep Neural Networks (DNNs) used by Industrial IoT (IIoT) applications. Due to biased training data or vulnerable underlying models, imperceptible modifications on inputs made by adversarial attacks may result in devastating consequences. Although existing methods are promising in defending such malicious attacks, most of them can only deal with limited existing attack types, which makes the deployment of large-scale IIoT devices a great challenge. To address this problem, we present an effective federated defense approach named FDA3 that can aggregate defense knowledge against adversarial examples from different sources. Inspired by federated learning, our proposed cloud-based architecture enables the sharing of defense capabilities against different attacks among IIoT devices. Comprehensive experimental results show that the generated DNNs by our approach can not only resist more malicious attacks than existing attack-specific adversarial training methods, but also can prevent IIoT applications from new attacks.

cs.LG↗

arXiv2020

Learning-Based Synthetic Dual Energy CT Imaging from Single Energy CT for Stopping Power Ratio Calculation in Proton Radiation Therapy

Purpose: Dual-energy CT (DECT) has been shown to derive stopping power ratio (SPR) map with higher accuracy than conventional single energy CT (SECT) by obtaining the energy dependence of photon interactions. However, DECT is not as widely implemented as SECT in proton radiation therapy simulation. This work presents a learning-based method to synthetize DECT images from SECT for proton radiation therapy. Methods: The proposed method uses a residual attention generative adversarial network. Residual blocks with attention gates were used to force the model focus on the difference between DECT maps and SECT images. To evaluate the accuracy of the method, we retrospectively investigated 20 head-and-neck cancer patients with both DECT and SECT scans available. The high and low energy CT images acquired from DECT acted as learning targets in the training process for SECT datasets and were evaluated against results from the proposed method using a leave-one-out cross-validation strategy. To evaluate our method in the context of a practical application, we generated SPR maps from sDECT using physics-based dual-energy stoichiometric method and compared the maps to those generated from DECT. Results: The synthesized DECT images showed an average mean absolute error around 30 Hounsfield Unit (HU) across the whole-body volume. The corresponding SPR maps generated from synthetic DECT showed an average normalized mean square error of about 1% with reduced noise level and artifacts than those from original DECT. Conclusions: The accuracy of the synthesized DECT image by our machine-learning-based method was evaluated on head and neck patient, and potential feasibility for proton treatment planning and dose calculation was shown by generating SPR map using the synthesized DECT.

physics.med-ph↗

arXiv2020

Deep learning-based Real-time Volumetric Imaging for Lung Stereotactic Body Radiation Therapy: A Proof of Concept Study

Due to the inter- and intra- variation of respiratory motion, it is highly desired to provide real-time volumetric images during the treatment delivery of lung stereotactic body radiation therapy (SBRT) for accurate and active motion management. In this proof-of-concept study, we propose a novel generative adversarial network integrated with perceptual supervision to derive instantaneous volumetric images from a single 2D projection. Our proposed network, named TransNet, consists of three modules, i.e., encoding, transformation and decoding modules. Rather than only using image distance loss between the generated 3D images and the ground truth 3D CT images to supervise the network, perceptual loss in feature space is integrated into loss function to force the TransNet to yield accurate lung boundary. Adversarial supervision is also used to improve the realism of generated 3D images. We conducted a simulation study on 20 patient cases, who had received lung SBRT treatments in our institution and undergone 4D-CT simulation, and evaluated the efficacy and consistency of our method for four different projection angles, i.e., 0, 30, 60 and 90 degree. For each 3D CT image set of a breathing phase, we simulated its 2D projections at these angles.Then for each projection angle, a patient's 3D CT images of 9 phases and the corresponding 2D projection data were used for training, with the remaining phase used for testing. The mean absolute error, normalized MAE, peak signal-to-noise ratio and structural similarity index metric achieved by our method are 99.3 HU, 0.032, 23.4 dB and 0.949, respectively. These results demonstrate the feasibility and efficacy of our 2D-to-3D method for lung cancer patients, which provides a potential solution for in-treatment real-time on-board volumetric imaging for accurate dose delivery to ensure the effectiveness of lung SBRT treatment.

physics.med-ph↗

arXiv2020

Spin caloritronics in a CrBr$_3$-based magnetic van der Waals heterostructure

The recently reported magnetic ordering in insulating two-dimensional (2D) materials, such as chromium triiodide (CrI$_3$) and chromium tribromide (CrBr$_3$), opens new possibilities for the fabrication of magneto-electronic devices based on 2D systems. Inevitably, the magnetization and spin dynamics in 2D magnets are strongly linked to Joule heating. Therefore, understanding the coupling between spin, charge and heat, i.e. spin caloritronic effects, is crucial. However, spin caloritronics in 2D ferromagnets remains mostly unexplored, due to their instability in air. Here we develop a fabrication method that integrates spin-active contacts with 2D magnets through hBN encapsulation, allowing us to explore the spin caloritronic effects in these materials. The angular dependence of the thermal spin signal of the CrBr$_3$/Pt system is studied, for different conditions of magnetic field and heating current. We highlight the presence of a significant magnetic proximity effect from CrBr$_3$ on Pt revealed by an anomalous Nernst effect in Pt, and suggest the contribution of the spin Seebeck effect from CrBr$_3$. These results pave the way for future magnonic devices using air-sensitive 2D magnetic insulators.

cond-mat.mes-hall↗

arXiv2020

Intensity Non-uniformity Correction in MR Imaging Using Residual Cycle Generative Adversarial Network

Purpose: Correcting or reducing the effects of voxel intensity non-uniformity (INU) within a given tissue type is a crucial issue for quantitative MRI image analysis in daily clinical practice. In this study, we present a deep learning-based approach for MRI image INU correction. Method: We developed a residual cycle generative adversarial network (res-cycle GAN), which integrates the residual block concept into a cycle-consistent GAN (cycle-GAN). In cycle-GAN, an inverse transformation was implemented between the INU uncorrected and corrected MRI images to constrain the model through forcing the calculation of both an INU corrected MRI and a synthetic corrected MRI. A fully convolution neural network integrating residual blocks was applied in the generator of cycle-GAN to enhance end-to-end raw MRI to INU corrected MRI transformation. A cohort of 30 abdominal patients with T1-weighted MR INU images and their corrections with a clinically established and commonly used method, namely, N4ITK were used as a pair to evaluate the proposed res-cycle GAN based INU correction algorithm. Quantitatively comparisons were made among the proposed method and other approaches. Result: Our res-cycle GAN based method achieved higher accuracy and better tissue uniformity compared to the other algorithms. Moreover, once the model is well trained, our approach can automatically generate the corrected MR images in a few minutes, eliminating the need for manual setting of parameters. Conclusion: In this study, a deep learning based automatic INU correction method in MRI, namely, res-cycle GAN has been investigated. The results show that learning based methods can achieve promising accuracy, while highly speeding up the correction through avoiding the unintuitive parameter tuning process in N4ITK correction.

physics.med-ph↗