arXiv subjects

Steve Jiang

Publications and source records attributed to Steve Jiang.

70 records · Page 4Linked to original sources

arXiv2018

Generating Synthesized Computed Tomography (CT) from Cone-Beam Computed Tomography (CBCT) using CycleGAN for Adaptive Radiation Therapy

Cone beam computed tomography (CBCT) images can be used for dose calculation in adaptive radiation therapy (ART). The main challenges are the large artefacts and inaccurate Hounsfield unit (HU) values. Currently, deformed planning CT images are often used for this purpose, although anatomical accuracy might be a concern. Ideally, we would like to convert CBCT images to CT images with artifacts removed or greatly reduced and HU values corrected while keeping the anatomical accuracy. Recently, deep learning has achieved great success in image-to-image translation tasks. It is very difficult to acquire paired CT and CBCT images with exactly matching anatomy for supervised training. To overcome this limitation, we developed and tested a cycle generative adversarial network (CycleGAN) which is an unsupervised learning method and does not require paired training datasets to synthesize CT images from CBCT images. The synthesized CT (sCT) images have been compared with the deformed planning CT (dpCT) showing visual and quantitative similarity with artifacts being removed and HU value errors being reduced from 71.78 HU to 27.98 HU. Dose calculation accuracy using sCT images has been improved over the original CBCT images, with the average Gamma Index passing rate increased from 95.4% to 97.4% for 1 mm/1% criteria. A deformable phantom study has been conducted and demonstrated better anatomical accuracy for sCT over dpCT.

physics.med-ph↗

arXiv2018

A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning

With the advancement of treatment modalities in radiation therapy for cancer patients, outcomes have improved, but at the cost of increased treatment plan complexity and planning time. The accurate prediction of dose distributions would alleviate this issue by guiding clinical plan optimization to save time and maintain high quality plans. We have modified a convolutional deep network model, U-net (originally designed for segmentation purposes), for predicting dose from patient image contours of the planning target volume (PTV) and organs at risk (OAR). We show that, as an example, we are able to accurately predict the dose of intensity-modulated radiation therapy (IMRT) for prostate cancer patients, where the average Dice similarity coefficient is 0.91 when comparing the predicted vs. true isodose volumes between 0% and 100% of the prescription dose. The average value of the absolute differences in [max, mean] dose is found to be under 5% of the prescription dose, specifically for each structure is [1.80%, 1.03%](PTV), [1.94%, 4.22%](Bladder), [1.80%, 0.48%](Body), [3.87%, 1.79%](L Femoral Head), [5.07%, 2.55%](R Femoral Head), and [1.26%, 1.62%](Rectum) of the prescription dose. We thus managed to map a desired radiation dose distribution from a patient's PTV and OAR contours. As an additional advantage, relatively little data was used in the techniques and models described in this paper.

physics.med-ph↗

arXiv2018

Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging utilizing Deep Learning

Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report a novel densely connected Unet (D-Unet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.

physics.med-ph↗

arXiv2018

Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning

Deep learning has started to revolutionize several different industries, and the applications of these methods in medicine are now becoming more commonplace. This study focuses on investigating the feasibility of tracking patients and clinical staff wearing Bluetooth Low Energy (BLE) tags in a radiation oncology clinic using artificial neural networks (ANNs) and convolutional neural networks (CNNs). The performance of these networks was compared to relative received signal strength indicator (RSSI) thresholding and triangulation. By utilizing temporal information, a combined CNN+ANN network was capable of correctly identifying the location of the BLE tag with an accuracy of 99.9%. It outperformed a CNN model (accuracy = 94%), a thresholding model employing majority voting (accuracy = 95%), and a triangulation classifier utilizing majority voting (accuracy = 95%). Future studies will seek to deploy this affordable real time location system in hospitals to improve clinical workflow, efficiency, and patient safety.

physics.med-ph↗

arXiv2018

Combining Many-objective Radiomics and 3-dimensional Convolutional Neural Network through Evidential Reasoning to Predict Lymph Node Metastasis in Head and Neck Cancer

Lymph node metastasis (LNM) is a significant prognostic factor in patients with head and neck cancer, and the ability to predict it accurately is essential for treatment optimization. PET and CT imaging are routinely used for LNM identification. However, uncertainties of LNM always exist especially for small size or reactive nodes. Radiomics and deep learning are the two preferred imaging-based strategies for node malignancy prediction. Radiomics models are built based on handcrafted features, and deep learning can learn the features automatically. We proposed a hybrid predictive model that combines many-objective radiomics (MO-radiomics) and 3-dimensional convolutional neural network (3D-CNN) through evidential reasoning (ER) approach. To build a more reliable model, we proposed a new many-objective radiomics model. Meanwhile, we designed a 3D-CNN that fully utilizes spatial contextual information. Finally, the outputs were fused through the ER approach. To study the predictability of the two modalities, three models were built for PET, CT, and PET&CT. The results showed that the model performed best when the two modalities were combined. Moreover, we showed that the quantitative results obtained from the hybrid model were better than those obtained from MO-radiomics and 3D-CNN.

physics.med-ph↗

arXiv2018

Deriving ventilation imaging from 4DCT by deep convolutional neural network

Purpose: Functional imaging is emerging as an important tool for lung cancer treatment planning and evaluation. Compared with traditional methods such as nuclear medicine ventilation-perfusion (VQ), positron emission tomography (PET), single photon emission computer tomography (SPECT), or magnetic resonance imaging (MRI), which use contrast agents to form 2D or 3D functional images, ventilation imaging obtained from 4DCT lung images is convenient and cost-effective because of its availability during radiation treatment planning. Current methods of obtaining ventilation images from 4DCT lung images involve deformable image registration (DIR) and a density (HU) change-based algorithm (DIR/HU); therefore the resulting ventilation images are sensitive to the selection of DIR algorithms. Methods: We propose a deep convolutional neural network (CNN)-based method to derive the ventilation images from 4DCT directly without explicit DIR, thereby improving consistency and accuracy of ventilation images. A total of 82 sets of 4DCT and ventilation images from patients with lung cancer were studied using this method. Results: The predicted images were comparable to the label images of the test data. The similarity index and correlation coefficient averaged over the ten-fold cross validation were 0.883+-0.034 and 0.878+-0.028, respectively. Conclusions: The results demonstrate that deep CNN can generate ventilation imaging from 4DCT without explicit deformable image registration, reducing the associated uncertainty.

physics.med-ph↗

arXiv2018

Multifactorial cancer treatment outcome prediction through multifaceted radiomics

Accurately predicting the treatment outcome plays a greatly important role in tailoring and adapting a treatment planning in cancer therapy. Although the development of different modalities and personalized medicine can greatly improve the accuracy of outcome prediction, they also bring the three mainly simultaneous challenges including multi-modality, multi-classifier and multi-criteria, which are summarized as multifactorial outcome prediction (MFOP) in this paper. Compared with traditional outcome prediction, MFOP is a more generalized problem. To handle this novel problem, based on the recent proposed radiomics, we propose a new unified framework termed as multifaceted radiomics (M-radiomics). M-radiomics trains multiple modality-specific classifiers first and then optimally combines the output from the outputs of different classifiers which are trained according to multiple different criteria such as sensitivity and specificity. It considers multi-modality, multi-classifier and multi-criteria into a unified framework, which makes the prediction more accurate. Furthermore, to obtain the more reliable predictive performance which is to maximize the similarity between predicted output and labelled vector, a new validation set based reliable fusion (VRF) strategy and reliable optimization models as well as a new recursive two stage hybrid optimization algorithm (RTSH) were also developed. Two clinical problems for predicting distant metastasis and locoregional recurrence in head & neck cancer were investigated to validate the performance and reliability of the proposed M-radiomics. By using the proposed RF strategy and RTSH optimization algorithm, the experimental results demonstrated that M-radiomics performed better than current radiomic models that rely on a single objective, modality or classifier.

physics.med-ph↗

arXiv2018

Acceleration and Quantitation of Localized Correlated Spectroscopy using Deep Learning: A Pilot Simulation Study

Nuclear magnetic resonance spectroscopy (MRS) allows for the determination of atomic structures and concentrations of different chemicals in a biochemical sample of interest. MRS is used in vivo clinically to aid in the diagnosis of several pathologies that affect metabolic pathways in the body. Typically, this experiment produces a one dimensional (1D) 1H spectrum containing several peaks that are well associated with biochemicals, or metabolites. However, since many of these peaks overlap, distinguishing chemicals with similar atomic structures becomes much more challenging. One technique capable of overcoming this issue is the localized correlated spectroscopy (L-COSY) experiment, which acquires a second spectral dimension and spreads overlapping signal across this second dimension. Unfortunately, the acquisition of a two dimensional (2D) spectroscopy experiment is extremely time consuming. Furthermore, quantitation of a 2D spectrum is more complex. Recently, artificial intelligence has emerged in the field of medicine as a powerful force capable of diagnosing disease, aiding in treatment, and even predicting treatment outcome. In this study, we utilize deep learning to: 1) accelerate the L-COSY experiment and 2) quantify L-COSY spectra. We demonstrate that our deep learning model greatly outperforms compressed sensing based reconstruction of L-COSY spectra at higher acceleration factors. Specifically, at four-fold acceleration, our method has less than 5% normalized mean squared error, whereas compressed sensing yields 20% normalized mean squared error. We also show that at low SNR (25% noise compared to maximum signal), our deep learning model has less than 8% normalized mean squared error for quantitation of L-COSY spectra. These pilot simulation results appear promising and may help improve the efficiency and accuracy of L-COSY experiments in the future.

physics.med-ph↗

arXiv2018

Predicting Lymph Node Metastasis in Head and Neck Cancer by Combining Many-objective Radiomics and 3-dimensioal Convolutional Neural Network through Evidential Reasoning

physics.med-ph↗

arXiv2018

Segmentation of the prostate and organs at risk in male pelvic CT images using deep learning

Inter-and intra-observer variation in delineating regions of interest (ROIs) occurs because of differences in expertise level and preferences of the radiation oncologists. We evaluated the accuracy of a segmentation model using the U-Net structure to delineate the prostate, bladder, and rectum in male pelvic CT images. The dataset used for training and testing the model consisted of raw CT scan images of 85 prostate cancer patients. We designed a 2D U-Net model to directly learn a mapping function that converts a 2D CT grayscale image to its corresponding 2D OAR segmented image. Our network contains blocks of convolution 2D layers with variable kernel sizes, channel number, and activation functions. On the left side of the U-Net model, we used three 3x3 convolutions, each followed by a rectified linear unit (ReLu) (activation function), and one max pooling operation. On the right side of the U-Net model, we used a 2x2 transposed convolution and two 3x3 convolution networks followed by a ReLu activation function. The automatic segmentation using the U-Net generated an average dice similarity coefficient (DC) and standard deviation (SD) of the following: DC +- SD (0.88 +- 0.12), (0.95 +- 0.04), and (0.92 +- 0.06) for the prostate, bladder, and rectum, respectively. Furthermore, the mean of average surface Hausdorff distance (ASHD) and SD were 1.2 +- 0.9 mm, 1.08 +- 0.8 mm, and 0.8 +- 0.6 mm for the prostate, bladder, and rectum, respectively. Our proposed method, which employs the U-Net structure, is highly accurate and reproducible for automated ROI segmentation. This provides a foundation to improve automatic delineation of the boundaries between the target and surrounding normal soft tissues on a standard radiation therapy planning CT scan.

physics.med-ph↗

arXiv2017

Towards automated patient data cleaning using deep learning: A feasibility study on the standardization of organ labeling

Data cleaning consumes about 80% of the time spent on data analysis for clinical research projects. This is a much bigger problem in the era of big data and machine learning in the field of medicine where large volumes of data are being generated. We report an initial effort towards automated patient data cleaning using deep learning: the standardization of organ labeling in radiation therapy. Organs are often labeled inconsistently at different institutions (sometimes even within the same institution) and at different time periods, which poses a problem for clinical research, especially for multi-institutional collaborative clinical research where the acquired patient data is not being used effectively. We developed a convolutional neural network (CNN) to automatically identify each organ in the CT image and then label it with the standardized nomenclature presented at AAPM Task Group 263. We tested this model on the CT images of 54 patients with prostate and 100 patients with head and neck cancer who previously received radiation therapy. The model achieved 100% accuracy in detecting organs and assigning standardized labels for the patients tested. This work shows the feasibility of using deep learning in patient data cleaning that enables standardized datasets to be generated for effective intra- and interinstitutional collaborative clinical research.

physics.med-ph↗

arXiv2017

Soft-NeuroAdapt: A 3-DOF Neuro-Adaptive Patient Pose Correction System For Frameless and Maskless Cancer Radiotherapy

Precise patient positioning is fundamental to successful removal of malignant tumors during treatment of head and neck cancers. Errors in patient positioning have been known to damage critical organs and cause complications. To better address issues of patient positioning and motion, we introduce a 3-DOF neuro-adaptive soft-robot, called Soft-NeuroAdapt to correct deviations along 3 axes. The robot consists of inflatable air bladders that adaptively control head deviations from target while ensuring patient safety and comfort. The adaptive-neuro controller combines a state feedback component, a feedforward regulator, and a neural network that ensures correct adaptation. States are measured by a 3D vision system. We validate Soft-NeuroAdapt on a 3D printed head-and-neck dummy, and demonstrate that the controller provides adaptive actuation that compensates for intrafractional deviations in patient positioning.

cs.RO↗

arXiv2016

Nonlinear Systems Identification Using Deep Dynamic Neural Networks

Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld systems. This paper investigates the effectiveness of deep neural networks in the modeling of dynamical systems with complex behavior. Three deep neural network structures are trained on sequential data, and we investigate the effectiveness of these networks in modeling associated characteristics of the underlying dynamical systems. We carry out similar evaluations on select publicly available system identification datasets. We demonstrate that deep neural networks are effective model estimators from input-output data

cs.NE↗

arXiv2016

Vision-based Control of a Soft Robot for Maskless Head and Neck Cancer Radiotherapy

This work presents an on-going investigation of the control of a pneumatic soft-robot actuator addressing accurate patient positioning systems in maskless head and neck cancer radiotherapy. We employ two RGB-D sensors in a sensor fusion scheme to better estimate a patient's head pitch motion. A system identification prediction error model is used to obtain a linear time invariant state space model. We then use the model to design a linear quadratic Gaussian feedback controller to manipulate the patient head position based on sensed head pitch motion. Experiments demonstrate the success of our approach.

cs.RO↗

arXiv2015

A Real-Time Soft Robotic Patient Positioning System for Maskless Head-and-Neck Cancer Radiotherapy: An Initial Investigation

We present an initial examination of a novel approach to accurately position a patient during head and neck intensity modulated radiotherapy (IMRT). Position-based visual-servoing of a radio-transparent soft robot is used to control the flexion/extension cranial motion of a manikin head. A Kinect RGB-D camera is used to measure head position and the error between the sensed and desired position is used to control a pneumatic system which regulates pressure within an inflatable air bladder (IAB). Results show that the system is capable of controlling head motion to within 2mm with respect to a reference trajectory. This establishes proof-of-concept that using multiple IABs and actuators can improve cancer treatment.

cs.RO↗

arXiv2009

A feasibility study of treatment verification using EPID cine images for hypofractionated lung radiotherapy

We propose a novel approach for potential on-line treatment verification using cine EPID (Electronic Portal Imaging Device) images for hypofractionated lung radiotherapy based on a machine learning algorithm. Hypofractionated radiotherapy requires high precision. It is essential to effectively monitor the target to ensure that the tumor is within the beam aperture. We modeled the treatment verification problem as a two-class classification problem and applied an Artificial Neural Network (ANN) to classify the cine EPID images acquired during the treatment into corresponding classes with the tumor inside or outside of the beam aperture. Training samples were generated for the ANN using digitally reconstructed radiographs (DRRs) with artificially added shifts in tumor location to simulate cine EPID images with different tumor locations. Principal Component Analysis (PCA) was used to reduce the dimensionality of the training samples and cine EPID images acquired during the treatment. The proposed treatment verification algorithm was tested on five hypofractionated lung patients in a retrospective fashion. On average, our proposed algorithm achieved a 98.0% classification accuracy, a 97.6% recall rate, and a 99.7% precision rate.

physics.med-ph↗