View Presentation Video

Jihun Kwon¹, Kohei Yuda², Masami Yoneyama¹, Yasutomo Katsumata³, and Marc Van Cauteren^3
1Philips Japan, Tokyo, Japan, ²Tokyo Metropolitan Police Hospital, Nakano, Japan, ³Philips Healthcare, Best, Netherlands

Keywords: Prostate, Diffusion/other diffusion imaging techniques

Diffusion-weighted imaging (DWI) plays an important role in assessing the significance of prostate cancer. DWI with Turbo Spin Echo readout (TSE-DWI) is robust to image distortion but suffers from low signal to noise ratio. In this study, we investigated the use of prototype AI-based reconstruction technique (SmartSpeed Precise Image) to improve the image quality of TSE-DWI images. The image quality was compared between conventional Compressed-SENSE (C-SENSE), SmartSpeed AI, and SmartSpeed Precise Image. Volunteer data demonstrated a significant improvement of sharpness in both b=0 and 1000 s/mm² images as well as ADC map, compared with C-SENSE and SmartSpeed AI reconstructions.

View Presentation Video

Eugene Milshteyn¹, Arnaud Guidon¹, and Mukesh G. Harisinghani^2
1GE Healthcare, Boston, MA, United States, ²Massachusetts General Hospital, Boston, MA, United States

Keywords: Prostate, Diffusion/other diffusion imaging techniques

Increasing the speed of multiparametric prostate MRI (mpMRI) is highly desirable. However, usual tradeoffs between signal-to-noise (SNR) and scan time must be considered and impact on quantitative metrics must be analyzed. One recently proposed approach applied a commercialized deep learning reconstruction (DL Recon) to prostate T2-weighted imaging, leveraging the capabilities of the DL algorithm to achieve a robust, high-quality T2-weighted acquisition in half the time. As such, this work focuses on evaluating the DL Recon on diffusion weighted imaging, which shows promise to cut acquisition time by ~70% and therefore benefit mpMRI.

Zan Ke¹, Liang Li¹, Zhi Wen¹, Weiyin Vivian Liu², and Yunfei Zha^1
1Radiology, Renmin Hospital of Wuhan University, Wuhan, China, ²GE Healthcare, MR Research China, Beijing, China

Keywords: Prostate, Prostate

Prostatic calcification is common in benign prostatic hyperplasia (BPH) and usually asymptomatic. Our study showed the prostate T₂WI_DL images have higher subjective rating scores, clearer lesion contrast and improved detection rate of prostatic calcification, higher SNR and CNR. In addition, T₂WI_DL more clearly and sharply displayed prostate capsule, lesion contrast, prostate calcification and anatomical details Therefore, AIR™ Recon DL based T₂WI (T₂WI_DL) quality in prostate MRI offer higher overall image quality and elevated a younger radiologist’s diagnostic performance on prostate calcification.

View Presentation Video

Ilyes Benslimane¹, Günther Grabner², Simon Hametner³, Thomas Jochmann^1,4, Robert Zivadinov^1,5, and Ferdinand Schweser^1
1Department of Neurology, Buffalo Neuroimaging Analysis Center, Buffalo, NY, United States, ²Department of Medical Engineering, Carinthia University of Applied Sciences, Klagenfurt, Austria, ³Department of Neuropathology and Neurochemistry, Medical University of Vienna, Vienna, Austria, ⁴Department of Computer Science and Automation, Technische Universität Ilmenau, Ilmenau, Germany, ⁵Department of Computer Science and Automation, Center for Biomedical Imaging, Clinical and Translational Science Institute at the University at Buffalo, Buffalo, NY, United States

Keywords: Machine Learning/Artificial Intelligence, Brain

The χ-separation method determines para- and diamagnetic susceptibility tissue compartments correlating to iron and myelin in the brain respectively. The method presupposes subject invariant relaxometry coefficients and compartments disregarding the changes in those parameters in disease or postmortem cases. We implement a biophysically informed autoencoder network developed for single subject use (BIOPHYSICSS-DL) to determine underlying biophysical model coefficients from individual datasets. We expand the current model with different combinations of relaxometry and susceptibility data to produce a self-calibrated χ separation method finding the network comparable to standard methods for iron and predicts myelin distribution more closely to ground truth histology.

View Presentation Video

Vanya Saksena^1,2, Silvia Arroyo-Camejo², Julian Hossbach^1,2, Rainer Schneider², and Andreas Maier^1
1Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Erlangen, Germany, ²Siemens Healthineers, Erlangen, Germany

Keywords: Machine Learning/Artificial Intelligence, Artifacts, Image quality

Magnetic resonance imaging (MRI) is a powerful imaging modality, but susceptible to various image quality problems. Today, technicians conduct image quality assurance (IQA) during scan-time as a manual, time-consuming, and subjective process. We propose a method towards adaptable automated IQA of MR images without the need of a large, annotated image database for training. Our method implements a machine learning-based module that uses multiple predictions from an ensemble of deep learning models trained with image quality metrics. The sensitivity of this method to detect image quality problems is adaptable to clinical requirements of the end user.

View Presentation Video

Yinghui Wang¹, Tian Li¹, Haonan Xiao¹, and Jing Cai^1
1Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong, Hong Kong

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence, 4D-MRI\Enhancement\Temporal-compensation

In this study, we proposed and evaluated a deep learning technique for refining four-dimensional magnetic resonance imaging (4D-MRI) in the post-processing stage. More specifically, we designed an implicit temporal-compensated adversarial network (ITAN) based on the intrinsic property of 4D-MRI to improve image quality with neighboring phases. It can overcome its inherent challenges of data deficiency, misalignment between training pairs, and complex texture details. The qualitative and quantitative results demonstrated that the proposed model can suppress the noise and artifacts in 4D-MR images, recover the missing details and perform better than a state-of-the-art method.  

View Presentation Video

Vadim Malis¹, Suraj Achar², Dosik Hwang³, and Won C. Bae^1,4
1Radiology, University of California, San Diego, La Jolla, CA, United States, ²Family Medicine, University of California, San Diego, La Jolla, CA, United States, ³Electrical and Electronics Engineering, Yonsei University, Seoul, Korea, Republic of, ⁴VA San Diego Healthcare System, San Diego, CA, United States

Keywords: Machine Learning/Artificial Intelligence, Bone, UTE, Deep Learning, Image Regression, Saliency Map

Isthmic spondylolysis results in fracture of pars interarticularis of the lumbar spine in young athletes. UTE MRI provide good bone contrast, although CT is still the gold standard. To take UTE MRI further, we developed supervised deep-learning tools to generate CT-like images and saliency maps of fracture probability from UTE MRI and CT, using ex vivo preparation of cadaveric spines. The results demonstrate feasibility of CT-like images to provide easier interpretability for bone fractures, due to improved image contrast and CNR, and the saliency maps to aid in quick detection of pars fracture by providing visual cues to the reader.

View Presentation Video

Tsutomu Inaoka¹, Akihiko Wada², Tomoya Nakatsuka¹, Masayuki Sugeta¹, Akinori Yamamoto¹, Hisanori Tomobe¹, Ryousuke Sakai¹, Hiroyuki Nakazawa¹, Masaru Sonoda³, Rumiko Ishikawa¹, Shusuke Kasuya¹, and Hitoshi Terada^1
1Radiology, Toho University Sakura Medical Center, Sakura, Japan, ²Radiology, Juntendo University, Tokyo, Japan, ³Radiology, Seirei Sakura Citizen Hospital, Sakura, Japan

Keywords: Machine Learning/Artificial Intelligence, Joints

 This fat-suppression subtraction-image method using a DL model with 2D CNNs may be useful for the detection and classification of abnormalities on knee MRI.

View Presentation Video

Kai Zhao¹, Haoxin Zheng¹, and Kyunghyun Sung^1
1Department of Radiological Sciences, University of California, Los Angeles, Los Angeles, CA, United States

Keywords: Machine Learning/Artificial Intelligence, Data Analysis, dynamic contrast enhanced

A deep learning based DCE-MRI analysis method was proposed with a dedicated neural network architecture and data generation framework.  The proposed method does not need DCE-MRI data acquisition or annotation for training. Compared to conventional non-linear least square (NLLS) fitting methods, the proposed method significantly reduced the average processing time from hours to few minutes while preserved the estimation quality.

View Presentation Video

Virendra Kumar Yadav¹, Suyash Mohan², Sumeet Kumar Agarwal^3,4, Laiz Laura de Godoy², Sumei Wang², MacLean P. Nasrallah⁵, Donald M. O’Rourke⁶, Stephen Bagley⁷, Harish Poptani⁸, Sanjeev Chawla², and Anup Kumar Singh^1,4,9
1Centre for Biomedical Engineering, Indian Institute of Technology, Delhi, India, ²Departments of Radiology, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, United States, ³Department of Electrical Engineering, Indian Institute of Technology, Delhi, India, ⁴Yardi School of Artificial Intelligence, Indian Institute of Technology, Delhi, India, ⁵Clinical Pathology and Laboratory, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, United States, ⁶Neurosurgery, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, United States, ⁷Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, United States, ⁸Department of Molecular and Clinical Cancer Medicine, University of Liverpool, United Kingdom, Liverpool, United Kingdom, ⁹Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India

Keywords: Machine Learning/Artificial Intelligence, Brain

Glioblastoma patients (n=93) exhibiting enhancing lesions within 6 months after completion of standard therapy underwent anatomical imaging, diffusion and perfusion MRI.  The median values of parameters (MD, FA, CL, CP, CS and rCBV) were computed from the enhancing regions. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status was available from 75 patients.  Subsequently, these patients were classified as TP (n=55) or PsP (n=20). The data were randomly split into training and testing sets. The best model for differentiating TP from PsP was obtained using quadratic SVM classifier with a training accuracy of 90.9%, cross-validation accuracy of 85.5% and testing accuracy of 85%.  

View Presentation Video

Ben A Duffy¹ and Ryan Chamberlain^1
1Subtle Medical Inc., Menlo Park, CA, United States

Keywords: Machine Learning/Artificial Intelligence, Data Processing

Automated metadata verification is essential for data quality checking. This study evaluates the extent to which self-supervised pretraining can improve performance on the anatomy and image contrast metadata verification tasks. On a small but diverse dataset, pretraining coupled with supervised finetuning, outperforms training from an ImageNet initialization, suggesting improved near out-of-distribution performance. On a larger brain-only dataset, training a linear classifier on the self-supervised pretrained network embeddings outperforms the corresponding ImageNet pretraining or random initialization on the image contrast prediction task. Cross-checking predictions against the DICOM metadata was an effective method for detecting artifacts and other quality issues.

View Presentation Video

Eros Montin^1,2, Daniele Panozzo³, and Riccardo Lattanzi^1,2,4
1Center for Advanced Imaging Innovation and Research (CAI2R) Department of Radiology, Radiology Department, New York University Grossman School of Medicine, New York, New York, USA, New York, NY, United States, ²Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, New York, USA, New York, NY, United States, ³New York University, New York, New York, USA, BROOKLYN, NY, United States, ⁴Vilcek Institute of Graduate Biomedical Sciences, New York University Grossman School of Medicine, New York, New York, USA, New York, NY, United States

Keywords: Machine Learning/Artificial Intelligence, Joints

We evaluated three neural network architectures for the automatic identification of the center of the femur head on 3D water-only Dixon MRI. We trained using a mixture of real and augmented data. The mean error of the best-performing network was three-time lower compared to a manual annotation and on the order of 1 voxel. We combined the network to create the first fully automated pipeline to assess the hip range of motion from 3D MR.

View Presentation Video

Michele Guerreri^1,2, Sean Epstein¹, Hojjat Azadbakht², and Hui Zhang^1
1Computer Science & Centre for Medical Image Computing, University College London, London, United Kingdom, ²AINOSTICS Ltd., Manchester, United Kingdom

Keywords: Machine Learning/Artificial Intelligence, Machine Learning/Artificial Intelligence

This work investigates the impact of model degeneracy on machine learning-based tissue microstructure estimation. While there have been several empirical reports suggesting machine learning can not resolve model degeneracy, the impact of model degeneracy is poorly understood. Here we show how model degeneracy can be categorised into three types with varying degrees of impact on machine learning-based microstructure estimation. Our finding is important for designing optimal training data distribution.

View Presentation Video

Meng Yan¹, Xiao Zhang², Bin Zhang¹, Zhendong Qi³, Xiaoyun Liang², Feng Huang², Shuixing Zhang¹, Xinming Li³, Shutong Wang⁴, and Xianyue Quan^3
1Department of Radiology, The First Affiliated Hospital of Jinan University, Guangzhou, China, ²Neusoft Medical Systems Co., Ltd, Shanghai, China, ³Department of Radiology, Zhujiang Hospital of Southern Medical University, Guangzhou, China, ⁴Department of Liver Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China

Keywords: Machine Learning/Artificial Intelligence, Cancer

Prognostic risk assessment after hepatectomy for patients with hepatocellular carcinoma (HCC) remains difficult. Previous studies have shown that Gd-EOB-DTPA MRI is sensitive and accurate for HCC detection, but studies in predicting early recurrence after hepatectomy based on deep learning (DL) are still lacking. This study investigated the performance of a Gd-EOB-DTPA MRI-based DL approach, and then evaluated the DL nomogram incorporating deep features and significant clinical indicators. DL nomogram outperformed the clinical nomogram (validation AUC: 0.909 vs. 0.715). The proposed DL nomogram could provide a noninvasive and comprehensive tool for predicting early recurrence of HCC after curative resection. 

View Presentation Video

Ye Tian¹, Junhao Zhang², Vish Mitnala Rao¹, and Jia Guo^3
1Biomedical Engineering, Columbia University, New York, NY, United States, ²BME, Columbia University, New York, NY, United States, ³Department of Psychiatry, Columbia University, New York, NY, United States

Keywords: Machine Learning/Artificial Intelligence, Brain, Deep Learning

Schizophrenia is a neurological disorder that requires accurate and rapid detection for earlier intervention. Previous explorations in artificial intelligence showed overwhelming performance using deep learning in schizophrenia classification, though the generalization remained a challenge. We propose our 3D Multi-scale Transformer (MST) using T1W structural MRI data to detect schizophrenia. By synthesizing reconstructed images at different scales, the transformer-based architecture improves robustness to generalize in unseen data. The proposed method reaches the same-level performance of AUROC to the benchmark mark model in schizophrenia identification, and performs better in all leave-one-site-out generality tests.

View Presentation Video

Long Cui¹, Bingmei Bai², Chenglong Wang¹, Yang Song³, Shengyong Li¹, Haijie Wang¹, Jinrong Qu², and Guang Yang^1
1Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, China, ²Department of Radiology, Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China, ³MR Scientific Marketing, Siemens Healthcare, Shanghai, China

Keywords: Cancer, Tumor

We assessed the performance of diffusion models for assessing response to neoadjuvant chemotherapy (NACT) using machine learning. Firstly, features were extracted from the region of interest on different parametric maps of different diffusion models for esophageal squamous cell carcinoma (ESCC) patients and changes of the parameters (Δ parameter) before and after NACT (pre-NACT and post-NACT) were calculated. Then different Δ-NACT models and pre-NACT models were built for using features from different diffusion models. The results demonstrated that diffusion models may be used to predict the efficacy of NACT in ESCC patients.

Zhuo Wang¹, Zhiqiang Chen², Xiaohua Chen¹, Shaoru Zhang¹, Yunshu Zhou¹, Ruodi Zhang¹, Shili Liu¹, Yuhui Xiong³, and Bing chen^4
1Department of Clinical Medicine of Ningxia Medical University, Yinchuan, China, ²Department of Radiology, the First Hospital Affiliated to Hainan Medical College, Haikou, China, ³GE Healthcare, Beijing, China, ⁴General Hospital of Ningxia Medical University, Yinchuan, China

Keywords: Cancer, Head & Neck/ENT, multi-parametric MRI-based radiomics

This study aims to evaluate the predictive performance of the nomogram integrating multi-parametric MRI-based radiomics and clinical characteristics in detecting therapeutic response to neoadjuvant chemotherapy (NAC) in nasopharyngeal carcinoma (NPC) patients. Least absolute shrinkage and selection operator (LASSO) regression was performed to select radiomics features. A nomogram was constructed using multivariable logistic regression. The receiver operating characteristic (ROC) curves, calibration, and decision curves were performed to assess the discriminative performance of the clinical, radiomics, and the combined models. The nomograms developed by integrating radiomics score (Rad-Score) with clinical factors outperformed the clinical model alone.

Zhuo Wang¹, Zhiqiang Chen², Xiaohua Chen¹, Shaoru Zhang¹, Shili Liu¹, Ruodi Zhang¹, Yunshu Zhou¹, Yuhui Xiong³, and AiJun  Wang^4
1Department of Clinical Medicine of Ningxia Medical University, Yinchuan, China, ²the First Hospital Affiliated to Hainan Medical College, Haikou, China, ³GE Healthcare, Beijing, China, ⁴General Hospital of Ningxia Medical University, Yinchuan, China

Keywords: Cancer, Head & Neck/ENT, multi-parametric MRI-based radiomics

To investigate the value of a nomogram based on multi-parametric MRI-based radiomics combined with clinical imaging features in predicting the Ki-67 LI in nasopharyngeal carcinoma. Least absolute shrinkage and selection operator (LASSO) regression was performed to select radiomics features. A nomogram was established using multivariable logistic regression. The receiver operating characteristic (ROC) curves, calibration, and decision curves were performed to evaluate the predictive performance of the different models. The nomograms constructed by integrating radiomics score (Rad-Score) with clinical imaging factors outperformed the clinical or the radiomics models alone.

View Presentation Video

Xuan Yu¹ and Meiyun Wang^1,2
1Henan Provincial People’s Hospital & the People’s Hospital of Zhengzhou University, Zhengzhou, China, ²Laboratory of Brain Science and Brain-Like Intelligence Technology, Institute for Integrated Medical Science and Engineering, Henan Academy of Sciences, Zhengzhou, China

Keywords: Brain Connectivity, Brain Connectivity

This study proposes a multi-branch deep learning model fused with multi-modal MRI for the differential diagnosis of ASD. We solve the problem that traditional ASD classification algorithms based on static functional network connections ignore the time-varying characteristics of brain functional connections. Study the spatiotemporal characteristics of ASD brain imaging, and mine the information of functional connectivity between brain regions over time.