Article
Oncology
Felipe Camelo, Kyung K. Peck, Atin Saha, Julio Arevalo-Perez, John K. Lyo, Jamie Tisnado, Eric Lis, Sasan Karimi, Andrei I. Holodny
Summary: Radiologists use dynamic contrast-enhanced MRI to study cancer in the vertebral bones. However, the current method does not account for the delayed contrast uptake in spinal cancers, leading to misdiagnosis. Researchers shifted the contrast curve and recalculated the contrast enhancement values, resulting in more accurate detection of cancer in the vertebral bones.
Article
Radiology, Nuclear Medicine & Medical Imaging
Stig P. Cramer, Henrik B. W. Larsson, Maria H. Knudsen, Helle J. Simonsen, Mark B. Vestergaard, Ulrich Lindberg
Summary: This study investigates the reproducibility of DCE-MRI in healthy controls and evaluates the impact of arterial input function selection and manual region of interests delineation versus automated global segmentation. The results show excellent reproducibility of pharmacokinetic variables derived from DCE-MRI in healthy controls.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Magne Kleppesto, Atle Bjornerud, Inge Rasmus Groote, Minjae Kim, Jonas Vardal, Christopher Larsson
Summary: This study investigated the impact of inter-operator variability in arterial input function (AIF) definition on kinetic parameter estimates from dynamic contrast-enhanced MRI in patients with high-grade gliomas. Results showed that AUC-normalized AIFs can reduce the variation in kinetic parameter results originating from operator input, and the pop-AIF presented in this work may be applied in absence of a satisfactory measurement.
MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Wanxin Dong, Andreas Volk, Meriem Djaroum, Charly Girot, Corinne Balleyguier, Vincent Lebon, Gabriel Garcia, Samy Ammari, Stephane Temam, Philippe Gorphe, Lecong Wei, Stephanie Pitre-Champagnat, Nathalie Lassau, Francois Bidault
Summary: This study evaluates the influence of four individual arterial input function measurement methods on quantitative DCE-MRI parameters. The findings highlight the importance of choosing a standardized method for accurate diagnosis in head and neck cancer patients.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Benoit Bourassa-Moreau, Rejean Lebel, Guillaume Gilbert, David Mathieu, Martin Lepage
Summary: Accurately estimating the arterial input function for dynamic contrast-enhanced MRI is challenging due to signal magnitude changes often leading to underestimation of peak concentrations. A state-of-the-art complex-based method proposed in this study shows promising results in accurately determining the peak concentration by directly compensating for blood inflow and correcting signal phase. This method outperforms traditional magnitude- and phase-based methods in both simulated biases and patient data, providing a high-quality and robust estimation of the venous output function.
MAGNETIC RESONANCE IN MEDICINE
(2021)
Article
Oncology
Michelle Roytman, Sean Kim, Shannon Glynn, Charlene Thomas, Eaton Lin, Whitney Feltus, Rajiv S. Magge, Benjamin Liechty, Theodore H. Schwartz, Rohan Ramakrishna, Nicolas A. Karakatsanis, Susan C. Pannullo, Joseph R. Osborne, Jonathan P. S. Knisely, Jana Ivanidze
Summary: This study investigated the correlation between tumor vascularity and SSTR2 expression in meningiomas using Gallium-68-DOTATATE PET/MRI. The results showed a strong correlation between tumor vascularity and SSTR2 expression in WHO-2 and WHO-3 meningiomas, but not in WHO-1 meningiomas.
FRONTIERS IN ONCOLOGY
(2022)
Article
Multidisciplinary Sciences
Yi-Jui Liu, Hou-Ting Yang, Melissa Min-Szu Yao, Shao-Chieh Lin, Der-Yang Cho, Wu-Chung Shen, Chun-Jung Juan, Wing P. Chan
Summary: This study investigated the impact of AIF selection on vertebral perfusion quantification using DCE-MRI. Simulation results showed that decreasing peak in AIF increased K-trans and v(e), while increasing delay time in AIF increased v(p). In human subjects, K-trans and v(e) were significantly smaller with AIF_A compared to AIF_SA, while both parameters were significantly greater with AIF_SA compared to AIF_A.
SCIENTIFIC REPORTS
(2021)
Article
Multidisciplinary Sciences
Woo Hyeon Lim, Joon Sik Park, Jaeseok Park, Seung Hong Choi
Summary: This study compared high-resolution DCE-MRI with conventional DCE-MRI in 30 consecutive patients suspected to have brain tumors. It was found that high-resolution DCE-MRI parameters showed better reproducibility and provided better quality of arterial input functions (AIFs) compared to conventional DCE-MRI.
SCIENTIFIC REPORTS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Andrew B. Gill, Ferdia A. Gallagher, Martin J. Graves
Summary: Customized digital reference objects (DROs) were generated and used to validate the accuracy of kinetic model analysis software packages for dynamic contrast-enhanced MR images. The generated DROs were input into three different software packages and compared with the 'ground-truth' values, showing excellent agreement. This suggests that the DRO generation code can be used to validate other third party software for DCE-MRI data analysis.
BRITISH JOURNAL OF RADIOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Jin Wang, Yinhang Jia, Qiyue Wang, Zeyu Liang, Guangxu Han, Zejun Wang, Jiyoung Lee, Meng Zhao, Fangyuan Li, Ruiliang Bai, Daishun Ling
Summary: The article introduces a T-1-T-2 dual-mode contrast agent designed for ultrahigh-field MRI, which not only improves resolution and signal-to-noise ratio, but also effectively displays microvasculature structures with high sensitivity and accuracy in detecting tumor vascular permeability.
ADVANCED MATERIALS
(2021)
Article
Oncology
Roberta Fusco, Vincenza Granata, Mauro Mattace Raso, Paolo Vallone, Alessandro Pasquale De Rosa, Claudio Siani, Maurizio Di Bonito, Antonella Petrillo, Mario Sansone
Summary: The study aimed to differentiate benign and malignant breast lesions by combining BOLD-MRI, DCE-MRI, and DW-MRI, but found that the combined use of these imaging techniques did not provide a significant improvement compared to using DCE-MRI alone. An interesting result was the negative correlation between R-2* and D.
Article
Biophysics
Chih-Hsien Tseng, Jaap Jaspers, Alejandra Mendez Romero, Piotr Wielopolski, Marion Smits, Matthias J. P. van Osch, Frans Vos
Summary: The arterial input function (AIF) is crucial for estimating perfusion properties from dynamic susceptibility contrast (DSC) MRI. Measuring the AIF in absolute contrast-agent concentrations is challenging, but deriving the AIF from separately acquired dynamic contrast enhanced (DCE) MRI data is a potential solution. This study compared the AIFs derived from DCE and DSC MRI data and found that the DCE-based AIFs provided more stable and realistic measurements of perfusion coefficients.
NMR IN BIOMEDICINE
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Gabriel Ifergan, Gwennhael Autret, Costantino Del Giudice, Augustin Lecler, Adrien Lalot, Camille Marijon, Amaury Casanova, Mailyn Perez-Liva, Valerie Bellamy, Patrick Bruneval, Olivier Clement, Marc Sapoval, Philippe Menasche, Daniel Balvay
Summary: Critical limb ischemia (CLI) is a severe disease that leads to muscle disorders in the limbs. Currently, there are no reliable tools to accurately assess perfusion defects in CLI. In this study, we propose new methodologies for evaluating perfusion defects using dynamic contrast-enhanced MRI and find that the inclusion of heterogeneity features significantly improves sensitivity and accuracy.
MAGNETIC RESONANCE IMAGING
(2022)
Article
Biophysics
Yousef Mazaheri, Nathanael Kim, Yulia Lakhman, Ramin Jafari, Alberto Vargas, Ricardo Otazo
Summary: The aim of this work is to develop a data-driven quantitative dynamic contrast-enhanced (DCE) MRI technique using Golden-angle RAdial Sparse Parallel (GRASP) MRI with high spatial resolution and high flexible temporal resolution and pharmacokinetic (PK) analysis. The results show that using GRASP image reconstruction and data-driven arterial input function (AIF), the joint estimation of AIF and PK parameters can be successfully performed, resulting in voxelwise PK parametric maps.
NMR IN BIOMEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Christian Toennes, Sonja Janssen, Alena-Kathrin Golla, Tanja Uhrig, Khanlian Chung, Lothar R. Schad, Frank Gerrit Zoellner
Summary: The deterministic algorithm developed in this study successfully detects the Arterial Input Function in DCEMRI of colorectal cancer with a lower error rate compared to algorithms from literature. The algorithm also produces reproducible results and supports robust and comparable perfusion analysis.
MAGNETIC RESONANCE IMAGING
(2021)
Article
Agriculture, Dairy & Animal Science
Ahmed M. M. Elbaz, Said E. E. El-sheikh, Ahmed Abdel-Maksoud
Summary: This study evaluated the effects of supplementing broiler diets with fermented canola meal and exogenous enzymes. The results showed that this supplementation improved growth performance, nutrient utilization, immunity, and gut health in broilers.
TROPICAL ANIMAL HEALTH AND PRODUCTION
(2023)
Article
Medicine, General & Internal
Israa Sharaby, Ahmed Alksas, Ahmed Nashat, Hossam Magdy Balaha, Mohamed Shehata, Mallorie Gayhart, Ali Mahmoud, Mohammed Ghazal, Ashraf Khalil, Rasha T. Abouelkheir, Ahmed Elmahdy, Ahmed Abdelhalim, Ahmed Mosbah, Ayman El-Baz
Summary: This study aims to develop a novel computer-aided prediction system for predicting the response of Wilms' tumors to preoperative chemotherapy in children. By integrating imaging markers with a machine learning classification model, the system can make early predictions about the tumor's response, leading to personalized management plans for Wilms' tumors.
Article
Biochemistry & Molecular Biology
Moumen El-Melegy, Rasha Kamel, Mohamed Abou El-Ghar, Norah S. Alghamdi, Ayman El-Baz
Summary: This paper proposes a new variational formulation for joint segmentation and registration of DCE-MRI kidney images. The method incorporates fuzzy c-means clustering within a level-set framework. Experimental results demonstrate that the proposed approach outperforms other methods in terms of accuracy and consistency.
Article
Biotechnology & Applied Microbiology
Yaser ElNakieb, Mohamed T. Ali, Ahmed Elnakib, Ahmed Shalaby, Ali Mahmoud, Ahmed Soliman, Gregory Neal Barnes, Ayman El-Baz
Summary: This study presents a pipelined framework using functional magnetic resonance imaging (fMRI) to accurately diagnose autism spectrum disorder (ASD) and identify the brain regions contributing to the diagnosis decision. The framework includes preprocessing, brain parcellation, feature representation, feature selection, and machine learning classification. Based on a large publicly available dataset, the research highlights the impact of different decisions along the pipeline on diagnostic accuracy. The proposed framework achieves state-of-the-art accuracy in ASD diagnosis.
BIOENGINEERING-BASEL
(2023)
Review
Oncology
Mohamed Shehata, Rasha T. Abouelkheir, Mallorie Gayhart, Eric Van Bogaert, Mohamed Abou El-Ghar, Amy C. Dwyer, Rosemary Ouseph, Jawad Yousaf, Mohammed Ghazal, Sohail Contractor, Ayman El-Baz
Summary: Renal cancer (RC) is ranked tenth among all types of cancer in men and women worldwide. Artificial intelligence (AI) and radiomics have allowed the development of AI-based computer-aided diagnostic/prediction (AI-based CAD/CAP) systems for noninvasive and precise diagnosis of RC and prediction of clinical outcome at an early stage. This review summarizes the studies from the last decade that used AI and radiomic markers for the early diagnosis of RC and prediction/assessment of clinical outcome/treatment response. Finally, a deep discussion, suggestions, and possible future avenues for improving diagnostic and treatment prediction performance is introduced, which might help fill the research gap.
Article
Biochemistry & Molecular Biology
Heba Kandil, Ahmed Soliman, Norah Saleh Alghamdi, J. Richard Jennings, Ayman El-Baz
Summary: Hypertension is a severe and highly prevalent disease. The study investigated the correlation between cerebrovascular changes (impacted by hypertension) and mean arterial pressure (MAP), systolic BP, and diastolic BP separately. The results showed that MAP is more accurate in identifying the cerebrovascular impact of hypertension compared to using systolic or diastolic BP alone.
Article
Computer Science, Information Systems
Mohammad (Behdad) Jamshidi, Omid Moztarzadeh, Alireza Jamshidi, Ahmed Abdelgawad, Ayman S. El-Baz, Lukas Hauer
Summary: The global spread of COVID-19 highlights the urgent need for drugs and vaccines, emphasizing the importance of overcoming the obstacles in drug development. While progress has been made in using AI, virologists, pharmaceutical companies, and investors seek long-term solutions and greater investment in emerging technologies. One potential solution involves combining IoMT, EC, and DL to aid in the drug-development process and monitor infected individuals or high-risk areas. However, these technologies have not been widely utilized in drug clinical trials. A new AI-based platform utilizing smartphones equipped with medical sensors can revolutionize the industry by collecting real-time physiological and healthcare information for efficient assessment of vaccine performance.
Review
Oncology
Gehad A. Saleh, Nihal M. Batouty, Abdelrahman Gamal, Ahmed Elnakib, Omar Hamdy, Ahmed Sharafeldeen, Ali Mahmoud, Mohammed Ghazal, Jawad Yousaf, Marah Alhalabi, Amal AbouEleneen, Ahmed Elsaid Tolba, Samir Elmougy, Sohail Contractor, Ayman El-Baz
Summary: Artificial intelligence has become an integral part of the medical field, particularly in the diagnosis and analysis of breast cancer. Machine learning and deep learning techniques are utilized to automate diagnosis, segment data, and predict tumor response to chemotherapy. Recent research has shown promising results with deep learning algorithms, indicating the potential to enhance diagnostic accuracy and efficiency. Additionally, non-ionizing imaging modalities play a significant role in the diagnosis process.
Review
Oncology
Basma Elsayed, Ahmed Alksas, Mohamed Shehata, Ali Mahmoud, Mona Zaky, Reham Alghandour, Khaled Abdelwahab, Mohamed Abdelkhalek, Mohammed Ghazal, Sohail Contractor, Hossam El-Din Moustafa, Ayman El-Baz
Summary: Breast cancer is the most common malignancy among females worldwide. Neoadjuvant chemotherapy (NACT) plays a crucial role in the treatment of breast cancer by reducing tumor size and making initially inoperable tumors amenable to surgery. However, the varying responses to NACT pose a challenge. Researchers have focused on developing prediction models to identify patients who would benefit from NACT. This review explores the effective radiomic markers correlated with NACT response and investigates the integration of radiomic markers with pathological markers for improved predictive accuracy. The review also sheds light on the emerging research direction of using artificial intelligence techniques to predict NACT response, shaping the future of breast cancer treatment.
Article
Biotechnology & Applied Microbiology
Oluwatunmise Akinniyi, Md Mahmudur Rahman, Harpal Singh Sandhu, Ayman El-Baz, Fahmi Khalifa
Summary: This work proposes a multi-stage classification network for retinal image classification using OCT images. It utilizes a scale-adaptive neural network and a feature-rich pyramidal architecture to extract multi-scale features for accurate classification of retinal disorders. Evaluation on two public OCT datasets demonstrates the advantages of the proposed architecture's ability to produce feature-rich classification with high accuracy.
BIOENGINEERING-BASEL
(2023)
Article
Biotechnology & Applied Microbiology
Moumen T. El-Melegy, Rasha M. Kamel, Mohamed Abou El-Ghar, Norah Saleh Alghamdi, Ayman El-Baz
Summary: The DCE-MRI technique is crucial for diagnosing and treating chronic kidney disease. This paper proposes a new automated approach that combines convolutional neural networks and level set methods to segment kidneys in DCE-MRI scans. Experimental results demonstrate the high performance of this approach.
BIOENGINEERING-BASEL
(2023)