Article
Radiology, Nuclear Medicine & Medical Imaging
Giuseppe Corrias, Giulio Micheletti, Luigi Barberini, Jasjit S. Suri, Luca Saba
Summary: Texture analysis and radiomics are tools used to explore the amount of data in images. Texture analysis extracts features to uncover disease characteristics, while radiomics extracts quantitative data from medical images to correlate with clinical outcomes. In recent years, these methods have been widely used in various fields, providing clinical radiologists with tools for data processing and identifying important papers.
EUROPEAN JOURNAL OF RADIOLOGY
(2022)
Review
Medicine, General & Internal
Alfonso Reginelli, Valerio Nardone, Giuliana Giacobbe, Maria Paola Belfiore, Roberta Grassi, Ferdinando Schettino, Mariateresa Del Canto, Roberto Grassi, Salvatore Cappabianca
Summary: This study aims to analyze the impact of texture analysis in predicting treatment response and stratifying prognosis in oncology, considering different pathologies, through the quantification and identification of parameters related to tumors by radiologists using texture analysis.
Article
Oncology
Mitchell Chen, Susan J. Copley, Patrizia Viola, Haonan Lu, Eric O. Aboagye
Summary: Lung cancer, the leading cause of cancer-related deaths worldwide, can be captured non-invasively on medical imaging as radiomic features, which can be used in an artificial intelligence paradigm to predict clinical outcomes and improve patient care. Compared to tissue sampling-driven approaches, radiomics-based methods are superior for being non-invasive, reproducible, cheaper, and less susceptible to intra-tumoral heterogeneity.
SEMINARS IN CANCER BIOLOGY
(2023)
Review
Oncology
Athanasios K. Anagnostopoulos, Anastasios Gaitanis, Ioannis Gkiozos, Emmanouil Athanasiadis, Sofia N. Chatziioannou, Konstantinos N. Syrigos, Dimitris Thanos, Achilles N. Chatziioannou, Nikolaos Papanikolaou
Summary: This review discusses the application of radiogenomics in cancer assessment, highlighting its limitations and offering solutions for clinical translation. Lung cancer, the leading cause of cancer-related deaths worldwide, has been studied using genomics and other high-throughput methods. Radiogenomics integrates genomics and radiomics to identify the molecular basis of imaging phenotypes. This review provides an overview of radiogenomics and its limitations in lung cancer clinical applications.
Article
Biochemistry & Molecular Biology
Jacobo Porto-Alvarez, Eva Cernadas, Rebeca Aldaz Martinez, Manuel Fernandez-Delgado, Emilio Huelga Zapico, Victor Gonzalez-Castro, Sandra Baleato-Gonzalez, Roberto Garcia-Figueiras, J. Ramon Antunez-Lopez, Miguel Souto-Bayarri
Summary: This article aims to prove that CT-based radiomics can predict KRAS mutation in CRC patients. The study used 56 CRC patients from the Hospital of Santiago de Compostela in Spain and obtained radiomics features through abdominal contrast enhancement CT. The results showed that AdaBoost ensemble on clinical patient data had the most reliable prediction ability, with a kappa and accuracy of 53.7% and 76.8% for KRAS mutation.
Article
Radiology, Nuclear Medicine & Medical Imaging
Jose Arimateia Batista Araujo-Filho, Maria Mayoral, Natally Horvat, Fernando C. Santini, Peter Gibbs, Michelle S. Ginsberg
Summary: With the rise of artificial intelligence, radiomics has emerged as a field of translational research that focuses on extracting mineable high-dimensional data from radiological images. This data is then used to create big data datasets for identifying distinct sub-visual imaging patterns. Radiomics can be integrated with genomic data in a strategy called radiogenomics, which holds promise in identifying potential imaging biomarkers for predicting driver mutations and other genomic parameters. This review discusses the basics, potential contributions, challenges, and opportunities of radiogenomics in managing patients with lung cancer.
Article
Oncology
Wenlong Ming, Fuyu Li, Yanhui Zhu, Yunfei Bai, Wanjun Gu, Yun Liu, Xiaoan Liu, Xiao Sun, Hongde Liu
Summary: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is an important method for diagnosing and evaluating breast cancer. In this study, three novel imaging subtypes were identified and validated, and their differences in tumor size and enhancement patterns were found to be associated with prognosis. Bioinformatics analysis revealed significant differences in gene expression profiling and tumor microenvironment characteristics among the subtypes.
Article
Computer Science, Information Systems
Dong Sui, Maozu Guo, Xiaoxuan Ma, Julian Baptiste, Lei Zhang
Summary: This study presents a deep learning-based radiogenomic framework that can provide more relevant features and vivid results to intuitively demonstrate the connections among medical data.
Review
Biochemistry & Molecular Biology
Davide Bellini, Marika Milan, Antonella Bordin, Roberto Rizzi, Marco Rengo, Simone Vicini, Alessandro Onori, Iacopo Carbone, Elena De Falco
Summary: Radiomics is a novel advanced approach to imaging, extracting quantitative and reproducible data from radiological images using sophisticated mathematical analysis. Radiogenomics, defined as the integration of radiology and genomics, explores the relationship between specific features extracted from radiological images and genetic or molecular traits of a particular disease. Despite advancements, standardized protocols in clinical practice are still lacking.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Oncology
Anahita Fathi Kazerooni, Stephen J. Bagley, Hamed Akbari, Sanjay Saxena, Sina Bagheri, Jun Guo, Sanjeev Chawla, Ali Nabavizadeh, Suyash Mohan, Spyridon Bakas, Christos Davatzikos, MacLean P. Nasrallah
Summary: Radiomics and radiogenomics, integrated with machine learning and medical imaging, have the potential to revolutionize precision diagnostics and personalized treatments for high-grade gliomas, improving prognostication accuracy and optimizing patient care.
Article
Oncology
Amrita Guha, Mustafa Anjari, Gary Cook, Vicky Goh, Steve Connor
Summary: This study aims to evaluate the heterogeneity changes on diffusion-weighted ADC maps and T1-weighted MRI in the treatment of head and neck carcinoma, and observe their relationship with chemo-radiotherapy response. The results show that successfully treated head and neck carcinoma demonstrate significant interval changes in ADC histogram parameters and T1w post gad GLCM by 6 weeks post CRT, while lymph nodes with treatment failure do not show this alteration.
FRONTIERS IN ONCOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Peng Lin, Yi-qun Lin, Rui-zhi Gao, Wei-jun Wan, Yun He, Hong Yang
Summary: This study aims to explore the integration of radiomics and transcriptomics analyses in non-small cell lung cancer (NSCLC) for molecular annotation and risk stratification. Through analysis of radiomics features and pathways enrichment profiles, three radiotranscriptomics subtypes (RTSs) with specific molecular characteristics were identified. The RTS strategy demonstrated significant prognostic value and could effectively stratify NSCLC patients based on prognosis.
EUROPEAN RADIOLOGY
(2023)
Review
Medicine, General & Internal
Dan Zheng, Xiujing He, Jing Jing
Summary: The heavy burden and mortality of breast cancer highlight the importance of early diagnosis and treatment. Imaging detection is a key tool in clinical practice for breast cancer screening, diagnosis, and treatment evaluation. The use of AI-assisted imaging diagnosis can improve efficiency and accuracy in recognizing, segmenting, and diagnosing tumor lesions.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Clinical Neurology
Norbert Galldiks, Frank Angenstein, Jan-Michael Werner, Elena K. Bauer, Robin Gutsche, Gereon R. Fink, Karl-Josef Langen, Philipp Lohmann
Summary: Anatomical cross-sectional imaging methods are standard for the diagnosis, treatment planning, and follow-up of meningioma patients, and advanced neuroimaging provides detailed information about the molecular and metabolic characteristics of meningiomas. Artificial intelligence methods like radiomics can extract imaging features from routine MRI and CT scans, linking imaging phenotypes to meningioma characteristics.
Review
Gastroenterology & Hepatology
Carolina de la Pinta
Summary: Radiomics is playing a crucial role in oncology, particularly in the early diagnosis, treatment response evaluation, and prognosis prediction of pancreatic cancer. Texture parameters can effectively differentiate tumor tissues from normal tissues and predict treatment response and survival rates.
HEPATOBILIARY & PANCREATIC DISEASES INTERNATIONAL
(2022)
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Vicky Goh
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
Paul Jenkins, Indrajeet Mandal, Jim Zhong, Vicky Goh
Summary: Research in Clinical Radiology is facing challenges due to increased clinical demand, workforce shortages, and lack of funding and protected research time. The 2023 radiology specialty application process prioritizes other domains like audit over research, which is concerning considering the lack of research culture within the specialty. To strengthen research within radiology training, attracting bright candidates and ensuring research remains a priority is crucial for the future radiology workforce.
BRITISH JOURNAL OF RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
T. D. Turmezei, S. C. Shelmerdine, A. H. Ashok, V. Goh
Summary: This study surveyed past and current radiology academic clinical fellows (ACFs) to gather feedback on their experiences, academic achievements, challenges in balancing academic and clinical responsibilities, and suggestions for optimizing the fellowship program. The results showed that many ACFs continue their academic interests after training, with some achieving higher research degrees. Balancing clinical workload was identified as a challenge, requiring flexibility from supervisors.
CLINICAL RADIOLOGY
(2023)
Review
Radiology, Nuclear Medicine & Medical Imaging
Tanuj Puri, Michelle L. Frost, Amelia E. B. Moore, Gary J. R. Cook, Glen M. Blake
Summary: This article introduces the method of measuring bone metabolic flux (K-i) using [F-18] sodium fluoride ([F-18]NaF) positron emission tomography (PET) scans, and proposes a simplified method that estimates K-i values from static scans and venous blood samples. By reviewing different methods of measuring arterial input functions (AIF), a non-invasive method for studying bone metabolism without arterial blood sampling is provided, which shortens scan times, simplifies procedures, and reduces costs.
Article
Oncology
Samuel J. Withey, Kasia Owczarczyk, Mariusz T. Grzeda, Connie Yip, Harriet Deere, Mike Green, Nick Maisey, Andrew R. Davies, Gary J. Cook, Vicky Goh
Summary: This study found that pre-treatment vascular and metabolic parameters of esophagogastric tumors may be associated with response to neoadjuvant therapy. However, these parameters showed no significant relationship with survival.
Article
Oncology
Janet E. Brown, Kara-Louise Royle, Walter Gregory, Christy Ralph, Anthony Maraveyas, Omar Din, Timothy Eisen, Paul Nathan, Tom Powles, Richard Griffiths, Robert Jones, Naveen Vasudev, Matthew Wheater, Abdel Hamid, Tom Waddell, Rhona McMenemin, Poulam Patel, James Larkin, Guy Faust, Adam Martin, Jayne Swain, Janine Bestall, Christopher McCabe, David Meads, Vicky Goh, Tze Min Wah, Julia Brown, Jenny Hewison, Peter Selby, Fiona Collinson
Summary: This study aimed to compare the non-inferiority of a tyrosine kinase inhibitor drug-free interval strategy with a conventional continuation strategy in the first-line treatment of advanced clear cell renal cell carcinoma. The results showed that non-inferiority between the two groups could not be concluded in terms of overall survival and quality-adjusted life-years (QALYs). However, treatment breaks might be a feasible and cost-effective option with lifestyle benefits for patients during tyrosine kinase inhibitor therapy in patients with renal cell carcinoma.
Article
Radiology, Nuclear Medicine & Medical Imaging
Muhummad Sohaib Nazir, Daniel Johnathan Hughes, Gitasha Chand, Kathryn Adamson, Jessica Johnson, Damion Bailey, Victoria Gibson, Hong Hoi Ting, Alexander Lyon, Gary J. R. Cook
Summary: This study determines a non-invasive method for assessing myocardial PD-L1 expression using [Tc-99m]-labelled anti-PD-L1 single-domain antibody (NM-01) SPECT/CT. The study finds that myocardial PD-L1 expression is higher than skeletal muscle in lung cancer patients, and this technique has high reliability and specificity. It can be applied to investigate ICI-associated myocarditis and cardiomyopathies.
Article
Radiology, Nuclear Medicine & Medical Imaging
Daniel Johnathan Hughes, Gitasha Chand, Jessica Johnson, Damion Bailey, Kathryn Adamson, Vicky Goh, Gary J. R. Cook
Summary: This study aims to determine the inter- and intra-rater agreement of the quantitative measurement of [Tc-99m]NM-01 SPECT/CT in NSCLC. The results show that using SUVmax and malignant lesion-to-blood pool ratios can provide accurate assessment of NSCLC. This study validates the effectiveness of [Tc-99m]NM-01 SPECT/CT in NSCLC.
Editorial Material
Radiology, Nuclear Medicine & Medical Imaging
S. A. Taylor, A. Darekar, V. Goh, S. Neubauer, A. Rockall, J. Solomon
CLINICAL RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Andrea G. Rockall, Xingfeng Li, Nicholas Johnson, Ioannis Lavdas, Shalini Santhakumaran, A. Toby Prevost, Shonit Punwani, Vicky Goh, Tara D. Barwick, Nishat Bharwani, Amandeep Sandhu, Harbir Sidhu, Andrew Plumb, James Burn, Aisling Fagan, Georg J. Wengert, Dow-Mu Koh, Krystyna Reczko, Qi Dou, Jane Warwick, Xinxue Liu, Christina Messiou, Nina Tunariu, Peter Boavida, Neil Soneji, Edward W. Johnston, Christian Kelly-Morland, Katja N. De Paepe, Heminder Sokhi, Kathryn Wallitt, Amish Lakhani, James Russell, Miriam Salib, Sarah Vinnicombe, Adam Haq, Eric O. Aboagye, Stuart Taylor, Ben Glocker
Summary: The study aimed to develop a machine learning algorithm to improve radiologists' sensitivity and specificity for metastasis detection in whole-body magnetic resonance imaging (WB-MRI). The results showed that using the algorithm can enhance the detection accuracy and reduce reading times for radiologists.
INVESTIGATIVE RADIOLOGY
(2023)
Article
Oncology
Jonathan L. Moore, Michael Green, Aida Santaolalla, Harriet Deere, Richard P. T. Evans, Mona Elshafie, Anita Lavery, Damian T. McManus, Andrew McGuigan, Rosalie Douglas, Joanne Horne, Robert Walker, Hira Mir, Monica Terlizzo, Sivesh K. Kamarajah, Mieke Van Hemelrijck, Nick Maisey, Ailsa Sita-Lumsden, Sarah Ngan, Mark Kelly, Cara R. Baker, Sacheen Kumar, Jesper Lagergren, William H. Allum, James A. Gossage, Ewen A. Griffiths, Heike I. Grabsch, Richard C. Turkington, Tim J. Underwood, Elizabeth C. Smyth, Rebecca C. Fitzgerald, David Cunningham, Andrew R. Davies
Summary: This study aimed to evaluate the influence of lymph node (LN) regression on survival after surgery for esophageal adenocarcinoma. The results showed that patients with complete LN regression, partial LN regression, or negative LNs had a lower mortality rate compared to those with poor/no LN regression.
JOURNAL OF CLINICAL ONCOLOGY
(2023)
Review
Oncology
Amy R. Sharkey, Timothy H. Witney, Gary J. R. Cook
Summary: This review summarizes the use of F-18-FSPG as a radiotracer in cancer patients. Although limited in number and with contrasting findings, the studies suggest a potential application of F-18-FSPG in assessing early treatment response and predicting treatment resistance.
Article
Radiology, Nuclear Medicine & Medical Imaging
Robert O'Shea, Thubeena Manickavasagar, Carolyn Horst, Daniel Hughes, James Cusack, Sophia Tsoka, Gary Cook, Vicky Goh
Summary: Interpretability is essential for reliable CNN image classifiers in radiological applications. This study applies weakly supervised segmentation to generate explainable image classifiers, achieving precise localization of lung tumors trained with only image-level labels.
INSIGHTS INTO IMAGING
(2023)