Article
Radiology, Nuclear Medicine & Medical Imaging
Stefanie J. Hectors, Christine Chen, Johnson Chen, Jade Wang, Sharon Gordon, Miko Yu, Bashir Al Hussein Al Awamlh, Mert R. Sabuncu, Daniel J. A. Margolis, Jim C. Hu
Summary: A machine learning model based on T2WI radiomics features was constructed to identify clinically significant prostate cancer in PI-RADS 3 lesions, showing good performance with statistically significant results.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2021)
Article
Oncology
Pengfei Jin, Liqin Yang, Xiaomeng Qiao, Chunhong Hu, Chenhan Hu, Ximing Wang, Jie Bao
Summary: The integrated model combining clinical factors and radiomic features can accurately identify clinically significant prostate cancer among PI-RADS 3 lesions. This is significant in avoiding unnecessary biopsies and improving patients' quality of life.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Pietro Andrea Bonaffini, Elisabetta De Bernardi, Andrea Corsi, Paolo Niccolo Franco, Dario Nicoletta, Riccardo Muglia, Giovanna Perugini, Marco Roscigno, Mariaelena Occhipinti, Luigi Filippo Da Pozzo, Sandro Sironi
Summary: Radiomic MRI feature analysis has the potential to improve the accuracy of mpMRI in discriminating between clinically significant cancers in PI-RADS 4 and 5 lesions.
Article
Computer Science, Hardware & Architecture
Kadir Yildirim, Muhammed Yildirim, Hasan Eryesil, Muhammed Talo, Ozal Yildirim, Murat Karabatak, Mehmet Sezai Ogras, Hakan Artas, U. Rajendra Acharya
Summary: Prostate cancer is the most common cancer among men, and accurate diagnosis is commonly achieved through digital rectal examination and prostate-specific antigen tests. To reduce unnecessary biopsies, multiparametric magnetic resonance imaging (mpMRI) is used. However, there is low-level agreement and subjectivity in the interpretation of mpMRI scores. This study proposes a hybrid model to accurately interpret mpMRI examinations and predict scores, achieving a 96.09% accuracy rate.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Saskia Vande Perre, Loic Duron, Audrey Milon, Asma Bekhouche, Daniel Balvay, Francois H. Cornelis, Laure Fournier, Isabelle Thomassin-Naggara
Summary: The study aimed to assess the diagnostic performance of radiomic analysis using high temporal resolution dynamic contrast enhancement MR sequences in distinguishing benign from malignant breast lesions. The results indicated that the radiomic model, incorporating kinetic textural features, outperformed BI-RADS analysis in accurately identifying benign and malignant breast lesions, significantly reducing false positives.
EUROPEAN RADIOLOGY
(2021)
Article
Medicine, General & Internal
Wenting Jiang, Yingying Lin, Varut Vardhanabhuti, Yanzhen Ming, Peng Cao
Summary: MRI is the primary approach for diagnosing prostate cancer, but suffers from inter-reader variability. Deep learning networks, such as MiniSegCaps, show great promise in automatic lesion segmentation and classification on mpMRI, reducing inter-reader variability. MiniSegCaps achieved high performance in lesion segmentation and PI-RADS classification, significantly outperforming existing methods.
Article
Oncology
Tong Chen, Zhiyuan Zhang, Shuangxiu Tan, Yueyue Zhang, Chaogang Wei, Shan Wang, Wenlu Zhao, Xusheng Qian, Zhiyong Zhou, Junkang Shen, Yakang Dai, Jisu Hu
Summary: This study compared the performance of radiomics and the PI-RADS v2.1 scoring system in detecting csPCa based on different imaging methods. The results showed that the radiomics model outperformed PI-RADS v2.1 in diagnosing csPCa, and the performance of radiomics models based on bpMRI and mpMRI was similar.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Ying-Ying Zhao, Mei-Lian Xiong, Yue-Feng Liu, Li-Juan Duan, Jia-Li Chen, Zhen Xing, Yan-Shun Lin, Tan-Hui Chen
Summary: This bi-institutional study aimed to establish a robust model for predicting clinically significant prostate cancer in PI-RADS 3 lesions in the transition zone. The XGboost model showed the best performance in predicting csPCa, but the addition of radiomic classifiers did not significantly enhance the compound model of clinical and radiological findings.
FRONTIERS IN ONCOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Karen-Cecilie Kortenbach, Vibeke Logager, Henrik S. Thomsen, Lars Boesen
Summary: The purpose of this study was to compare two strategies, PSAd and lesion volume measurement, in ruling out significant prostate cancer in men with equivocal PI-RADS category 3 index lesions. The study found that the PSAd strategy performed better than the lesion volume strategy in ruling out sPCa.
ABDOMINAL RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Christopher S. Lim, Jorge Abreu-Gomez, Ivan Carrion, Nicola Schieda
Summary: This study aimed to evaluate the prevalence of prostate cancer in DWI-upgraded transitional zone nodules and compare the diagnosis rates with conventional score 3 nodules. The prevalence of prostate cancer in DWI-upgraded TZ atypical nodules was found to be low compared to conventional score 3 nodules.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2021)
Article
Medicine, General & Internal
Andrea Corsi, Elisabetta De Bernardi, Pietro Andrea Bonaffini, Paolo Niccolo Franco, Dario Nicoletta, Roberto Simonini, Davide Ippolito, Giovanna Perugini, Mariaelena Occhipinti, Luigi Filippo Da Pozzo, Marco Roscigno, Sandro Sironi
Summary: The clinical management of PI-RADS 3 prostate lesions is still debated, and the application of radiomics to multiparametric MR shows promise. External validation is needed to assess reproducibility. This study proposes a new model combining PSA density and radiomic features from routinely performed sequences to differentiate clinically significant cancers.
JOURNAL OF CLINICAL MEDICINE
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Rajesh Bhayana, Aileen O'Shea, Mark A. Anderson, William R. Bradley, Ravi Gottumukkala, Amirkasra Mojtahed, Theodore T. Pierce, Mukesh Harisinghani
Summary: This study compared the interobserver agreement of PI-RADS v2 and v2.1 in the prostate peripheral and transition zones, and conducted a pilot comparison of their diagnostic performance in these zones. The results showed that v2.1 improved interobserver agreement in the peripheral zone but not in the transition zone, with improved diagnostic performance for experienced readers in the peripheral zone. Specific modifications in v2.1 yielded mixed results, suggesting areas for further improvement in interobserver agreement and performance.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Daniel N. Costa, Liwei Jia, Naveen Subramanian, Yin Xi, Neil M. Rofsky, Debora Z. Recchimuzzi, Alberto Diaz de Leon, Patrick Arraj, Ivan Pedrosa
Summary: This study compared the detection rates of clinically significant prostate cancer in prospectively reported 2 + 1 TZ lesions and conventional 3 + 0 TZ lesions defined by PI-RADS v2.1, finding no significant difference in cancer detection rates between the two groups.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Christopher S. Lim, Jorge Abreu-Gomez, Rebecca Thornhill, Nick James, Ahmed Al Kindi, Andrew S. Lim, Nicola Schieda
Summary: Machine learning of radiomic features extracted from T2W and ADC achieved moderate accuracy in determining whether PI-RADS category 3 lesions represent PCa.
ABDOMINAL RADIOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Sarmad Aslam, Jeffrey Tsang, Ian Bickle, Ali Saiepour
Summary: The study aimed to determine the correlation of PI-RADS 3 prostatic lesions with histology proven, clinically significant cancer. Results showed that a score of PI-RADS 3 does not accurately differentiate between malignant and non-malignant lesions.
BRITISH JOURNAL OF RADIOLOGY
(2022)
Review
Oncology
Anna Maria Grimaldi, Marco Salvatore, Carlo Cavaliere
Summary: Our analysis provides a snapshot of the current scenario regarding EVs as potential clinical biomarkers in resistant prostate cancer. Nevertheless, despite many efforts, the use of EV biomarkers in PCa is currently at an early stage: none of the selected EV biomarkers goes beyond preclinical studies, and their translatability is yet far from clinical settings.
PROSTATE CANCER AND PROSTATIC DISEASES
(2023)
Article
Psychology, Experimental
Giovanni Federico, Francois Osiurak, Maria Antonella Brandimonte, Marco Salvatore, Carlo Cavaliere
Summary: This study investigated the visual encoding modalities of participants in a free-observation task using eye-tracking. The results showed that participants allocated their visual-spatial attention differently to the manipulation and functional areas of objects over time. The repetition of stimuli significantly decreased attention to the functional areas, while attention to the manipulation areas remained stable.
PSYCHOLOGICAL RESEARCH-PSYCHOLOGISCHE FORSCHUNG
(2023)
Article
Chemistry, Analytical
Valentina Brancato, Nadia Brancati, Giusy Esposito, Massimo La Rosa, Carlo Cavaliere, Ciro Allara, Valeria Romeo, Giuseppe De Pietro, Marco Salvatore, Marco Aiello, Mara Sangiovanni
Summary: Breast cancer is the most common cancer among women worldwide, and its heterogeneity can be predicted through radiomics using medical imaging. However, the lack of comprehensive datasets and a general methodology limits the routine use of radiomics in breast cancer clinical practice.
Article
Medicine, General & Internal
Rossana Castaldo, Valentina Brancato, Carlo Cavaliere, Francesco Trama, Ester Illiano, Elisabetta Costantini, Alfonso Ragozzino, Marco Salvatore, Emanuele Nicolai, Monica Franzese
Summary: Pooling radiomic features across different centers is challenging due to technical variability. This study proposed a statistical framework to harmonize multicenter radiomic features from prostate MRI and improve their clinical utility for PCa management. Four statistical methods (ComBat, SVA, Arsynseq, and mixed effect) were evaluated and ComBat outperformed others by achieving high accuracy and AUC in patient classification. The proposed framework provides a standardized pipeline for harmonizing multicenter radiomic features, showing great promise in supporting PCa clinical practice.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Cardiac & Cardiovascular Systems
Paola Gargiulo, Federica Marzano, Marco Salvatore, Christian Basile, Davide Buonocore, Antonio Luca Maria Parlati, Ermanno Nardi, Gaetano Asile, Vincenza Abbate, Angela Colella, Alfonsina Chirico, Caterina Marciano, Stefania Paolillo, Pasquale Perrone-Filardi
Summary: Heart failure is a significant health issue with a high burden on both society and the economy. Recent research has shown that microRNAs play an important role in the development and prognosis of heart failure, serving as biomarkers for diagnosis and prognosis. Exploration of microRNAs as potential therapeutic targets is also ongoing.
Article
Clinical Neurology
A. Scaravilli, M. Tranfa, G. Pontillo, F. Falco, C. Criscuolo, M. Moccia, S. Monti, R. Lanzillo, V. Brescia Morra, G. Palma, M. Petracca, E. Tedeschi, A. Elefante, A. Brunetti, S. Cocozza
Summary: This study aimed to evaluate the long-term impact of gadolinium retention in the dentate nuclei on motor and cognitive disability in patients with MS. The findings showed no significant association between gadolinium retention and long-term motor or cognitive outcomes in these patients.
AMERICAN JOURNAL OF NEURORADIOLOGY
(2023)
Article
Physiology
Marika Valentino, Vittorio Bianco, Lisa Miccio, Pasquale Memmolo, Valentina Brancato, Paolo Libretti, Marcello Gambacorta, Marco Salvatore, Pietro Ferraro
Summary: Kidney microscopy is essential for studying the morphology, physiology, and pathology of kidney tissues, providing important results for diagnosis. Fourier Ptychography (FP) is a microscopy technique that offers high-resolution images and a wide field of view, making it an attractive option for histopathology. This study presents the first comprehensive collection of kidney tissue images captured by an FP microscope, demonstrating the potential of FP microscopy in clinical practice for kidney histopathology.
FRONTIERS IN PHYSIOLOGY
(2023)
Article
Medicine, General & Internal
Lorena Buono, Concetta Iside, Giovanni Pecoraro, Antonia De Matteo, Giuliana Beneduce, Roberta Penta de Vera d'Aragona, Rosanna Parasole, Peppino Mirabelli, Luigi Vitagliano, Marco Salvatore, Giovanni Smaldone
Summary: Acute leukemia, the most common pediatric cancer, is caused by the malignant transformation of B-cell or T-cell progenitors. The study found that KCTD15 was overexpressed in both B-ALL and T-ALL patients, while KCTD1 was upregulated in T-ALL patients. This study not only evaluated the dysregulation of all KCTDs simultaneously in specific pathological contexts for the first time, but also identified a potential biomarker for T-ALL.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Biology
Giovanni Smaldone, Giovanni Pecoraro, Katia Pane, Monica Franzese, Alessia Ruggiero, Luigi Vitagliano, Marco Salvatore
Summary: The KCTD protein family has been traditionally recognized as playing important roles in neurological physiopathology, but recent studies have shown their involvement in various biological processes, including cancers. This study focused on KCTD1 and its role in colorectal cancer. Knocking down KCTD1 in SW480 cells led to significant effects on their motility and stemness, indicating an oncosuppressor role for this protein. Similar effects were also observed with KCTD12 misregulation. These results expand the understanding of KCTD1's involvement in different physiological and pathological processes and suggest analogous activities among KCTD protein family members.
Article
Multidisciplinary Sciences
Mario Verdicchio, Valentina Brancato, Carlo Cavaliere, Francesco Isgro, Marco Salvatore, Marco Aiello
Summary: This study proposed a novel pathomic approach for the classification of tumor-infiltrating lymphocytes (TILs) in breast cancer histopathological whole slide images. By extracting pathomic features and using machine learning models, the researchers achieved a good classification performance for TILs.
Article
Medicine, General & Internal
Concetta Iside, Ornella Affinito, Bruna Punzo, Marco Salvatore, Peppino Mirabelli, Carlo Cavaliere, Monica Franzese
Summary: Coronary artery disease (CAD) is a long-term inflammatory process in which atherosclerosis plays a key role. Damaged endothelial cells release pro-inflammatory cytokines, contributing to vascular inflammation and disease progression. This study found increased levels of several cytokines in the serum of CAD patients, with most cytokines showing a gradual increase with disease severity. Moreover, the combination of serum cytokines may aid in risk stratification for patients suspected of having CAD.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Health Care Sciences & Services
Serena Monti, Maria Elena Truppa, Sandra Albanese, Marcello Mancini
Summary: In the past decade, medical imaging technologies have played an increasingly significant role in clinical and preclinical research. Radiomic and radiogenomic approaches have provided valuable insights for personalized medicine by exploring the relationship between imaging characteristics, genomic information, and outcomes. Preclinical research using animal models allows for the investigation of the causal connection between imaging and molecular factors. This review aims to present the current state of the art in the application of radiomics and radiogenomics on murine models, discussing the implications and potential translational relevance of these findings.
JOURNAL OF PERSONALIZED MEDICINE
(2023)