Article
Neurosciences
Mahsa Dadar, Olivier Potvin, Richard Camicioli, Simon Duchesne
Summary: The study investigated the impact of white matter hyperintensities (WMHs) on FreeSurfer gray matter (GM) structure volumes, finding higher overlaps of WMHs with GM volumes in several brain structures for participants with higher WMH volumes. Uncorrected caudate volumes increased with age, with no difference between cognitively healthy individuals and probable Alzheimer's disease patients. However, after correcting for WMHs, caudate volumes decreased with age and Alzheimer's disease patients had lower caudate volumes than cognitively healthy individuals. The presence of WMHs can lead to systematic inaccuracies in GM segmentations and change clinical associations, affecting cognitive performance assessments.
HUMAN BRAIN MAPPING
(2021)
Article
Cell Biology
Nira Cedres, Patricia Diaz-Galvan, Lucio Diaz-Flores, J-Sebastian Muehlboeck, Yaiza Molina, Jose Barroso, Eric Westman, Daniel Ferreira
Summary: The study found that subjective cognitive decline (SCD) is associated with neurodegeneration in both gray matter and white matter, involving brain areas beyond those typically targeted by Alzheimer's disease. This suggests that SCD may be a sensitive behavioral marker of heterogeneous brain pathologies in individuals recruited from the community.
Article
Health Care Sciences & Services
Yoko Shigemoto, Noriko Sato, Norihide Maikusa, Daichi Sone, Miho Ota, Yukio Kimura, Emiko Chiba, Kyoji Okita, Tensho Yamao, Moto Nakaya, Hiroyuki Maki, Elly Arizono, Hiroshi Matsuda
Summary: Recent developments in image analysis have allowed for the evaluation of brain networks and prediction of brain age from gray matter images. This study examined the effects of age and sex on gray matter networks in a large sample of healthy individuals. The findings revealed that while the brain network retained its small-world properties regardless of age, reduced small-world properties were observed with advancing age. Women showed higher network properties than men, but had faster age-related network declines, leading to no sex differences in participants aged >= 70 years. The study provides new insights into network alterations that occur with aging.
JOURNAL OF PERSONALIZED MEDICINE
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Qiang Zheng, Bin Liu, Yan Gao, Lijun Bai, Yu Cheng, Honglun Li
Summary: A robust cascaded deep learning framework with integrated hippocampal gray matter probability map was developed to improve hippocampus segmentation. The proposed method outperformed other methods in terms of evaluation metrics, especially in capturing hippocampal atrophy in Alzheimer's disease analysis.
EUROPEAN JOURNAL OF RADIOLOGY
(2023)
Article
Neurosciences
Sarah Treit, Nashwan Naji, Peter Seres, Julia Rickard, Emily Stolz, Alan H. Wilman, Christian Beaulieu
Summary: The study found that QSM and R2* values in the caudate, putamen, and globus pallidus of healthy individuals increased most rapidly during childhood and continued to increase gradually throughout adulthood, with caudate susceptibility reaching a plateau in the late 30s. The thalamus showed a unique profile with R2* changes peaking in childhood and both R2* and QSM reaching a plateau in the mid-30s to early 40s.
HUMAN BRAIN MAPPING
(2021)
Article
Psychiatry
Arne Doose, Friederike I. Tam, Inger Hellerhoff, Joseph A. King, Ilka Boehm, Kim Gottloeber, Hannes Wahl, Annett Werner, Felix Raschke, Brenda Bartnik-Olson, Alexander P. Lin, Katja Akguen, Veit Roessner, Jennifer Linn, Stefan Ehrlich
Summary: The acute state of anorexia nervosa (AN) is associated with reductions in cortical gray matter (GM) thickness, changes in myelin content, and elevated levels of neurofilament light (NF-L). However, the underlying mechanisms are unclear. This study used advanced neuroimaging methods and blood-derived biomarkers to investigate brain changes in AN patients. The results suggest neuronal damage and increased membrane lipid catabolism and turnover in GM, but no evidence of white matter (WM) pathology. Multimodal research, including tissue-specific proton magnetic resonance spectroscopy analysis, can provide insights into brain changes in psychiatric and neurological conditions.
TRANSLATIONAL PSYCHIATRY
(2023)
Article
Engineering, Electrical & Electronic
Ju Zhang, Dechen Chen, Dong Ma, Changgang Ying, Xiaoyan Sun, Xiaobing Xu, Yun Cheng
Summary: It has been more than two years since the outbreak of COVID-19, and rapid detection and screening are crucial for controlling the spread of the virus. This study proposes a deep learning model called CdcSegNet to accurately segment lung lesions from CT images infected by COVID-19. Extensive experiments demonstrate that CdcSegNet achieves high accuracy in COVID-19 segmentation and outperforms state-of-the-art models in terms of various evaluation metrics.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Qi Lu, Wan Liu, Zhizheng Zhuo, Yuxing Li, Yunyun Duan, Pinnan Yu, Liying Qu, Chuyang Ye, Yaou Liu
Summary: Convolutional neural networks have achieved excellent performance in white matter tract segmentation based on diffusion magnetic resonance imaging. This work proposes an improved transfer learning approach that incorporates knowledge from a pretrained model into the fine-tuning process for segmenting novel white matter tracts in a few-shot setting. The use of a data augmentation strategy further enhances the segmentation performance.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Clinical Neurology
Luca M. Villa, Lejla Colic, Jihoon A. Kim, Anjali Sankar, Danielle A. Goldman, Brandon Lessing, Brian Pittman, George S. Alexopoulos, Christopher H. van Dyck, Hilary P. Blumberg
Summary: This study found widespread gray matter decreases in older adults with bipolar disorder (BD), and a subset of individuals with later-onset BD also showed cognitive dysfunction. Furthermore, a history of suicide attempts was associated with structural brain differences.
JOURNAL OF AFFECTIVE DISORDERS
(2023)
Article
Computer Science, Artificial Intelligence
Soner Civilibal, Kerim Kursat Cevik, Ahmet Bozkurt
Summary: This study investigates the implementation of deep learning approaches, specifically Mask R-CNN, for breast tumor recognition based on thermal images. The results show that the classification and segmentation performances of the proposed method are better than those reported in the literature for similar studies.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Sezin Barin, Gur Emre Guraksin
Summary: This study compared different criteria for improving the performance of skin lesion segmentation and proposed a hybrid FCN-based deep learning architecture. The results showed that the proposed architecture outperformed traditional architectures in terms of accuracy, dice coefficient, and Jaccard index.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)
Article
Neurosciences
Isabel Hotz, Pascal Frederic Deschwanden, Franziskus Liem, Susan Merillat, Brigitta Malagurski, Spyros Kollias, Lutz Jaencke
Summary: In this study, three algorithms for WMH extraction in older adults were compared and validated, with UBO Detector performing the best in 2D FLAIR images and showing very high associations with Fazekas scores. Meanwhile, FreeSurfer had lower Dice Similarity Coefficient (DSC) and weaker correlations with Fazekas scores.
HUMAN BRAIN MAPPING
(2022)
Article
Geriatrics & Gerontology
M. M. Mulholland, A. Meguerditchian, W. D. Hopkins
Summary: Age-related changes in cognition, brain morphology, and behavior are observed in primate species, including baboons. This study used magnetic resonance imaging to analyze gray matter covariation in 89 olive baboons and found significant age differences in various brain regions. Elderly baboons showed reduced gray matter covariation in regions associated with age-related decline in humans and other nonhuman primates. Further research should investigate the relationship between these gray matter covariation changes and age-related cognitive decline.
NEUROBIOLOGY OF AGING
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Choong Heon Lee, Piotr Walczak, Jiangyang Zhang
Summary: In this study, we investigated the ability of ihMT MRI to detect white matter structures in the hypomyelinated shiverer mouse brain. Our results showed that ihMT can provide clear visualization of the hypomyelinated corpus callosum, with higher myelin contrast compared to conventional MT. These findings suggest the potential use of ihMT as a marker for early myelination or myelin repair.
MAGNETIC RESONANCE IN MEDICINE
(2022)
Article
Geriatrics & Gerontology
Hollis C. Karoly, Carillon J. Skrzynski, Erin Moe, Angela D. Bryan, Kent E. Hutchison
Summary: The study explored associations between age, inflammatory markers, neurofilament levels, brain volume, and cognitive performance in healthy older adults. Results indicated that multiple gray matter regions in the brain link age and cognitive performance, suggesting that neurofilament levels alone may not be sufficient markers of brain changes related to aging, inflammation, and cognitive performance.
FRONTIERS IN AGING NEUROSCIENCE
(2021)
Article
Psychology, Clinical
Graeme Fairchild, Kate Sully, Luca Passamonti, Marlene Staginnus, Angela Darekar, Edmund J. S. Sonuga-Barke, Nicola Toschi
Summary: This study investigated brain structure in adolescents with conduct disorder (CD) and their unaffected relatives (URs), and found that alterations in inferior parietal cortical structure partly mediate the effects of familial risk for CD. Neuroanatomical changes in medial orbitofrontal and anterior cingulate cortex differentiated between URs and the other groups, potentially reflecting neural mechanisms of resilience to CD.
PSYCHOLOGICAL MEDICINE
(2023)
Article
Neurosciences
Chiara Marzi, Alessandro d'Ambrosio, Stefano Diciotti, Alvino Bisecco, Manuela Altieri, Massimo Filippi, Maria Assunta Rocca, Loredana Storelli, Patrizia Pantano, Silvia Tommasin, Rosa Cortese, Nicola De Stefano, Gioacchino Tedeschi, Antonio Gallo
Summary: This study used machine learning techniques to assess the relationship between brain MRI structural volumes and cognitive deficits in MS patients, and found that damage to gray matter structures is most closely related to cognitive performance.
HUMAN BRAIN MAPPING
(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
Neurosciences
Allegra Conti, Constantina Andrada Treaba, Ambica Mehndiratta, Valeria Teresa Barletta, Caterina Mainero, Nicola Toschi
Summary: The relationship between central hallmarks of multiple sclerosis (MS), such as white matter (WM)/cortical demyelinated lesions and cortical gray matter atrophy, remains unclear. A machine learning model was employed to predict mean cortical thinning in different brain regions using demographic and lesion-related characteristics. The study found that volume and rimless WM lesions, patient age, and volume of intracortical lesions have the most predictive power.
Article
Biotechnology & Applied Microbiology
Chiara Marzi, Daniela Marfisi, Andrea Barucci, Jacopo Del Meglio, Alessio Lilli, Claudio Vignali, Mario Mascalchi, Giancarlo Casolo, Stefano Diciotti, Antonio Claudio Traino, Carlo Tessa, Marco Giannelli
Summary: Radiomics and artificial intelligence have the potential to be valuable tools in clinical applications. This study assessed the effect of preprocessing, such as voxel size resampling, discretization, and filtering, on correlation-based dimensionality reduction of radiomic features from cardiac T1 and T2 maps. The results showed that the percentage of eliminated radiomic features was more dependent on resampling voxel size and discretization bin width for textural features. Correlation-based dimensionality reduction was less sensitive to preprocessing when considering T2 features compared to T1 features.
BIOENGINEERING-BASEL
(2023)
Article
Behavioral Sciences
Maria Giovanna Bianco, Andrea Duggento, Salvatore Nigro, Allegra Conti, Nicola Toschi, Luca Passamonti
Summary: This study investigated the heritability of directed functional connections in the brain using the state-space formulation of Granger causality (GC) method. The results showed that the directed connectivity of certain cortico-subcortical circuits is strongly influenced by genetic factors, while other connections are less affected.
BRAIN AND BEHAVIOR
(2023)
Article
Health Care Sciences & Services
Marianna Inglese, Matteo Ferrante, Tommaso Boccato, Allegra Conti, Chiara A. Pistolese, Oreste C. Buonomo, Rolando M. D'Angelillo, Nicola Toschi
Summary: Traditional imaging techniques such as X-rays and MRI have limitations in breast cancer diagnosis and prediction, leading to the emergence of PET as a more effective tool. This study used dynamic PET scans to extract radiomic features and trained a model for classification and prognosis prediction. The results showed superior performance of the dynamic radiomics approach, outperforming standard PET imaging in accuracy. This study demonstrates the enhanced clinical utility of dynomics in improving breast cancer diagnosis and prognosis.
JOURNAL OF PERSONALIZED MEDICINE
(2023)
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
Clinical Neurology
Nicola Toschi, Andrea Duggento, Riccardo Barbieri, Ronald G. Garcia, Harrison P. Fisher, Norman W. Kettner, Vitaly Napadow, Roberta Sclocco
Summary: This study evaluated the brain-heart interaction in response to transcutaneous auricular vagus nerve stimulation (taVNS) using ultrahigh field functional magnetic resonance imaging (fMRI) and a causal approach based on Granger causality. The results demonstrated that taVNS evoked functional brainstem responses and identified causal links between brainstem nuclei and cardiovagal outflow. The study also elucidated potential mechanisms by which information is relayed between brainstem nuclei and high-frequency heart rate variability in response to taVNS.
Article
Medicine, General & Internal
Francesco Alfano, Francesca Cesari, Anna Maria Gori, Martina Berteotti, Emilia Salvadori, Betti Giusti, Alessia Bertelli, Ada Kura, Carmen Barbato, Benedetta Formelli, Francesca Pescini, Enrico Fainardi, Stefano Chiti, Chiara Marzi, Stefano Diciotti, Rossella Marcucci, Anna Poggesi
Summary: This study aims to evaluate the predictive capability of biomarkers for vascular damage and brain tissue injury in anticoagulated atrial fibrillation (AF) patients. The results show that circulating biomarkers MMP-2 and TIMP are associated with cerebral microbleeds, white matter hyperintensity, and small vessel disease. IL-8 and TIMP are associated with enlarged perivascular spaces.
JOURNAL OF CLINICAL MEDICINE
(2023)
Review
Medicine, General & Internal
Mario Mascalchi, Giulia Picozzi, Donella Puliti, Stefano Diciotti, Annalisa Deliperi, Chiara Romei, Fabio Falaschi, Francesco Pistelli, Michela Grazzini, Letizia Vannucchi, Simonetta Bisanzi, Marco Zappa, Giuseppe Gorini, Francesca Maria Carozzi, Laura Carrozzi, Eugenio Paci
Summary: The ITALUNG trial, conducted from 2004, compared the mortality rates of lung cancer and other causes in smokers and ex-smokers aged 55-69 who were randomly assigned to receive low-dose CT (LDCT) or usual care. After 13 years of follow-up, the ITALUNG trial demonstrated a lower mortality rate for lung cancer and cardiovascular diseases in the screened subjects, particularly in women. In addition, the trial generated multiple ancillary studies on various aspects of lung cancer screening, including software development, assessment of lung nodules and calcifications, and biomarker assays.
Article
Psychology, Multidisciplinary
Claudio Paolucci, Federica Giorgini, Riccardo Scheda, Flavio Valerio Alessi, Stefano Diciotti
Summary: This study proposes an AI pre-screening tool to identify potentially alarming signs of Autism Spectrum Disorder (ASD) in pre-verbal interactions. The effectiveness of these features in classifying individuals with ASD vs. controls is evaluated using explainable artificial intelligence, with a focus on body-related sensorimotor features. The results highlight the significance of early detection in ASD diagnosis.
COMPUTERS IN HUMAN BEHAVIOR
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Marianna Inglese, Matteo Ferrante, Andrea Duggento, Tommaso Boccato, Nicola Toschi
Summary: Positron emission tomography (PET) is a noninvasive imaging technology used to assess tissue metabolism and function. Dynamic PET acquisitions provide information about tracer delivery, target interaction, and physiological washout, which can be analyzed using time activity curves (TACs). Conventional PET analysis requires invasive arterial blood sampling, but this study demonstrates that deep learning models can accurately discriminate breast cancer lesions using TACs without arterial blood sampling, outperforming traditional SUV analysis.
IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES
(2023)
Review
Endocrinology & Metabolism
F. Giorgini, G. Di Dalmazi, S. Diciotti
Summary: This comprehensive review provides an overview of the current applications of artificial intelligence (AI) in the field of endocrinology, highlighting the use of machine learning algorithms and deep learning models. The studies discussed in this review demonstrate the valuable contributions of AI in optimizing healthcare outcomes and uncovering new understandings of endocrine disorders.
JOURNAL OF ENDOCRINOLOGICAL INVESTIGATION
(2023)
