sensors-logo

Journal Browser

Journal Browser

Sensing Functional Imaging Biomarkers and Artificial Intelligence

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Biosensors".

Deadline for manuscript submissions: 30 November 2024 | Viewed by 6901

Special Issue Editor


E-Mail Website
Guest Editor
Unit of Nuclear Medicine, Department of Medicine, Surgery and Pharmacy, Università degli Studi di Sassari, Viale San Pietro 8, 07100 Sassari, Italy
Interests: imaging biomarkers; computed tomography(CT); positron emission tomography(PET); biosensors; diagnostic imaging; functional neuroimaging

Special Issue Information

Dear Colleagues,

In the new era of target therapy, approaches to imaging are shifting from qualitative to quantitative. The sensing of functional imaging biomarkers could narrow quantitative data, reflecting microenvironmental diseases’ heterogeneity, and usually serve to refine or enhance the diagnostic information obtained by conventional image analysis, assess early therapeutic responses, predict individual outcomes, and guide treatment based on patient- and disease-specific features.

Following the appearance of artificial intelligence and its fantastic performance, research using machine learning and AI has been conducted in medical image analysis. At present, medical image analysis is one of the leading fields of AI application. Machine learning and deep learning are now being used not only for lesion detection, differential diagnosis, and region extraction but also for image alignment and reconstruction. The dramatic improvement in AI performance has led to the adoption of AI in clinical sites, especially in the fields of nuclear medicine and radiology.

This Special Issue aims to cover recent advances in the development of sensing functional imaging biomarkers using clinically translatable modalities such as nuclear medicine imaging and radiological imaging, and a wide range of research on all types of medical image analysis using AI, machine learning, and deep learning.

Dr. Susanna Nuvoli
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

9 pages, 2651 KiB  
Communication
Optimization of Gradient-Echo Echo-Planar Imaging for T2* Contrast in the Brain at 0.5 T
by Arjama Halder, Chad T. Harris, Curtis N. Wiens, Andrea Soddu and Blaine A. Chronik
Sensors 2023, 23(20), 8428; https://doi.org/10.3390/s23208428 - 12 Oct 2023
Viewed by 920
Abstract
Gradient-recalled echo (GRE) echo-planar imaging (EPI) is an efficient MRI pulse sequence that is commonly used for several enticing applications, including functional MRI (fMRI), susceptibility-weighted imaging (SWI), and proton resonance frequency (PRF) thermometry. These applications are typically not performed in the mid-field (<1 [...] Read more.
Gradient-recalled echo (GRE) echo-planar imaging (EPI) is an efficient MRI pulse sequence that is commonly used for several enticing applications, including functional MRI (fMRI), susceptibility-weighted imaging (SWI), and proton resonance frequency (PRF) thermometry. These applications are typically not performed in the mid-field (<1 T) as longer T2* and lower polarization present significant challenges. However, recent developments of mid-field scanners equipped with high-performance gradient sets offer the possibility to re-evaluate the feasibility of these applications. The paper introduces a metric “T2* contrast efficiency” for this evaluation, which minimizes dead time in the EPI sequence while maximizing T2* contrast so that the temporal and pseudo signal-to-noise ratios (SNRs) can be attained, which could be used to quantify experimental parameters for future fMRI experiments in the mid-field. To guide the optimization, T2* measurements of the cortical gray matter are conducted, focusing on specific regions of interest (ROIs). Temporal and pseudo SNR are calculated with the measured time-series EPI data to observe the echo times at which the maximum T2* contrast efficiency is achieved. T2* for a specific cortical ROI is reported at 0.5 T. The results suggest the optimized echo time for the EPI protocols is shorter than the effective T2* of that region. The effective reduction of dead time prior to the echo train is feasible with an optimized EPI protocol, which will increase the overall scan efficiency for several EPI-based applications at 0.5 T. Full article
(This article belongs to the Special Issue Sensing Functional Imaging Biomarkers and Artificial Intelligence)
Show Figures

Figure 1

15 pages, 3357 KiB  
Article
Performance Analysis of Six Semi-Automated Tumour Delineation Methods on [18F] Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG PET/CT) in Patients with Head and Neck Cancer
by Francesco Bianconi, Roberto Salis, Mario Luca Fravolini, Muhammad Usama Khan, Matteo Minestrini, Luca Filippi, Andrea Marongiu, Susanna Nuvoli, Angela Spanu and Barbara Palumbo
Sensors 2023, 23(18), 7952; https://doi.org/10.3390/s23187952 - 18 Sep 2023
Viewed by 889
Abstract
Background. Head and neck cancer (HNC) is the seventh most common neoplastic disorder at the global level. Contouring HNC lesions on [18F] Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) scans plays a fundamental role for diagnosis, risk assessment, radiotherapy planning and [...] Read more.
Background. Head and neck cancer (HNC) is the seventh most common neoplastic disorder at the global level. Contouring HNC lesions on [18F] Fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) scans plays a fundamental role for diagnosis, risk assessment, radiotherapy planning and post-treatment evaluation. However, manual contouring is a lengthy and tedious procedure which requires significant effort from the clinician. Methods. We evaluated the performance of six hand-crafted, training-free methods (four threshold-based, two algorithm-based) for the semi-automated delineation of HNC lesions on FDG PET/CT. This study was carried out on a single-centre population of n=103 subjects, and the standard of reference was manual segmentation generated by nuclear medicine specialists. Figures of merit were the Sørensen–Dice coefficient (DSC) and relative volume difference (RVD). Results. Median DSC ranged between 0.595 and 0.792, median RVD between −22.0% and 87.4%. Click and draw and Nestle’s methods achieved the best segmentation accuracy (median DSC, respectively, 0.792 ± 0.178 and 0.762 ± 0.107; median RVD, respectively, −21.6% ± 1270.8% and −32.7% ± 40.0%) and outperformed the other methods by a significant margin. Nestle’s method also resulted in a lower dispersion of the data, hence showing stronger inter-patient stability. The accuracy of the two best methods was in agreement with the most recent state-of-the art results. Conclusions. Semi-automated PET delineation methods show potential to assist clinicians in the segmentation of HNC lesions on FDG PET/CT images, although manual refinement may sometimes be needed to obtain clinically acceptable ROIs. Full article
(This article belongs to the Special Issue Sensing Functional Imaging Biomarkers and Artificial Intelligence)
Show Figures

Figure 1

19 pages, 5943 KiB  
Article
Improved Resting-State Functional MRI Using Multi-Echo Echo-Planar Imaging on a Compact 3T MRI Scanner with High-Performance Gradients
by Daehun Kang, Myung-Ho In, Hang Joon Jo, Maria A. Halverson, Nolan K. Meyer, Zaki Ahmed, Erin M. Gray, Radhika Madhavan, Thomas K. Foo, Brice Fernandez, David F. Black, Kirk M. Welker, Joshua D. Trzasko, John Huston III, Matt A. Bernstein and Yunhong Shu
Sensors 2023, 23(9), 4329; https://doi.org/10.3390/s23094329 - 27 Apr 2023
Cited by 2 | Viewed by 2718
Abstract
In blood-oxygen-level-dependent (BOLD)-based resting-state functional (RS-fMRI) studies, usage of multi-echo echo-planar-imaging (ME-EPI) is limited due to unacceptable late echo times when high spatial resolution is used. Equipped with high-performance gradients, the compact 3T MRI system (C3T) enables a three-echo whole-brain ME-EPI protocol with [...] Read more.
In blood-oxygen-level-dependent (BOLD)-based resting-state functional (RS-fMRI) studies, usage of multi-echo echo-planar-imaging (ME-EPI) is limited due to unacceptable late echo times when high spatial resolution is used. Equipped with high-performance gradients, the compact 3T MRI system (C3T) enables a three-echo whole-brain ME-EPI protocol with smaller than 2.5 mm isotropic voxel and shorter than 1 s repetition time, as required in landmark fMRI studies. The performance of the ME-EPI was comprehensively evaluated with signal variance reduction and region-of-interest-, seed- and independent-component-analysis-based functional connectivity analyses and compared with a counterpart of single-echo EPI with the shortest TR possible. Through the multi-echo combination, the thermal noise level is reduced. Functional connectivity, as well as signal intensity, are recovered in the medial orbital sulcus and anterior transverse collateral sulcus in ME-EPI. It is demonstrated that ME-EPI provides superior sensitivity and accuracy for detecting functional connectivity and/or brain networks in comparison with single-echo EPI. In conclusion, the high-performance gradient enabled high-spatial-temporal resolution ME-EPI would be the method of choice for RS-fMRI study on the C3T. Full article
(This article belongs to the Special Issue Sensing Functional Imaging Biomarkers and Artificial Intelligence)
Show Figures

Figure 1

20 pages, 31443 KiB  
Article
Identification of Homogeneous Subgroups from Resting-State fMRI Data
by Hanlu Yang, Trung Vu, Qunfang Long, Vince Calhoun and Tülay Adali
Sensors 2023, 23(6), 3264; https://doi.org/10.3390/s23063264 - 20 Mar 2023
Cited by 2 | Viewed by 1881
Abstract
The identification of homogeneous subgroups of patients with psychiatric disorders can play an important role in achieving personalized medicine and is essential to provide insights for understanding neuropsychological mechanisms of various mental disorders. The functional connectivity profiles obtained from functional magnetic resonance imaging [...] Read more.
The identification of homogeneous subgroups of patients with psychiatric disorders can play an important role in achieving personalized medicine and is essential to provide insights for understanding neuropsychological mechanisms of various mental disorders. The functional connectivity profiles obtained from functional magnetic resonance imaging (fMRI) data have been shown to be unique to each individual, similar to fingerprints; however, their use in characterizing psychiatric disorders in a clinically useful way is still being studied. In this work, we propose a framework that makes use of functional activity maps for subgroup identification using the Gershgorin disc theorem. The proposed pipeline is designed to analyze a large-scale multi-subject fMRI dataset with a fully data-driven method, a new constrained independent component analysis algorithm based on entropy bound minimization (c-EBM), followed by an eigenspectrum analysis approach. A set of resting-state network (RSN) templates is generated from an independent dataset and used as constraints for c-EBM. The constraints present a foundation for subgroup identification by establishing a connection across the subjects and aligning subject-wise separate ICA analyses. The proposed pipeline was applied to a dataset comprising 464 psychiatric patients and discovered meaningful subgroups. Subjects within the identified subgroups share similar activation patterns in certain brain areas. The identified subgroups show significant group differences in multiple meaningful brain areas including dorsolateral prefrontal cortex and anterior cingulate cortex. Three sets of cognitive test scores were used to verify the identified subgroups, and most of them showed significant differences across subgroups, which provides further confirmation of the identified subgroups. In summary, this work represents an important step forward in using neuroimaging data to characterize mental disorders. Full article
(This article belongs to the Special Issue Sensing Functional Imaging Biomarkers and Artificial Intelligence)
Show Figures

Figure 1

Back to TopTop