AI Imaging Diagnostic Tools

A special issue of Tomography (ISSN 2379-139X).

Deadline for manuscript submissions: closed (31 March 2022) | Viewed by 11024

Special Issue Editor

School of Computing and Mathematical Sciences, University of Greenwich, London SE10 9LS, UK
Interests: control systems; context-awareness; engineering, applied and computational mathematics; implementation; automotive; computing; algorithms; software; cloud computing; embedded systems

Special Issue Information

Dear Colleagues,

Without a doubt, over the last few decades widely understood diagnostic imaging (MRI, CT, etc.) has played crucial role in preventing severe consequences or health-related complications to which many diseases can lead. In such cases precise early-stage diagnosis is of utmost importance and becomes the key to successful therapy and treatment of even potentially deadly diseases. Unfortunately, civilisation development or demographic trends result in increasing numbers of patients which could benefit from making the whole diagnostic process more effective and simply faster. However, processing the diagnostic data (e.g. MRI / CT scans) acquired from so many patients is often beyond human capability. In such situation employing AI / ML tools and methods as well as different kinds of expert systems seem the only reasonable solution of the problem. Solution which requires many challenges to be addressed ranging from proper features extraction and pattern recognition up to elaborating some problem-specific validation and verification methods. All papers addressing those challenges and topics and especially those combining various theoretical and practical approaches are invited for this special issue. 

Dr. Mariusz Pelc
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. Tomography is an international peer-reviewed open access monthly 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 2400 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.

Keywords

  • diagnostic imaging
  • machine learning
  • expert systems
  • image processing
  • features extraction
  • pattern recognition
  • validation and verification methods

Published Papers (3 papers)

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

Research

11 pages, 3800 KiB  
Article
AI Lung Segmentation and Perfusion Analysis of Dual-Energy CT Can Help to Distinguish COVID-19 Infiltrates from Visually Similar Immunotherapy-Related Pneumonitis Findings and Can Optimize Radiological Workflows
by Andreas S. Brendlin, Markus Mader, Sebastian Faby, Bernhard Schmidt, Ahmed E. Othman, Sebastian Gassenmaier, Konstantin Nikolaou and Saif Afat
Tomography 2022, 8(1), 22-32; https://doi.org/10.3390/tomography8010003 - 23 Dec 2021
Cited by 4 | Viewed by 3263
Abstract
(1) To explore the potential impact of an AI dual-energy CT (DECT) prototype on decision making and workflows by investigating its capabilities to differentiate COVID-19 from immunotherapy-related pneumonitis. (2) Methods: From 3 April 2020 to 12 February 2021, DECT from biometrically matching patients [...] Read more.
(1) To explore the potential impact of an AI dual-energy CT (DECT) prototype on decision making and workflows by investigating its capabilities to differentiate COVID-19 from immunotherapy-related pneumonitis. (2) Methods: From 3 April 2020 to 12 February 2021, DECT from biometrically matching patients with COVID-19, pneumonitis, and inconspicuous findings were selected from our clinical routine. Three blinded readers independently scored each pulmonary lobe analogous to CO-RADS. Inter-rater agreement was determined with an intraclass correlation coefficient (ICC). Averaged perfusion metrics per lobe (iodine uptake in mg, volume without vessels in ml, iodine concentration in mg/mL) were extracted using manual segmentation and an AI DECT prototype. A generalized linear mixed model was used to investigate metric validity and potential distinctions at equal CO-RADS scores. Multinomial regression measured the contribution “Reader”, “CO-RADS score”, and “perfusion metrics” to diagnosis. The time to diagnosis was measured for manual vs. AI segmentation. (3) Results: We included 105 patients (62 ± 13 years, mean BMI 27 ± 2). There were no significant differences between manually and AI-extracted perfusion metrics (p = 0.999). Regardless of the CO-RADS score, iodine uptake and concentration per lobe were significantly higher in COVID-19 than in pneumonitis (p < 0.001). In regression, iodine uptake had a greater contribution to diagnosis than CO-RADS scoring (Odds Ratio (OR) = 1.82 [95%CI 1.10–2.99] vs. OR = 0.20 [95%CI 0.14–0.29]). The AI prototype extracted the relevant perfusion metrics significantly faster than radiologists (10 ± 1 vs. 15 ± 2 min, p < 0.001). (4) Conclusions: The investigated AI prototype positively impacts decision making and workflows by extracting perfusion metrics that differentiate COVID-19 from visually similar pneumonitis significantly faster than radiologists. Full article
(This article belongs to the Special Issue AI Imaging Diagnostic Tools)
Show Figures

Figure 1

10 pages, 1502 KiB  
Article
Carotid Phase-Contrast Magnetic Resonance before Treatment: 4D-Flow versus Standard 2D Imaging
by Francesco Secchi, Caterina Beatrice Monti, Davide Capra, Renato Vitale, Daniela Mazzaccaro, Michele Conti, Ning Jin, Daniel Giese, Giovanni Nano, Francesco Sardanelli and Massimiliano M. Marrocco-Trischitta
Tomography 2021, 7(4), 513-522; https://doi.org/10.3390/tomography7040044 - 28 Sep 2021
Viewed by 1816
Abstract
The purpose of this study was to evaluate the level of agreement between flow/velocity data obtained from 2D-phase-contrast (PC) and 4D-flow in patients scheduled for treatment of carotid artery stenosis. Image acquisition was performed using a 1.5 T scanner. We compared mean flow [...] Read more.
The purpose of this study was to evaluate the level of agreement between flow/velocity data obtained from 2D-phase-contrast (PC) and 4D-flow in patients scheduled for treatment of carotid artery stenosis. Image acquisition was performed using a 1.5 T scanner. We compared mean flow rates, vessel areas, and peak velocities obtained during the acquisition with both techniques in 20 consecutive patients, 15 males and 5 females aged 69 ± 5 years (mean ± standard deviation). There was a good correlation between both techniques for the CCA flow (r = 0.65, p < 0.001), whereas for the ICA flow and ECA flow the correlation was only moderate (r = 0.4, p = 0.011 and r = 0.45, p = 0.003, respectively). Correlations of peak velocities between methods were good for CCA (r = 0.56, p < 0.001) and moderate for ECA (r = 0.41, p = 0.008). There was no correlation for ICA (r = 0.04, p = 0.805). Cross-sectional area values between methods showed no significant correlations for CCA (r = 0.18, p = 0.269), ICA (r = 0.1, p = 0.543), and ECA (r = 0.05, p = 0.767). Conclusion: the 4D-flow imaging provided a good correlation of CCA and a moderate correlation of ICA flow rates against 2D-PC, underestimating peak velocities and overestimating cross-sectional areas in all carotid segments. Full article
(This article belongs to the Special Issue AI Imaging Diagnostic Tools)
Show Figures

Figure 1

12 pages, 995 KiB  
Article
Evaluating a Machine Learning Tool for the Classification of Pathological Uptake in Whole-Body PSMA-PET-CT Scans
by Annette Erle, Sobhan Moazemi, Susanne Lütje, Markus Essler, Thomas Schultz and Ralph A. Bundschuh
Tomography 2021, 7(3), 301-312; https://doi.org/10.3390/tomography7030027 - 29 Jul 2021
Cited by 15 | Viewed by 4865
Abstract
The importance of machine learning (ML) in the clinical environment increases constantly. Differentiation of pathological from physiological tracer-uptake in positron emission tomography/computed tomography (PET/CT) images is considered time-consuming and attention intensive, hence crucial for diagnosis and treatment planning. This study aimed at comparing [...] Read more.
The importance of machine learning (ML) in the clinical environment increases constantly. Differentiation of pathological from physiological tracer-uptake in positron emission tomography/computed tomography (PET/CT) images is considered time-consuming and attention intensive, hence crucial for diagnosis and treatment planning. This study aimed at comparing and validating supervised ML algorithms to classify pathological uptake in prostate cancer (PC) patients based on prostate-specific membrane antigen (PSMA)-PET/CT. Retrospective analysis of 68Ga-PSMA-PET/CTs of 72 PC patients resulted in a total of 77 radiomics features from 2452 manually delineated hotspots for training and labeled pathological (1629) or physiological (823) as ground truth (GT). As the held-out test dataset, 331 hotspots (path.:128, phys.: 203) were delineated in 15 other patients. Three ML classifiers were trained and ranked to assess classification performance. As a result, a high overall average performance (area under the curve (AUC) of 0.98) was achieved, especially to detect pathological uptake (0.97 mean sensitivity). However, there is still room for improvement to detect physiological uptake (0.82 mean specificity), especially for glands. The ML algorithm applied to manually delineated lesions predicts hotspot labels with high accuracy on unseen data and may be an important tool to assist in clinical diagnosis. Full article
(This article belongs to the Special Issue AI Imaging Diagnostic Tools)
Show Figures

Figure 1

Back to TopTop