Machine-Extractable Knowledge from the Shape of Anatomical Structures 2024

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Medical Imaging and Theranostics".

Deadline for manuscript submissions: 30 June 2025 | Viewed by 5081

Special Issue Editors


E-Mail Website
Guest Editor
1. International Research Organization for Advanced Science and Technology (IROAST), Kumamoto University, Kumamoto, Japan
2. Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, Singapore
3. Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore 599494, Singapore
4. Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung 41354, Taiwan
5. School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD, Australia
Interests: biomedical signal processing; bioimaging; data mining; visualization; biophysics for better health care design; drug delivery and therapy
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
1. Professor of Neuroimaging, Department of Neuroscience, The University of Sheffield, Sheffield S10 2TN, UK
2. ARUK Senior Research Fellow, Department of Psychiatry, University of Cambridge, Cambridge CB2 1TN, UK
Interests: neuroimaging (PET/MR/MEG/EEG); cognitive neuroscience; artificial intelligence; computational modelling; formal methods
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

All anatomical structures in the human body, such as organs, bones, and muscles, are three-dimensional objects with a defined shape, and some diseases may alter that shape. As humans, we can detect shapes and indeed shape change because evolution has equipped us with spatial vision. Within the diagnosis process, we underutilize our spatial vision when we look at two-dimensional medical images. The argument for humans working with two dimensional images is centered on standardization and data reduction. For example, oncologists train to recognize cancer texture in medical images. They use this ability to measure tumor cross-sections on specific MRI slices. This operation condenses all the data from the MRI measurement corpus into a single standardized number which is easy to handle by human experts. Unfortunately, information is lost during that operation. Most current computer-aided diagnosis procedures mimic this approach by considering only texture features from a specific image. This approach has two conceptional shortcomings. The first of these shortcomings results from the fact that computing machines are capable of handling and processing large data volumes because they are not limited by the human perception system. Hence, computers can interpret the shape of relevant objects, such as tumors, and shape change caused by specific diseases based on three-dimensional image data. The second shortcoming arises from the selection process, which determines the specific image of interest. In many cases, that process relies on human decision making, where a clinical expert selects one cross-sectional image from a 3D measurement corpus. Inevitably, executing this choice introduces inter- and intra-observer variability. Furthermore, involving human expertise early on in the analysis goes against the goal of reducing workload through computer-aided diagnosis. For this Special Issue, we are interested in studies that push the boundaries of science and technology by offering computer-aided diagnosis based on machine-extractable knowledge from the shape of anatomical structures.

Dr. Oliver Faust
Dr. U. Rajendra Acharya
Prof. Dr. Li Su
Guest Editors

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. Diagnostics 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.

Keywords

  • medical image processing
  • computer-aided diagnosis
  • artificial intelligence
  • 3D imaging
  • hybrid decision support
  • magnetic resonance imaging
  • computed tomography
  • positron emission tomography
  • ultrasound

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Related Special Issue

Published Papers (4 papers)

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

Research

Jump to: Other

14 pages, 3082 KiB  
Article
Automating Dental Condition Detection on Panoramic Radiographs: Challenges, Pitfalls, and Opportunities
by Sorana Mureșanu, Mihaela Hedeșiu, Liviu Iacob, Radu Eftimie, Eliza Olariu, Cristian Dinu, Reinhilde Jacobs and on behalf of Team Project Group
Diagnostics 2024, 14(20), 2336; https://doi.org/10.3390/diagnostics14202336 - 21 Oct 2024
Viewed by 593
Abstract
Background/Objectives: The integration of AI into dentistry holds promise for improving diagnostic workflows, particularly in the detection of dental pathologies and pre-radiotherapy screening for head and neck cancer patients. This study aimed to develop and validate an AI model for detecting various dental [...] Read more.
Background/Objectives: The integration of AI into dentistry holds promise for improving diagnostic workflows, particularly in the detection of dental pathologies and pre-radiotherapy screening for head and neck cancer patients. This study aimed to develop and validate an AI model for detecting various dental conditions, with a focus on identifying teeth at risk prior to radiotherapy. Methods: A YOLOv8 model was trained on a dataset of 1628 annotated panoramic radiographs and externally validated on 180 radiographs from multiple centers. The model was designed to detect a variety of dental conditions, including periapical lesions, impacted teeth, root fragments, prosthetic restorations, and orthodontic devices. Results: The model showed strong performance in detecting implants, endodontic treatments, and surgical devices, with precision and recall values exceeding 0.8 for several conditions. However, performance declined during external validation, highlighting the need for improvements in generalizability. Conclusions: YOLOv8 demonstrated robust detection capabilities for several dental conditions, especially in training data. However, further refinement is needed to enhance generalizability in external datasets and improve performance for conditions like periapical lesions and bone loss. Full article
Show Figures

Figure 1

16 pages, 2600 KiB  
Article
Assessment of Calcaneal Spongy Bone Magnetic Resonance Characteristics in Women: A Comparison between Measures Obtained at 0.3 T, 1.5 T, and 3.0 T
by Silvia Capuani, Alessandra Maiuro, Emiliano Giampà, Marco Montuori, Viviana Varrucciu, Gisela E. Hagberg, Vincenzo Vinicola and Sergio Colonna
Diagnostics 2024, 14(10), 1050; https://doi.org/10.3390/diagnostics14101050 - 18 May 2024
Viewed by 998
Abstract
Background: There is a growing interest in bone tissue MRI and an even greater interest in using low-cost MR scanners. However, the characteristics of bone MRI remain to be fully defined, especially at low field strength. This study aimed to characterize the signal-to-noise [...] Read more.
Background: There is a growing interest in bone tissue MRI and an even greater interest in using low-cost MR scanners. However, the characteristics of bone MRI remain to be fully defined, especially at low field strength. This study aimed to characterize the signal-to-noise ratio (SNR), T2, and T2* in spongy bone at 0.3 T, 1.5 T, and 3.0 T. Furthermore, relaxation times were characterized as a function of bone-marrow lipid/water ratio content and trabecular bone density. Methods: Thirty-two women in total underwent an MR-imaging investigation of the calcaneus at 0.3 T, 1.5 T, and 3.0 T. MR-spectroscopy was performed at 3.0 T to assess the fat/water ratio. SNR, T2, and T2* were quantified in distinct calcaneal regions (ST, TC, and CC). ANOVA and Pearson correlation statistics were used. Results: SNR increase depends on the magnetic field strength, acquisition sequence, and calcaneal location. T2* was different at 3.0 T and 1.5 T in ST, TC, and CC. Relaxation times decrease as much as the magnetic field strength increases. The significant linear correlation between relaxation times and fat/water found in healthy young is lost in osteoporotic subjects. Conclusion: The results have implications for the possible use of relaxation vs. lipid/water marrow content for bone quality assessment and the development of quantitative MRI diagnostics at low field strength. Full article
Show Figures

Figure 1

15 pages, 12093 KiB  
Article
Diagnosis of Delayed Post-Hypoxic Leukoencephalopathy (Grinker’s Myelinopathy) with MRI Using Divided Subtracted Inversion Recovery (dSIR) Sequences: Time for Reappraisal of the Syndrome?
by Gil Newburn, Paul Condron, Eryn E. Kwon, Joshua P. McGeown, Tracy R. Melzer, Mark Bydder, Mark Griffin, Miriam Scadeng, Leigh Potter, Samantha J. Holdsworth, Daniel M. Cornfeld and Graeme M. Bydder
Diagnostics 2024, 14(4), 418; https://doi.org/10.3390/diagnostics14040418 - 14 Feb 2024
Cited by 3 | Viewed by 1914
Abstract
Background: Delayed Post-Hypoxic Leukoencephalopathy (DPHL), or Grinker’s myelinopathy, is a syndrome in which extensive changes are seen in the white matter of the cerebral hemispheres with MRI weeks or months after a hypoxic episode. T2-weighted spin echo (T2-wSE) and/or [...] Read more.
Background: Delayed Post-Hypoxic Leukoencephalopathy (DPHL), or Grinker’s myelinopathy, is a syndrome in which extensive changes are seen in the white matter of the cerebral hemispheres with MRI weeks or months after a hypoxic episode. T2-weighted spin echo (T2-wSE) and/or T2-Fluid Attenuated Inversion Recovery (T2-FLAIR) images classically show diffuse hyperintensities in white matter which are thought to be near pathognomonic of the condition. The clinical features include Parkinsonism and akinetic mutism. DPHL is generally regarded as a rare condition. Methods and Results: Two cases of DPHL imaged with MRI nine months and two years after probable hypoxic episodes are described. No abnormalities were seen on the T2-FLAIR images with MRI, but very extensive changes were seen in the white matter of the cerebral and cerebellar hemisphere on divided Subtraction Inversion Recovery (dSIR) images. dSIR sequences may produce ten times the contrast of conventional inversion recovery (IR) sequences from small changes in T1. The clinical findings in both cases were of cognitive impairment without Parkinsonism or akinetic mutism. Conclusion: The classic features of DPHL may only represent the severe end of a spectrum of diseases in white matter following global hypoxic injury to the brain. The condition may be much more common than is generally thought but may not be recognized using conventional clinical and MRI criteria for diagnosis. Reappraisal of the syndrome of DPHL to include clinically less severe cases and to encompass recent advances in MRI is advocated. Full article
Show Figures

Figure 1

Other

Jump to: Research

12 pages, 7328 KiB  
Case Report
Long-Term Comparison of Two- and Three-Dimensional Computed Tomography Analyses of Cranial Bone Defects in Severe Parietal Thinning
by Johannes Dominikus Pallua, Anton Kasper Pallua, Werner Streif, Harald Spiegl, Clemens Halder, Rohit Arora and Michael Schirmer
Diagnostics 2024, 14(4), 446; https://doi.org/10.3390/diagnostics14040446 - 17 Feb 2024
Viewed by 1153
Abstract
Parietal thinning was detected in a 72-year-old with recurrent headaches. Quantification of bone loss was performed applying two- and three-dimensional methods using computerized tomographies. Two-dimensional methods provided accurate measurements using single-line analyses of bone thicknesses (2.13 to 1.65 and 1.86 mm on the [...] Read more.
Parietal thinning was detected in a 72-year-old with recurrent headaches. Quantification of bone loss was performed applying two- and three-dimensional methods using computerized tomographies. Two-dimensional methods provided accurate measurements using single-line analyses of bone thicknesses (2.13 to 1.65 and 1.86 mm on the left and 4.44 to 3.08 and 4.20 mm on the right side), single-point analyses of bone intensities (693 to 375 and 403 on the left and 513 to 393 and 411 Houndsfield Units on the right side) and particle-size analyses of low density areas (16 to 22 and 12 on the left and 18 to 23 and 14 on the right side). Deteriorations between days 0 and 220 followed by bone stability on day 275 were paralleled using the changed volumes of bone defects to 1200 and finally 1133 mm3 on the left side and to 331 and finally 331 mm3 on the right side. Interfolding as measurement of the bones’ shape provided changes to −1.23 and −1.72 mm on the left and to −1.42 and −1.30 mm on the right side. These techniques suggest a stabilizing effect of corticosteroids between days 220 and 275. Reconstruction of computerized tomographies appears justified to allow for quantification of bone loss during long-term follow-up. Full article
Show Figures

Figure 1

Back to TopTop