Special Issue "Artificial Intelligence in Image-Based Diagnostics of Oncological and Neurological Disorders"

A special issue of Diagnostics (ISSN 2075-4418). This special issue belongs to the section "Machine Learning and Artificial Intelligence in Diagnostics".

Deadline for manuscript submissions: 31 October 2021.

Special Issue Editors

Prof. Dr. Barbara Palumbo
E-Mail Website
Guest Editor
Section of Nuclear Medicine and Health Physics, Department of Surgical and Biomedical Sciences, Università degli Studi di Perugia, Perugia, Italy
Interests: nuclear medicine; image-based diagnostics; artificial intelligence; PET/CT; SPECT; SPECT/CT; radiomics; oncology; neurodegenerative disorders
Prof. Dr. Angela Spanu
E-Mail Website
Guest Editor
Nuclear Medicine Unit, Department of Medical, Surgical and Experimental Sciences, Università degli Studi di Sassari, Sassari, Italy
Interests: nuclear medicine; image-based diagnostics; SPECT; SPECT/CT; PET/CT; molecular breast imaging; oncology (breast cancer, lung cancer, thyroid cancer, neuroendocrine tumors, prostate cancer); radiomics; neurodegenerative disorders; radiometabolic therapy
Special Issues and Collections in MDPI journals
Prof. Dr. Luca Brunese
E-Mail Website
Guest Editor
Department of Medicine and Health Sciences “Vincenzo Tiberio”, Università degli Studi del Molise, Campobasso, Italy
Interests: artificial intelligence; image-based diagnostics; CT; MRI; radiology; radiomics; oncology
Prof. Dr. Francesco Bianconi
E-Mail Website
Guest Editor
Department of Engineering, Università degli Studi di Perugia, Italy
Interests: artificial intelligence; computational imaging; computer vision; image processing; medical image analysis; radiomics
Special Issues and Collections in MDPI journals

Special Issue Information

Dear Colleagues,

Diagnostic imaging has experienced major changes in recent years. Radiological and nuclear medicine modalities represent the option of choice to investigate the main oncological and neurological diseases. The improving capabilities of the imaging devices and the increasing availability of storing, sharing and computing facilities have been generating larger and larger amounts of data. Consequently, there has been increasing attention on the development of computational methods for the extraction of objective imaging features (biomarkers) capable of correlating with disease phenotype, clinical outcome and/or response to treatment. The combined use of imaging data, biomarkers and artificial intelligence techniques makes it possible to build powerful predictive models which can assist the physician in the management of patients with a wide range of disorders, particularly oncological and neurological, ultimately leading to personalised treatment and better clinical outcome. However, there are still open challenges before these methods can be translated into clinical practice. Critical to this process, for instance, are standardisation, strong interdisciplinary cooperation, and the availability of centralised repositories of annotated data.  

This Special Issue wants to provide a forum to discuss challenges, discoveries and opportunities in the field, with specific focus on the diagnosis of oncological and neurological disorders by radiological and nuclear medicine modalities. We encourage the submission research papers as well as review articles; comparative evaluations and new datasets are also welcome.

Prof. Dr. Barbara Palumbo
Prof. Dr. Angela Spanu
Prof. Dr. Luca Brunese
Prof. Dr. Francesco Bianconi
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 papers will be 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 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 1600 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

  • Artificial intelligence in diagnostic imaging
  • Computer-assisted diagnosis and prognostication
  • Data mining and big data
  • Deep Learning
  • Image processing (including acquisition, segmentation and feature extraction)
  • Radiology
  • Nuclear Medicine
  • Imaging modalities (including CT, MRI, PET, PET/CT, PET/MRI, SPECT, SPECT/CT)
  • Oncological and neurological disorders
  • Personalised medicine

Published Papers (2 papers)

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

Research

Open AccessArticle
Adding Value of MRI over CT in Predicting Peritoneal Cancer Index and Completeness of Cytoreduction
Diagnostics 2021, 11(4), 674; https://doi.org/10.3390/diagnostics11040674 - 08 Apr 2021
Viewed by 407
Abstract
Background: This study aimed to investigate the adding value of MRI over CT for preoperative cytoreductive surgery with hyperthermic intraperitoneal chemotherapies (CRS/HIPEC). Methods: Imaging and intraoperative peritoneal cancer index (PCI) were calculated in 62 patients with peritoneal metastasis. Predictive models for the completeness [...] Read more.
Background: This study aimed to investigate the adding value of MRI over CT for preoperative cytoreductive surgery with hyperthermic intraperitoneal chemotherapies (CRS/HIPEC). Methods: Imaging and intraoperative peritoneal cancer index (PCI) were calculated in 62 patients with peritoneal metastasis. Predictive models for the completeness of cytoreductive score using PCI data were established using decision tree algorithms. Results: In gastric cancer patients, a large discrepancy and poor agreement was appreciated between CT and surgical PCI, and a nonsignificant difference was noted between MRI and surgical PCI. In colon cancer patients, a better agreement and higher correlation with a smaller error was observed in PCI score using MRI than in that using CT. However, the addition of MRI to CT was limited for appendiceal and ovarian cancer patients. For predicting incomplete cytoreduction, CT models yielded inadequate accuracy while MRI models were more accurate with fair discrimination ability. Conclusions: CT was suitable for estimating PCI and surgery outcome in appendiceal and ovarian cancer patients, while further MRI in addition to CT was recommended for colon and gastric cancer patients. However, for classifying patients with peritoneal carcinomatosis into complete and incomplete cytoreduction, MRI was more effective than CT. Full article
Show Figures

Graphical abstract

Open AccessArticle
On the Adoption of Radiomics and Formal Methods for COVID-19 Coronavirus Diagnosis
Diagnostics 2021, 11(2), 293; https://doi.org/10.3390/diagnostics11020293 - 12 Feb 2021
Viewed by 492
Abstract
Considering the current pandemic, caused by the spreading of the novel Coronavirus disease, there is the urgent need for methods to quickly and automatically diagnose infection. To assist pathologists and radiologists in the detection of the novel coronavirus, in this paper we propose [...] Read more.
Considering the current pandemic, caused by the spreading of the novel Coronavirus disease, there is the urgent need for methods to quickly and automatically diagnose infection. To assist pathologists and radiologists in the detection of the novel coronavirus, in this paper we propose a two-tiered method, based on formal methods (to the best of authors knowledge never previously introduced in this context), aimed to (i) detect whether the patient lungs are healthy or present a generic pulmonary infection; (ii) in the case of the previous tier, a generic pulmonary disease is detected to identify whether the patient under analysis is affected by the novel Coronavirus disease. The proposed approach relies on the extraction of radiomic features from medical images and on the generation of a formal model that can be automatically checked using the model checking technique. We perform an experimental analysis using a set of computed tomography medical images obtained by the authors, achieving an accuracy of higher than 81% in disease detection. Full article
Show Figures

Figure 1

Back to TopTop