Advances in Artificial Intelligence in Healthcare

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 July 2024 | Viewed by 1324

Special Issue Editors


E-Mail Website
Guest Editor

Special Issue Information

Dear Colleagues,

In the era of precision medicine, digital radiology and AI-driven radiomics analysis are at the forefront of healthcare transformation. This convergence enables personalized preventive and therapeutic interventions tailored to individual patient characteristics, minimizing the costs and side effects. Medical imaging plays a pivotal role by facilitating screening, early diagnosis, response evaluation and recurrence assessment. Radiomics extracts mineable, high-dimensional data from routine medical images to create an 'imaging phenotype,' which categorizes disease severity, predicts therapy response and forecasts patient outcomes. The aim of this research proposal is to investigate and promote the integration of digital radiology and AI-driven radiomics for precision medicine in healthcare.

Recent advances in smart computer vision have spurred significant interest in AI applications within radiology and in healthcare. While some AI software applications have received clinical approval, numerous unexplored possibilities remain. AI-driven computer-assisted detection and diagnosis, utilizing deep neural networks, automates tasks such as image classification and object localization. AI also extends its potential to clinical decision support, protocol optimization and workflow improvement. This Special Issue explores various network architectures suitable for digitalization in radiology and will be able to advance healthcare based on AI. We seek the support and engagement of experts, researchers and authors in this exciting endeavor to advance healthcare through the fusion of radiology and AI.

The convergence of artificial intelligence and digital imaging offers a unique opportunity to shift from qualitative to quantitative data, fostering the development of clinical decision support systems. Radiomics and deep learning, as two prominent quantitative imaging techniques, promise efficiency, minimal invasiveness and high accuracy. Challenges such as model explainability, feature reproducibility and sensitivity to imaging variations must be addressed before clinical implementation. This narrative review assesses the status of quantitative medical image analysis, outlines challenges in the field, proposes a robust radiomics analysis framework and discusses future prospects. The Special Issue we aim to create will consolidate research findings on AI in digital radiology and inspire a new era of precision medicine and smart healthcare.

  • Radiology and AI-driven radiomics as the key for precise, cost-effective and personalized medicine;
  • Medical imaging as the pivot for screening, diagnosis and treatment monitoring in this convergence;
  • AI's role in digital radiology, particularly in computer-assisted detection and diagnosis;
  • The 'imaging phenotype' via radiomics for disease categorization and outcome prediction;
  • Deep convolutional neural networks for radiology tasks;
  • Seeking research community support to advance digital radiology and AI in healthcare;
  • Quantitative image analysis potential and Special Issue for precision medicine.

Prof. Dr. Kelvin K.L. Wong
Prof. Dr. Dhanjoo N. Ghista
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

  • artificial intelligence
  • AI-driven radiomics
  • healthcare
  • digital radiology
  • precision medicine

Published Papers (2 papers)

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

Research

39 pages, 1496 KiB  
Article
Interactions between Cognitive, Affective, and Respiratory Profiles in Chronic Respiratory Disorders: A Cluster Analysis Approach
by Iulian-Laurențiu Buican, Victor Gheorman, Ion Udriştoiu, Mădălina Olteanu, Dumitru Rădulescu, Dan Marian Calafeteanu, Alexandra Floriana Nemeş, Cristina Călăraşu, Patricia-Mihaela Rădulescu and Costin-Teodor Streba
Diagnostics 2024, 14(11), 1153; https://doi.org/10.3390/diagnostics14111153 - 30 May 2024
Viewed by 223
Abstract
This study conducted at Leamna Pulmonology Hospital investigated the interrelations among cognitive, affective, and respiratory variables within a cohort of 100 patients diagnosed with chronic respiratory conditions, utilizing sophisticated machine learning-based clustering techniques. Spanning from October 2022 to February 2023, hospitalized individuals confirmed [...] Read more.
This study conducted at Leamna Pulmonology Hospital investigated the interrelations among cognitive, affective, and respiratory variables within a cohort of 100 patients diagnosed with chronic respiratory conditions, utilizing sophisticated machine learning-based clustering techniques. Spanning from October 2022 to February 2023, hospitalized individuals confirmed to have asthma or COPD underwent extensive evaluations using standardized instruments such as the mMRC scale, the CAT test, and spirometry. Complementary cognitive and affective assessments were performed employing the MMSE, MoCA, and the Hamilton Anxiety and Depression Scale, furnishing a holistic view of patient health statuses. The analysis delineated three distinct clusters: Moderate Cognitive Respiratory, Severe Cognitive Respiratory, and Stable Cognitive Respiratory, each characterized by unique profiles that underscore the necessity for tailored therapeutic strategies. These clusters exhibited significant correlations between the severity of respiratory symptoms and their effects on cognitive and affective conditions. The results highlight the benefits of an integrated treatment approach for COPD and asthma, which is personalized based on the intricate patterns identified through clustering. Such a strategy promises to enhance the management of these diseases, potentially elevating the quality of life and everyday functionality of the patients. These findings advocate for treatment customization according to the specific interplays among cognitive, affective, and respiratory dimensions, presenting substantial prospects for clinical advancement and pioneering new avenues for research in the domain of chronic respiratory disease management. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence in Healthcare)
Show Figures

Figure 1

19 pages, 4142 KiB  
Article
Three-Dimensional Virtual Reconstruction of External Nasal Defects Based on Facial Mesh Generation Network
by Qingzhao Qin, Yinglong Li, Aonan Wen, Yujia Zhu, Zixiang Gao, Shenyao Shan, Hongyu Wu, Yijiao Zhao and Yong Wang
Diagnostics 2024, 14(6), 603; https://doi.org/10.3390/diagnostics14060603 - 12 Mar 2024
Viewed by 772
Abstract
(1) Background: In digital-technology-assisted nasal defect reconstruction methods, a crucial step involves utilizing computer-aided design to virtually reconstruct the nasal defect’s complete morphology. However, current digital methods for virtual nasal defect reconstruction have yet to achieve efficient, precise, and personalized outcomes. In this [...] Read more.
(1) Background: In digital-technology-assisted nasal defect reconstruction methods, a crucial step involves utilizing computer-aided design to virtually reconstruct the nasal defect’s complete morphology. However, current digital methods for virtual nasal defect reconstruction have yet to achieve efficient, precise, and personalized outcomes. In this research paper, we propose a novel approach for reconstructing external nasal defects based on the Facial Mesh Generation Network (FMGen-Net), aiming to enhance the levels of automation and personalization in virtual reconstruction. (2) Methods: We collected data from 400 3D scans of faces with normal morphology and combined the structured 3D face template and the Meshmonk non-rigid registration algorithm to construct a structured 3D facial dataset for training FMGen-Net. Guided by defective facial data, the trained FMGen-Net automatically generated an intact 3D face that was similar to the defective face, and maintained a consistent spatial position. This intact 3D face served as the 3D target reference face (3D-TRF) for nasal defect reconstruction. The reconstructed nasal data were extracted from the 3D-TRF based on the defective area using reverse engineering software. The ‘3D surface deviation’ between the reconstructed nose and the original nose was calculated to evaluate the effect of 3D morphological restoration of the nasal defects. (3) Results: In the simulation experiment of 20 cases involving full nasal defect reconstruction, the ‘3D surface deviation’ between the reconstructed nasal data and the original nasal data was 1.45 ± 0.24 mm. The reconstructed nasal data, constructed from the personalized 3D-TRF, accurately reconstructed the anatomical morphology of nasal defects. (4) Conclusions: This paper proposes a novel method for the virtual reconstruction of external nasal defects based on the FMGen-Net model, achieving the automated and personalized construction of the 3D-TRF and preliminarily demonstrating promising clinical application potential. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence in Healthcare)
Show Figures

Figure 1

Back to TopTop