Artificial Intelligence (AI) as One Health Tool in Pathology to Monitor and Control Infectious Diseases

A special issue of Pathogens (ISSN 2076-0817). This special issue belongs to the section "Epidemiology of Infectious Diseases".

Deadline for manuscript submissions: 15 December 2024 | Viewed by 3881

Special Issue Editors


E-Mail Website
Guest Editor
Pathology Unit, Department of Veterinary Science, University of Parma, 43126 Parma, Italy
Interests: oncology; immunopathology; swine pathology
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Faculty of Veterinary Medicine, University of Teramo, 64100 Teramo, Italy
Interests: veterinary pathology; diseases of swine; scoring methods; artificial intelligence in veterinary pathology

E-Mail Website
Guest Editor
AImageLab, Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41124 Modena, Italy
Interests: deep learning; continual learning; self-supervised learning; anomaly detection; satellite imagery; AI in earth observations applications

E-Mail Website
Guest Editor
Pathology Unit, Department of Veterinary Science, University of Parma, 43126 Parma, Italy
Interests: veterinary immunology; immunopathology; pathology; cellular and molecular biology
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Pathology Unit, Department of Veterinary Science, University of Parma, 43126 Parma, Italy
Interests: veterinary pathology; veterinary oncology

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) can be defined as the intelligence presented by some artificial entities, such as robots and computers. Over the last decade, AI has received much attention and is dramatically transforming all forms of human activities, including those in the medical field.

The first attempts to apply AI to medicine date back to the dawn of this new technological era, during the 1960s. However, more recently, the development of “deep learning” (DL) has driven and accelerated the use of AI in the framework of biomedical sciences, further widening its fields of application. This is clearly testified by the exponential growth of the scientific community’s commitment in this area of interest (https://pubmed.ncbi.nlm.nih.gov/?term=artificial+intelligence+AND+medicine&filter=years.2012-2022&timeline=expanded, accessed on 14 October 2022).

DL is a subset of machine learning and currently represents the state of the art in the field of visual object recognition (“computer vision”). In particular, the so-called “convolutional neural network” (CNN) is the most famous and effective DL model for image recognition tasks, which has been successfully applied to diagnostic imaging and pathology.

The effectiveness of these models relies on their ability to automatically infer hidden relations and patterns from a huge amount of data. Before the advent of these new technologies, indeed, it was the responsibility of the expert in the human domain to design the entire feature engineering pipeline; today, instead, these tools noticeably help in reducing that effort and in improving the overall performance of predictive models.

As far as pathology is concerned, most AI research is currently targeted toward use in neoplastic disorders, aiming to improve/standardize the diagnosis and grading of cancer. However, several research groups are currently developing CNNs to detect and score lesions caused by different pathogens. This is particularly true in veterinary medicine, as CNNs could act as efficient and effective tools to monitor the trend of infectious diseases and to detect severe threats to human health and/or livestock production early.

As a matter of fact, the slaughterhouse is widely recognized as a unique checkpoint that is used to assess the health status of farm animals, and it can suitably provide reliable information to the entire livestock industry. Consequently, several countries decided to adopt specific schemes to record inspection (i.e., pathological) data from slaughtered animals. Despite this, the overall size of the slaughtering industry, the impressive number of slaughtered animals per day in high-throughput abattoirs, as well as the high speed of the slaughter chain, make the systematic collection of data very challenging. Preliminary results indicate that CNN-based methods could be successfully applied to carry out such highly repetitive tasks, thus allowing farmers to properly monitor and control infectious diseases (e.g., enzootic pneumonia by Mycoplasma hyopneumoniae), which are distributed worldwide and strongly affect the use/abuse of antimicrobials. Likewise, CNNs could be trained to detect emerging, foreign, and zoonotic diseases early, which might represent a serious threat to human health, food safety, and the profitability of livestock farming.

Considering the recent occurrence and spread of severe human infectious diseases (e.g., COVID-19 and monkeypox virus infection), we do not rule out the concept that AI-based technologies could gain greater importance in human pathology in the near future.

Prof. Dr. Attilio Corradi
Prof. Dr. Giuseppe Marruchella
Dr. Angelo Porrello
Dr. Luca Ferrari
Prof. Dr. Anna Maria Cantoni
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. Pathogens 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 2700 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

  • pathology
  • Artificial Intelligence (AI)
  • computer vision
  • scoring methods
  • diagnosis and monitoring of infectious diseases

Published Papers (2 papers)

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

Research

10 pages, 2833 KiB  
Communication
Scoring Enzootic Pneumonia-like Lesions in Slaughtered Pigs: Traditional vs. Artificial-Intelligence-Based Methods
by Jasmine Hattab, Angelo Porrello, Anastasia Romano, Alfonso Rosamilia, Sergio Ghidini, Nicola Bernabò, Andrea Capobianco Dondona, Attilio Corradi and Giuseppe Marruchella
Pathogens 2023, 12(12), 1460; https://doi.org/10.3390/pathogens12121460 - 17 Dec 2023
Viewed by 1234
Abstract
Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of [...] Read more.
Artificial-intelligence-based methods are regularly used in the biomedical sciences, mainly in the field of diagnostic imaging. Recently, convolutional neural networks have been trained to score pleurisy and pneumonia in slaughtered pigs. The aim of this study is to further evaluate the performance of a convolutional neural network when compared with the gold standard (i.e., scores provided by a skilled operator along the slaughter chain through visual inspection and palpation). In total, 441 lungs (180 healthy and 261 diseased) are included in this study. Each lung was scored according to traditional methods, which represent the gold standard (Madec’s and Christensen’s grids). Moreover, the same lungs were photographed and thereafter scored by a trained convolutional neural network. Overall, the results reveal that the convolutional neural network is very specific (95.55%) and quite sensitive (85.05%), showing a rather high correlation when compared with the scores provided by a skilled veterinarian (Spearman’s coefficient = 0.831, p < 0.01). In summary, this study suggests that convolutional neural networks could be effectively used at slaughterhouses and stimulates further investigation in this field of research. Full article
Show Figures

Figure 1

16 pages, 3378 KiB  
Article
A Deep Batch Normalized Convolution Approach for Improving COVID-19 Detection from Chest X-ray Images
by Ibrahim Al-Shourbaji, Pramod H. Kachare, Laith Abualigah, Mohammed E. Abdelhag, Bushra Elnaim, Ahmed M. Anter and Amir H. Gandomi
Pathogens 2023, 12(1), 17; https://doi.org/10.3390/pathogens12010017 - 22 Dec 2022
Cited by 7 | Viewed by 1945
Abstract
Pre-trained machine learning models have recently been widely used to detect COVID-19 automatically from X-ray images. Although these models can selectively retrain their layers for the desired task, the output remains biased due to the massive number of pre-trained weights and parameters. This [...] Read more.
Pre-trained machine learning models have recently been widely used to detect COVID-19 automatically from X-ray images. Although these models can selectively retrain their layers for the desired task, the output remains biased due to the massive number of pre-trained weights and parameters. This paper proposes a novel batch normalized convolutional neural network (BNCNN) model to identify COVID-19 cases from chest X-ray images in binary and multi-class frameworks with a dual aim to extract salient features that improve model performance over pre-trained image analysis networks while reducing computational complexity. The BNCNN model has three phases: Data pre-processing to normalize and resize X-ray images, Feature extraction to generate feature maps, and Classification to predict labels based on the feature maps. Feature extraction uses four repetitions of a block comprising a convolution layer to learn suitable kernel weights for the features map, a batch normalization layer to solve the internal covariance shift of feature maps, and a max-pooling layer to find the highest-level patterns by increasing the convolution span. The classifier section uses two repetitions of a block comprising a dense layer to learn complex feature maps, a batch normalization layer to standardize internal feature maps, and a dropout layer to avoid overfitting while aiding the model generalization. Comparative analysis shows that when applied to an open-access dataset, the proposed BNCNN model performs better than four other comparative pre-trained models for three-way and two-way class datasets. Moreover, the BNCNN requires fewer parameters than the pre-trained models, suggesting better deployment suitability on low-resource devices. Full article
Show Figures

Figure 1

Back to TopTop