Submit to Diagnostics Review for Diagnostics Propose a Special Issue

Journal Browser

Artificial Intelligence in Diagnostics

Special Issue Editors
Special Issue Information
Keywords
Published Papers

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: closed (20 January 2020) | Viewed by 59793

Share This Special Issue

Special Issue Editors

Prof. Dr. Emanuele Neri

E-Mail Website
Guest Editor

Department of Diagnostic and Interventional Radiology, University of Pisa, Pisa, Italy
Interests: imaging biomarkers; imaging biobanks; oncologic imaging; imaging informatics; health technology assessment

Prof. Dr. Katja Pinker-Domenig

E-Mail Website
Co-Guest Editor

Memorial Sloan Kettering Cancer Center, Department of Radiology, Breast Imaging Service, 300 E 66th St., New York, NY 10065, USA
Interests: breast cancer; breast imaging; women's health; PET/MRI; MRI; DWI; hybrid imaging; radiomics; radiogenomics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence is defined as "the capacity of machines to mimic the cognitive functions of humans”. The term was first used in 1956 at the summer workshop at Dartmouth College in Hanover, New Hampshire, organized by John McCarthy, an American computer scientist, pioneer, and inventor.

For many years, artificial intelligence remained a research box, tested in different types of human activity, including healthcare, where a narrow type of artificial intelligence, called "computer aided diagnosis (CAD)”, has been used to improve the accuracy of diagnostic tests.

More recently, with the improvement of convolutional neural networks and the evolution of machine learning toward deep learning, artificial intelligence entered into medical research and clinical practice.

The aim of this Special issue is to explore and collect the ongoing research activities and clinical application of artificial intelligence in the field of Diagnostics.

Prof. Emanuele Neri
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. 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;
deep learning;
machine learning;
convolutional neural networks;
diagnosis;
clinical decision support systems

Published Papers (11 papers)

Download All Papers

Research

Jump to: Review

11 pages, 2607 KiB

Open AccessArticle

Machine Learning Confirms Nonlinear Relationship between Severity of Peripheral Arterial Disease, Functional Limitation and Symptom Severity

by Zulfiqar Qutrio Baloch, Syed Ali Raza, Rahul Pathak, Luke Marone and Abbas Ali

Diagnostics 2020, 10(8), 515; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10080515 - 24 Jul 2020

Cited by 16 | Viewed by 2836

Abstract

Background: Peripheral arterial disease (PAD) involves arterial blockages in the body, except those serving the heart and brain. We explore the relationship of functional limitation and PAD symptoms obtained from a quality-of-life questionnaire about the severity of the disease. We used a supervised artificial intelligence-based method of data analyses known as machine learning (ML) to demonstrate a nonlinear relationship between symptoms and functional limitation amongst patients with and without PAD. Objectives: This paper will demonstrate the use of machine learning to explore the relationship between functional limitation and symptom severity to PAD severity. Methods: We performed supervised machine learning and graphical analysis, analyzing 703 patients from an administrative database with data comprising the toe–brachial index (TBI), baseline demographics and symptom score(s) derived from a modified vascular quality-of-life questionnaire, calf circumference in centimeters and a six-minute walk (distance in meters). Results: Graphical analysis upon categorizing patients into critical limb ischemia (CLI), severe PAD, moderate PAD and no PAD demonstrated a decrease in walking distance as symptoms worsened and the relationship appeared nonlinear. A supervised ML ensemble (random forest, neural network, generalized linear model) found symptom score, calf circumference (cm), age in years, and six-minute walk (distance in meters) to be important variables to predict PAD. Graphical analysis of a six-minute walk distance against each of the other variables categorized by PAD status showed nonlinear relationships. For low symptom scores, a six-minute walk test (6MWT) demonstrated high specificity for PAD. Conclusions: PAD patients with the greatest functional limitation may sometimes be asymptomatic. Patients without PAD show no relationship between functional limitation and symptoms. Machine learning allows exploration of nonlinear relationships. A simple linear model alone would have overlooked or considered such a nonlinear relationship unimportant. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

9 pages, 197 KiB

Open AccessArticle

Artificial Intelligence in Radiology—Ethical Considerations

by Adrian P. Brady and Emanuele Neri

Diagnostics 2020, 10(4), 231; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10040231 - 17 Apr 2020

Cited by 54 | Viewed by 7646

Abstract

Artificial intelligence (AI) is poised to change much about the way we practice radiology in the near future. The power of AI tools has the potential to offer substantial benefit to patients. Conversely, there are dangers inherent in the deployment of AI in radiology, if this is done without regard to possible ethical risks. Some ethical issues are obvious; others are less easily discerned, and less easily avoided. This paper explains some of the ethical difficulties of which we are presently aware, and some of the measures we may take to protect against misuse of AI. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

18 pages, 4186 KiB

Open AccessArticle

SD-UNet: Stripping down U-Net for Segmentation of Biomedical Images on Platforms with Low Computational Budgets

by Pius Kwao Gadosey, Yujian Li, Enock Adjei Agyekum, Ting Zhang, Zhaoying Liu, Peter T. Yamak and Firdaous Essaf

Diagnostics 2020, 10(2), 110; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10020110 - 18 Feb 2020

Cited by 55 | Viewed by 10236

Abstract

During image segmentation tasks in computer vision, achieving high accuracy performance while requiring fewer computations and faster inference is a big challenge. This is especially important in medical imaging tasks but one metric is usually compromised for the other. To address this problem, this paper presents an extremely fast, small and computationally effective deep neural network called Stripped-Down UNet (SD-UNet), designed for the segmentation of biomedical data on devices with limited computational resources. By making use of depthwise separable convolutions in the entire network, we design a lightweight deep convolutional neural network architecture inspired by the widely adapted U-Net model. In order to recover the expected performance degradation in the process, we introduce a weight standardization algorithm with the group normalization method. We demonstrate that SD-UNet has three major advantages including: (i) smaller model size (23x smaller than U-Net); (ii) 8x fewer parameters; and (iii) faster inference time with a computational complexity lower than 8M floating point operations (FLOPs). Experiments on the benchmark dataset of the Internatioanl Symposium on Biomedical Imaging (ISBI) challenge for segmentation of neuronal structures in electron microscopic (EM) stacks and the Medical Segmentation Decathlon (MSD) challenge brain tumor segmentation (BRATs) dataset show that the proposed model achieves comparable and sometimes better results compared to the current state-of-the-art. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

13 pages, 2261 KiB

Open AccessArticle

Assessment of Renal Osteodystrophy via Computational Analysis of Label-free Raman Detection of Multiple Biomarkers

by Marian Manciu, Mario Cardenas, Kevin E. Bennet, Avudaiappan Maran, Michael J. Yaszemski, Theresa A. Maldonado, Diana Magiricu and Felicia S. Manciu

Diagnostics 2020, 10(2), 79; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10020079 - 31 Jan 2020

Cited by 6 | Viewed by 2615

Abstract

Accurate clinical evaluation of renal osteodystrophy (ROD) is currently accomplished using invasive in vivo transiliac bone biopsy, followed by in vitro histomorphometry. In this study, we demonstrate that an alternative method for ROD assessment is through a fast, label-free Raman recording of multiple biomarkers combined with computational analysis for predicting the minimally required number of spectra for sample classification at defined accuracies. Four clinically relevant biomarkers: the mineral-to-matrix ratio, the carbonate-to-matrix ratio, phenylalanine, and calcium contents were experimentally determined and simultaneously considered as input to a linear discriminant analysis (LDA). Additionally, sample evaluation was performed with a linear support vector machine (LSVM) algorithm, with a 300 variable input. The computed probabilities based on a single spectrum were only marginally different (~80% from LDA and ~87% from LSVM), both providing an unacceptable classification power for a correct sample assignment. However, the Type I and Type II assignment errors confirm that a relatively small number of independent spectra (7 spectra for Type I and 5 spectra for Type II) is necessary for a p < 0.05 error probability. This low number of spectra supports the practicality of future in vivo Raman translation for a fast and accurate ROD detection in clinical settings. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

23 pages, 1111 KiB

Open AccessArticle

“PhysIt”—A Diagnosis and Troubleshooting Tool for Physiotherapists in Training

by Reuth Mirsky, Shay Hibah, Moshe Hadad, Ariel Gorenstein and Meir Kalech

Diagnostics 2020, 10(2), 72; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10020072 - 28 Jan 2020

Cited by 3 | Viewed by 3428

Abstract

Many physiotherapy treatments begin with a diagnosis process. The patient describes symptoms, upon which the physiotherapist decides which tests to perform until a final diagnosis is reached. The relationships between the anatomical components are too complex to keep in mind and the possible actions are abundant. A trainee physiotherapist with little experience naively applies multiple tests to reach the root cause of the symptoms, which is a highly inefficient process. This work proposes to assist students in this challenge by presenting three main contributions: (1) A compilation of the neuromuscular system as components of a system in a Model-Based Diagnosis problem; (2) The PhysIt is an AI-based tool that enables an interactive visualization and diagnosis to assist trainee physiotherapists; and (3) An empirical evaluation that comprehends performance analysis and a user study. The performance analysis is based on evaluation of simulated cases and common scenarios taken from anatomy exams. The user study evaluates the efficacy of the system to assist students in the beginning of the clinical studies. The results show that our system significantly decreases the number of candidate diagnoses, without discarding the correct diagnosis, and that students in their clinical studies find PhysIt helpful in the diagnosis process. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

15 pages, 5565 KiB

Open AccessArticle

Deep and Densely Connected Networks for Classification of Diabetic Retinopathy

by Hamza Riaz, Jisu Park, Hojong Choi, Hyunchul Kim and Jungsuk Kim

Diagnostics 2020, 10(1), 24; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics10010024 - 02 Jan 2020

Cited by 53 | Viewed by 4571

Abstract

Diabetes has recently emerged as a worldwide problem, and diabetic retinopathy is an abnormal state associated with the human retina. Due to the increase in daily screen-related activities of modern human beings, diabetic retinopathy is more prevalent among adults, leading to minor and major blindness. Doctors and clinicians are unable to perform early diagnoses due to the large number of patients. To solve this problem, this study introduces a classification model for retinal images that distinguishes between the various stages of diabetic retinopathy. This work involves deploying deep and densely connected networks for retinal image analysis with training from scratch. Dense connections between the convolutional layers of the network are an essential factor to enhance accuracy owing to the deeper supervision between layers. Another factor is the growth rate that further assists our model in learning more sophisticated feature maps regarding retinal images from every stage of the network. We compute the area under the curve, sensitivity, and specificity, particularly for messidor-2 and EyePACS. Compared to existing approaches, our method achieved better results, with an approximate rise rate of 0.01, 0.03, and 0.01, respectively. Therefore, computer-aided programs can help in diagnostic centers as automated detection systems. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

24 pages, 419 KiB

Open AccessArticle

Novel Data Mining Methodology for Healthcare Applied to a New Model to Diagnose Metabolic Syndrome without a Blood Test

by Mauricio Barrios, Miguel Jimeno, Pedro Villalba and Edgar Navarro

Diagnostics 2019, 9(4), 192; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics9040192 - 15 Nov 2019

Cited by 7 | Viewed by 3352

Abstract

Metabolic Syndrome (MetS) is a cluster of risk factors that increase the likelihood of heart disease and diabetes mellitus. It is crucial to get diagnosed with time to take preventive measures, especially for patients in locations without proper access to laboratories and medical consultations. This work presented a new methodology to diagnose diseases using data mining that documents all the phases thoroughly for further improvement of the resulting models. We used the methodology to create a new model to diagnose the syndrome without using biochemical variables. We compared similar classification models, using their reported variables and previously obtained data from a study in Colombia. We built a new model and compared it to previous models using the holdout, and random subsampling validation methods to get performance evaluation indicators between the models. Our resulting ANN model used three hidden layers and only Hip Circumference, dichotomous Waist Circumference, and dichotomous blood pressure variables. It gave an Area Under Curve (AUC) of 87.75% by the IDF and 85.12% by HMS MetS diagnosis criteria, higher than previous models. Thanks to our new methodology, diagnosis models can be thoroughly documented for appropriate future comparisons, thus benefiting the diagnosis of the studied diseases. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

21 pages, 2557 KiB

Open AccessArticle

A Machine-Learning-Based Prediction Method for Hypertension Outcomes Based on Medical Data

by Wenbing Chang, Yinglai Liu, Yiyong Xiao, Xinglong Yuan, Xingxing Xu, Siyue Zhang and Shenghan Zhou

Diagnostics 2019, 9(4), 178; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics9040178 - 07 Nov 2019

Cited by 109 | Viewed by 7736

Abstract

The outcomes of hypertension refer to the death or serious complications (such as myocardial infarction or stroke) that may occur in patients with hypertension. The outcomes of hypertension are very concerning for patients and doctors, and are ideally avoided. However, there is no satisfactory method for predicting the outcomes of hypertension. Therefore, this paper proposes a prediction method for outcomes based on physical examination indicators of hypertension patients. In this work, we divide the patients’ outcome prediction into two steps. The first step is to extract the key features from the patients’ many physical examination indicators. The second step is to use the key features extracted from the first step to predict the patients’ outcomes. To this end, we propose a model combining recursive feature elimination with a cross-validation method and classification algorithm. In the first step, we use the recursive feature elimination algorithm to rank the importance of all features, and then extract the optimal features subset using cross-validation. In the second step, we use four classification algorithms (support vector machine (SVM), C4.5 decision tree, random forest (RF), and extreme gradient boosting (XGBoost)) to accurately predict patient outcomes by using their optimal features subset. The selected model prediction performance evaluation metrics are accuracy, F1 measure, and area under receiver operating characteristic curve. The 10-fold cross-validation shows that C4.5, RF, and XGBoost can achieve very good prediction results with a small number of features, and the classifier after recursive feature elimination with cross-validation feature selection has better prediction performance. Among the four classifiers, XGBoost has the best prediction performance, and its accuracy, F1, and area under receiver operating characteristic curve (AUC) values are 94.36%, 0.875, and 0.927, respectively, using the optimal features subset. This article’s prediction of hypertension outcomes contributes to the in-depth study of hypertension complications and has strong practical significance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

16 pages, 897 KiB

Open AccessArticle

Detection of Lower Albuminuria Levels and Early Development of Diabetic Kidney Disease Using an Artificial Intelligence-Based Rule Extraction Approach

by Yoichi Hayashi

Diagnostics 2019, 9(4), 133; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics9040133 - 29 Sep 2019

Cited by 10 | Viewed by 3890

Abstract

The aim of the present study was to determine the lowest cut-off value for albuminuria levels, which can be used to detect diabetic kidney disease (DKD) using the urinary albumin-to-creatinine ratio (UACR). National Health and Nutrition Examination Survey (NHANES) data for US adults were used, and participants were classified as having diabetes or prediabetes based on a self-report and physiological measures. The study dataset comprised 942 diabetes and 524 prediabetes samples. This study clarified the significance of the lower albuminuria (UACR) levels, which can detect DKD, using an artificial intelligence-based rule extraction approach. The diagnostic rules (15 concrete rules) for both samples were extracted using a recursive-rule eXtraction (Re-RX) algorithm with continuous attributes (continuous Re-RX) to discriminate between prediabetes and diabetes datasets. Continuous Re-RX showed high test accuracy (77.56%) and a large area under the receiver operating characteristics curve (75%), which derived the two cut-off values (6.1 mg/g Cr and 71.00 mg/g Cr) for the lower albuminuria level in the UACR to detect early development of DKD. The early cut-off values for normoalbuminuria (NA) and microalbuminuria (MA) will be determined to help detect CKD and DKD, and to detect diabetes before MA develop and to prevent diabetic complications. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

Review

Jump to: Research

14 pages, 435 KiB

Open AccessReview

The Performance of Deep Learning Algorithms on Automatic Pulmonary Nodule Detection and Classification Tested on Different Datasets That Are Not Derived from LIDC-IDRI: A Systematic Review

by Dana Li, Bolette Mikela Vilmun, Jonathan Frederik Carlsen, Elisabeth Albrecht-Beste, Carsten Ammitzbøl Lauridsen, Michael Bachmann Nielsen and Kristoffer Lindskov Hansen

Diagnostics 2019, 9(4), 207; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics9040207 - 29 Nov 2019

Cited by 43 | Viewed by 5828

Abstract

The aim of this study was to systematically review the performance of deep learning technology in detecting and classifying pulmonary nodules on computed tomography (CT) scans that were not from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) database. Furthermore, we explored the difference in performance when the deep learning technology was applied to test datasets different from the training datasets. Only peer-reviewed, original research articles utilizing deep learning technology were included in this study, and only results from testing on datasets other than the LIDC-IDRI were included. We searched a total of six databases: EMBASE, PubMed, Cochrane Library, the Institute of Electrical and Electronics Engineers, Inc. (IEEE), Scopus, and Web of Science. This resulted in 1782 studies after duplicates were removed, and a total of 26 studies were included in this systematic review. Three studies explored the performance of pulmonary nodule detection only, 16 studies explored the performance of pulmonary nodule classification only, and 7 studies had reports of both pulmonary nodule detection and classification. Three different deep learning architectures were mentioned amongst the included studies: convolutional neural network (CNN), massive training artificial neural network (MTANN), and deep stacked denoising autoencoder extreme learning machine (SDAE-ELM). The studies reached a classification accuracy between 68–99.6% and a detection accuracy between 80.6–94%. Performance of deep learning technology in studies using different test and training datasets was comparable to studies using same type of test and training datasets. In conclusion, deep learning was able to achieve high levels of accuracy, sensitivity, and/or specificity in detecting and/or classifying nodules when applied to pulmonary CT scans not from the LIDC-IDRI database. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

8 pages, 211 KiB

Open AccessReview

Application of Artificial Intelligence in the Detection and Differentiation of Colon Polyps: A Technical Review for Physicians

by Wei-Lun Chao, Hanisha Manickavasagan and Somashekar G. Krishna

Diagnostics 2019, 9(3), 99; https://0-doi-org.brum.beds.ac.uk/10.3390/diagnostics9030099 - 20 Aug 2019

Cited by 26 | Viewed by 4786

Abstract

Research in computer-aided diagnosis (CAD) and the application of artificial intelligence (AI) in the endoscopic evaluation of the gastrointestinal tract is novel. Since colonoscopy and detection of polyps can decrease the risk of colon cancer, it is recommended by multiple national and international societies. However, the procedure of colonoscopy is performed by humans where there are significant interoperator and interpatient variations, and hence, the risk of missing detection of adenomatous polyps. Early studies involving CAD and AI for the detection and differentiation of polyps show great promise. In this appraisal, we review existing scientific aspects of AI in CAD of colon polyps and discuss the pitfalls and future directions for advancing the science. This review addresses the technical intricacies in a manner that physicians can comprehend to promote a better understanding of this novel application. Full article

(This article belongs to the Special Issue Artificial Intelligence in Diagnostics)

Journal Menu

Journal Browser

Artificial Intelligence in Diagnostics

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (11 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI