1
|
Valeri F, Bartolucci M, Cantoni E, Carpi R, Cisbani E, Cupparo I, Doria S, Gori C, Grigioni M, Lasagni L, Marconi A, Mazzoni LN, Miele V, Pradella S, Risaliti G, Sanguineti V, Sona D, Vannucchi L, Taddeucci A. UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images. J Med Imaging (Bellingham) 2023; 10:S11904. [PMID: 36895439 PMCID: PMC9989681 DOI: 10.1117/1.jmi.10.s1.s11904] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2022] [Accepted: 02/09/2023] [Indexed: 03/09/2023] Open
Abstract
Purpose The aim of this work is the development and characterization of a model observer (MO) based on convolutional neural networks (CNNs), trained to mimic human observers in image evaluation in terms of detection and localization of low-contrast objects in CT scans acquired on a reference phantom. The final goal is automatic image quality evaluation and CT protocol optimization to fulfill the ALARA principle. Approach Preliminary work was carried out to collect localization confidence ratings of human observers for signal presence/absence from a dataset of 30,000 CT images acquired on a PolyMethyl MethAcrylate phantom containing inserts filled with iodinated contrast media at different concentrations. The collected data were used to generate the labels for the training of the artificial neural networks. We developed and compared two CNN architectures based respectively on Unet and MobileNetV2, specifically adapted to achieve the double tasks of classification and localization. The CNN evaluation was performed by computing the area under localization-ROC curve (LAUC) and accuracy metrics on the test dataset. Results The mean of absolute percentage error between the LAUC of the human observer and MO was found to be below 5% for the most significative test data subsets. An elevated inter-rater agreement was achieved in terms of S-statistics and other common statistical indices. Conclusions Very good agreement was measured between the human observer and MO, as well as between the performance of the two algorithms. Therefore, this work is highly supportive of the feasibility of employing CNN-MO combined with a specifically designed phantom for CT protocol optimization programs.
Collapse
Affiliation(s)
- Federico Valeri
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy.,Università degli Studi di Firenze, Scuola di Scienze della Salute Umana, Florence, Italy
| | - Maurizio Bartolucci
- Ospedale S. Stefano, Azienda USL Toscana Centro, SOC Radiodiagnostica, Prato, Italy
| | - Elena Cantoni
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy
| | - Roberto Carpi
- Ospedale Santa Maria Nuova, Azienda USL Toscana Centro, SOC Radiologia, Florence, Italy
| | - Evaristo Cisbani
- Istituto Superiore di Sanità, Centro Nazionale Tecnologie Innvative in Sanità Pubblica, Rome, Italy
| | - Ilaria Cupparo
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy.,Università degli Studi di Firenze, Scuola di Scienze della Salute Umana, Florence, Italy
| | - Sandra Doria
- Istituto di Chimica dei Composti OrganoMetallici, Consiglio Nazionale delle Ricerche, Florence, Italy.,Università degli Studi di Firenze, European Laboratory for Nonlinear Spectroscopy, Florence, Italy
| | - Cesare Gori
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy
| | - Mauro Grigioni
- Istituto Superiore di Sanità, Centro Nazionale Tecnologie Innvative in Sanità Pubblica, Rome, Italy
| | - Lorenzo Lasagni
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy.,Università degli Studi di Firenze, Scuola di Scienze della Salute Umana, Florence, Italy
| | - Alessandro Marconi
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy
| | - Lorenzo Nicola Mazzoni
- Ospedale San Jacopo, Azienda USL Toscana Centro, UO Fisica Sanitaria Prato e Pistoia, Pistoia, Italy
| | - Vittorio Miele
- Azienda Ospedaliero-Universitaria Careggi, SOD Radiodiagnostica di Emergenza-Urgenza, Florence, Italy
| | - Silvia Pradella
- Azienda Ospedaliero-Universitaria Careggi, SOD Radiodiagnostica di Emergenza-Urgenza, Florence, Italy
| | - Guido Risaliti
- Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, Florence, Italy
| | - Valentina Sanguineti
- Istituto Italiano di Tecnologia, Pattern Analysis & Computer Vision, Genoa, Italy
| | - Diego Sona
- Fondazione Bruno Kessler, Data Science for Health Unit, Trento, Italy
| | - Letizia Vannucchi
- Ospedale S. Jacopo, AUSL Toscana Centro, SOC Radiodiagnostica, Pistoia, Italy
| | - Adriana Taddeucci
- Azienda Ospedaliero-Universitaria Careggi, UO Fisica Sanitaria, Florence, Italy.,Istituto Nazionale di Fisica Nucleare - Sezione di Firenze, Sesto Fiorentino, Italy
| |
Collapse
|
2
|
Gomes R, Kamrowski C, Langlois J, Rozario P, Dircks I, Grottodden K, Martinez M, Tee WZ, Sargeant K, LaFleur C, Haley M. A Comprehensive Review of Machine Learning Used to Combat COVID-19. Diagnostics (Basel) 2022; 12:diagnostics12081853. [PMID: 36010204 PMCID: PMC9406981 DOI: 10.3390/diagnostics12081853] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Revised: 07/22/2022] [Accepted: 07/26/2022] [Indexed: 12/19/2022] Open
Abstract
Coronavirus disease (COVID-19) has had a significant impact on global health since the start of the pandemic in 2019. As of June 2022, over 539 million cases have been confirmed worldwide with over 6.3 million deaths as a result. Artificial Intelligence (AI) solutions such as machine learning and deep learning have played a major part in this pandemic for the diagnosis and treatment of COVID-19. In this research, we review these modern tools deployed to solve a variety of complex problems. We explore research that focused on analyzing medical images using AI models for identification, classification, and tissue segmentation of the disease. We also explore prognostic models that were developed to predict health outcomes and optimize the allocation of scarce medical resources. Longitudinal studies were conducted to better understand COVID-19 and its effects on patients over a period of time. This comprehensive review of the different AI methods and modeling efforts will shed light on the role that AI has played and what path it intends to take in the fight against COVID-19.
Collapse
Affiliation(s)
- Rahul Gomes
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
- Correspondence:
| | - Connor Kamrowski
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Jordan Langlois
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Papia Rozario
- Department of Geography and Anthropology, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA;
| | - Ian Dircks
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Keegan Grottodden
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Matthew Martinez
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Wei Zhong Tee
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Kyle Sargeant
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Corbin LaFleur
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| | - Mitchell Haley
- Department of Computer Science, University of Wisconsin-Eau Claire, Eau Claire, WI 54701, USA; (C.K.); (J.L.); (I.D.); (K.G.); (M.M.); (W.Z.T.); (K.S.); (C.L.); (M.H.)
| |
Collapse
|
3
|
A New Approach to COVID-19 Detection: An ANN Proposal Optimized through Tree-Seed Algorithm. Symmetry (Basel) 2022. [DOI: 10.3390/sym14071310] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023] Open
Abstract
Coronavirus disease (COVID-19), which affects the whole world, continues to spread. This disease has infected and killed millions of people worldwide. To limit the rate of spread of the disease, early detection should be provided and then the infected person should be quarantined. This paper proposes a Deep Learning-based application for early and accurate diagnosis of COVID-19. Compared to other studies, this application’s biggest difference and contribution are that it uses Tree Seed Algorithm (TSA)-optimized Artificial Neural Networks (ANN) to classify deep architectural features. Previous studies generally use fully connected layers for end-to-end learning classification. However, this study proves that even relatively simple AlexNet features can be classified more accurately with the TSA-ANN structure. The proposed hybrid model provides diagnosis with 98.54% accuracy for COVID-19 disease, which shows asymmetric distribution on Computed Tomography (CT) images. As a result, it is shown that using the proposed classification strategy, the features of end-to-end architectures can be classified more accurately.
Collapse
|