1
|
Baffa MDFO, Zezell DM, Bachmann L, Pereira TM, Deserno TM, Felipe JC. Deep neural networks can differentiate thyroid pathologies on infrared hyperspectral images. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 247:108100. [PMID: 38442622 DOI: 10.1016/j.cmpb.2024.108100] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Revised: 02/12/2024] [Accepted: 02/23/2024] [Indexed: 03/07/2024]
Abstract
BACKGROUND AND OBJECTIVE The thyroid is a gland responsible for producing important body hormones. Several pathologies can affect this gland, such as thyroiditis, hypothyroidism, and thyroid cancer. The visual histological analysis of thyroid specimens is a valuable process that enables pathologists to detect diseases with high efficiency, providing the patient with a better prognosis. Existing computer vision systems developed to aid in the analysis of histological samples have limitations in distinguishing pathologies with similar characteristics or samples containing multiple diseases. To overcome this challenge, hyperspectral images are being studied to represent biological samples based on their molecular interaction with light. METHODS In this study, we address the acquisition of infrared absorbance spectra from each voxel of histological specimens. This data is then used for the development of a multiclass fully-connected neural network model that discriminates spectral patterns, enabling the classification of voxels as healthy, cancerous, or goiter. RESULTS Through experiments using the k-fold cross-validation protocol, we obtained an average accuracy of 93.66 %, a sensitivity of 93.47 %, and a specificity of 96.93 %. Our results demonstrate the feasibility of using infrared hyperspectral imaging to characterize healthy tissue and thyroid pathologies using absorbance measurements. The proposed deep learning model has the potential to improve diagnostic efficiency and enhance patient outcomes.
Collapse
Affiliation(s)
| | | | - Luciano Bachmann
- Department of Physics, University of São Paulo, Ribeirão Preto, SP, Brazil
| | - Thiago Martini Pereira
- Department of Science and Technology, Federal University of São Paulo, São José dos Campos, SP, Brazil
| | - Thomas Martin Deserno
- Peter L. Reichertz Institute for Medical Informatics, Technische Universität Braunschweig, Braunschweig, Germany
| | - Joaquim Cezar Felipe
- Department of Computing and Mathematics, University of São Paulo, Ribeirão Preto, SP, Brazil
| |
Collapse
|
2
|
Contributions of vibrational spectroscopy to virology: A review. CLINICAL SPECTROSCOPY 2022; 4:100022. [PMCID: PMC9093054 DOI: 10.1016/j.clispe.2022.100022] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 04/30/2022] [Accepted: 05/04/2022] [Indexed: 06/17/2023]
Abstract
Vibrational spectroscopic techniques, both infrared absorption and Raman scattering, are high precision, label free analytical techniques which have found applications in fields as diverse as analytical chemistry, pharmacology, forensics and archeometrics and, in recent times, have attracted increasing attention for biomedical applications. As analytical techniques, they have been applied to the characterisation of viruses as early as the 1970 s, and, in the context of the coronavirus disease 2019 (COVID-19) pandemic, have been explored in response to the World Health Organisation as novel methodologies to aid in the global efforts to implement and improve rapid screening of viral infection. This review considers the history of the application of vibrational spectroscopic techniques to the characterisation of the morphology and chemical compositions of viruses, their attachment to, uptake by and replication in cells, and their potential for the detection of viruses in population screening, and in infection response monitoring applications. Particular consideration is devoted to recent efforts in the detection of severe acute respiratory syndrome coronavirus 2, and monitoring COVID-19.
Collapse
|
3
|
Calvo-Gomez O, Calvo H, Cedillo-Barrón L, Vivanco-Cid H, Alvarado-Orozco JM, Fernandez-Benavides DA, Arriaga-Pizano L, Ferat-Osorio E, Anda-Garay JC, López-Macias C, López MG. Potential of ATR-FTIR-Chemometrics in Covid-19: Disease Recognition. ACS OMEGA 2022; 7:30756-30767. [PMID: 36092630 PMCID: PMC9453986 DOI: 10.1021/acsomega.2c01374] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
The COVID-19 pandemic has caused major disturbances to human health and economy on a global scale. Although vaccination campaigns and important advances in treatments have been developed, an early diagnosis is still crucial. While PCR is the golden standard for diagnosing SARS-CoV-2 infection, rapid and low-cost techniques such as ATR-FTIR followed by multivariate analyses, where dimensions are reduced for obtaining valuable information from highly complex data sets, have been investigated. Most dimensionality reduction techniques attempt to discriminate and create new combinations of attributes prior to the classification stage; thus, the user needs to optimize a wealth of parameters before reaching reliable and valid outcomes. In this work, we developed a method for evaluating SARS-CoV-2 infection and COVID-19 disease severity on infrared spectra of sera, based on a rather simple feature selection technique (correlation-based feature subset selection). Dengue infection was also evaluated for assessing whether selectivity toward a different virus was possible with the same algorithm, although independent models were built for both viruses. High sensitivity (94.55%) and high specificity (98.44%) were obtained for assessing SARS-CoV-2 infection with our model; for severe COVID-19 disease classification, sensitivity is 70.97% and specificity is 94.95%; for mild disease classification, sensitivity is 33.33% and specificity is 94.64%; and for dengue infection assessment, sensitivity is 84.27% and specificity is 94.64%.
Collapse
Affiliation(s)
- Octavio Calvo-Gomez
- Centro
de Investigación y de Estudios Avanzados del IPN, Km. 9.6 Libramiento Norte Carretera
Irapuato León, 36824 Irapuato, Guanajuato, Mexico
| | - Hiram Calvo
- Center
for Computing Research, Instituto Politécnico
Nacional, 07738 Mexico City, Mexico
| | - Leticia Cedillo-Barrón
- Centro
de Investigación y de Estudios Avanzados del IPN. Avenida IPN #2508, Col. San Pedro
Zacatenco, CP 07360 Mexico, Distrito Federal, Mexico
| | - Héctor Vivanco-Cid
- Laboratorio
Multidisciplinario en Ciencias Biomédicas, Instituto de Investigaciones
Médico-Biológicas, Universidad
Veracruzana, 91000Veracruz, Mexico
| | - Juan Manuel Alvarado-Orozco
- Centro
de Ingeniería y Desarrollo Industrial, Avenida Playa Pie de la Cuesta No.
702, Desarrollo San Pablo, 76125 Santiago de Querétaro, Mexico
| | - David Andrés Fernandez-Benavides
- Centro
de Ingeniería y Desarrollo Industrial, Avenida Playa Pie de la Cuesta No.
702, Desarrollo San Pablo, 76125 Santiago de Querétaro, Mexico
| | - Lourdes Arriaga-Pizano
- Unidad
de
Investigación Médica en Inmunoquímica, UMAE,
Hospital de Especialidades del Centro Médico Nacional Siglo
XXI. Instituto Mexicano del Seguro Social
(IMSS), 06600 Mexico City, Mexico
| | - Eduardo Ferat-Osorio
- Unidad
de
Investigación Médica en Inmunoquímica, UMAE,
Hospital de Especialidades del Centro Médico Nacional Siglo
XXI. Instituto Mexicano del Seguro Social
(IMSS), 06600 Mexico City, Mexico
| | - Juan Carlos Anda-Garay
- Unidad
de
Investigación Médica en Inmunoquímica, UMAE,
Hospital de Especialidades del Centro Médico Nacional Siglo
XXI. Instituto Mexicano del Seguro Social
(IMSS), 06600 Mexico City, Mexico
| | - Constantino López-Macias
- Unidad
de
Investigación Médica en Inmunoquímica, UMAE,
Hospital de Especialidades del Centro Médico Nacional Siglo
XXI. Instituto Mexicano del Seguro Social
(IMSS), 06600 Mexico City, Mexico
| | - Mercedes G. López
- Centro
de Investigación y de Estudios Avanzados del IPN, Km. 9.6 Libramiento Norte Carretera
Irapuato León, 36824 Irapuato, Guanajuato, Mexico
| |
Collapse
|