Analysis of Static and Dynamic Infrared Images for Thyroid Nodules Investigation

González, José Ramón García; Conci, Aura; Morán, Maira Beatriz Hernández; Araujo, Adriel S.; Paes, Aline; Ch., Damiao; Fiirst, W. G.

doi:10.1109/aiccsa47632.2019.9035300

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This protocol is used to perform the infrared neck examinations of volunteers with benign and malign thyroid nodules on follow up by the medical doctors of our research group [30]. Even following this protocol for all patients, the analysis of preliminary thermographies ([31–33]) showed to be insufficient to promote a differentiate nodule diagnosis. These results could be related to the influence of more factors than those previously considered [29].…”

Section: Introductionmentioning

confidence: 99%

A computational study on the role of parameters for identification of thyroid nodules by infrared images (and its comparison with real data)

Montero

Damiao

Moran

et al. 2021

Preprint

View full text Add to dashboard Cite

According to experts and medical literature, a healthy thyroid gland, or a thyroid containing benign nodules, tend to be less inflamed and less active than one with malignant nodules. It seems to be a consensus that malignant nodules have more blood veins and it may be related to the maintenance of high and constant temperatures. Investigation of these characteristics, detectable by infrared sensors, and answering if they constitute patterns of malignancy are the aims of this work. Experiments considering biological heat transfer analysis by Finite Element numerical simulations are used to show the influence of nodule and patient characteristics on the identification of malignancy of thyroid nodule by thermography. The used and approved protocol for infrared examination are analyzed and simulated during all its phase that is on transient and steady state behavior, in order to verify how and when their influence can be really recognized in patients. Simulation results and the analysis of infrared exams show that the tissues between the skin and the thyroid, as well as the nodule size, have influence in superficial temperatures. Other thermal parameters of thyroid nodules are also investigated and show little influence on surface temperatures. These characteristics must be considered in nodular infrared analysis and diagnosis by thermography. The infrared examinations of patients that meet the hypotheses related to the vascularization of the nodule confirm the numerical results. All details of the physical parameters used in the simulations, characteristics of the nodules, and their complete thermal examinations are public and available, turning possible that the presented simulation could be compared with other types of heat transfer solutions. This study is a concrete contribution to the answer of under what conditions thermography can be useful in the identification of thyroid nodules.Author summaryThyroid nodules are very common health problems. These nodules may have different characteristics, and some of them could influence the temperature of the region. Many works in the medical literature report that the healthy thyroid and even benign nodules tend to be less inflamed and active than malignant nodules and therefore should exhibit some variation in patterns of behavior related to the temperature variation between them. The focus of this work is to analyze some parameters of the nodules and details of the patients that can influence the identification and diagnosis of thyroid nodules by infrared images. To reach the objective, simulations of bioheat transfer in the neck (using a simple neck geometry and Finite Elements Analysis in COMSOL Multiphysics Software) and real infrared examinations (performed with a FLIR Infrared Camera model SC620 and a proposed protocol) were analyzed. Our results show the thermal insulation effect of the neck fat tissue, and that the effect of nodule sizes can be decremented by a thicker layer of fat. The analysis of the nodule parameters as blood perfusion rate and metabolic heat, which could be related with the nodule vascularization (an important condition related with malignancy), suggest that the thermal effects of thyroid nodules on the neck surface are not sufficient to differentiate benign from malign, and for this other features or methods must be considered.

show abstract

Section: Introductionmentioning

confidence: 99%

A computational study on the role of parameters for identification of thyroid nodules by infrared images (and its comparison with real data)

Montero

Damiao

Moran

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Figure 1 shows how this imaging is done, with a person in front of the camera and the sequence of images stored for each person. The work here presented is motivated by the fact that even following this protocol for all patients, the analysis of ours previous works using IRT [ 33 , 34 , 35 ] showed insufficient evidences to promote a differentiated diagnosis of the nodules. These results could be related to the influence of more factors than those previously considered [ 31 ] indicating the importance of better analysis of the problem and the here proposed simulation of patient characteristic in numerical analysis.…”

Section: Introductionmentioning

confidence: 99%

A Computational Study on the Role of Parameters for Identification of Thyroid Nodules by Infrared Images (and Comparison with Real Data)

González

Damião

Morán

et al. 2021

Sensors

View full text Add to dashboard Cite

According to experts and medical literature, healthy thyroids and thyroids containing benign nodules tend to be less inflamed and less active than those with malignant nodules. It seems to be a consensus that malignant nodules have more blood veins and more blood circulation. This may be related to the maintenance of the nodule’s heat at a higher level compared with neighboring tissues. If the internal heat modifies the skin radiation, then it could be detected by infrared sensors. The goal of this work is the investigation of the factors that allow this detection, and the possible relation with any pattern referent to nodule malignancy. We aim to consider a wide range of factors, so a great number of numerical simulations of the heat transfer in the region under analysis, based on the Finite Element method, are performed to study the influence of each nodule and patient characteristics on the infrared sensor acquisition. To do so, the protocol for infrared thyroid examination used in our university’s hospital is simulated in the numerical study. This protocol presents two phases. In the first one, the body under observation is in steady state. In the second one, it is submitted to thermal stress (transient state). Both are simulated in order to verify if it is possible (by infrared sensors) to identify different behavior referent to malignant nodules. Moreover, when the simulation indicates possible important aspects, patients with and without similar characteristics are examined to confirm such influences. The results show that the tissues between skin and thyroid, as well as the nodule size, have an influence on superficial temperatures. Other thermal parameters of thyroid nodules show little influence on surface infrared emissions, for instance, those related to the vascularization of the nodule. All details of the physical parameters used in the simulations, characteristics of the real nodules and thermal examinations are publicly available, allowing these simulations to be compared with other types of heat transfer solutions and infrared examination protocols. Among the main contributions of this work, we highlight the simulation of the possible range of parameters, and definition of the simulation approach for mapping the used infrared protocol, promoting the investigation of a possible relation between the heat transfer process and the data obtained by infrared acquisitions.

show abstract

“…Logo, se alguma região de nódulo for descartada no processo de geração da imagem de entrada da rede, o resultado final será afetado. González et al (2019) investigaram duas técnicas de análise de nódulos tireoidianos em imagens térmicas. São elas: o uso de umaúnica imagem do exame, verificando se existe um limiar de temperatura que diferencia os nódulos de regiões saudáveis do pescoço; e o uso de séries de temperatura, analisando o comportamento do nódulo ao longo do tempo.…”

Section: Introductionunclassified

Detecção de Nódulos da Tireoide em Exames de Termografia utilizando Redes Neurais Convolucionais em Cascata

Júnior

Silva

et al. 2021

Anais Do XXI Simpósio Brasileiro De Computação Aplicada À Saúde (SBCAS 2021)

View full text Add to dashboard Cite

Os exames de termograﬁa podem ser utilizados como um meio não invasivo para a detecção de doenças através da análise de imagens térmicas do corpo humano. O presente trabalho apresenta um método para detectar nódulos da glândula tireoide em imagens térmicas utilizando duas Redes Neurais Convolucionais (CNN's) em cascata. A primeira CNN atua na geração de candidatos a nódulo, e a segunda faz o reﬁnamento da detecção, eliminando falsos positivos. Os experimentos foram realizados com imagens térmicas de 20 pacientes. O resultado ﬁnal atinge 97% de acurácia, 95% de sensibilidade e 80% de f1-score utilizando duas CNN's AlexNet.

show abstract

Analysis of Static and Dynamic Infrared Images for Thyroid Nodules Investigation

Cited by 6 publications

References 12 publications

A computational study on the role of parameters for identification of thyroid nodules by infrared images (and its comparison with real data)

A computational study on the role of parameters for identification of thyroid nodules by infrared images (and its comparison with real data)

A Computational Study on the Role of Parameters for Identification of Thyroid Nodules by Infrared Images (and Comparison with Real Data)

Detecção de Nódulos da Tireoide em Exames de Termografia utilizando Redes Neurais Convolucionais em Cascata

Contact Info

Product

Resources

About