RESUMO
BACKGROUND: Colon capsule endoscopy (CCE) is a minimally invasive alternative for patients unwilling to undergo conventional colonoscopy, or for whom the latter exam is contraindicated. This is particularly important in the setting of colorectal cancer screening. Nevertheless, these exams produce large numbers of images, and reading them is a monotonous and time-consuming task, with the risk of overlooking important lesions. The development of automated tools based on artificial intelligence (AI) technology may improve some of the drawbacks of this diagnostic instrument. METHODS: A database of CCE images was used for development of a Convolutional Neural Network (CNN) model. This database included anonymized images of patients with protruding lesions in the colon or patients with normal colonic mucosa or with other pathologic findings. A total of 3,387,259 frames from 24 CCE exams were retrospectively reviewed. For CNN development, 3640 images (860 protruding lesions and 2780 with normal mucosa or other findings) were ultimately extracted. Training and validation datasets were constructed for the development and testing of the CNN. RESULTS: The CNN detected protruding lesions with a sensitivity, specificity, positive and negative predictive values of 90.7, 92.6, 79.2 and 96.9%, respectively. The area under the receiver operating characteristic curve for detection of protruding lesions was 0.97. CONCLUSIONS: The deep learning algorithm we developed is capable of accurately detecting protruding lesions. The application of AI technology to CCE may increase its diagnostic accuracy and acceptance for screening of colorectal neoplasia.
Assuntos
Endoscopia por Cápsula , Neoplasias Colorretais , Inteligência Artificial , Colo/diagnóstico por imagem , Colonoscopia , Neoplasias Colorretais/diagnóstico por imagem , Humanos , Estudos RetrospectivosRESUMO
The purpose of this study was to determine the influence of different levels of regular physical exercise on the frequency of urinary incontinence in young nulliparous women from the northern region of Portugal. Participants (n=386) self-reported demographic variables, frequency, and time spent practicing organized exercise per week, as well as completed the International Consultation on Incontinence Questionnaire-Short Form. The level of exercise was calculated based on the time (in minutes) usually spent per week in organized exercise. 19.9% of Portuguese nulliparous women reported incontinence symptoms. Considering the distribution of urinary incontinence among the different quartiles of organized exercise, women from the 4(th)quartile (those who train for competitive purposes) demonstrated highest relative frequency (p=0.000) and a 2.53 greater relative risk to develop (95% CIs,1.3-2.7) incontinence compared to women from the 1(st) quartile (inactive). Women who practice exercise for recreational purposes (2(nd) and 3(rd) quartiles) did not show significant differences in the urinary incontinence prevalence and relative risk of developing it compared to women from the 1(st) quartile. The results showed that women participating in organized exercise involving high volume training for competition are potentially at risk of developing urinary incontinence, although organized exercise undertaken without the intent to compete seems to be safe for maintaining urinary continence.
Assuntos
Exercício Físico/fisiologia , Incontinência Urinária/epidemiologia , Adolescente , Adulto , Índice de Massa Corporal , Comportamento Competitivo/fisiologia , Estudos Transversais , Feminino , Humanos , Paridade , Educação Física e Treinamento , Portugal/epidemiologia , Prevalência , Fatores de Risco , Inquéritos e Questionários , Incontinência Urinária/etiologia , Adulto JovemRESUMO
The interest in computer modelling of biomechanical systems, mainly by using the finite element method (FEM), has been increasing, in particular for analysis of the mechanical behaviour of the human ear. In this work, a finite element model of the middle ear was developed to study the dynamic structural response to harmonic vibrations for distinct sound pressure levels applied on the eardrum. The model includes different ligaments and muscle tendons with elastic and hyperelastic behaviour for these supportive structures. Additionally, the nonlinear behaviour of the ligaments and muscle tendons was investigated, as they are the connection between ossicles by contact formulation. Harmonic responses of the umbo and stapes footplate displacements, between 100 Hz and 10 kHz, were obtained and compared with previously published work. The stress state of ligaments (superior, lateral, and anterior of malleus and superior and posterior of incus) was analysed, with the focus on balance of the supportive structures of the middle ear, as ligaments make the link between the ossicular chain and the walls of the tympanic cavity. The results obtained in this work highlight the importance of using hyperelastic models to simulate the mechanical behaviour for the ligaments and tendons.
Assuntos
Orelha Média/fisiologia , Ligamentos/fisiologia , Modelos Biológicos , Idoso , Fenômenos Biomecânicos , Engenharia Biomédica , Simulação por Computador , Orelha Média/anatomia & histologia , Análise de Elementos Finitos , Humanos , Imageamento Tridimensional , Modelos Anatômicos , VibraçãoRESUMO
The present study aims to compare spinal stability after two different minimally invasive techniques, the lateral lumbar interbody fusion (LLIF) and the transforaminal lumbar interbody fusion (TLIF) approaches. Two nonlinear three-dimensional finite element (FE) models of the L4-L5 functional spinal unit (FSU) were subjected to the loads that usually act on the lumbar spine. Findings show that the LLIF approach yields better results for torsion load case, due to the larger surface area of the implant. For extension, flexion and lateral bending loads, the TLIF approach presents smaller displacements probably due to the anterior placement of the cage and to the smaller damaged area of the annulus fibrosus.
Assuntos
Simulação por Computador , Vértebras Lombares/cirurgia , Procedimentos Cirúrgicos Minimamente Invasivos , Análise Numérica Assistida por Computador , Fusão Vertebral , Fenômenos Biomecânicos , Osso Esponjoso/cirurgia , Osso Cortical/cirurgia , Humanos , Modelos Teóricos , Próteses e Implantes , Reprodutibilidade dos Testes , Rotação , Estresse MecânicoRESUMO
This paper presents a finite element analysis to investigate the biomechanical changes caused by transforaminal (TLIF) and anterior lumbar interbody fusion (ALIF) at the L5-S1 level, applying two different implants: T_PAL (TLIF) and SynFix (ALIF). The main objective is to determine which one is more stable for patients. Numerical simulations of segmental motion show that, in the early postoperative phase, displacements and rotation angles obtained in ALIF are greater than the corresponding ones obtained in TLIF, as well as the principal stress values on the ligaments. So, TLIF performed with T_PAL is more stable than ALIF, especially during the recovery phase.