Technology and Health Care - Volume 30, issue 1

Authors: Liu, Mingzhu | Lv, Weifu | Yin, Baocai | Ge, Yaqiong | Wei, Wei

Article Type: Research Article

Abstract: BACKGROUND: Chest computed tomography (CT) plays an important role in the diagnosis and assessment of coronavirus disease 2019 (COVID-19). OBJECTIVE: To evaluate the value of an artificial intelligence (AI) scoring system for radiologically assessing the severity of COVID-19. MATERIALS AND METHODS: Chest CT images of 81 patients (61 of normal type and 20 of severe type) with confirmed COVID-19 were used. The test data were anonymized. The scores achieved by four methods (junior radiologists; AI scoring system; human-AI segmentation system; human-AI scoring system) were compared with that by two experienced radiologists (reference score). …The mean absolute errors (MAEs) between the four methods and experienced radiologists were calculated separately. The Wilcoxon test is used to predict the significance of the severity of COVID-19. Then use Spearman correlation analysis ROC analysis was used to evaluate the performance of different scores. RESULTS: The AI score had a relatively low MAE (1.67–2.21). Score of human-AI scoring system had the lowest MAE (1.67), a diagnostic value almost equal to reference score (r = 0.97), and a strongest correlation with clinical severity (r = 0.59, p < 0.001). The AUCs of reference score, score of junior radiologists, AI score, score of human-AI segmentation system, and score of human-AI scoring system were 0.874, 0.841, 0.852, 0.857 and 0.865, respectively. CONCLUSION: The human-AI scoring system can help radiologists to improve the accuracy of COVID-19 severity assessment. Show more

Keywords: COVID-19, chest CT, severity assessment, artificial intelligence

DOI: 10.3233/THC-213199

Citation: Technology and Health Care, vol. 30, no. 1, pp. 1-10, 2022

Authors: Shao, Qi | Liu, Ning | Li, Guo-Fu | Meng, Qian-Cheng | Yao, Jia-Hao | Wang, Ning

Article Type: Research Article

Abstract: BACKGROUND: IL-18 is known as an interferon-inducing factor that belongs to the IL-1 family, and is synthesized as an inactive precursor protein. OBJECTIVE: The present study aims to investigate the expression of IL-18, IL-18R, R and IL-18 binding protein (BP) mRNA in various types of human pituitary tumors, such as adrenocorticotropic hormone (ACTH), growth hormone (GH), prolactin (PRL), thyroid stimulating hormone (TSH)-producing adenomas and non-function adenomas. METHODS: Pituitary adenoma tissues were obtained during the surgery of 41 patients: nine patients had ACTH-producing pituitary adenomas, nine patients had GH-producing pituitary adenomas, five patients had TSH-producing pituitary …adenomas, seven patients had PRL-producing pituitary adenomas, and 11 patients had non-functioning adenomas. The mRNA expression levels of IL-18, IL-18BP, IL-18R and IL-18R were quantified using real-time quantitative PCR. RESULTS: The mRNA expression of IL-18 was significantly higher in ACTH-, GH- and PRL-producing adenomas, when compared to non-function tumors. Similarly, a significantly higher mRNA expression of IL-18BP and IL-18R was observed in ACTH-, GH- and PRL-producing adenomas, when compared with non-functional adenomas. In contrast, no upregulation of IL-18R mRNA was observed in any of the pituitary adenomas. CONCLUSIONS: The mRNA levels of IL-18, IL-18BP and IL-18R are significantly elevated in clinical pituitary tumors, such as ACTH-, GH- and PRL-producing adenomas, when compared to non-functional adenomas. These present results suggest the possibility that IL-18 may be involved in the pathogenesis of pituitary adenoma. Show more

Keywords: Interleukin-18, Human pituitary adenoma, Interleukin-18 receptor, gene expression, hormone

DOI: 10.3233/THC-191967

Citation: Technology and Health Care, vol. 30, no. 1, pp. 11-16, 2022

Authors: Savarraj, Jude P.J. | Kitagawa, Ryan | Kim, Dong H. | Choi, Huimahn A.

Article Type: Research Article

Abstract: BACKGROUND: Early diagnosis of Alzheimer’s disease (AD) remains challenging. It is speculated that structural atrophy in white matter tracts commences prior to the onset of AD symptoms. OBJECTIVE: We hypothesize that disruptions in white matter tract connectivity precedes the onset of AD symptoms and these disruptions could be leveraged for early prediction of AD. METHODS: Diffusion tensor images (DTI) from 52 subjects with mild cognitive impairment (MCI) were selected. Subjects were dichotomized into two age and gender matched groups; the MCI-AD group (22 subjects who progressed to develop AD) and the MCI-control group …(who did not develop AD). DTI images were anatomically parcellated into 90 distinct regions ROIs followed by tractography methods to obtain different biophysical networks. Features extracted from these networks were used to train predictive algorithms with the objective of discriminating the MCI-AD and MCI-control groups. Model performance and best features are reported. RESULTS: Up to 80% prediction accuracy was achieved using a combination of features from the ‘right anterior cingulum’ and ‘right frontal superior medial’. Additionally, local network features were more useful than global in improving the model’s performance. CONCLUSION: Connectivity-based characterization of white matter tracts offers potential for early detection of MCI-AD and in the discovery of novel imaging biomarkers. Show more

Keywords: Diffusion tensor imaging, Alzheimer’s disease, mild cognitive impairment, network modelling, machine learning

DOI: 10.3233/THC-192012

Citation: Technology and Health Care, vol. 30, no. 1, pp. 17-28, 2022

Authors: Zhang, Meng | Cheng, Yanyan | Liu, Hongxing | Nan, Qun

Article Type: Research Article

Abstract: OBJECTIVE: To cure atrial fibrillation, the maximum ablation depth (⩾ 50 ∘ C) should exceed the myocardial thickness to achieve the effect of transmural ablation. The blood flow of pulmonary vein in the endocardium can cause the change in the myocardial temperature distribution. Therefore, the study investigated the effect of different pulmonary vein blood flow velocities on the endocardial microwave ablation. METHODS: The finite element model of the endocardial microwave ablation of pulmonary vein was simulated by electromagnetic thermal flow coupling. The ablation power was 30 W and the ablation …time was within 30 s. The blood flow in the coupling of fluid mechanics equation and heat transfer equation results in the heat damage. Furthermore, the cause of the different lesion dimensions is the blood flow velocity. The flow velocities were set as 0, 0.02, 0.05, 0.07, 0.12, 0.16, 0.20, 0.25 and 0.30 m/s. RESULTS: When the flow velocities were 0, 0.02, 0.05, 0.07, 0.12, 0.16, 0.20, 0.25 and 0.30 m/s, the maximum ablation depth were 6.00, 5.56, 5.16, 5.12, 5.04, 5.01, 4.98, 4.96 and 4.94 mm, respectively; the maximum ablation width were 12.53, 9.63, 9.23, 9.16, 9.07, 9.05, 8.94, 8.91 and 8.90 mm, respectively; the maximum ablation length were 12.00, 11.61, 8.98, 8.59, 8.37, 8.23, 8.16, 8.06 and 8.04 mm respectively. To achieve transmural ablation, the time was 3, 3, 3, 3, 3, 4, 4, 4, 4 s, respectively when the myocardial thickness was 2 mm; the time was 7, 8, 8, 8, 9, 9, 9, 9, 9 s, respectively when 3 mm; the time was 15, 16, 18, 19, 19, 20, 20, 20, 20 s, respectively when 4 mm. CONCLUSIONS: When the velocity increases from 0 m/s to 0.3 m/s, the microwave lesion depth decreases by 1.06 mm. To achieve transmural ablation, when the myocardial thickness is 2 mm, 3 and 4 s should be taken when the velocity is 0–0.12 and 0.12–0.30 m/s, respectively; when the myocardial thickness is 3 mm, 7, 8 and 9 s should be taken when 0, 0–0.07 and 0.07–0.30 m/s respectively; when the myocardial thickness is 4 mm, 15, 16, 18, 19, 20 s should be taken when 0, 0–0.02, 0.02–0.05, 0.05–0.12, 0.12 m/s–0.30 m/s. Show more

Keywords: Atrial fibrillation, pulmonary vein, microwave ablation, blood flow velocity, numerical simulation

DOI: 10.3233/THC-202421

Citation: Technology and Health Care, vol. 30, no. 1, pp. 29-41, 2022

Authors: Wang, Junsig | Siddicky, Safeer F. | Johnson, Tara | Kapil, Namarta | Majmudar, Bittu | Mannen, Erin M.

Article Type: Research Article

Abstract: BACKGROUND: Absent or abnormal fidgety movements in young infants are associated with subsequent diagnoses of developmental disorders such as cerebral palsy. The General Movement Assessment (GMA) is a qualitative clinical tool to visually identify infants with absent or abnormal fidgety movements associated with developmental stage, yet no quantitative measures exist to detect fidgety activity. OBJECTIVE: To determine whether a correlation exists between quantitative Center of Pressure (CoP) measurements during supine lying and age. METHODS: Twenty-four healthy full-term infants participated in the Institutional Review Board-approved study. Participants were placed supine in view of a …GoPro camera on an AMTI force plate for two minutes. Spontaneous movements were evaluated by three trained raters using the GMA. Traditional CoP parameters (range, total path length, mean velocity, and mean acceleration of resultant CoP) were assessed, and complexity of each of the resultant CoP variables (location, velocity, and acceleration) was calculated by sample entropy. Linear regression with Pearson correlation was performed to assess the correlations between the CoP parameters and adjusted age. RESULTS: Nineteen infants were deemed fidgety per the GMA and were included in further analyses. All Sample entropy measures and range of resultant CoP had significant correlations with adjusted age (p < 0.05). Sample entropy of resultant CoP decreased with increasing age while range of resultant CoP increased with increasing age. CONCLUSION: The results suggest that complexity of CoP and range of CoP are good predictors of age in typical developing infants during the fidgety period. Therefore, an approach using these parameters should be explored further as a quantifiable tool to identify infants at risk for neurodevelopmental impairment. Show more

Keywords: Center of pressure, supine lying, sample entropy, baby, neurodevelopment, fidgety

DOI: 10.3233/THC-202754

Citation: Technology and Health Care, vol. 30, no. 1, pp. 43-49, 2022

Authors: Camacho-Zavala, Jessica K. | Perez-Medina, Ana L. | Mercado-Gutierrez, Jorge A. | Gutierrez, Mario I. | Gutierrez-Martinez, Josefina | Aguirre-Güemez, A. Valeria | Quinzaños-Fresnedo, Jimena | Perez-Orive, Javier

Article Type: Research Article

Abstract: BACKGROUND: Complex personalized Functional Electrical Stimulation (FES) protocols for calibrating parameters and electrode positioning have been proposed, most being time-consuming or technically cumbersome for clinical settings. Therefore, there is a need for new personalized FES protocols that generate comfortable, functional hand movements, while being feasible for clinical translation. OBJECTIVE: To develop a personalized FES protocol, comprising electrode placement and parameter selection, to generate hand opening (HO), power grasp (PW) and precision grip (PG) movements, and compare in a pilot feasibility study its performance to a non-personalized protocol based on standard FES guidelines. METHODS: …Two FES protocols, one personalized (P1) and one non-personalized (P2), were used to produce hand movements in twenty-three healthy participants. FES-induced movements were assessed with a new scoring scale which comprises items for selectivity, functionality, and comfort. RESULTS: Higher FES-HSS scores were obtained with P1 for all movements: HO (p = 0.00013), PW (p = 0.00007), PG (p = 0.00460). Electrode placement time was significantly shorter for P2 (p = 0.00003). Comfort scores were similar for both protocols. CONCLUSIONS: The personalized protocol for electrode placement and parameter selection enabled functional FES-induced hand movements and presented advantages over a non-personalized protocol. This protocol warrants further investigation to confirm its suitability for developing upper-limb rehabilitation interventions with clinical translational potential. Show more

Keywords: Electric stimulation, upper extremity, motor activity, electrodes, rehabilitation, technology

DOI: 10.3233/THC-213016

Citation: Technology and Health Care, vol. 30, no. 1, pp. 51-63, 2022

Authors: Hamze, Noura | Nocker, Lukas | Rauch, Nikolaus | Walzthöni, Markus | Carrillo, Fabio | Fürnstahl, Philipp | Harders, Matthias

Article Type: Research Article

Abstract: BACKGROUND: Accurate segmentation of connective soft tissues in medical images is very challenging, hampering the generation of geometric models for bio-mechanical computations. Alternatively, one could predict ligament insertion sites and then approximate the shapes, based on anatomical knowledge and morphological studies. OBJECTIVE: In this work, we describe an integrated framework for automatic modelling of human musculoskeletal ligaments. METHOD: We combine statistical shape modelling with geometric algorithms to automatically identify insertion sites, based on which geometric surface/volume meshes are created. As clinical use case, the framework has been applied to generate models of the …forearm interosseous membrane. Ligament insertion sites in the statistical model were defined according to anatomical predictions following a published approach. RESULTS: For evaluation we compared the generated sites, as well as the ligament shapes, to data obtained from a cadaveric study, involving five forearms with 15 ligaments. Our framework permitted the creation of models approximating ligaments’ shapes with good fidelity. However, we found that the statistical model trained with the state-of-the-art prediction of the insertion sites was not always reliable. Average mean square errors as well as Hausdorff distances of the meshes could increase by an order of magnitude, as compared to employing known insertion locations of the cadaveric study. Using those, an average mean square error of 0.59 mm and an average Hausdorff distance of less than 7 mm resulted, for all ligaments. CONCLUSIONS: The presented approach for automatic generation of ligament shapes from insertion points appears to be feasible but the detection of the insertion sites with a SSM is too inaccurate, thus making a patient-specific approach necessary. Show more

Keywords: Musculoskeletal ligaments, Gaussian Process Models, geometric modelling

DOI: 10.3233/THC-202550

Citation: Technology and Health Care, vol. 30, no. 1, pp. 65-78, 2022

Authors: Liu, Xiaoying | Yue, Yong | Wu, Xuyang | Huang, Xianwei | Hao, Yanhua | Lu, Yong

Article Type: Research Article

Abstract: BACKGROUND: The foot is an important part of the human body. Its functions are mainly walking and load-bearing. It also keeps the human body stable and absorbs ground vibrations to protect important human organs. OBJECTIVE: Many researchers use finite element methods to study the biomechanics of the foot. However, current studies on the finite element of the foot are based on the stress and displacement response analysis of the foot under static or quasi-static conditions, ignoring the movement process of the foot and the impact of vibration. Moreover, the joint application of energy method and finite …element analysis in foot biomechanics is rarely reported. METHODS: In this paper, to obtain the foot energy transfer process, the transient response of the foot under neutral position is analyzed based on the energy method. RESULTS: The results show that: (1) In this model, the energy analysis follows the conservation of energy, which indicates that the transient response analysis has obtained a reasonable response. (2) When the foot touches the ground, the strain energy of the calcaneus, second metatarsal and third metatarsal is relatively large, which is consistent with the main stress concentration area of the plantar. (3) The gravity of the human body is mainly transmitted through the talus to the calcaneus, while the effect of transmittal through the scaphoid to the cuneiform bone and metatarsal is weak. CONCLUSION: This study can not only more clearly and intuitively reflect the energy transfer and source of various skeletal foreheads in the foot, but also provide a new research idea for the study of foot biomechanics. Show more

Keywords: Transient response, foot, energy method

DOI: 10.3233/THC-202673

Citation: Technology and Health Care, vol. 30, no. 1, pp. 79-92, 2022

Authors: Cho, Hui-Sup | Park, Young-Jin

Article Type: Research Article

Abstract: BACKGROUND: The motion or gestures of a person are primarily recognized by detecting a specific object and the change in its position from image information obtained via an image sensor. However, the use of such systems is limited due to privacy concerns. OBJECTIVE: To overcome these concerns, this study proposes a radar-based motion recognition method. METHODS: Detailed human body movement data were generated using ultra-wideband (UWB) radar pulses, which provide precise spatial resolution. The pulses reflected from the body were stacked to reveal the body’s movements and these movements were expressed in detail …in the micro-range components. The collected radar data with emphasized micro-ranges were converted into an image. Convolutional neural networks (CNN) trained on radar images for various motions were used to classify specific motions. Instead of training the CNNs from scratch, transfer learning is performed by importing pretrained CNNs and fine-tuning their parameters with the radar images. Three pretrained CNNs, Resnet18, Resnet101, and Inception-Resnet-V2, were retrained under various training conditions and their performance was experimentally verified. RESULTS: As a result of various experiments, we conclude that detailed motions of subjects can be accurately classified by utilizing CNNs that were retrained with images obtained from the UWB pulse radar. Show more

Keywords: Pulse radar, image processing, micro-range, motion classification, convolutional neural network

DOI: 10.3233/THC-212827

Citation: Technology and Health Care, vol. 30, no. 1, pp. 93-104, 2022

Authors: Xu, Zhenyu | Guo, Shuai | Zhang, Leigang

Article Type: Research Article

Abstract: BACKGROUND: With the population aging, post-stroke patients suffering from hemiplegia are also rapidly increasing. It is essential to provide valid rehabilitation methods for hemiplegia patients. Mirror therapy is an effective rehabilitation method and is widely applied in many rehabilitation robots. OBJECTIVE: The aim of this paper is to present a path planning method to guarantee the robot’s motion performance during mirror therapy. METHODS: The kinematic framework of the proposed rehabilitation system is detailed, then the reference motion path of the manipulator is calculated according to kinematic transformation. The concept of manipulability is introduced …to describe the motion performance of the manipulator. Based on the above work, a path planning method based on A* algorithm is proposed to quantitatively analyze and optimize the motion performance of the manipulator. RESULTS: Preliminary experiments with the proposed rehabilitation system are conducted to verify the proposed path planning method. The characteristics of the proposed method are analyzed through two typical situations. The results showed that the proposed method can build a new path for manipulator, which can ensure the robot’s motion performance and is highly consistent with the reference path. CONCLUSION: The results showed that the manipulator could achieve the task with acceptable error, which indicates the potential of the proposed path planning method for mirror therapy. Show more

Keywords: Mirror therapy, path planning, A* algorithm, manipulability, stroke

DOI: 10.3233/THC-202551

Citation: Technology and Health Care, vol. 30, no. 1, pp. 105-116, 2022