Factors influencing the accuracy of intraoral impression in implant restoration / 口腔疾病防治

@#Due to advances in digital technology, intraoral impressions have been increasingly used to fabricate implant restorations because of its simplicity, high efficiency, comfortableness and convenience. In clinical practice, the accuracy of intraoral impressions depends on various factors, including scanner technique, status of dentition and implants, auxiliary devices, materials and environment, which might influence its accuracy and limit its application. When applied to patients missing more teeth, its accuracy may be insufficient. It is suggested that intraoral impressions be used cautiously when there are multiple and far apart implants and that the scan body not be tightened excessively and that maintain appropriate environmental conditions. In this article, we have reviewed recent relevant literature and the factors affecting the accuracy of intraoral impressions for implant restoration.

The specificity of body surface temperature of relevant back-shu points in patients with chronic persistent asthma based on infrared thermal imaging technology / 中国针灸

OBJECTIVE@#To detect the body surface temperature of the relevant back-shu points in patients with chronic persistent asthma by infrared thermal imaging technology, and observe the specific changes of the body surface temperature of the relevant back-shu points under the condition of lung disease.@*METHODS@#Forty-five patients with chronic persistent asthma (observation group) and 45 healthy subjects (control group) were selected. The body surface temperature of bilateral Feishu (BL 13), Geshu (BL 17), Pishu (BL 20) and Shenshu (BL 23) were measured by BK-MT02A medical infrared thermography.@*RESULTS@#The body surface temperature of bilateral Feishu (BL 13), Geshu (BL 17), Pishu (BL 20) and Shenshu (BL 23) in the observation group was higher than that in the control group (P<0.01, P<0.05). The body surface temperature of bilateral Feishu (BL 13) and Geshu (BL 17) was higher than that of ipsilateral Pishu (BL 20) and Shenshu (BL 23) in the two groups (P<0.01, P<0.05). There was no statistically significant difference in body surface temperature between ipsilateral Feishu (BL 13) and Geshu (BL 17), between ipsilateral Pishu (BL 20) and Shenshu (BL 23) (P>0.05).@*CONCLUSION@#The pathological increase of body surface temperature of Feishu (BL 13), Geshu (BL 17), Pishu (BL 20) and Shenshu (BL 23) in patients with chronic persistent asthma indicates that above acupoints have specificity in reflecting lung diseases. The Feishu (BL 13) and Geshu (BL 17), which have significantly increased body surface temperature, not only provide objective basis for the pathological pathogenesis of "deficiency in origin and excess in symptom" in patients with chronic persistent asthma, but also reflect the different expressions of different acupoints on the same meridian for the lung diseases.

Hyperspectral imaging technology distinguishes between Puerariae Lobatae Radix and Puerariae Lobatae Caulis / 中国中药杂志

Puerariae Lobatae Radix, the dried root of Pueraria lobata, is a traditional Chinese medicine with a long history. Puerariae Lobatae Caulis as an adulterant is always mixed into Puerariae Lobatae Radix for sales in the market. This study employed hyperspectral imaging(HSI) to distinguish between the two products. VNIR lens(spectral scope of 410-990 nm) and SWIR lens(spectral scope of 950-2 500 nm) were used for image acquiring. Multi-layer perceptron(MLP), partial least squares discriminant analysis(PLS-DA), and support vector machine(SVM) were employed to establish the full-waveband models and select the effective wavelengths for the distinguishing between Puerariae Lobatae Caulis and Puerariae Lobatae Radix, which provided technical and data support for the development of quick inspection equipment based on HSI. The results showed that MLP model outperformed PLS-DA and SVM models in the accuracy of discrimination with full wavebands in VNIR, SWIR, and VNIR+SWIR lens, which were 95.26%, 99.11%, and 99.05%, respectively. The discriminative band selection(DBS) algorithm was employed to select the effective wavelengths, and the discrimination accuracy was 93.05%, 98.05%, and 98.74% in the three different spectral scopes, respectively. On this basis, the MLP model combined with the effective wavelengths within the range of 2 100-2 400 nm can achieve the accuracy of 97.74%, which was close to that obtained with the full waveband. This waveband can be used to develop quick inspection devices based on HSI for the rapid and non-destructive distinguishing between Puerariae Lobatae Radix and Puerariae Lobatae Caulis.

Origin identification of Poria cocos based on hyperspectral imaging technology / 中国中药杂志

To realize the non-destructive and rapid origin discrimination of Poria cocos in batches, this study established the P. cocos origin recognition model based on hyperspectral imaging combined with machine learning. P. cocos samples from Anhui, Fujian, Guangxi, Hubei, Hunan, Henan and Yunnan were used as the research objects. Hyperspectral data were collected in the visible and near infrared band(V-band, 410-990 nm) and shortwave infrared band(S-band, 950-2 500 nm). The original spectral data were divided into S-band, V-band and full-band. With the original data(RD) of different bands, multiplicative scatter correction(MSC), standard normal variation(SNV), S-G smoothing(SGS), first derivative(FD), second derivative(SD) and other pretreatments were carried out. Then the data were classified according to three different types of producing areas: province, county and batch. The origin identification model was established by partial least squares discriminant analysis(PLS-DA) and linear support vector machine(LinearSVC). Finally, confusion matrix was employed to evaluate the optimal model, with F1 score as the evaluation standard. The results revealed that the origin identification model established by FD combined with LinearSVC had the highest prediction accuracy in full-band range classified by province, V-band range by county and full-band range by batch, which were 99.28%, 98.55% and 97.45%, respectively, and the overall F1 scores of these three models were 99.16%, 98.59% and 97.58%, respectively, indicating excellent performance of these models. Therefore, hyperspectral imaging combined with LinearSVC can realize the non-destructive, accurate and rapid identification of P. cocos from different producing areas in batches, which is conducive to the directional research and production of P. cocos.

Rapid detection technology of chemical component content in Lycii Fructus based on hyperspectral technology / 中国中药杂志

This Fructus,study including and aimed to construct a rapid and nondestructive detection flavonoid,model betaine,for and of the content vitamin of(Vit four four quality C).index components Lycium barbarum polysaccharide,of inL ycii rawma total and C Hyperspectral data quantitative of terials modelswere powder developed Lycii using Fructus partial were squares effects collected,regression raw based LSR),on the support content vector the above components,the forest least(P regression compared,(SVR),the and effects random three regression(RFR)were algorithms.also The Four spectral predictive commonly data of the materialsand powder were were applied and of spectral quantitative for models reduction.compared.used were pre-processing screened methods feature to successive pre-process projection the raw algorithm data(SPA),noise competitive Thepre-processed for bands using adaptive reweigh ted sampling howed(CARS),the and maximal effects relevance based and raw minimal materials redundancy and(MRMR)were algorithms Following to optimize multiplicative the models.scatter The correction Based resultss(MS that prediction SPA on feature the powder prediction similar.PLSR C)denoising sproposed and integrated for model,screening the the coefficient bands,determination the effect(R_C~2)of(MSC-SPA-PLSR)coefficient was optimal.of on(R_P~2)thi of of calibration flavonoid,and and of all determination greater prediction0.83,L.barbarum inconte nt prediction of polysaccharide,total mean betaine,of Vit C were than smallest In the compared study,root with mean other prediction content squareserror models of the calibration(RMSEC)residual and deviation root squares was error2.46,prediction2.58,(RMSEP)and were the,and prediction(RPD)2.50,developed3.58,achieve respectively.rapid this the the quality mod el(MSC-SPA-PLSR)fourcomponents based Fructus,on hyperspectral which technology was approach to rapid and effective detection detection of the of Lycii in Lycii provided a new to the and nondestructive of of Fructus.

Research and application of intelligent hyperspectral analysis technology for Chinese materia medica / 中国中药杂志

With the development of imaging technology and artificial intelligence, hyperspectral imaging technology provides a fast, non-destructive, intelligent, and precise new method for the analysis of Chinese materia medica(CMM). This paper summarized the methods and applications of hyperspectral imaging technology combined with intelligent analysis technology in the field of CMM in recent years, focusing on the acquisition and preprocessing of hyperspectral data, intelligent analysis methods of hyperspectral data, and practical cases of these technologies in the field of CMM. Hyperspectral data of CMM can provide spectral information with nanometer-level resolution and rich spatial texture information simultaneously. This paper summarized the acquisition process, including black-and-white board calibration and region-of-interest extraction, and preprocessing methods including smoothing, differentiation, scale-space, and scattering correction. The feature extraction methods in terms of spectral, spatial, color, and texture were briefly described, and common modeling methods were summarized. Finally, this paper reviewed the research cases of the application of the above methods to the fields of CMM, such as authenticity identification, origin tracing, variety recognition, year identification, sulfur fumigation degree determination, and quantitative measurement.

Application of case-based learning in the image post-processing teaching of standardized training of medical imaging technology / 中华医学教育探索杂志

Objective:To explore the application effect of case-based learning (CBL) and lecture-based learning (LBL) in the teaching of image post-processing course in the standardized training system of medical imaging technology.Methods:A total of 34 trainees in the standardized training of imaging technology of Batch 2018 in West China Hospital of Sichuan University were divided into the experimental group and the control group according to their student numbers, with 17 students in each group. CBL teaching was carried out in the experimental group, and LBL teaching was carried out in the control group. According to the standardized training course design, after one year of image post-processing course teaching, the teaching effect was evaluated through closed-book examination, questionnaire survey and post-processing test. SPSS 20.0 was used for t-test and Mann-Whitney U test. Results:The scores of closed-book examinations (74.42±6.10) and post-processing test (73.47±6.03) in the experimental group were higher than those in the control group [(69.11±3.70) and (69.08±6.51)], and the difference was statistically significant ( P<0.05). The questionnaire survey showed that the students in the experimental group recognized CBL teaching in terms of learning interests stimulation, classroom atmosphere mobilization, clinical thinking cultivation, self-study ability training, and analysis of difficult and rare cases, etc. Conclusion:In the image post-processing course of standardized training of medical imaging technology, the rational application of CBL teaching mode is helpful to improve students' learning enthusiasm, self-learning ability, comprehensive analysis of clinical ability, practical ability, innovation consciousness and so on.

Research Progress of Indocyanine Green Fluorescence Laparoscopic Technique in Clinical Application / 中国医疗器械杂志

Indocyanine green (ICG) is the most commonly used near-infrared fluorescent (NIRF) dye in clinical practice, and its mediated near-infrared fluorescence imaging technology is gradually applied in clinical practice. It has shown great potential in invasive surgery (MIS) and is expected to become the standard technology for surgical diagnosis and treatment of diseases. The clinical application of ICG fluorescence laparoscopy is reviewed here.

Clinical application of near-infrared fluorescence positive imaging combined with intraoperative rapid PTH determination in parathyroid identification and functional protection / 中华内分泌外科杂志

Objective:To investigate the feasibility and clinical significance of near-infrared fluorescence positive imaging combined with intraoperative rapid parathyroid hormone (PTH) determination in identification and function protection of the parathyroid gland during thyroidectomy.Methods:According to the inclusion and exclusion criteria, patients in the Affiliated Lihuili Hospital of Ningbo University, who needed bilateral thyroidecto-my and central lymph node dissection due to suspected bilateral thyroid cancer from Mar. 2020 to Oct. 2020 were selected for a prospective clinical study. They were randomly divided into the study group (near-infrared fluorescence positive imaging combined with intraoperative rapid PTH determination) and the control group (intraoperative experience identification) . The number of parathyroid glands found during operation, PTH before and after the operation, blood calcium, blood phosphorus, the presence of parathyroid tissues in routine pathological section examinations, and postoperative symptoms were collected. SPSS 25.0 statistical software was used for analysis, the measurement data were expressed by mean±standard deviation ( ± s) , t test was used for comparison between groups, and χ2 test was used for counting date. Results:In the study group of 33 cases, 135 suspicious parathyroid glands were exhibited during operation, with an average of (4.09±0.52) ; Hand and foot numbness occurred in 1 case (3.03%) ; On the 1st after the operation, PTH was (23.68±9.48) ng/L. In the control group of 31 cases, 109 parathyroid glands were identified by naked eyes, with an average of (3.52±0.63) ; Hand and foot numbness occurred in 6 cases (19.35%) ; On the 1st after the operation, PTH was (17.93±11.58) ng/L. The differences were statistically significant ( P<0.05) . But no statistical significance was found in operation duration (79.45±30.18) min, postoperative hospitalization days (5.85±2.27) days, PTH (27.10±9.80, 33.08±10.21) ng/L, blood calcium (2.11±0.10,2.25±0.09) mmol/L, and blood phosphorus (1.20±0.20,1.15±0.12) mmol/L on the 3rd day and the 6th month after the operation. Conclusion:Near-infrared fluorescence positive imaging combined with intraoperative rapid PTH determination can improve the recognition rate of the parathyroid gland and reduce postoperative complications, which is a safe, effective and rapid method for intraoperative parathyroid gland recognition.

Skin imaging technologies for photoaging / 中华皮肤科杂志

Skin photoaging not only affects the appearance, but also is associated with skin tumors. It is very important to objectively and effectively evaluate photoaging. Histopathological examination is the gold standard for the diagnosis of photoaging, but it can not be used repeatedly because of its invasiveness, and is not suitable for dynamic monitoring and evaluation of photoaging. Skin imaging technologies can realize in vivo, real-time and non-invasive two- or three-dimensional image analysis, which facilitate the visual assessment of skin photoaging. This review summarizes research progress in dermoscopy, reflectance confocal microscopy, high-frequency ultrasound and optical coherence tomography in evaluation of photoaging.

TiRobot combined with three-dimensional imaging to assist minimally invasive treatment of pelvic fractures / 中华创伤骨科杂志

Objective:To explore the efficacy and safety of TiRobot combined with three-dimensional imaging in the minimally invasive surgery for pelvic fractures.Methods:A retrospective analysis was conducted of the 40 patients with pelvic fracture who had been treated by fixation with S1 and S2 sacroiliac screws at Department of Orthopaedics and Traumatology, Yangjiang People's Hospital from January 2019 to May 2021. They were divided into 2 groups according to their treatment methods. In the TiRobot group of 20 cases subjected to percutaneous sacroiliac screw fixation assisted by TiRobot combined with three-dimensional imaging, there were 13 males and 7 females with an age of (38.2 ± 8.8) years. In the manual group of 20 cases subjected to fixation with manual placement of sacroiliac screws under conventional C-arm fluoroscopy, there were 11 males and 9 females with an age of (37.3 ± 9.2) years. The 2 groups were compared in terms of fluoroscopy time for screw placement, guide needle adjustment, operation time, intraoperative blood loss, visual analogue scale (VAS) 72 hours after operation, postoperative hospital stay, time to ambulation, excellent to good rate of screw placement, complication rate, fracture union time, Majeed score at 6 months after operation, and excellent to good rate of functional evaluation.Results:There was no significant difference between the 2 groups in their preoperative general data, showing they were comparable ( P > 0.05). In the TiRobot group, fluoroscopy time for screw placement [(8.2 ± 2.9) s], guide needle adjustment [(0.4 ± 0.2) times], operation time [(67.4 ± 5.5) min], and intraoperative blood loss [(36.5 ± 8.0) mL] were significantly less than those in the manual group [(40.4 ± 4.5) s, (8.6 ± 0.7) times, (78.4 ± 7.2) min, and (41.6 ± 7.8) mL], postoperative VAS [3.0 (4.0, 5.0) points] was significantly lower than that in the manual group [4.0 (5.0, 6.0) points], the excellent to good rate of screw placement (100%, 40/40) was significantly higher than that in the manual group (85.0%, 34/40), and the complication rate (5.0%,1/20) was significantly lower than that in the manual group (35.0%, 7/20) (all P < 0.05). There was no significant difference between the 2 groups in postoperative hospital stay, time to ambulation, fracture union time, Majeed score, or excellent to good rate of functional evaluation ( P > 0.05). Conclusion:In the minimally invasive surgery for pelvic fractures, TiRobot combined with three-dimensional imaging leads to positive outcomes, because it can reduce operation time and radiation exposure, improve accuracy of screw placement, and increase safety.

Exploration on teaching and experiment reform of medical imaging technology course from the perspective of "Internet Plus-based teaching diagnosis and reform" / 中华医学教育探索杂志

Medical imaging technology course has the characteristics of strong professionalism, complicated content to understand, and quickly updated knowledge. In traditional teaching mode, it takes teachers a lot of time to prepare lessons, and the teaching tools are limited like only taking use of blackboard, model and wall maps, which not only makes teaching content boring but also hardly stimulates students' initiative. Teaching reform of medical imaging technology courses from the perspective of "Internet Plus-based teaching and diagnosis reform" involves teaching content, teaching concept, teaching mode, teaching evaluation and experiments, etc., in which computer-aided teaching, flipped classroom, micro-course and high-quality resource-sharing course are used to increase experimental content, reform experimental teaching methods, and create "real-situation" experimental environment as well as other teaching diagnosis and reform measures, aiming to explore a new teaching pattern that meets the development of students majoring in medical imaging technology and the demand for social talents.

Research progress of molecular imaging technology in the diagnosis and treatment of epilepsy / 中华行为医学与脑科学杂志

Molecular imaging is a developing research field and it has become a research hotspot.It integrates molecular biochemistry, data processing, nanotechnology, image processing and other technologies and has high specificity, high sensitivity, and high image resolution.It can provide qualitative, positioning, and quantitative data for clinical diagnosis.Clinically, 30% of epileptic patients develop into intractable epilepsy, but magnetic resonance imaging(MRI) can not detect structural lesions.These patients need accurate positioning in order to improve the effectiveness of epilepsy surgery.Because the current preoperative positioning methods have certain limitations, some epileptic patients still have recurrent seizures after the operation.Therefore, researchers continue to explore targeted tracers with high specificity and strong sensitivity.Various nanotechnology and functional magnetic resonance imaging methods are used to study the accurate localization methods of epilepsy.This paper summarized and analyzed the latest research of molecular imaging technology in China and abroad, such as the latest research of single photon emission computed tomography(SPECT) and positron emission tomography(PET) molecular imaging, the application of various nanotechnology combined with functional magnetic resonance in the accurate diagnosis and treatment of epilepsy, and various targeted tracers that haven been developed at present.The results suggest that the continuous improvement of quantitative image analysis, the integration of multi-mode imaging, the development of PET radioactive tracers, and the combination of nanotechnology and functional magnetic resonance imaging(fMRI) will facilitate a more comprehensive understanding of the pathophysiological mechanism of epilepsy.It is promising to realize the accurate diagnosis and treatment of intractable epilepsy.

Application of bone suppression imaging in the diagnosis of occupational pneumoconiosis / 中国职业医学

@#Objective （ ） To explore the application value of bone suppression imaging BSI in the diagnosis of occupational （ pneumoconiosis） Methods - pneumoconiosis hereinafter referred to as " " . A total of 330 chest films of high kV digital （ ） radiograph DR of patients with suspected pneumoconiosis were selected by convenient sampling method. BSI is applied to the ， ， ， ， chest films and the differences of small opacity shape small opacity aggregation the number of large opacity lung areas small （ ）， opacity profusion and diagnostic stage of pneumoconiosis were analyzed by simple DR reading DR group simple BSI reading （ ） （ ） Results BSI group and DR and BSI combined reading combined group . There was no significant difference in the distribution of small shadows and the detection rate of small shadows aggregation and large shadows in pneumoconiosis among （ P ） ， the three film reading methods all >0.05 . For the concentration distribution of each lung area there was statistically （P< ）， significant difference between the DR group and the BSI group 0.05 but there was no statistically significant difference ， （ P ） between the DR group and the combined group and between the BSI group and the combined group all >0.05 . The results of ， consistency analysis showed that the DR group and the BSI group and the DR group and the combined group had high （ ， P< consistency in the judgment of small shadow intensity in the lung region both weighted Kappa coefficient were 0.75 all ） 0.01 . There was a high consistency between BSI group and DR group and combined group and DR group in the diagnosis of （ ， ， P< ） ， pneumoconiosis stage weighted Kappa coefficient were 0.77 0.79 all 0.01 . Compared with the DR group the diagnostic ， rate of pneumoconiosis stage Ⅰwas significantly reduced and the diagnostic rate of pneumoconiosis stage Ⅱ was significantly （ P< ） ， increased in the BSI group and the combined group all 0.01 . However there was no significant difference in the diagnosticrate of pneumoconiosis stage Ⅲ >0.05 . Both the BSI reading and DR and BSI combined reading can improve ， the display of pneumoconiosis lesions to varying degrees and therefore can improve the diagnosis of pneumoconiosis. In ， addition the identification and diagnosis of pneumoconiosis lesions in the BSI reading is comparable to that in the combined ， group which has a good application value in the diagnosis of pneumoconiosis.

Comparative study of infrared thermal imaging technology and colour Doppler ultrasound in the detection of perforator vessels before anterolateral femoral perforator flap / 中华显微外科杂志

Objective:To compare the reliability between infrared thermal imaging technology(IRT) and colour Doppler ultrasound (CDU) in the detection of perforators for anterolateral femoral perforator flap(ALTPF).Methods:From September, 2017 to September, 2019, a total of 25 patients(16 males and 9 females, aged 12-53 years old with an average age of 38.7 years old) underwent ALTPF surgery for the purpose of resurfacing and reconstruction. All patients had pedicled or free ALTPF sized from 5.0 cm×8.0 cm to 7.5 cm×30.0 cm. Among all cases, 21 received free flaps and 4 received pedicled flaps. All patients underwent routine IRT and CDU examinations to locate the perforators preoperatively.Results:Of the 25 patients, CDU detected 53 perforators and IRT detected 51 "hot spots". There were 50 "hot spots" that corresponded to the findings of CDU with a κ index at 0.712( P<0.05), representing a high degree of consistency. The sensitivity and specificity were 94.3% and 85.7%, respectively. Conclusion:IRT has a high consistency in detecting perforators for ALTPF in comparison with CDU. IRT features portable, low cost, non-invasive, and easy to operate. At the same time, IRT has advantages in the patients who have thin subcutaneous tissue. With higher accuracy, IRT is expected to become an important part of preoperative perforator navigation.

Research progress of stem cells imaging technology in the diagnosis and treatment of liver diseases / 中华肝胆外科杂志

Liver disease is one of the main causes of human deaths in the world. Orthotopic liver transplantation is the most effective treatment for severe liver diseases, such as liver cirrhosis, hepatocellular carcinoma, etc. However, liver transplantation was limited because of donors shortage, and immunological. In recent years, stem cell therapy with the ability of multi-directional differentiation has potential application value in the treatment of patients with liver diseases. However, the mechanisms of stem cell therapy have not yet been fully understood. Stem cells can be detected under in vivo cell imaging. It can noninvasively trace the distribution, migration, proliferation and differentiation of stem cells, and it is an important link to study the mechanism of stem cells in the treatment of liver diseases. Therefore, this review briefly introduces the latest research progress of stem cell in vivo imaging techniques in the field of stem cell diagnosis and treatment of liver diseases.

Application of real-time three-dimensional speckle tracking echocardiography in the evaluation of early cardiac function damage in patients with pregnancy induced hypertension / 中国基层医药

Objective:To investigate the clinical value of real-time three-dimensional speckle tracking echocardiography in the evaluation of early cardiac function damage in patients with pregnancy induced hypertension.Methods:Sixty-five pregnant women with pregnancy induced hypertension (patient group) and 65 healthy pregnant women (healthy group) who received prenatal examination and delivered between January 2018 and June 2020 in Wenzhou Hospital of Integrated Traditional Chinese and Western Medicine were included in this study. The patient and healthy groups were subjected to routine echocardiography and real-time three-dimensional speckle tracking echocardiography at 24-36 and 32-34 weeks of gestation. The imaging parameters of routine echocardiography and real-time three-dimensional speckle tracking echocardiography measured at different periods of gestation were compared between the two groups.Results:At 24-36 weeks of gestation, there were no significant difference in routine echocardiography parameters of the left ventricle between patient and healthy groups ( t = 0.793-1.748; P = 0.129-0.458). Left ventricular diameter (LVD), intra-ventricular septum diastole (IVSD) and left ventricular posterior wall diameter (LVPWD) in the patient group at 32-34 weeks of gestation were (34.97 ± 2.66) mm, (11.96 ± 1.85) mm, (12.07 ± 1.73) mm, respectively, which were significantly greater than those in the healthy group at the same time [(31.56 ± 2.58) mm, (9.17 ± 1.70) mm, (9.23 ± 1.62) mm] and those in the patient group at 24-36 weeks of gestation [(32.36 ± 2.61) mm, (10.15 ± 1.79) mm, (10.19 ± 1.64) mm, t = 5.437, 6.274, 6.319, 3.621, 4.017, 5.241, all P < 0.001]. Left ventricular ejection fraction (LVEF) in the patient group at 32-34 weeks of gestation was (54.36 ± 4.71)%, which was significantly lower than (63.27 ± 5.04)% in the healthy group at the same time and (59.65 ± 4.62) % in the healthy group at 24-36 weeks of gestation ( t = 7.682, 5.483, both P < 0.001). At 24-36 and 32-34 weeks of gestation, the absolute values of real-time three-dimensional speckle tracking echocardiography parameters left ventricular global longitudinal strain, left ventricular global circumferential strain, left ventricular global radial strain and left ventricular global area strain in the patient group were (23.45 ± 2.58)%, (34.09 ± 3.28)%, (22.03 ± 2.31)%, (34.73 ± 3.58)%, (18.63 ± 2.42)%, (30.74 ± 3.07)%, (19.56 ± 2.28)%, (25.85 ± 3.37)%, respectively, which were significantly lower than those in the healthy group [(26.27 ± 2.74)%, (37.62 ± 3.61)%, (24.67 ± 2.59)%, (39.41 ± 3.96)%, (26.10 ± 2.81)%, (37.56 ± 3.64)%, (24.82 ± 2.59)%, (40.16 ± 3.96)%, t = 4.415, 5.013, 4.724, 6.253, 10.736, 8.592, 7.627, 14.319, all P < 0.001]. In patient group, the absolute values of left ventricular global longitudinal strain, left ventricular global circumferential strain, left ventricular global radial strain and left ventricular global area strain at 32-34 weeks of gestation were (18.63 ± 2.42)%, (30.74 ± 3.07)%, (19.56 ± 2.28)%, (25.85 ± 3.37)%], respectively, which were significantly lower than those at 24-36 weeks of gestation [(23.45 ± 2.58)%, (34.09 ± 3.28)%, (22.03 ± 2.31)% (34.73 ± 3.58)%, t = 7.529, 4.785, 5.194, 8.413, all P < 0.001]. Conclusion:Real-time three-dimensional speckle tracking echocardiography is advantageous in identifying the damage to cardiac function over routine echocardiography. Findings from this study provides a great clinical guiding value for protecting the cardiac function of patients with pregnancy induced hypertension.

Deep Learning-Based Cardiac Imaging Data Measurement and Its Application in Diagnosis of Sudden Cardiac Death / 法医学杂志

In the field of forensic medicine, diagnosis of sudden cardiac death is limited by subjective factors and manual measurement methods, so some parameters may have estimation deviation or measurement deviation. As postmortem CT imaging plays a more and more important role in the appraisal of cause of death and cardiopathology research, the application of deep learning such as artificial intelligence technology to analyze vast amounts of cardiac imaging data has provided a possibility for forensic identification and scientific research workers to conduct precise diagnosis and quantitative analysis of cardiac diseases. This article summarizes the main researches on deep learning in the field of cardiac imaging in recent years, and proposes a feasible development direction for the application of deep learning in the virtual anatomy of sudden cardiac death at present.

Research Progress on Computer-Aided Skeleton-Based Individual Identification in Forensic Radiology / 法医学杂志

Individual identification based on imaging data of the skeleton of a corpse is a key technique for forensic identification. To reduce the influence of artificial factors, computer-aided semi-automatic or automatic individual identification has become one of the research directions of skeleton-based individual identification in forensic radiology. Therefore, this paper reviews and summarizes literatures related to estimation of anthropological information such as, age and sex by computer-aided forensic radiology bone characteristics and individual identification based on bone imaging characteristics, in order to provide reference on skeleton-based individual identification in forensic radiology.

Chlorophyll content for millet leaf using hyperspectral imaging and an attention-convolutional neural network / Estimativa do teor de clorofila para folhas de milheto usando imagens hiperespectrais e uma rede neural atenção-convolucional

ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.

RESUMO: A clorofila é um fator importante que afeta a fotossíntese e, consequentemente, o crescimento e o rendimento das culturas. Neste estudo, um modelo de detecção de conteúdo de clorofila é construído para folhas de milheto em diferentes estágios de crescimento, com base em dados hiperespectrais. As imagens hiperespectrais dos diferentes estágios de crescimento das folhas de milheto foram obtidas para 380-1000 nm, utilizando um gerador de imagens hiperespectrais. Uma segmentação de limiar foi realizada com refletância no infravermelho próximo (NIR) e índice de vegetação com diferença normalizada (NDVI) para adquirir de forma inteligente as regiões de interesse (ROI). Além disso, os dados espectrais brutos foram pré-processados usando o método de correção de dispersão multivariada (MSC). Um algoritmo de projeção de coeficiente de correlação sucessivo (CC-SPA) foi utilizado para extrair os comprimentos de onda característicos, e os parâmetros característicos foram extraídos com base nas informações espectrais e de imagem. O modelo de previsão de regressão parcial dos mínimos quadrados (PLSR) foi estabelecido com base nos parâmetros de característica única e na fusão de parâmetros de característica múltipla. O coeficiente de determinação (Rv2) e o erro quadrático médio da raiz (RMSEv) do conjunto de validação para o modelo de fusão de parâmetros com várias características foram obtidos como 0,813 e 1,766, sendo melhores do que os do modelo de parâmetro de característica única. Com base na fusão de parâmetros com várias características, foi estabelecida uma rede neural atenção-convolucional (atenção-CNN) (Rv2 = 0,839, RMSEv = 1,451, RPD = 2,355) mais eficaz que o PLSR (Rv2 = 0,813, RMSEv = 1,766, RPD = 2,167) e mínimos quadrados que suportam modelos de máquina de vetores (LS-SVM) (Rv2 = 0,806, RMSEv = 1,576, RPD = 2,061). Estes resultados indicam que o modelo atenção-CNN atinge uma previsão efetiva do teor de clorofila nas folhas de milheto usando os dados hiperespectrais. Além disso, esta pesquisa demonstra que a combinação de imagens hiperespectrais e a atenção-CNN se mostra benéfica para a aplicação do monitoramento dos elementos nutricionais das culturas.