1.Artificial intelligence-based sequential ultrasound-MRI strategy for ovarian masses:dual evaluation of diagnostic accuracy and healthcare costs
Jingjing YU ; Ruixia DAI ; Xiaomin LIU ; Peijun HU ; Xiaochen WANG ; Sihui HU ; Shanshan ZHANG ; Wenqian WANG ; Yu TIAN ; Jiale QIN
Chinese Journal of Ultrasonography 2025;34(9):759-765
Objective:To develop an artificial intelligence(AI)-based sequential ultrasound-magnetic resonance imaging(US-MRI)diagnostic strategy to optimize the imaging workflow for ovarian masses.Methods:A total of 1 120 patients with pathologically confirmed ovarian masses who underwent both preoperative pelvic ultrasound and MRI between January 2021 and December 2023 at Women's Hospital,Zhejiang University School of Medicine were retrospectively included. Patients were randomly divided into the training( n=672)and internal test set( n=448)at a ratio of 6∶4. An external test set( n=128)was established at the Forth Affiliated Hospital of School of Medicine. Deep learning was used for automated segmentation of MRI lesions,followed by radiomic feature extraction and machine learning classification to construct both a US-MRI multimodal model and sequential US-MRI strategy. Diagnostic performance and potential healthcare cost-saving effects were evaluated across strategies. Results:In the internal test set( n=448),the AI-based sequential US-MRI strategy achieved a F1 score of 0.863 and a diagnostic accuracy of 82.14%,with no significant difference compared to the US-MRI multi-modal model( P>0.05). The sequential strategy identified 82 cases(18.30%,82/448)of patients as low-risk true negatives during initial ultrasound screening,suggesting a potential to reduce the need for MRI examinations in future clinical practice. In the external test set( n=128),the strategy achieved an F1 score of 0.800 and a confirmed diagnosis rate of 85.94%,with a theoretical reduction of 26.56%(34 cases)in MRI utilization while maintaining a diagnostic accuracy rate higher than that of the multi-modal model(82.18%). Conclusions:The AI-based US-MRI sequential diagnostic strategy demonstrates favorable diagnostic accuracy while offering the potential to optimize MRI utilization. This approach may enhance the efficiency of imaging resource allocation and reduce healthcare burden in the management of ovarian masses.
2.Four decades of gynecological ultrasound in China:A review of advances and perspectives
Jiale QIN ; Xinling ZHANG ; Xiaoqiu DONG ; Longxia WANG ; Qing DAI
Chinese Journal of Medical Imaging Technology 2025;41(8):1340-1345
Over the past 40 years,gynecological ultrasound in China has evolved from two-dimensional imaging to multi-modal imaging,quantitative analysis,artificial intelligence analysis and minimally invasive treatment,playing more and more important role in diagnosis and treatment of gynecological diseases.The development of diagnostic and therapeutic gynecological ultrasound techniques and relative clinical application advances in China were reviewed,and the future development prospects were looked forward to in this article.
3.Four decades of gynecological ultrasound in China:A review of advances and perspectives
Jiale QIN ; Xinling ZHANG ; Xiaoqiu DONG ; Longxia WANG ; Qing DAI
Chinese Journal of Medical Imaging Technology 2025;41(8):1340-1345
Over the past 40 years,gynecological ultrasound in China has evolved from two-dimensional imaging to multi-modal imaging,quantitative analysis,artificial intelligence analysis and minimally invasive treatment,playing more and more important role in diagnosis and treatment of gynecological diseases.The development of diagnostic and therapeutic gynecological ultrasound techniques and relative clinical application advances in China were reviewed,and the future development prospects were looked forward to in this article.
4.Artificial intelligence-based sequential ultrasound-MRI strategy for ovarian masses:dual evaluation of diagnostic accuracy and healthcare costs
Jingjing YU ; Ruixia DAI ; Xiaomin LIU ; Peijun HU ; Xiaochen WANG ; Sihui HU ; Shanshan ZHANG ; Wenqian WANG ; Yu TIAN ; Jiale QIN
Chinese Journal of Ultrasonography 2025;34(9):759-765
Objective:To develop an artificial intelligence(AI)-based sequential ultrasound-magnetic resonance imaging(US-MRI)diagnostic strategy to optimize the imaging workflow for ovarian masses.Methods:A total of 1 120 patients with pathologically confirmed ovarian masses who underwent both preoperative pelvic ultrasound and MRI between January 2021 and December 2023 at Women's Hospital,Zhejiang University School of Medicine were retrospectively included. Patients were randomly divided into the training( n=672)and internal test set( n=448)at a ratio of 6∶4. An external test set( n=128)was established at the Forth Affiliated Hospital of School of Medicine. Deep learning was used for automated segmentation of MRI lesions,followed by radiomic feature extraction and machine learning classification to construct both a US-MRI multimodal model and sequential US-MRI strategy. Diagnostic performance and potential healthcare cost-saving effects were evaluated across strategies. Results:In the internal test set( n=448),the AI-based sequential US-MRI strategy achieved a F1 score of 0.863 and a diagnostic accuracy of 82.14%,with no significant difference compared to the US-MRI multi-modal model( P>0.05). The sequential strategy identified 82 cases(18.30%,82/448)of patients as low-risk true negatives during initial ultrasound screening,suggesting a potential to reduce the need for MRI examinations in future clinical practice. In the external test set( n=128),the strategy achieved an F1 score of 0.800 and a confirmed diagnosis rate of 85.94%,with a theoretical reduction of 26.56%(34 cases)in MRI utilization while maintaining a diagnostic accuracy rate higher than that of the multi-modal model(82.18%). Conclusions:The AI-based US-MRI sequential diagnostic strategy demonstrates favorable diagnostic accuracy while offering the potential to optimize MRI utilization. This approach may enhance the efficiency of imaging resource allocation and reduce healthcare burden in the management of ovarian masses.
5.Comparison of the chemical components in Artemisiae Scopariae Herba standard decoction and its decoction pieces
Luyao WANG ; Yujia LI ; Jiale GENG ; Chuanjuan LI ; Ying DAI ; Zhihua DOU
China Pharmacy 2024;35(12):1451-1456
OBJECTIVE To compare the chemical components contained in Artemisiae Scopariae Herba (ASH) standard decoction and its decoction pieces, and provide foundation of their pharmacological substances. METHODS ASH standard decoction and its decoction pieces were prepared; UFLC-Q-TOF-MS/MS method was used for the detection in the negative ion mode, and the total ion chromatogram was extracted by the PeakView 1.6 software. By comparing with reference substances, literature data, and online search of compound database such as PubChem, the chemical components contained in ASH standard decoction and its decoction pieces were identified and analyzed for the differences. RESULTS A total of 125 chemical components were identified in ASH standard decoction and its decoction pieces, including 50 organic acids, 39 flavonoids, 3 coumarins, 2 amino acids, 5 lignans, and 26 others. 3-methoxy-caffeic acid-4-O- β -D-glucoside, p-hydroxybenzoic acid, caffeic acid 4-O- glucoside, spiraeoside, and phenyl β-D-glucoside in ASH standard decoction were not detected in its decoction pieces, while 6′-6′ chlorogenic acid dimer, quercetin-5-glucoside, apigenin 7-methyl ether 5-(6″-malonylglucoside), quercetin-3-O-arabinoside, 6″-caffeoylhyperin and 6-O-caffeoyl-D-glucoside in decoction pieces were not detected in the standard decoction. CONCLUSIONS Most components in ASH decoction pieces are transferred to its standard decoction, but a few components undergo chemical reactions in whole or in part during the boiling process, transforming into other or new components in the standard decoction.
6.Research progress of mechanism and risk factors of retinal vein occlusion
Shui LI ; Huajing YANG ; Jiale DAI ; Jianbin CHEN
International Eye Science 2024;24(1):72-76
Retinal vein occlusion(RVO), the second most prevalent retinal vascular disease, has complex pathophysiological mechanism. Except for mechanical pressure on blood vessel, inflammation and endothelin have been confirmed to be involved in the pathogenesis of RVO. However, its specific mechanism remains unclear. Hypertension, diabetes and dyslipidemia have been previously shown to be the most common risk factors in elder population, while recent studies found that coagulation and hemorheological abnormalities are more common in people under 50 years old. Ocular risk factors including glaucoma, high corrected intraocular pressure and retinal vessels abnormality, have gained more and more attention. These factors probably exert a synergistic effect when present simultaneously in the same patient. Therefore, early identification and intervention of those factors could lower the incidence of RVO. This article aims to review recent research and summarize existing mechanism and theories, giving some new research ideas for potential therapy targets and providing references for identification and management of risk factors.
7.Current Status and Future Trends of Cold Atmospheric Plasma as an Oncotherapy
Xiaofeng DAI ; Jiale WU ; Lianghui LU ; Yuyu CHEN
Biomolecules & Therapeutics 2023;31(5):496-514
Cold atmospheric plasma (CAP), a redox modulation tool, is capable of inhibiting a wide spectrum of cancers and has thus been proposed as an emerging onco-therapy. However, with incremental successes consecutively reported on the anticancer efficacy of CAP, no consensus has been made on the types of tumours sensitive to CAP due to the different intrinsic characteristics of the cells and the heterogeneous design of CAP devices and their parameter configurations. These factors have substantially hindered the clinical use of CAP as an oncotherapy. It is thus imperative to clarify the tumour types responsive to CAP, the experimental models available for CAP-associated investigations, CAP administration strategies and the mechanisms by which CAP exerts its anticancer effects with the aim of identifying important yet less studied areas to accelerate the process of translating CAP into clinical use and fostering the field of plasma oncology.
8.Effect of edaravone combined with batroxobin in treatment of acute progressive cerebral infarction
Huijuan XU ; Hong LUO ; Jiale DAI
Chinese Journal of Primary Medicine and Pharmacy 2016;23(18):2821-2824
Objective To discuss the efficacy of edaravone combined with batroxobin in the treatment of patients with acute progressive infarction,and its influence on neurological deficit and coagulation.Methods 64 patients with acute and progressive infarction were selected,they were randomly divided into the control group and the observation group,32 cases in each group.The patients of the observation group were given edaravone combined with batroxobin,while the patients of the control group were given batroxobin only.Results The total effective rate of the observation group was 91.63%,which was obviously higher than 78.13% of the control group(χ2 =11.274,P <0.05).The NDS of the observation group was (14.8 ±2.9 )points,which was obviously lower than (17.9 ± 3.3)points of the control group(t =9.98,P <0.05).The level of Fib of the observation group was (2.9 ±0.3)g/L, which was obviously lower than (3.2 ±0.4)g/L of the control group(t =9.34,P <0.05).Conclusion Edaravone combined with batroxobin in the treatment of patients with acute and progressive infarction has significant effect and deserve promotion.
9.Monitoring and analysis of birth defects in 73498 infants
Min YANG ; Jimei WANG ; Beiqian QIAN ; Jiale DAI ; Xiaolei ZHUANG ; Aiju CHEN ; Yongqin MENG
Journal of Clinical Pediatrics 2015;(6):553-557
Objective To understand the occurrence and the related risk factors of birth defects. Methods Descriptive analysis was conducted on birth detect surveillance in the infants during January 2008 to June 2014. Results A total of 777 cases of birth defect were detected in 73498 infants, and the incidence of birth defect was 1.06%. The 5 most common birth de-fects were congenital heart disease, multi ifnger (toe), hypospadias, cleft lip, and palate and deformity of external ear. Compared infants born with no birth defects, male, preterm, low birth weight, twin and multiple births and resident were statistically higher in infants with birth defects (P<0.05). The major risk factors of birth defects were the medication history, spontaneous abortion, gestational diabetes mellitus, and family history. Conclusions The incidence of birth defect can be reduced by providing good health care during pre-marriage and pregnant so as to decrease the occurrence of premature infants, twins and multiple births, and low birth weight as well as improving prenatal diagnosis and intensifying birth defects surveillance.
10.Clinical features of non-immune hydrops fetalis in neonates
Xiaoxia AN ; Jimei WANG ; Xiaolei ZHUANG ; Jiale DAI ; Chengqiu LU ; Xiaotian LI ; Yingliu YAN
Chinese Journal of Perinatal Medicine 2015;18(12):896-903
Objective To summarize the clinical characteristics of neonates with non-immune hydrops fetalis.Methods The clinical data of ten neonates with non-immune hydrops fetalis, who were admitted to the Department of Neonatology, Gynecology and Obstetrics Hospital of Fudan University between January 2012 and June 2014, were retrospectively studied.Prenatal characteristics, causes, clinical features and prognosis were explored and analyzed with descriptive statistical methods.Results (1) One of the ten neonates was diagnosed after birth presented with hydroderma and abdominal distension, and the rest ones were diagnosed antenatally.There were six males and four females, and eight premature and two term neonates with the average gestational age of (33.6±2.4) weeks and birth weight of(2 680±478) g.(2) The mean maternal age was (30.3 ±4.6) years.Two of the mothers had gestational diabetes mellitus and one had gestational diabetes mellitus complicating with hyperthyroidism.The blood types of all mothers were O and Rh(+).None of the mothers were tested for parvovirus B19 and no fetus was reported with abnormal chromosome karyotype in the five cases received fetal karyotype analysis.(3) The average gestational age at initial identification of hydrops fetalis by fetal ultrasound was (31.3 ± 2.4) weeks (25.1~37.0 weeks) among nine cases diagnosed prenatally.By ultrasound screening, there were seven cases with hydrothorax, six with seroperitoneum, five with polyhydramnios and four with hydroderm.(4) Two neonates had normal non-stress test results during labor, and eight were abnormal and suffered from severe neonatal asphyxia at birth and resuscitated by endotracheal intubation.Ten neonates had hydroderm, seven had hydrothorax, six had seroperitoneum and one had hydropericardium.One complicated with multiple malformations and one had chromosome abnormality.Four cases received thoracentesis and three had abdominal paracentesis after parturition.(5) Prognosis: One neonate survived and nine died among which six due to resuscitation failure in delivery room, two died one day after giving up treatment after one day, and one died due to treatment failure six months after birth.(6) The causes of hydrops fetalis were anemia (two cases) and congenital diaphragmatic hemangioma, recurrent atrial premature beat, Down's syndrome, congenital pulmonary lymphangiectasia, paroxysmal supraventricular tachycardia, placental chorioangioma, suspicious genetic syndrome and idiopathic (one for each).Conclusions The prognosis varies because of different etiology of non-immune hydrops fetalis.Neonates with hydrops fetalis might have a higher rate of asphyxia and mortality rate, and difficulties in resuscitation at birth.

Result Analysis
Print
Save
E-mail