1.Expert Consensus on Clinical Application of Yifei Zhike Capsules
Xin CUI ; Hongchun ZHANG ; Weiwei GUO ; Chengjun BAN ; Zhifei WANG ; Yuanyuan LI ; Yingjie ZHI ; Xuefeng YU ; Yanming XIE
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(11):218-224
As an exclusive Miao medicine of Honwing Pharma (Guizhou) Co. Ltd., Yifei Zhike capsules are both a prescription drug and an over-the-counter (OTC) drug. Its main ingredients include Ranunculus ternatus and Panax notoginseng. With the effects of nourishing Yin and moistening the lungs, as well as relieving cough and reducing phlegm, Yifei Zhike capsules are often used in the treatment of acute and chronic bronchitis, pulmonary tuberculosis, and other diseases. However, there is insufficient understanding of their efficacy, suitable syndromes, and safety in clinical practice, with a lack of relevant expert consensus on clinical application. To standardize their clinical application, 30 experts from the fields of respiratory medicine, pharmacy, and evidence-based medicine were invited to develop an Expert Consensus on the Clinical Application of Yifei Zhike Capsules (Consensus for short) through evidence-based medicine methods. The Consensus clarified the syndrome characteristics, disease stages, dosages, treatment courses, combined medication, and other norms in the treatment of acute/chronic bronchitis and pulmonary tuberculosis and could be applicable to clinical physicians and pharmacists in medical and health institutions at all levels. In disease diagnosis, it provided diagnostic criteria for traditional Chinese medicine and Western medicine and clarified that the suitable traditional Chinese medicine syndrome was the syndrome of Qi-Yin deficiency with intermingled phlegm-blood stasis. Clinical studies have confirmed that Yifei Zhike capsules combined with standard anti-tuberculosis therapy can effectively improve the symptoms of pulmonary tuberculosis patients, increase the sputum smear conversion rate, and promote the absorption of lesions. When treating acute cough caused by respiratory tract infections, Yifei Zhike capsules can increase the markedly effective rate and the seven-day disappearance rate of cough symptoms. Meanwhile, recommendations for specific usage, dosages, and treatment courses were given for different diseases, and it was pointed out that long-term medication required key monitoring of adverse reactions. In safety, the adverse reactions of Yifei Zhike capsules involved multiple aspects such as the digestive system and allergic reactions, and pregnant women and women during menstruation were prohibited from using it. In addition, modern research has shown that Yifei Zhike capsules have an adjuvant therapeutic effect on tuberculous pleurisy and may be effective for inflammatory and benign pulmonary nodules. However, further research should be conducted on the toxicological safety of long-term medication. The formulation of the Consensus provides a scientific basis for the rational clinical application of Yifei Zhike capsules, which helps to improve clinical efficacy and reduce medication risks.
2.Expert Consensus on Clinical Application of Yifei Zhike Capsules
Xin CUI ; Hongchun ZHANG ; Weiwei GUO ; Chengjun BAN ; Zhifei WANG ; Yuanyuan LI ; Yingjie ZHI ; Xuefeng YU ; Yanming XIE
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(11):218-224
As an exclusive Miao medicine of Honwing Pharma (Guizhou) Co. Ltd., Yifei Zhike capsules are both a prescription drug and an over-the-counter (OTC) drug. Its main ingredients include Ranunculus ternatus and Panax notoginseng. With the effects of nourishing Yin and moistening the lungs, as well as relieving cough and reducing phlegm, Yifei Zhike capsules are often used in the treatment of acute and chronic bronchitis, pulmonary tuberculosis, and other diseases. However, there is insufficient understanding of their efficacy, suitable syndromes, and safety in clinical practice, with a lack of relevant expert consensus on clinical application. To standardize their clinical application, 30 experts from the fields of respiratory medicine, pharmacy, and evidence-based medicine were invited to develop an Expert Consensus on the Clinical Application of Yifei Zhike Capsules (Consensus for short) through evidence-based medicine methods. The Consensus clarified the syndrome characteristics, disease stages, dosages, treatment courses, combined medication, and other norms in the treatment of acute/chronic bronchitis and pulmonary tuberculosis and could be applicable to clinical physicians and pharmacists in medical and health institutions at all levels. In disease diagnosis, it provided diagnostic criteria for traditional Chinese medicine and Western medicine and clarified that the suitable traditional Chinese medicine syndrome was the syndrome of Qi-Yin deficiency with intermingled phlegm-blood stasis. Clinical studies have confirmed that Yifei Zhike capsules combined with standard anti-tuberculosis therapy can effectively improve the symptoms of pulmonary tuberculosis patients, increase the sputum smear conversion rate, and promote the absorption of lesions. When treating acute cough caused by respiratory tract infections, Yifei Zhike capsules can increase the markedly effective rate and the seven-day disappearance rate of cough symptoms. Meanwhile, recommendations for specific usage, dosages, and treatment courses were given for different diseases, and it was pointed out that long-term medication required key monitoring of adverse reactions. In safety, the adverse reactions of Yifei Zhike capsules involved multiple aspects such as the digestive system and allergic reactions, and pregnant women and women during menstruation were prohibited from using it. In addition, modern research has shown that Yifei Zhike capsules have an adjuvant therapeutic effect on tuberculous pleurisy and may be effective for inflammatory and benign pulmonary nodules. However, further research should be conducted on the toxicological safety of long-term medication. The formulation of the Consensus provides a scientific basis for the rational clinical application of Yifei Zhike capsules, which helps to improve clinical efficacy and reduce medication risks.
3.Compilation Instructions for Expert Consensus on Clinical Application of Yifei Zhike Capsules
Xin LI ; Hongchun ZHANG ; Xuefeng YU ; Weiwei GUO ; Chengjun BAN ; Zhifei WANG ; Yuanyuan LI ; Yingjie ZHI ; Xin CUI ; Yanming XIE
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(18):143-148
The compilation instructions for the Expert Consensus on Clinical Application of Yifei Zhike Capsules systematically expound the development background, methodological framework, and core achievements of this consensus. In view of the problems existing in the clinical application of Yifei Zhike Capsules, such as insufficient efficacy evidence and lack of standardized syndrome differentiation, the Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences took the lead and collaborated with 21 tertiary grade-A hospitals and research institutions across China to form a multidisciplinary expert group (comprising 30 experts in clinical medicine, pharmacy, and methodology). The compilation work was carried out in strict accordance with the World Health Organization (WHO) guidelines, the GB/T 1.1-2020 standard, and the writing specifications for the explanatory notes of expert consensus on clinical application of Chinese patent medicines. Through systematic literature retrieval (including 32 studies, with 24 clinical studies), Grading of Recommendations Assessment, Development and Evaluations (GRADE)-based evidence grading, and multiple rounds of discussions using the nominal group method (25 experts voted to determine 17 clinical questions), 5 evidence-based recommendations and 11 expert consensus suggestions were formed. It is clarified that this medicine (Yifei Zhike Capsules) is applicable to the treatment of expectoration/hemoptysis in acute and chronic bronchitis and the adjuvant treatment of pulmonary tuberculosis. It is recommended that it can be used alone or in combination with anti-tuberculosis drugs. The safety evaluation shows that this medicine mainly induces the following adverse reactions: mild gastrointestinal reactions (such as nausea and abdominal pain) and rashes. The contraindicated populations include pregnant women and women during menstruation. The compilation process of the consensus underwent three rounds of expert letter reviews, two rounds of peer reviews, and quality control assessments to ensure methodological rigor and clinical applicability. In addition, through policy alignment, academic promotion, and a dynamic revision mechanism, the standardization of clinical application was promoted, providing a demonstration for the evidence-based transformation of characteristic therapies of Miao medicine.
4.Development of intelligent equipment for rapid microbial detection of Atractylodis Macrocephalae Rhizoma decoction pieces based on measurement technology for traditional Chinese medicine manufacturing.
Yang LIU ; Wu-Zhen QI ; Yu-Tong WU ; Shan-Xi ZHU ; Xiao-Jun ZHAO ; Qia-Tong XIE ; Yu-Feng GUO ; Jing ZHAO ; Nan LI ; Shi-Jun WANG ; Qi-Hui SUN ; Zhi-Sheng WU
China Journal of Chinese Materia Medica 2025;50(16):4610-4618
Microbial detection and control of traditional Chinese medicine(TCM) decoction pieces are crucial for the quality control of TCM preparations. It is also a key area of research in the measurement technology and equipment development for TCM manufacturing. Guided by TCM manufacturing measurement methodologies, this study presented a design of a novel portable microbial detection device, using Atractylodis Macrocephalae Rhizoma decoction pieces as a demonstration. Immunomagnetic separation technology was employed for specific isolation and labeling of target microorganisms. Enzymatic signal amplification was utilized to convert weak biological signals into colorimetric signals, constructing an optical biosensor. A self-developed smartphone APP was further applied to analyze the colorimetric signals and quantify target concentrations. A portable and automated detection system based on Arduino microcontroller was developed to automatically perform target microbial separation/extraction, as well as mimetic enzyme labeling and catalytic reactions. The developed equipment specifically focuses on the rapid and quantitative microbial analysis of TCM active pharmaceutical ingredients, intermediates in TCM manufacturing, and final TCM products. Experimental results demonstrate that the equipment could detect Salmonella in samples within 2 h, with a detection limit as low as 5.1 × 10~3 CFU·mL~(-1). The equipment enables the rapid detection of microorganisms in TCM decoction pieces, providing a potential technical solution for on-site rapid screening of microbial contamination indicators in TCM. It has broad application prospects in measurement technology for TCM manufacturing and offers strong technical support for the modernization, industrialization, and intelligent development of TCM.
Drugs, Chinese Herbal/analysis*
;
Atractylodes/microbiology*
;
Rhizome/microbiology*
;
Biosensing Techniques/methods*
;
Medicine, Chinese Traditional
;
Colorimetry/instrumentation*
;
Quality Control
5.ADAR1 Regulates the ERK/c-FOS/MMP-9 Pathway to Drive the Proliferation and Migration of Non-small Cell Lung Cancer Cells.
Li ZHANG ; Xue PAN ; Wenqing YAN ; Shuilian ZHANG ; Chiyu MA ; Chenpeng LI ; Kexin ZHU ; Nijia LI ; Zizhong YOU ; Xueying ZHONG ; Zhi XIE ; Zhiyi LV ; Weibang GUO ; Yu CHEN ; Danxia LU ; Xuchao ZHANG
Chinese Journal of Lung Cancer 2025;28(9):647-657
BACKGROUND:
Double-stranded RNA-specific adenosine deaminase 1 (ADAR1) binds to double-stranded RNA and catalyzes the deamination of adenosine (A) to inosine (I). The functional mechanism of ADAR1 in non-small cell lung cancer (NSCLC) remains incompletely understood. This study aimed to investigate the prognostic significance of ADAR1 in NSCLC and to elucidate its potential role in regulating tumor cell proliferation and migration.
METHODS:
Data from The Cancer Genome Atlas (TCGA) and cBioPortal were analyzed to assess the correlation between high ADAR1 expression and clinicopathological features as well as prognosis in lung cancer. We performed Western blot (WB), cell proliferation assays, Transwell invasion/migration assays, and nude mouse xenograft modeling to examine the phenotypic changes and molecular mechanisms induced by ADAR1 knockdown. Furthermore, the ADAR1 p150 overexpression model was utilized to validate the proposed mechanism.
RESULTS:
ADAR1 expression was significantly elevated in lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) tissues compared with adjacent non-tumor tissues (LUAD: P=3.70×10-15, LUSC: P=0.016). High ADAR1 expression was associated with poor prognosis (LUAD: P=2.03×10-2, LUSC: P=2.81×10-2) and distant metastasis (P=0.003). Gene Set Enrichment Analysis (GSEA) indicated that elevated ADAR1 was associated with mitogen-activated protein kinase/extracellular signal-regulated kinase (MAPK/ERK) pathway activation, matrix metalloproteinase-9 (MMP-9) expression, and cell adhesion. ADAR1 and MMP-9 levels showed a strongly positive correlation (P=6.45×10-34) in 10 lung cancer cell lines, highest in H1581. Knockdown of ADAR1 in H1581 cells induced a rounded cellular morphology with reduced pseudopodia. Concomitantly, it suppressed cell proliferation, invasion, migration, and in vivo tumorigenesis. It also suppressed ERK phosphorylation and downregulated cellular Finkel-Biskis-Jinkins murine osteosarcoma viral oncogene homolog (c-FOS), MMP-9, N-cadherin, and Vimentin. Conversely, ADAR1 p150 overexpression in PC9 cells enhanced ERK phosphorylation and increased c-FOS and MMP-9 expression.
CONCLUSIONS
High ADAR1 expression is closely associated with poor prognosis and distant metastasis in NSCLC patients. Mechanistically, ADAR1 may promote proliferation, invasion, migration, and tumorigenesis in lung cancer cells via the ERK/c-FOS/MMP-9 axis.
Humans
;
Lung Neoplasms/physiopathology*
;
Adenosine Deaminase/genetics*
;
Matrix Metalloproteinase 9/genetics*
;
Cell Proliferation
;
Carcinoma, Non-Small-Cell Lung/physiopathology*
;
Cell Movement
;
Animals
;
Mice
;
RNA-Binding Proteins/genetics*
;
Female
;
Male
;
Cell Line, Tumor
;
Proto-Oncogene Proteins c-fos/genetics*
;
Middle Aged
;
MAP Kinase Signaling System
;
Gene Expression Regulation, Neoplastic
;
Mice, Nude
;
Extracellular Signal-Regulated MAP Kinases/genetics*
6.Pien Tze Huang Attenuates Cell Proliferation and Stemness Promoted by miR-483-5p in Hepatocellular Carcinoma Cells.
Li-Hui WEI ; Xi CHEN ; A-Ling SHEN ; Yi FANG ; Qiu-Rong XIE ; Zhi GUO ; Thomas J SFERRA ; You-Qin CHEN ; Jun PENG
Chinese journal of integrative medicine 2025;31(9):782-791
OBJECTIVE:
To investigate the effect of miR-483-5p on hepatocellular carcinoma (HCC) cells proliferation and stemness, as well as the attenuating effect of Pien Tze Huang (PZH).
METHODS:
Differentially expressed miRNA between HepG2 cells and hepatic cancer stem-like cells (HCSCs) were identified by a miRNA microarray assay. miR-483-5p mimics were transfected into HepG2 cells to explore the effects of miR-483-5p on cell proliferation and stemness. HepG2 cells and HCSCs were treated with PZH (0, 0.25, 0.50 and 0.75 mg/mL) to explore the effects of PZH on the proliferation and stemness, both in non-induced state and the state induced by miR-483-5p mimics.
RESULTS:
miR-483-5p was significantly up-regulated in HCSCs and its overexpression increased cell proliferation and stemness in HepG2 cells (P<0.05). PZH not only significantly inhibited proliferation in HepG2 cells, but also significantly suppressed the cell proliferation and self-renewal of HCSCs (P<0.05). The effects of miR-483-5p mimics on proliferation and stemness of HepG2 cells were partially abolished by PZH.
CONCLUSIONS
miR-483-5p promotes proliferation and enhances stemness of HepG2 cells, which were attenuated by PZH, demonstrating that miR-483-5p is a potential molecular target for the treatment of HCC and provide experimental evidence to support clinical use of PZH for patients with HCC.
Humans
;
MicroRNAs/metabolism*
;
Cell Proliferation/drug effects*
;
Liver Neoplasms/drug therapy*
;
Carcinoma, Hepatocellular/drug therapy*
;
Hep G2 Cells
;
Neoplastic Stem Cells/metabolism*
;
Drugs, Chinese Herbal/therapeutic use*
;
Gene Expression Regulation, Neoplastic/drug effects*
7.Clinical trial of Morinda officinalis oligosaccharides in the continuation treatment of adults with mild and moderate depression
Shu-Zhe ZHOU ; Zu-Cheng HAN ; Xiu-Zhen WANG ; Yan-Qing CHEN ; Ya-Ling HU ; Xue-Qin YU ; Bin-Hong WANG ; Guo-Zhen FAN ; Hong SANG ; Ying HAI ; Zhi-Jie JIA ; Zhan-Min WANG ; Yan WEI ; Jian-Guo ZHU ; Xue-Qin SONG ; Zhi-Dong LIU ; Li KUANG ; Hong-Ming WANG ; Feng TIAN ; Yu-Xin LI ; Ling ZHANG ; Hai LIN ; Bin WU ; Chao-Ying WANG ; Chang LIU ; Jia-Fan SUN ; Shao-Xiao YAN ; Jun LIU ; Shou-Fu XIE ; Mao-Sheng FANG ; Wei-Feng MI ; Hong-Yan ZHANG
The Chinese Journal of Clinical Pharmacology 2024;40(6):815-819
Objective To observe the efficacy and safety of Morinda officinalis oligosaccharides in the continuation treatment of mild and moderate depression.Methods An open,single-arm,multi-center design was adopted in our study.Adult patients with mild and moderate depression who had received acute treatment of Morinda officinalis oligosaccharides were enrolled and continue to receive Morinda officinalis oligosaccharides capsules for 24 weeks,the dose remained unchanged during continuation treatment.The remission rate,recurrence rate,recurrence time,and the change from baseline to endpoint of Hamilton Depression Scale(HAMD),Hamilton Anxiety Scale(HAMA),Clinical Global Impression-Severity(CGI-S)and Arizona Sexual Experience Scale(ASEX)were evaluated.The incidence of treatment-related adverse events was reported.Results The scores of HAMD-17 at baseline and after treatment were 6.60±1.87 and 5.85±4.18,scores of HAMA were 6.36±3.02 and 4.93±3.09,scores of CGI-S were 1.49±0.56 and 1.29±0.81,scores of ASEX were 15.92±4.72 and 15.57±5.26,with significant difference(P<0.05).After continuation treatment,the remission rate was 54.59%(202 cases/370 cases),and the recurrence rate was 6.49%(24 cases/370 cases),the recurrence time was(64.67±42.47)days.The incidence of treatment-related adverse events was 15.35%(64 cases/417 cases).Conclusion Morinda officinalis oligosaccharides capsules can be effectively used for the continuation treatment of mild and moderate depression,and are well tolerated and safe.
8.The Development of Chinese Herbal Formulae for Non-severe COVID-19 Based on Artificial Intelligence Technology and Investigation of Its Action Mechanisms
Wenting HUANG ; Liansheng QIAO ; Di YAN ; Tengwen LIU ; Hongmei CAO ; Hongyan GUO ; Zhi ZHANG ; Jing CHENG ; Lan XIE ; Qingquan LIU
Journal of Traditional Chinese Medicine 2024;65(1):103-112
ObjectiveTo develop traditional Chinese medicine (TCM) formulae for the treatment of nonsevere coronavirus disease 2019 (COVID-19) and to explore its anti-inflammatory mechanism. MethodsThe dysregulated signaling pathways were determined in macrophages from bronchoalveolar lavage fluid of COVID-19 patients and in lung epithelial cells infected with SARS-CoV-2 in vitro based on transcriptome analysis. A total of 102 TCM formulae for the clinical treatment of nonsevere COVID-19 were collected through literature. The pathway-reversing rates of these formulae in macrophages and lung epithelial cells were evaluated based on signature signaling pathways, and the basic formula was determined in conjunction with TCM theory. The commonly used Chinese materia medica for nonsevere COVID-19 were summarized from the 102 TCM formulae as abovementioned. And together with the screening results from the Pharmacopoeia of the People's Republic of China, a “Chinese materia medica pool” was esta-blished for the development of TCM formulae for COVID-19. The regulatory effects of each herb on signaling pathways were obtained based on targeted transcriptome analysis. Oriented at reversing dysregulated signaling pathways of COVID-19, the calculation was carried out, and the artificial intelligent methods for compositing formulae, that are exhaustive method and parallel computing, were used to obtain candidate compound formulas. Finally, with reference to professional experience, an innovative formula for the treatment of nonsevere COVID-19 was developed. The ethanol extract of the formula was evaluated for its anti-inflammatory effects by detecting the mRNA expression of interleukin 1b (Il1b), C-X-C motif chemokine ligand 2 (Cxcl2), C-X-C motif chemokine ligand 10 (Cxcl10), C-C motif chemokine ligand 2 (Ccl2), nitric oxide synthase 2 (Nos2), and prostaglandin-endoperoxide synthase 2 (Ptgs2) using reverse transcription-quantitative polymerase chain reaction (RT-qPCR) in RAW264.7 cells treated with lipopolysaccharide (LPS). ResultsIn macrophages and lung epithelial cells, 34 dysregulated signaling pathways associated with COVID-19 were identified respectively. The effects of the 102 formulae for clinical treatment of nonsevere COVID-19 were evaluated based on the dysregulated signaling pathways and targeted transcriptome, and the result showed that Yinqiao Powder and Pingwei Powder (银翘散合平胃散, YQPWP) ranked first, reversing 91.18% of the dysregulated signaling pathways in macrophages and 100% of the dysregulated signaling pathways in lung epithelial cells. Additionally, YQPWP had the function of scattering wind and clearing heat, resolving toxins and removing dampness in accordance with the pathogenesis of wind-heat with dampness in COVID-19. It was selected as the basic formula, and was further modified and optimized to develop an innovative fomula Qiaobang Zhupi Yin (翘蒡术皮饮, QBZPY) based on expert experience and artificial intelligence in composing formulae. QBZPY can reverse all the dysregulated signaling pathways associated with COVID-19 in macrophages and lung epithelial cells, with the reversing rates of 100%. The chief medicinal of QBZPY, including Lianqiao (Fructus Forsythiae), Xixiancao (Herba Siegesbeckiae) and Niubangzi (Fructus Arctii), can down-regulate multiple signaling pathways related with virus infection, immune response, and epithelial damage. RT-qPCR results indicated that compared with the model group, the QBZPY group down-regulated the mRNA expression of Il1b, tumor necrosis factor (Tnf), Cxcl2, Cxcl10, Ccl2, Nos2 and Ptgs2 induced by LPS in RAW264.7 cells (P<0.05 or P<0.01). ConclusionBased on targeted transcriptome analysis, expert experience in TCM and artificial intelligence, QBZPY has been developed for the treatment of nonsevere COVID-19. The ethanol extract of QBZPY has been found to inhibit mRNA expression of several pro-inflammatory genes in a cellular inflammation model.
9.Computer-vision-based artificial intelligence for detection and recognition of instruments and organs during radical laparoscopic gastrectomy for gastric cancer: a multicenter study
Kecheng ZHANG ; Zhi QIAO ; Li YANG ; Tao ZHANG ; Fenglin LIU ; Dachuan SUN ; Tianyu XIE ; Lei GUO ; Canrong LU
Chinese Journal of Gastrointestinal Surgery 2024;27(5):464-470
Objective:To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer.Methods:Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5–10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy.Results:The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing.Conclusion:The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.
10.Computer-vision-based artificial intelligence for detection and recognition of instruments and organs during radical laparoscopic gastrectomy for gastric cancer: a multicenter study
Kecheng ZHANG ; Zhi QIAO ; Li YANG ; Tao ZHANG ; Fenglin LIU ; Dachuan SUN ; Tianyu XIE ; Lei GUO ; Canrong LU
Chinese Journal of Gastrointestinal Surgery 2024;27(5):464-470
Objective:To investigate the feasibility and accuracy of computer vision-based artificial intelligence technology in detecting and recognizing instruments and organs in the scenario of radical laparoscopic gastrectomy for gastric cancer.Methods:Eight complete laparoscopic distal radical gastrectomy surgery videos were collected from four large tertiary hospitals in China (First Medical Center of Chinese PLA General Hospital [three cases], Liaoning Cancer Hospital [two cases], Liyang Branch of Jiangsu Province People's Hospital [two cases], and Fudan University Shanghai Cancer Center [one case]). PR software was used to extract frames every 5–10 seconds and convert them into image frames. To ensure quality, deduplication was performed manually to remove obvious duplication and blurred image frames. After conversion and deduplication, there were 3369 frame images with a resolution of 1,920×1,080 PPI. LabelMe was used for instance segmentation of the images into the following 23 categories: veins, arteries, sutures, needle holders, ultrasonic knives, suction devices, bleeding, colon, forceps, gallbladder, small gauze, Hem-o-lok, Hem-o-lok appliers, electrocautery hooks, small intestine, hepatogastric ligaments, liver, omentum, pancreas, spleen, surgical staplers, stomach, and trocars. The frame images were randomly allocated to training and validation sets in a 9:1 ratio. The YOLOv8 deep learning framework was used for model training and validation. Precision, recall, average precision (AP), and mean average precision (mAP) were used to evaluate detection and recognition accuracy.Results:The training set contained 3032 frame images comprising 30 895 instance segmentation counts across 23 categories. The validation set contained 337 frame images comprising 3407 instance segmentation counts. The YOLOv8m model was used for training. The loss curve of the training set showed a smooth gradual decrease in loss value as the number of iteration calculations increased. In the training set, the AP values of all 23 categories were above 0.90, with a mAP of 0.99, whereas in the validation set, the mAP of the 23 categories was 0.82. As to individual categories, the AP values for ultrasonic knives, needle holders, forceps, gallbladders, small pieces of gauze, and surgical staplers were 0.96, 0.94, 0.91, 0.91, 0.91, and 0.91, respectively. The model successfully inferred and applied to a 5-minutes video segment of laparoscopic gastroenterostomy suturing.Conclusion:The primary finding of this multicenter study is that computer vision can efficiently, accurately, and in real-time detect organs and instruments in various scenarios of radical laparoscopic gastrectomy for gastric cancer.

Result Analysis
Print
Save
E-mail