BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some ...BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.展开更多
Objective To explore the association of genetic polymorphisms in the genes encoding the anti-Miillerian hormone (AMH) and its type H receptor (AMHRII) with ovarian hyperstimulation syndrome (OHSS). Methods Using...Objective To explore the association of genetic polymorphisms in the genes encoding the anti-Miillerian hormone (AMH) and its type H receptor (AMHRII) with ovarian hyperstimulation syndrome (OHSS). Methods Using polymerase chain reaction (PCR) and DNA sequencing techniques, the exons of AMH and AMHRII were analyzed in 27 OHSS patients (OHSS group) and 22 non-OHSS patients (control group) who were applied controlled ovarian hyper- stimulation (COH). Single nucleotide polymorphisms (SNPs) were also analyzed. Results SNPs G〉 T at position 146 of AMH exon 1 and G〉 A at position 134 of AMH exon 2 showed significant differences between the OHSS group and control group (P〈0.05). SNP G〉 T at position 303 of AMH exon 1 showed no significant difference between the OHSS group and control group (P〉0.05). No SNP was detected from the AMHR H exons 1 to 11 in either groups. Conclusion Genetic polymorphisms in the AMH gene may be a cause of ovarian hypersensitivity to exogenous hormone stimulation and the development of OHSS.展开更多
基金The Shanxi Provincial Administration of Traditional Chinese Medicine,No.2023ZYYDA2005.
文摘BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.
基金supported by a scientific research grant from Tongji Hospital of Tongji Medical College of Huazhong University of Science and Technologythe National Natural Science Fund (Project No. 81200474)
文摘Objective To explore the association of genetic polymorphisms in the genes encoding the anti-Miillerian hormone (AMH) and its type H receptor (AMHRII) with ovarian hyperstimulation syndrome (OHSS). Methods Using polymerase chain reaction (PCR) and DNA sequencing techniques, the exons of AMH and AMHRII were analyzed in 27 OHSS patients (OHSS group) and 22 non-OHSS patients (control group) who were applied controlled ovarian hyper- stimulation (COH). Single nucleotide polymorphisms (SNPs) were also analyzed. Results SNPs G〉 T at position 146 of AMH exon 1 and G〉 A at position 134 of AMH exon 2 showed significant differences between the OHSS group and control group (P〈0.05). SNP G〉 T at position 303 of AMH exon 1 showed no significant difference between the OHSS group and control group (P〉0.05). No SNP was detected from the AMHR H exons 1 to 11 in either groups. Conclusion Genetic polymorphisms in the AMH gene may be a cause of ovarian hypersensitivity to exogenous hormone stimulation and the development of OHSS.