An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging
Abstract Introduction Near‐infrared autofluorescence imaging (NIFI) can be used to identify parathyroid gland (PG) during surgery. The purpose of the study is to establish a new model, help surgeons better identify, and protect PGs. Methods Five hundred and twenty three NIFI images were selected. Th...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-02-01
|
| Series: | Cancer Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cam4.7065 |
| _version_ | 1797265477372739584 |
|---|---|
| author | Fan Yu Tian Sang Jie Kang Xianzhao Deng Bomin Guo Hangzhou Yang Xiaoyi Chen Youben Fan Xuehai Ding Bo Wu |
| author_facet | Fan Yu Tian Sang Jie Kang Xianzhao Deng Bomin Guo Hangzhou Yang Xiaoyi Chen Youben Fan Xuehai Ding Bo Wu |
| author_sort | Fan Yu |
| collection | DOAJ |
| description | Abstract Introduction Near‐infrared autofluorescence imaging (NIFI) can be used to identify parathyroid gland (PG) during surgery. The purpose of the study is to establish a new model, help surgeons better identify, and protect PGs. Methods Five hundred and twenty three NIFI images were selected. The PGs were recorded by NIFI and marked with artificial intelligence (AI) model. The recognition rate for PGs was calculated. Analyze the differences between surgeons of different years of experience and AI recognition, and evaluate the diagnostic and therapeutic efficacy of AI model. Results Our model achieved 83.5% precision and 57.8% recall in the internal validation set. The visual recognition rate of AI model was 85.2% and 82.4% on internal and external sets. The PG recognition rate of AI model is higher than that of junior surgeons (p < 0.05). Conclusions This AI model will help surgeons identify PGs, and develop their learning ability and self‐confidence. |
| first_indexed | 2024-04-25T00:45:25Z |
| format | Article |
| id | doaj.art-b25b25953ec944eeb7cbe0ef855b2567 |
| institution | Directory Open Access Journal |
| issn | 2045-7634 |
| language | English |
| last_indexed | 2024-04-25T00:45:25Z |
| publishDate | 2024-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Medicine |
| spelling | doaj.art-b25b25953ec944eeb7cbe0ef855b25672024-03-12T04:52:34ZengWileyCancer Medicine2045-76342024-02-01134n/an/a10.1002/cam4.7065An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imagingFan Yu0Tian Sang1Jie Kang2Xianzhao Deng3Bomin Guo4Hangzhou Yang5Xiaoyi Chen6Youben Fan7Xuehai Ding8Bo Wu9Department of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaSchool of Computer Engineering and Science Shanghai University Shanghai ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaNingbo Institute of Life and Health Industry University of Chinese Academy of Sciences Ningbo ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaSchool of Computer Engineering and Science Shanghai University Shanghai ChinaDepartment of Thyroid Breast and Hernia Surgery, Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai ChinaAbstract Introduction Near‐infrared autofluorescence imaging (NIFI) can be used to identify parathyroid gland (PG) during surgery. The purpose of the study is to establish a new model, help surgeons better identify, and protect PGs. Methods Five hundred and twenty three NIFI images were selected. The PGs were recorded by NIFI and marked with artificial intelligence (AI) model. The recognition rate for PGs was calculated. Analyze the differences between surgeons of different years of experience and AI recognition, and evaluate the diagnostic and therapeutic efficacy of AI model. Results Our model achieved 83.5% precision and 57.8% recall in the internal validation set. The visual recognition rate of AI model was 85.2% and 82.4% on internal and external sets. The PG recognition rate of AI model is higher than that of junior surgeons (p < 0.05). Conclusions This AI model will help surgeons identify PGs, and develop their learning ability and self‐confidence.https://doi.org/10.1002/cam4.7065artificial intelligencemedical segmentationnear‐infrared autofluorescence imagingparathyroid glandthyroidectomy |
| spellingShingle | Fan Yu Tian Sang Jie Kang Xianzhao Deng Bomin Guo Hangzhou Yang Xiaoyi Chen Youben Fan Xuehai Ding Bo Wu An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging Cancer Medicine artificial intelligence medical segmentation near‐infrared autofluorescence imaging parathyroid gland thyroidectomy |
| title | An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging |
| title_full | An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging |
| title_fullStr | An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging |
| title_full_unstemmed | An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging |
| title_short | An automatic parathyroid recognition and segmentation model based on deep learning of near‐infrared autofluorescence imaging |
| title_sort | automatic parathyroid recognition and segmentation model based on deep learning of near infrared autofluorescence imaging |
| topic | artificial intelligence medical segmentation near‐infrared autofluorescence imaging parathyroid gland thyroidectomy |
| url | https://doi.org/10.1002/cam4.7065 |
| work_keys_str_mv | AT fanyu anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT tiansang anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT jiekang anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xianzhaodeng anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT bominguo anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT hangzhouyang anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xiaoyichen anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT youbenfan anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xuehaiding anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT bowu anautomaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT fanyu automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT tiansang automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT jiekang automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xianzhaodeng automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT bominguo automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT hangzhouyang automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xiaoyichen automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT youbenfan automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT xuehaiding automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging AT bowu automaticparathyroidrecognitionandsegmentationmodelbasedondeeplearningofnearinfraredautofluorescenceimaging |