AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology
Background: Whole-slide image (WSI) is foundational for artificial intelligence in tumor diagnosis, treatment planning, and prognosis prediction. Efficient management of WSI labels is crucial for clinical digitalization; however, manual or semiautomatic methods limit scalability. Enhancing automatic...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | EngMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2950489925000065 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864115907526656 |
|---|---|
| author | Yingnan Zhao Huifen Ye Jing Yang Su Yao Maohua Lv Zhihong Chen Yunrui Ye Qingru Hu Cheng Lu Zaiyi Liu Ke Zhao Zhihua Chen |
| author_facet | Yingnan Zhao Huifen Ye Jing Yang Su Yao Maohua Lv Zhihong Chen Yunrui Ye Qingru Hu Cheng Lu Zaiyi Liu Ke Zhao Zhihua Chen |
| author_sort | Yingnan Zhao |
| collection | DOAJ |
| description | Background: Whole-slide image (WSI) is foundational for artificial intelligence in tumor diagnosis, treatment planning, and prognosis prediction. Efficient management of WSI labels is crucial for clinical digitalization; however, manual or semiautomatic methods limit scalability. Enhancing automatic pathological label recognition is critical to advancing digital pathology, improving efficiency, and drive precision oncology. Methods: We developed Auto LDP, a method for automatic labeling of digital pathology, which identifies textual information used for labeling slides. The method includes four steps: identifying text position using the CRAFT model, recognizing text content using the ParSeq model, identifying slice type using the ConvNext classifier, and combining relevant information to generate a new name. The naming format is divided into four parts: pathology ID, wax block ID, staining type, and slice type. We used the accuracy and processing time to validate our method using two validation sets. Results: The AutoLDP system was 20 times faster than manual labeling. The files per minute in the solid-state drives of CRAFT + ParSeq were the highest among all methods at 136.95 in validation set 1 and 170.95 in validation set 2. We compared the proposed model with several commonly used text detection and recognition models including ABinet, CRNN, TRBA, and Vitstr. The results show that we achieved an accuracy of 97.60 % in just 87.62 s in validation set 1 with 200 cases, which was significantly better than that of the other models. In addition, the accuracy reached 96.98 % in validation set 2 with 13,667 cases, confirming the generalization ability of the model. Conclusion: In this study, we proposed a new model, AutoLDP, automates the extraction and recognition of key information from WSI, enabling standardized naming, and significantly improving labeling efficiency. This innovation supports the digital transformation of pathology and advances precision medicine. |
| format | Article |
| id | doaj-art-bfc9b36c5df54bb58d5d156846badfbb |
| institution | Kabale University |
| issn | 2950-4899 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EngMedicine |
| spelling | doaj-art-bfc9b36c5df54bb58d5d156846badfbb2025-02-09T05:02:06ZengElsevierEngMedicine2950-48992025-03-0121100060AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathologyYingnan Zhao0Huifen Ye1Jing Yang2Su Yao3Maohua Lv4Zhihong Chen5Yunrui Ye6Qingru Hu7Cheng Lu8Zaiyi Liu9Ke Zhao10Zhihua Chen11Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China; Huadu District Maternal and Child Health Care Hospital, Guangzhou 510800, China; Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, ChinaDepartment of Radiology, Fudan University Shanghai Cancer Center, Shanghai 200032, China; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, ChinaDepartment of Gastroenterology, The Second Affiliated Hospital, Guangzhou Medical University, Guangzhou 510260, ChinaDepartment of Pathology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, ChinaDepartment of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, ChinaInstitute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, ChinaDepartment of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, ChinaDepartment of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, ChinaDepartment of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, China; Medical Research Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Corresponding author. Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan Er Road, Guangzhou 510080, China.Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, China; Corresponding author. Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan Er Road, Guangzhou 510080, China.Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong Provincial People's Hospital, Guangzhou 510080, China; Medical Research Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou 510080, China; Corresponding author. Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan Er Road, Guangzhou 510080, China.Institute of Computing Science and Technology, Guangzhou University, Guangzhou 510006, China; Corresponding author. Institute of Computing Science and Technology, Guangzhou University, 230 West Waihuan Road, Guangzhou 510006, China.Background: Whole-slide image (WSI) is foundational for artificial intelligence in tumor diagnosis, treatment planning, and prognosis prediction. Efficient management of WSI labels is crucial for clinical digitalization; however, manual or semiautomatic methods limit scalability. Enhancing automatic pathological label recognition is critical to advancing digital pathology, improving efficiency, and drive precision oncology. Methods: We developed Auto LDP, a method for automatic labeling of digital pathology, which identifies textual information used for labeling slides. The method includes four steps: identifying text position using the CRAFT model, recognizing text content using the ParSeq model, identifying slice type using the ConvNext classifier, and combining relevant information to generate a new name. The naming format is divided into four parts: pathology ID, wax block ID, staining type, and slice type. We used the accuracy and processing time to validate our method using two validation sets. Results: The AutoLDP system was 20 times faster than manual labeling. The files per minute in the solid-state drives of CRAFT + ParSeq were the highest among all methods at 136.95 in validation set 1 and 170.95 in validation set 2. We compared the proposed model with several commonly used text detection and recognition models including ABinet, CRNN, TRBA, and Vitstr. The results show that we achieved an accuracy of 97.60 % in just 87.62 s in validation set 1 with 200 cases, which was significantly better than that of the other models. In addition, the accuracy reached 96.98 % in validation set 2 with 13,667 cases, confirming the generalization ability of the model. Conclusion: In this study, we proposed a new model, AutoLDP, automates the extraction and recognition of key information from WSI, enabling standardized naming, and significantly improving labeling efficiency. This innovation supports the digital transformation of pathology and advances precision medicine.http://www.sciencedirect.com/science/article/pii/S2950489925000065Digital pathologyWhole slide imageAutoLDPPrecision oncologyDeep learning |
| spellingShingle | Yingnan Zhao Huifen Ye Jing Yang Su Yao Maohua Lv Zhihong Chen Yunrui Ye Qingru Hu Cheng Lu Zaiyi Liu Ke Zhao Zhihua Chen AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology EngMedicine Digital pathology Whole slide image AutoLDP Precision oncology Deep learning |
| title | AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology |
| title_full | AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology |
| title_fullStr | AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology |
| title_full_unstemmed | AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology |
| title_short | AutoLDP: An accurate and efficient artificial intelligence-based tool for automatic labeling of digital pathology |
| title_sort | autoldp an accurate and efficient artificial intelligence based tool for automatic labeling of digital pathology |
| topic | Digital pathology Whole slide image AutoLDP Precision oncology Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2950489925000065 |
| work_keys_str_mv | AT yingnanzhao autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT huifenye autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT jingyang autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT suyao autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT maohualv autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT zhihongchen autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT yunruiye autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT qingruhu autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT chenglu autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT zaiyiliu autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT kezhao autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology AT zhihuachen autoldpanaccurateandefficientartificialintelligencebasedtoolforautomaticlabelingofdigitalpathology |