Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features
Abstract Recurrence is the key factor affecting the prognosis of osteosarcoma. Currently, there is a lack of clinically useful tools to predict osteosarcoma recurrence. The application of pathological images for artificial intelligence‐assisted accurate prediction of tumour outcomes is increasing. T...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-09-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12175 |
| _version_ | 1797682941255483392 |
|---|---|
| author | Zhan Wang Haoda Lu Yan Wu Shihong Ren Diarra mohamed Diaty Yanbiao Fu Yi Zou Lingling Zhang Zenan Wang Fangqian Wang Shu Li Xinmi Huo Weimiao Yu Jun Xu Zhaoming Ye |
| author_facet | Zhan Wang Haoda Lu Yan Wu Shihong Ren Diarra mohamed Diaty Yanbiao Fu Yi Zou Lingling Zhang Zenan Wang Fangqian Wang Shu Li Xinmi Huo Weimiao Yu Jun Xu Zhaoming Ye |
| author_sort | Zhan Wang |
| collection | DOAJ |
| description | Abstract Recurrence is the key factor affecting the prognosis of osteosarcoma. Currently, there is a lack of clinically useful tools to predict osteosarcoma recurrence. The application of pathological images for artificial intelligence‐assisted accurate prediction of tumour outcomes is increasing. Thus, the present study constructed a quantitative histological image classifier with tumour nuclear features to predict osteosarcoma outcomes using haematoxylin and eosin (H&E)‐stained whole‐slide images (WSIs) from 150 osteosarcoma patients. We first segmented eight distinct tissues in osteosarcoma H&E‐stained WSIs, with an average accuracy of 90.63% on the testing set. The tumour areas were automatically and accurately acquired, facilitating the tumour cell nuclear feature extraction process. Based on six selected tumour nuclear features, we developed an osteosarcoma histological image classifier (OSHIC) to predict the recurrence and survival of osteosarcoma following standard treatment. The quantitative OSHIC derived from tumour nuclear features independently predicted the recurrence and survival of osteosarcoma patients, thereby contributing to precision oncology. Moreover, we developed a fully automated workflow to extract quantitative image features, evaluate the diagnostic values of feature sets and build classifiers to predict osteosarcoma outcomes. Thus, the present study provides a novel tool for predicting osteosarcoma outcomes, which has a broad application prospect in clinical practice. |
| first_indexed | 2024-03-12T00:07:11Z |
| format | Article |
| id | doaj.art-74ac60931e8c4de6a4b3c7f9fa5a5ee6 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-03-12T00:07:11Z |
| publishDate | 2023-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-74ac60931e8c4de6a4b3c7f9fa5a5ee62023-09-16T16:19:34ZengWileyCAAI Transactions on Intelligence Technology2468-23222023-09-018383684810.1049/cit2.12175Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological featuresZhan Wang0Haoda Lu1Yan Wu2Shihong Ren3Diarra mohamed Diaty4Yanbiao Fu5Yi Zou6Lingling Zhang7Zenan Wang8Fangqian Wang9Shu Li10Xinmi Huo11Weimiao Yu12Jun Xu13Zhaoming Ye14Department of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaInstitute for AI in Medicine School of Artificial Intelligence, Nanjing University of Information Science & Technology Nanjing ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Pathology The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Pathology The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaDepartment of Hematology Shanghai General Hospital Shanghai Jiao Tong University School of Medicine Shanghai ChinaBioinformatics Institute (BII) Agency for Science, Technology and Research (A*STAR) Singapore SingaporeBioinformatics Institute (BII) Agency for Science, Technology and Research (A*STAR) Singapore SingaporeInstitute for AI in Medicine School of Artificial Intelligence, Nanjing University of Information Science & Technology Nanjing ChinaDepartment of Orthopedic Surgery The Second Affiliated Hospital Zhejiang University School of Medicine Hangzhou ChinaAbstract Recurrence is the key factor affecting the prognosis of osteosarcoma. Currently, there is a lack of clinically useful tools to predict osteosarcoma recurrence. The application of pathological images for artificial intelligence‐assisted accurate prediction of tumour outcomes is increasing. Thus, the present study constructed a quantitative histological image classifier with tumour nuclear features to predict osteosarcoma outcomes using haematoxylin and eosin (H&E)‐stained whole‐slide images (WSIs) from 150 osteosarcoma patients. We first segmented eight distinct tissues in osteosarcoma H&E‐stained WSIs, with an average accuracy of 90.63% on the testing set. The tumour areas were automatically and accurately acquired, facilitating the tumour cell nuclear feature extraction process. Based on six selected tumour nuclear features, we developed an osteosarcoma histological image classifier (OSHIC) to predict the recurrence and survival of osteosarcoma following standard treatment. The quantitative OSHIC derived from tumour nuclear features independently predicted the recurrence and survival of osteosarcoma patients, thereby contributing to precision oncology. Moreover, we developed a fully automated workflow to extract quantitative image features, evaluate the diagnostic values of feature sets and build classifiers to predict osteosarcoma outcomes. Thus, the present study provides a novel tool for predicting osteosarcoma outcomes, which has a broad application prospect in clinical practice.https://doi.org/10.1049/cit2.12175diseaseslearning (artificial intelligence)surgerytumours |
| spellingShingle | Zhan Wang Haoda Lu Yan Wu Shihong Ren Diarra mohamed Diaty Yanbiao Fu Yi Zou Lingling Zhang Zenan Wang Fangqian Wang Shu Li Xinmi Huo Weimiao Yu Jun Xu Zhaoming Ye Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features CAAI Transactions on Intelligence Technology diseases learning (artificial intelligence) surgery tumours |
| title | Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| title_full | Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| title_fullStr | Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| title_full_unstemmed | Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| title_short | Predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| title_sort | predicting recurrence in osteosarcoma via a quantitative histological image classifier derived from tumour nuclear morphological features |
| topic | diseases learning (artificial intelligence) surgery tumours |
| url | https://doi.org/10.1049/cit2.12175 |
| work_keys_str_mv | AT zhanwang predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT haodalu predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT yanwu predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT shihongren predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT diarramohameddiaty predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT yanbiaofu predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT yizou predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT linglingzhang predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT zenanwang predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT fangqianwang predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT shuli predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT xinmihuo predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT weimiaoyu predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT junxu predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures AT zhaomingye predictingrecurrenceinosteosarcomaviaaquantitativehistologicalimageclassifierderivedfromtumournuclearmorphologicalfeatures |