Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia
Abstract The rapid development of deep learning has revolutionized medical image processing, including analyzing whole slide images (WSIs). Despite the demonstrated potential for characterizing gene mutations directly from WSIs in certain cancers, challenges remain due to image resolution and relian...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Precision Oncology |
| Online Access: | https://doi.org/10.1038/s41698-025-00804-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863429184618496 |
|---|---|
| author | Bo-Han Wei Xavier Cheng-Hong Tsai Kuo-Jui Sun Min-Yen Lo Sheng-Yu Hung Wen-Chien Chou Hwei-Fang Tien Hsin-An Hou Chien-Yu Chen |
| author_facet | Bo-Han Wei Xavier Cheng-Hong Tsai Kuo-Jui Sun Min-Yen Lo Sheng-Yu Hung Wen-Chien Chou Hwei-Fang Tien Hsin-An Hou Chien-Yu Chen |
| author_sort | Bo-Han Wei |
| collection | DOAJ |
| description | Abstract The rapid development of deep learning has revolutionized medical image processing, including analyzing whole slide images (WSIs). Despite the demonstrated potential for characterizing gene mutations directly from WSIs in certain cancers, challenges remain due to image resolution and reliance on manual annotations for acute myeloid leukemia (AML). We, therefore, propose a deep learning model based on multiple instance learning (MIL) with ensemble techniques to predict gene mutations from AML WSIs. Our model predicts NPM1 mutations and FLT3-ITD without requiring patch-level or cell-level annotations. Using a dataset of 572 WSIs, the largest database with both WSI and genetic mutation information, our model achieved an AUC of 0.90 ± 0.08 for NPM1 and 0.80 ± 0.10 for FLT3-ITD in the testing cohort. Additionally, we found that blasts are pivotal indicators for gene mutation predictions, with their proportions varying between mutated and standard WSIs, highlighting the clinical potential of AML WSI analysis. |
| format | Article |
| id | doaj-art-82339090b2b6416b985c3a044a999de8 |
| institution | Kabale University |
| issn | 2397-768X |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Precision Oncology |
| spelling | doaj-art-82339090b2b6416b985c3a044a999de82025-02-09T12:09:23ZengNature Portfolionpj Precision Oncology2397-768X2025-02-01911810.1038/s41698-025-00804-0Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemiaBo-Han Wei0Xavier Cheng-Hong Tsai1Kuo-Jui Sun2Min-Yen Lo3Sheng-Yu Hung4Wen-Chien Chou5Hwei-Fang Tien6Hsin-An Hou7Chien-Yu Chen8Center for Advanced Computing and Imaging in Biomedicine, National Taiwan UniversityDivision of Hematology, Department of Internal Medicine, National Taiwan University HospitalDivision of Hematology, Department of Internal Medicine, National Taiwan University HospitalDivision of Hematology, Department of Internal Medicine, National Taiwan University Hospital Yunlin BranchDepartment of Hematological Oncology, National Taiwan University Cancer CenterDivision of Hematology, Department of Internal Medicine, National Taiwan University HospitalDivision of Hematology, Department of Internal Medicine, National Taiwan University HospitalDivision of Hematology, Department of Internal Medicine, National Taiwan University HospitalCenter for Advanced Computing and Imaging in Biomedicine, National Taiwan UniversityAbstract The rapid development of deep learning has revolutionized medical image processing, including analyzing whole slide images (WSIs). Despite the demonstrated potential for characterizing gene mutations directly from WSIs in certain cancers, challenges remain due to image resolution and reliance on manual annotations for acute myeloid leukemia (AML). We, therefore, propose a deep learning model based on multiple instance learning (MIL) with ensemble techniques to predict gene mutations from AML WSIs. Our model predicts NPM1 mutations and FLT3-ITD without requiring patch-level or cell-level annotations. Using a dataset of 572 WSIs, the largest database with both WSI and genetic mutation information, our model achieved an AUC of 0.90 ± 0.08 for NPM1 and 0.80 ± 0.10 for FLT3-ITD in the testing cohort. Additionally, we found that blasts are pivotal indicators for gene mutation predictions, with their proportions varying between mutated and standard WSIs, highlighting the clinical potential of AML WSI analysis.https://doi.org/10.1038/s41698-025-00804-0 |
| spellingShingle | Bo-Han Wei Xavier Cheng-Hong Tsai Kuo-Jui Sun Min-Yen Lo Sheng-Yu Hung Wen-Chien Chou Hwei-Fang Tien Hsin-An Hou Chien-Yu Chen Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia npj Precision Oncology |
| title | Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| title_full | Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| title_fullStr | Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| title_full_unstemmed | Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| title_short | Annotation-free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| title_sort | annotation free deep learning for predicting gene mutations from whole slide images of acute myeloid leukemia |
| url | https://doi.org/10.1038/s41698-025-00804-0 |
| work_keys_str_mv | AT bohanwei annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT xavierchenghongtsai annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT kuojuisun annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT minyenlo annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT shengyuhung annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT wenchienchou annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT hweifangtien annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT hsinanhou annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia AT chienyuchen annotationfreedeeplearningforpredictinggenemutationsfromwholeslideimagesofacutemyeloidleukemia |