Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach
Machine learning assisted diagnosis of acromegaly from facial photographs has been proved feasible in recent years. According to our previous research, facial and limb changes exist in patients with acromegaly at early stage. We aimed to facilitate the process of early self-screening for acromegaly...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9305194/ |
| _version_ | 1818936151012016128 |
|---|---|
| author | Chengbin Duan Wenli Chen Shun Yao Zhigang Mao Zongming Wang Bin Hu Haosen Jiao Dimin Zhu Yonghong Zhu Haijun Wang |
| author_facet | Chengbin Duan Wenli Chen Shun Yao Zhigang Mao Zongming Wang Bin Hu Haosen Jiao Dimin Zhu Yonghong Zhu Haijun Wang |
| author_sort | Chengbin Duan |
| collection | DOAJ |
| description | Machine learning assisted diagnosis of acromegaly from facial photographs has been proved feasible in recent years. According to our previous research, facial and limb changes exist in patients with acromegaly at early stage. We aimed to facilitate the process of early self-screening for acromegaly from hand photographs by using a deep-learning approach. In this study, a dataset containing hand photographs of 635 acromegaly patients and 192 normal people were used to train a Deep Convolution Neural Network (DCNN). We augmented these images with tailed raw data. The prediction is performed in an end-to-end paradigm without manual pre-processing, from the input photograph to the final prediction. The trained models were evaluated on a separate dataset to validate the effectiveness. Different kinds of advanced DCNN architecture were explored in this novel task and they showed significant performance compared with the results from human doctors specialized in pituitary adenoma. We further used heat-map to provide visual explanations to illustrate how the DCNN diagnosed the acromegaly. The final result of our experiment showed a sensitivity of 0.983, a specificity of 0.920, a PPV of 0.966, a NPV of 0.958 and a F1-score of 0.974. In our method, the sensitivity was higher than doctors' predictions, which indicates that our method could effectively help people detect acromegaly by themselves. Furthermore, our algorithm paid more attention to fingers and joints on which human doctors focused. This is the first study to investigate whether it is possible to detect acromegaly by machine learning from hand photographs and compare the result with human doctors specialized in pituitary adenoma. This study provided an easy-to-use tool for early self-screening of acromegaly for people without medical knowledge, so that acromegaly patients can get more timely treatment. |
| first_indexed | 2024-12-20T05:31:30Z |
| format | Article |
| id | doaj.art-f55fa544cfda4d7194f8b7322461b4e4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T05:31:30Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f55fa544cfda4d7194f8b7322461b4e42022-12-21T19:51:43ZengIEEEIEEE Access2169-35362021-01-0192846285310.1109/ACCESS.2020.30468789305194Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning ApproachChengbin Duan0Wenli Chen1Shun Yao2https://orcid.org/0000-0003-1727-4078Zhigang Mao3Zongming Wang4Bin Hu5Haosen Jiao6Dimin Zhu7Yonghong Zhu8Haijun Wang9Department of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaDepartment of Histology and Embryology, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, ChinaDepartment of Neurosurgery, Center for Pituitary Tumor Surgery, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, ChinaMachine learning assisted diagnosis of acromegaly from facial photographs has been proved feasible in recent years. According to our previous research, facial and limb changes exist in patients with acromegaly at early stage. We aimed to facilitate the process of early self-screening for acromegaly from hand photographs by using a deep-learning approach. In this study, a dataset containing hand photographs of 635 acromegaly patients and 192 normal people were used to train a Deep Convolution Neural Network (DCNN). We augmented these images with tailed raw data. The prediction is performed in an end-to-end paradigm without manual pre-processing, from the input photograph to the final prediction. The trained models were evaluated on a separate dataset to validate the effectiveness. Different kinds of advanced DCNN architecture were explored in this novel task and they showed significant performance compared with the results from human doctors specialized in pituitary adenoma. We further used heat-map to provide visual explanations to illustrate how the DCNN diagnosed the acromegaly. The final result of our experiment showed a sensitivity of 0.983, a specificity of 0.920, a PPV of 0.966, a NPV of 0.958 and a F1-score of 0.974. In our method, the sensitivity was higher than doctors' predictions, which indicates that our method could effectively help people detect acromegaly by themselves. Furthermore, our algorithm paid more attention to fingers and joints on which human doctors focused. This is the first study to investigate whether it is possible to detect acromegaly by machine learning from hand photographs and compare the result with human doctors specialized in pituitary adenoma. This study provided an easy-to-use tool for early self-screening of acromegaly for people without medical knowledge, so that acromegaly patients can get more timely treatment.https://ieeexplore.ieee.org/document/9305194/Machine learningcomputer visionacromegalyautomatic diagnosis |
| spellingShingle | Chengbin Duan Wenli Chen Shun Yao Zhigang Mao Zongming Wang Bin Hu Haosen Jiao Dimin Zhu Yonghong Zhu Haijun Wang Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach IEEE Access Machine learning computer vision acromegaly automatic diagnosis |
| title | Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach |
| title_full | Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach |
| title_fullStr | Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach |
| title_full_unstemmed | Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach |
| title_short | Automatic Detection for Acromegaly Using Hand Photographs: A Deep-Learning Approach |
| title_sort | automatic detection for acromegaly using hand photographs a deep learning approach |
| topic | Machine learning computer vision acromegaly automatic diagnosis |
| url | https://ieeexplore.ieee.org/document/9305194/ |
| work_keys_str_mv | AT chengbinduan automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT wenlichen automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT shunyao automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT zhigangmao automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT zongmingwang automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT binhu automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT haosenjiao automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT diminzhu automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT yonghongzhu automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach AT haijunwang automaticdetectionforacromegalyusinghandphotographsadeeplearningapproach |