A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer
Confirming histological patterns of lung carcinoma is important for determining the prognosis and the next steps of treatment for a patient. Confirming the histologic patterns (subtype) of lung adenocarcinoma is important for determining the prognosis and treatment options for a patient. The task is...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-12-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844022032698 |
| _version_ | 1797960973271695360 |
|---|---|
| author | Bingzhang Qiao Kawuli Jumai Julaiti Ainiwaer Madinyat Niyaz Yingxin Zhang Yuqing Ma Liwei Zhang Wesley Luh Ilyar Sheyhidin |
| author_facet | Bingzhang Qiao Kawuli Jumai Julaiti Ainiwaer Madinyat Niyaz Yingxin Zhang Yuqing Ma Liwei Zhang Wesley Luh Ilyar Sheyhidin |
| author_sort | Bingzhang Qiao |
| collection | DOAJ |
| description | Confirming histological patterns of lung carcinoma is important for determining the prognosis and the next steps of treatment for a patient. Confirming the histologic patterns (subtype) of lung adenocarcinoma is important for determining the prognosis and treatment options for a patient. The task is challenging, and often requires the input of experienced pathologists, who by themselves lack interobserver concordance. A computer-aided diagnosis holds the potential to accelerate the time to diagnosis. As many adenocarcinoma tissue samples contain multiple histologic patterns, accurate computer-aided diagnosis requires annotations manually labeled by pathologists. We propose a method that merges weak supervised learning and Integrated Learning using Transfer Learning using two datasets: The Cancer Genome Atlas (TCGA), and the Clinical Proteomic Tumor Analysis Consortium (CPTAC) to reduce the need for manual annotation by a pathologist while maintaining accuracy. Whole-slide images (WSI) are first determined to be either adenocarcinoma or squamous cell carcinoma, then further identify the subtypes by generating weak classifiers for each subtype, then using integrated learning to create a strong classifier.Our model was evaluated with independent datasets from the CPTAC dataset and a dataset from a private hospital. It can achieve AUC values of 0.86, 0.91, 0.82, 0.77, 0.96, 0.98 in Acinar, LPA, Micropapillary, Papillary, Solid, and Normal, respectively. |
| first_indexed | 2024-04-11T00:52:13Z |
| format | Article |
| id | doaj.art-681f4c6b82b7483fb8ae325ffca9b6f5 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-11T00:52:13Z |
| publishDate | 2022-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-681f4c6b82b7483fb8ae325ffca9b6f52023-01-05T08:37:44ZengElsevierHeliyon2405-84402022-12-01812e11981A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancerBingzhang Qiao0Kawuli Jumai1Julaiti Ainiwaer2Madinyat Niyaz3Yingxin Zhang4Yuqing Ma5Liwei Zhang6Wesley Luh7Ilyar Sheyhidin8Department of Thoracic Surgery, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaDepartment of Thoracic Surgery, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaDepartment of Thoracic Surgery, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaClinical Medicine Research Institute, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaJiaxing Qingge Medical Technologies Co. Ltd., Zhejiang, 314006, ChinaDepartment of Pathology, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaDepartment of Thoracic Surgery, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, ChinaNew York University, New York, NY 10003; Singularity.ai, San Jose, CA 95129Department of Thoracic Surgery, First Affiliated Hospital of Xinjiang Medical University, No.137 Liyu Shan Road, Urumqi, Xinjiang 830054, China; Corresponding author.Confirming histological patterns of lung carcinoma is important for determining the prognosis and the next steps of treatment for a patient. Confirming the histologic patterns (subtype) of lung adenocarcinoma is important for determining the prognosis and treatment options for a patient. The task is challenging, and often requires the input of experienced pathologists, who by themselves lack interobserver concordance. A computer-aided diagnosis holds the potential to accelerate the time to diagnosis. As many adenocarcinoma tissue samples contain multiple histologic patterns, accurate computer-aided diagnosis requires annotations manually labeled by pathologists. We propose a method that merges weak supervised learning and Integrated Learning using Transfer Learning using two datasets: The Cancer Genome Atlas (TCGA), and the Clinical Proteomic Tumor Analysis Consortium (CPTAC) to reduce the need for manual annotation by a pathologist while maintaining accuracy. Whole-slide images (WSI) are first determined to be either adenocarcinoma or squamous cell carcinoma, then further identify the subtypes by generating weak classifiers for each subtype, then using integrated learning to create a strong classifier.Our model was evaluated with independent datasets from the CPTAC dataset and a dataset from a private hospital. It can achieve AUC values of 0.86, 0.91, 0.82, 0.77, 0.96, 0.98 in Acinar, LPA, Micropapillary, Papillary, Solid, and Normal, respectively.http://www.sciencedirect.com/science/article/pii/S2405844022032698Lung adenocarcinomaAdenocarcinoma subtype classificationTransfer learningWeak supervised learningThe cancer genome atlasSquamous cell carcinoma |
| spellingShingle | Bingzhang Qiao Kawuli Jumai Julaiti Ainiwaer Madinyat Niyaz Yingxin Zhang Yuqing Ma Liwei Zhang Wesley Luh Ilyar Sheyhidin A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer Heliyon Lung adenocarcinoma Adenocarcinoma subtype classification Transfer learning Weak supervised learning The cancer genome atlas Squamous cell carcinoma |
| title | A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer |
| title_full | A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer |
| title_fullStr | A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer |
| title_full_unstemmed | A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer |
| title_short | A novel transfer-learning based physician-level general and subtype classifier for non-small cell lung cancer |
| title_sort | novel transfer learning based physician level general and subtype classifier for non small cell lung cancer |
| topic | Lung adenocarcinoma Adenocarcinoma subtype classification Transfer learning Weak supervised learning The cancer genome atlas Squamous cell carcinoma |
| url | http://www.sciencedirect.com/science/article/pii/S2405844022032698 |
| work_keys_str_mv | AT bingzhangqiao anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT kawulijumai anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT julaitiainiwaer anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT madinyatniyaz anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT yingxinzhang anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT yuqingma anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT liweizhang anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT wesleyluh anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT ilyarsheyhidin anoveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT bingzhangqiao noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT kawulijumai noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT julaitiainiwaer noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT madinyatniyaz noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT yingxinzhang noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT yuqingma noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT liweizhang noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT wesleyluh noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer AT ilyarsheyhidin noveltransferlearningbasedphysicianlevelgeneralandsubtypeclassifierfornonsmallcelllungcancer |