Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers
The deep learning (DL)-based approaches in tumor pathology help to overcome the limitations of subjective visual examination from pathologists and improve diagnostic accuracy and objectivity. However, it is unclear how a DL system trained to discriminate normal/tumor tissues in a specific cancer cou...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/2/808 |
| _version_ | 1797410800035430400 |
|---|---|
| author | Hyun-Jong Jang In Hye Song Sung Hak Lee |
| author_facet | Hyun-Jong Jang In Hye Song Sung Hak Lee |
| author_sort | Hyun-Jong Jang |
| collection | DOAJ |
| description | The deep learning (DL)-based approaches in tumor pathology help to overcome the limitations of subjective visual examination from pathologists and improve diagnostic accuracy and objectivity. However, it is unclear how a DL system trained to discriminate normal/tumor tissues in a specific cancer could perform on other tumor types. Herein, we cross-validated the DL-based normal/tumor classifiers separately trained on the tissue slides of cancers from bladder, lung, colon and rectum, stomach, bile duct, and liver. Furthermore, we compared the differences between the classifiers trained on the frozen or formalin-fixed paraffin-embedded (FFPE) tissues. The Area under the curve (AUC) for the receiver operating characteristic (ROC) curve ranged from 0.982 to 0.999 when the tissues were analyzed by the classifiers trained on the same tissue preparation modalities and cancer types. However, the AUCs could drop to 0.476 and 0.439 when the classifiers trained for different tissue modalities and cancer types were applied. Overall, the optimal performance could be achieved only when the tissue slides were analyzed by the classifiers trained on the same preparation modalities and cancer types. |
| first_indexed | 2024-03-09T04:35:28Z |
| format | Article |
| id | doaj.art-008a4c3b5cb349148d72297ed4abf591 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T04:35:28Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-008a4c3b5cb349148d72297ed4abf5912023-12-03T13:27:37ZengMDPI AGApplied Sciences2076-34172021-01-0111280810.3390/app11020808Generalizability of Deep Learning System for the Pathologic Diagnosis of Various CancersHyun-Jong Jang0In Hye Song1Sung Hak Lee2Catholic Big Data Integration Center, Department of Physiology, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaDepartment of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaDepartment of Hospital Pathology, Seoul St. Mary’s Hospital, College of Medicine, The Catholic University of Korea, 222 Banpodae-ro, Seocho-gu, Seoul 06591, KoreaThe deep learning (DL)-based approaches in tumor pathology help to overcome the limitations of subjective visual examination from pathologists and improve diagnostic accuracy and objectivity. However, it is unclear how a DL system trained to discriminate normal/tumor tissues in a specific cancer could perform on other tumor types. Herein, we cross-validated the DL-based normal/tumor classifiers separately trained on the tissue slides of cancers from bladder, lung, colon and rectum, stomach, bile duct, and liver. Furthermore, we compared the differences between the classifiers trained on the frozen or formalin-fixed paraffin-embedded (FFPE) tissues. The Area under the curve (AUC) for the receiver operating characteristic (ROC) curve ranged from 0.982 to 0.999 when the tissues were analyzed by the classifiers trained on the same tissue preparation modalities and cancer types. However, the AUCs could drop to 0.476 and 0.439 when the classifiers trained for different tissue modalities and cancer types were applied. Overall, the optimal performance could be achieved only when the tissue slides were analyzed by the classifiers trained on the same preparation modalities and cancer types.https://www.mdpi.com/2076-3417/11/2/808computational pathologycomputer-aided diagnosisconvolutional neural networkdigital pathology |
| spellingShingle | Hyun-Jong Jang In Hye Song Sung Hak Lee Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers Applied Sciences computational pathology computer-aided diagnosis convolutional neural network digital pathology |
| title | Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers |
| title_full | Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers |
| title_fullStr | Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers |
| title_full_unstemmed | Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers |
| title_short | Generalizability of Deep Learning System for the Pathologic Diagnosis of Various Cancers |
| title_sort | generalizability of deep learning system for the pathologic diagnosis of various cancers |
| topic | computational pathology computer-aided diagnosis convolutional neural network digital pathology |
| url | https://www.mdpi.com/2076-3417/11/2/808 |
| work_keys_str_mv | AT hyunjongjang generalizabilityofdeeplearningsystemforthepathologicdiagnosisofvariouscancers AT inhyesong generalizabilityofdeeplearningsystemforthepathologicdiagnosisofvariouscancers AT sunghaklee generalizabilityofdeeplearningsystemforthepathologicdiagnosisofvariouscancers |