Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images
Background - The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25-26% of discordance for classifying a benign nevus...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
18 July 2019
|
| In: |
European journal of cancer
Year: 2019, Volume: 118, Pages: 91-96 |
| ISSN: | 1879-0852 |
| DOI: | 10.1016/j.ejca.2019.06.012 |
| Online Access: | Verlag, Volltext: https://doi.org/10.1016/j.ejca.2019.06.012 Verlag, Volltext: http://www.sciencedirect.com/science/article/pii/S0959804919303806 
|
| Author Notes: | Achim Hekler, Jochen S. Utikal, Alexander H. Enk, Wiebke Solass, Max Schmitt, Joachim Klode, Dirk Schadendorf, Wiebke Sondermann, Cindy Franklin, Felix Bestvater, Michael J. Flaig, Dieter Krahl, Christof von Kalle, Stefan Fröhling, Titus J. Brinker |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1677529520 | ||
| 003 | DE-627 | ||
| 005 | 20240323101300.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 190923s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.ejca.2019.06.012 |2 doi | |
| 035 | |a (DE-627)1677529520 | ||
| 035 | |a (DE-599)KXP1677529520 | ||
| 035 | |a (OCoLC)1341244262 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Hekler, Achim |e VerfasserIn |4 aut | |
| 245 | 1 | 0 | |a Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images |c Achim Hekler, Jochen S. Utikal, Alexander H. Enk, Wiebke Solass, Max Schmitt, Joachim Klode, Dirk Schadendorf, Wiebke Sondermann, Cindy Franklin, Felix Bestvater, Michael J. Flaig, Dieter Krahl, Christof von Kalle, Stefan Fröhling, Titus J. Brinker |
| 264 | 1 | |c 18 July 2019 | |
| 300 | |a 6 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 23.09.2019 | ||
| 520 | |a Background - The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25-26% of discordance for classifying a benign nevus versus malignant melanoma. A recent study indicated the potential of deep learning to lower these discordances. However, the performance of deep learning in classifying histopathologic melanoma images was never compared directly to human experts. The aim of this study is to perform such a first direct comparison. - Methods - A total of 695 lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi/345 melanoma). Only the haematoxylin & eosin (H&E) slides of these lesions were digitalised via a slide scanner and then randomly cropped. A total of 595 of the resulting images were used to train a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison to 11 histopathologists. Three combined McNemar tests comparing the results of the CNNs test runs in terms of sensitivity, specificity and accuracy were predefined to test for significance (p < 0.05). - Findings - The CNN achieved a mean sensitivity/specificity/accuracy of 76%/60%/68% over 11 test runs. In comparison, the 11 pathologists achieved a mean sensitivity/specificity/accuracy of 51.8%/66.5%/59.2%. Thus, the CNN was significantly (p = 0.016) superior in classifying the cropped images. - Interpretation - With limited image information available, a CNN was able to outperform 11 histopathologists in the classification of histopathological melanoma images and thus shows promise to assist human melanoma diagnoses. | ||
| 650 | 4 | |a Artificial intelligence | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Histopathology | |
| 650 | 4 | |a Melanoma | |
| 650 | 4 | |a Pathology | |
| 700 | 1 | |a Enk, Alexander |d 1963- |e VerfasserIn |0 (DE-588)1032757140 |0 (DE-627)739272535 |0 (DE-576)166173517 |4 aut | |
| 700 | 1 | |a Brinker, Titus Josef |d 1990- |e VerfasserIn |0 (DE-588)1156309395 |0 (DE-627)1018860487 |0 (DE-576)502097434 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t European journal of cancer |d Amsterdam [u.a.] : Elsevier, 1992 |g 118(2019), Seite 91-96 |w (DE-627)266883400 |w (DE-600)1468190-0 |w (DE-576)090954173 |x 1879-0852 |7 nnas |a Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images |
| 773 | 1 | 8 | |g volume:118 |g year:2019 |g pages:91-96 |g extent:6 |a Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images |
| 856 | 4 | 0 | |u https://doi.org/10.1016/j.ejca.2019.06.012 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u http://www.sciencedirect.com/science/article/pii/S0959804919303806 |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20190923 | ||
| 993 | |a Article | ||
| 994 | |a 2019 | ||
| 998 | |g 1156309395 |a Brinker, Titus Josef |m 1156309395:Brinker, Titus Josef |d 910000 |d 911300 |e 910000PB1156309395 |e 911300PB1156309395 |k 0/910000/ |k 1/910000/911300/ |p 15 |y j | ||
| 998 | |g 1032757140 |a Enk, Alexander |m 1032757140:Enk, Alexander |d 910000 |d 911300 |e 910000PE1032757140 |e 911300PE1032757140 |k 0/910000/ |k 1/910000/911300/ |p 3 | ||
| 999 | |a KXP-PPN1677529520 |e 351725472X | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"language":["eng"],"title":[{"title":"Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images","title_sort":"Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"recId":"1677529520","origin":[{"dateIssuedDisp":"18 July 2019","dateIssuedKey":"2019"}],"relHost":[{"title":[{"title":"European journal of cancer","title_sort":"European journal of cancer"}],"language":["eng"],"part":{"pages":"91-96","extent":"6","volume":"118","text":"118(2019), Seite 91-96","year":"2019"},"pubHistory":["28.1992 -"],"id":{"eki":["266883400"],"zdb":["1468190-0"],"issn":["1879-0852"]},"disp":"Deep learning outperformed 11 pathologists in the classification of histopathological melanoma imagesEuropean journal of cancer","corporate":[{"role":"isb","display":"European Organization for Research on Treatment of Cancer"},{"display":"European Association for Cancer Research","role":"isb"},{"role":"isb","display":"European School of Oncology"}],"note":["Gesehen am 21.03.24","Ungezählte Beil.: Supplement"],"origin":[{"publisherPlace":"Amsterdam [u.a.] ; [Erscheinungsort nicht ermittelbar]","dateIssuedKey":"1992","publisher":"Elsevier ; Pergamon Press","dateIssuedDisp":"1992-"}],"recId":"266883400","type":{"media":"Online-Ressource","bibl":"periodical"},"titleAlt":[{"title":"EJC online"}]}],"note":["Gesehen am 23.09.2019"],"id":{"eki":["1677529520"],"doi":["10.1016/j.ejca.2019.06.012"]},"physDesc":[{"extent":"6 S."}],"name":{"displayForm":["Achim Hekler, Jochen S. Utikal, Alexander H. Enk, Wiebke Solass, Max Schmitt, Joachim Klode, Dirk Schadendorf, Wiebke Sondermann, Cindy Franklin, Felix Bestvater, Michael J. Flaig, Dieter Krahl, Christof von Kalle, Stefan Fröhling, Titus J. Brinker"]},"person":[{"display":"Hekler, Achim","given":"Achim","role":"aut","family":"Hekler"},{"family":"Enk","role":"aut","given":"Alexander","display":"Enk, Alexander"},{"display":"Brinker, Titus Josef","role":"aut","given":"Titus Josef","family":"Brinker"}]} | ||
| SRT | |a HEKLERACHIDEEPLEARNI1820 | ||