Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions
Background: In recent months, multiple publications have demonstrated the use of convolutional neural networks (CNN) to classify images of skin cancer as precisely as dermatologists. However, these CNNs failed to outperform the International Symposium on Biomedical Imaging (ISBI) 2016 challenge whic...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
June 24, 2019
|
| In: |
PLOS ONE
Year: 2019, Jahrgang: 14, Heft: 6 |
| ISSN: | 1932-6203 |
| DOI: | 10.1371/journal.pone.0218713 |
| Online-Zugang: | Verlag, Volltext: https://doi.org/10.1371/journal.pone.0218713 Verlag: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0218713 
|
| Verfasserangaben: | Titus J. Brinker, Achim Hekler, Alexander H. Enk, Christof von Kalle |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1679278827 | ||
| 003 | DE-627 | ||
| 005 | 20220817004522.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 191022s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1371/journal.pone.0218713 |2 doi | |
| 035 | |a (DE-627)1679278827 | ||
| 035 | |a (DE-599)KXP1679278827 | ||
| 035 | |a (OCoLC)1341248424 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Brinker, Titus Josef |d 1990- |e VerfasserIn |0 (DE-588)1156309395 |0 (DE-627)1018860487 |0 (DE-576)502097434 |4 aut | |
| 245 | 1 | 0 | |a Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions |c Titus J. Brinker, Achim Hekler, Alexander H. Enk, Christof von Kalle |
| 264 | 1 | |c June 24, 2019 | |
| 300 | |a 8 | ||
| 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 22.10.2019 | ||
| 520 | |a Background: In recent months, multiple publications have demonstrated the use of convolutional neural networks (CNN) to classify images of skin cancer as precisely as dermatologists. However, these CNNs failed to outperform the International Symposium on Biomedical Imaging (ISBI) 2016 challenge which ranked the average precision for classification of dermoscopic melanoma images. Accordingly, the technical progress represented by these studies is limited. In addition, the available reports are impossible to reproduce, due to incomplete descriptions of training procedures and the use of proprietary image databases or non-disclosure of used images. These factors prevent the comparison of various CNN classifiers in equal terms. Objective: To demonstrate the training of an image-classifier CNN that outperforms the winner of the ISBI 2016 CNNs challenge by using open source images exclusively. Methods: A detailed description of the training procedure is reported while the used images and test sets are disclosed fully, to insure the reproducibility of our work. Results: Our CNN classifier outperforms all recent attempts to classify the original ISBI 2016 challenge test data (full set of 379 test images), with an average precision of 0.709 (vs. 0.637 of the ISBI winner) and with an area under the receiver operating curve of 0.85. Conclusion: This work illustrates the potential for improving skin cancer classification with enhanced training procedures for CNNs, while avoiding the use of costly equipment or proprietary image data. | ||
| 650 | 4 | |a Archives | |
| 650 | 4 | |a Biopsy | |
| 650 | 4 | |a Cancer detection and diagnosis | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Human learning | |
| 650 | 4 | |a Lesions | |
| 650 | 4 | |a Melanomas | |
| 650 | 4 | |a Neural networks | |
| 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 Kalle, Christof von |d 1962- |e VerfasserIn |0 (DE-588)1036481115 |0 (DE-627)75107926X |0 (DE-576)168957396 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t PLOS ONE |d San Francisco, California, US : PLOS, 2006 |g 14(2019,6) Artikel-Nummer e0218713, 8 Seiten |h Online-Ressource |w (DE-627)523574592 |w (DE-600)2267670-3 |w (DE-576)281331979 |x 1932-6203 |7 nnas |a Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions |
| 773 | 1 | 8 | |g volume:14 |g year:2019 |g number:6 |g extent:8 |a Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions |
| 856 | 4 | 0 | |u https://doi.org/10.1371/journal.pone.0218713 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0218713 |x Verlag |
| 951 | |a AR | ||
| 992 | |a 20191022 | ||
| 993 | |a Article | ||
| 994 | |a 2019 | ||
| 998 | |g 1036481115 |a Kalle, Christof von |m 1036481115:Kalle, Christof von |d 910000 |e 910000PK1036481115 |k 0/910000/ |p 4 |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 | ||
| 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 1 |x j | ||
| 999 | |a KXP-PPN1679278827 |e 3526009198 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"relHost":[{"part":{"volume":"14","extent":"8","year":"2019","text":"14(2019,6) Artikel-Nummer e0218713, 8 Seiten","issue":"6"},"title":[{"title_sort":"PLOS ONE","title":"PLOS ONE"}],"physDesc":[{"extent":"Online-Ressource"}],"origin":[{"dateIssuedDisp":"2006-","publisherPlace":"San Francisco, California, US ; Lawrence, Kan.","dateIssuedKey":"2006","publisher":"PLOS ; PLoS"}],"note":["Schreibweise des Titels bis 2012: PLoS ONE","Gesehen am 20.03.19"],"pubHistory":["1.2006 -"],"recId":"523574592","name":{"displayForm":["Public Library of Science"]},"disp":"Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesionsPLOS ONE","language":["eng"],"type":{"bibl":"periodical","media":"Online-Ressource"},"corporate":[{"display":"Public Library of Science","role":"isb"}],"id":{"zdb":["2267670-3"],"issn":["1932-6203"],"eki":["523574592"]}}],"physDesc":[{"extent":"8 S."}],"person":[{"role":"aut","display":"Brinker, Titus Josef","family":"Brinker","given":"Titus Josef"},{"role":"aut","family":"Enk","display":"Enk, Alexander","given":"Alexander"},{"role":"aut","given":"Christof von","display":"Kalle, Christof von","family":"Kalle"}],"title":[{"title_sort":"Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions","title":"Enhanced classifier training to improve precision of a convolutional neural network to identify images of skin lesions"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"id":{"eki":["1679278827"],"doi":["10.1371/journal.pone.0218713"]},"language":["eng"],"origin":[{"dateIssuedKey":"2019","dateIssuedDisp":"June 24, 2019"}],"recId":"1679278827","note":["Gesehen am 22.10.2019"],"name":{"displayForm":["Titus J. Brinker, Achim Hekler, Alexander H. Enk, Christof von Kalle"]}} | ||
| SRT | |a BRINKERTITENHANCEDCL2420 | ||