Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification
Background and objectives Convolutional neural networks (CNN) have proven dermatologist-level performance in skin lesion classification. Prior to a broader clinical application, an assessment of limitations is crucial. Therefore, the influence of a dark tubular periphery in dermatoscopic images (als...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
2021
|
| In: |
Journal der Deutschen Dermatologischen Gesellschaft
Year: 2021, Volume: 19, Issue: 6, Pages: 842-850 |
| ISSN: | 1610-0387 |
| DOI: | 10.1111/ddg.14384 |
| Online Access: | Verlag, kostenfrei, Volltext: https://doi.org/10.1111/ddg.14384 Verlag, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1111/ddg.14384 
|
| Author Notes: | Katharina Sies, Julia K. Winkler, Christine Fink, Felicitas Bardehle, Ferdinand Toberer, Felix K.F. Kommoss, Timo Buhl, Alexander Enk, Albert Rosenberger, Holger A. Haenssle |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1780387431 | ||
| 003 | DE-627 | ||
| 005 | 20220208210206.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 211206s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1111/ddg.14384 |2 doi | |
| 035 | |a (DE-627)1780387431 | ||
| 035 | |a (DE-599)KXP1780387431 | ||
| 035 | |a (OCoLC)1295678282 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Kommoss, Katharina |e VerfasserIn |0 (DE-588)1216661227 |0 (DE-627)1727913124 |4 aut | |
| 245 | 1 | 0 | |a Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification |c Katharina Sies, Julia K. Winkler, Christine Fink, Felicitas Bardehle, Ferdinand Toberer, Felix K.F. Kommoss, Timo Buhl, Alexander Enk, Albert Rosenberger, Holger A. Haenssle |
| 264 | 1 | |c 2021 | |
| 300 | |a 9 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a First published: 10 May 2021 | ||
| 500 | |a Gesehen am 06.12.2021 | ||
| 520 | |a Background and objectives Convolutional neural networks (CNN) have proven dermatologist-level performance in skin lesion classification. Prior to a broader clinical application, an assessment of limitations is crucial. Therefore, the influence of a dark tubular periphery in dermatoscopic images (also called dark corner artefact [DCA]) on the diagnostic performance of a market-approved CNN for skin lesion classification was investigated. Patients and methods A prospective image set of 233 skin lesions (60 malignant, 173 benign) without DCA (control-set) was modified to show small, medium or large DCA. All 932 images were analyzed by a market-approved CNN (Moleanalyzer-Pro®, FotoFinder Systems), providing malignancy scores (range 0-1) with the cut-off > 0.5 indicating malignancy. Results In the control-set the CNN achieved a sensitivity of 90.0 % (79.9 % - 95.3 %), a specificity of 96.5 % (92.6 % - 98.4 %), and an area under the curve (AUC) of receiver operating characteristics (ROC) of 0.961 (0.932 - 0.989). Comparable diagnostic performance was observed in the DCAsmall-set and DCAmedium-set. Conversely, in the DCAlarge-set significantly increased malignancy scores triggered a significantly decreased specificity (87.9 % [82.2 % - 91.9 %], P < 0.001), non-significantly increased sensitivity (96.7 % [88.6 % - 99.1 %]) and unchanged ROC-AUC of 0.962 (0.935 - 0.989). Conclusions Convolutional neural network classification was robust in images with small and medium DCA, but impaired in images with large DCA. Physicians should be aware of this limitation when submitting images to CNN classification. | ||
| 700 | 1 | |a Winkler, Julia K. |d 1987- |e VerfasserIn |0 (DE-588)1038218993 |0 (DE-627)756780721 |0 (DE-576)392196514 |4 aut | |
| 700 | 1 | |a Müller-Christmann, Christine |d 1983- |e VerfasserIn |0 (DE-588)143738127 |0 (DE-627)654330387 |0 (DE-576)338647651 |4 aut | |
| 700 | 1 | |a Niedermair, Felicitas |d 1992- |e VerfasserIn |0 (DE-588)1208730061 |0 (DE-627)1695350405 |4 aut | |
| 700 | 1 | |a Toberer, Ferdinand |d 1981- |e VerfasserIn |0 (DE-588)102155832X |0 (DE-627)715821962 |0 (DE-576)362852367 |4 aut | |
| 700 | 1 | |a Kommoss, Felix |d 1991- |e VerfasserIn |0 (DE-588)1171010427 |0 (DE-627)1040361315 |0 (DE-576)512915164 |4 aut | |
| 700 | 1 | |a Buhl, Timo |e VerfasserIn |4 aut | |
| 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 Rosenberger, Albert |e VerfasserIn |4 aut | |
| 700 | 1 | |a Hänßle, Holger |e VerfasserIn |0 (DE-588)1074971531 |0 (DE-627)832791733 |0 (DE-576)443174598 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |a Deutsche Dermatologische Gesellschaft |t Journal der Deutschen Dermatologischen Gesellschaft |d Berlin : Wiley-Blackwell, 2003 |g 19(2021), 6, Seite 842-850 |h Online-Ressource |w (DE-627)362755833 |w (DE-600)2099463-1 |w (DE-576)103373837 |x 1610-0387 |7 nnas |
| 773 | 1 | 8 | |g volume:19 |g year:2021 |g number:6 |g pages:842-850 |g extent:9 |a Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification |
| 856 | 4 | 0 | |u https://doi.org/10.1111/ddg.14384 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 856 | 4 | 0 | |u https://onlinelibrary.wiley.com/doi/abs/10.1111/ddg.14384 |x Verlag |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20211206 | ||
| 993 | |a Article | ||
| 994 | |a 2021 | ||
| 998 | |g 1074971531 |a Hänßle, Holger |m 1074971531:Hänßle, Holger |d 910000 |d 911300 |e 910000PH1074971531 |e 911300PH1074971531 |k 0/910000/ |k 1/910000/911300/ |p 10 |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 8 | ||
| 998 | |g 1171010427 |a Kommoss, Felix |m 1171010427:Kommoss, Felix |d 910000 |d 912000 |e 910000PK1171010427 |e 912000PK1171010427 |k 0/910000/ |k 1/910000/912000/ |p 6 | ||
| 998 | |g 102155832X |a Toberer, Ferdinand |m 102155832X:Toberer, Ferdinand |d 910000 |d 911300 |e 910000PT102155832X |e 911300PT102155832X |k 0/910000/ |k 1/910000/911300/ |p 5 | ||
| 998 | |g 1208730061 |a Niedermair, Felicitas |m 1208730061:Niedermair, Felicitas |d 910000 |d 911300 |e 910000PN1208730061 |e 911300PN1208730061 |k 0/910000/ |k 1/910000/911300/ |p 4 | ||
| 998 | |g 143738127 |a Müller-Christmann, Christine |m 143738127:Müller-Christmann, Christine |d 910000 |d 911300 |e 910000PM143738127 |e 911300PM143738127 |k 0/910000/ |k 1/910000/911300/ |p 3 | ||
| 998 | |g 1038218993 |a Winkler, Julia K. |m 1038218993:Winkler, Julia K. |d 910000 |d 911300 |e 910000PW1038218993 |e 911300PW1038218993 |k 0/910000/ |k 1/910000/911300/ |p 2 | ||
| 998 | |g 1216661227 |a Kommoss, Katharina |m 1216661227:Kommoss, Katharina |d 910000 |d 911300 |e 910000PK1216661227 |e 911300PK1216661227 |k 0/910000/ |k 1/910000/911300/ |p 1 |x j | ||
| 999 | |a KXP-PPN1780387431 |e 4014552152 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"physDesc":[{"extent":"9 S."}],"person":[{"family":"Kommoss","display":"Kommoss, Katharina","given":"Katharina","role":"aut"},{"family":"Winkler","display":"Winkler, Julia K.","given":"Julia K.","role":"aut"},{"family":"Müller-Christmann","display":"Müller-Christmann, Christine","given":"Christine","role":"aut"},{"family":"Niedermair","display":"Niedermair, Felicitas","given":"Felicitas","role":"aut"},{"role":"aut","given":"Ferdinand","display":"Toberer, Ferdinand","family":"Toberer"},{"role":"aut","family":"Kommoss","display":"Kommoss, Felix","given":"Felix"},{"display":"Buhl, Timo","family":"Buhl","given":"Timo","role":"aut"},{"given":"Alexander","family":"Enk","display":"Enk, Alexander","role":"aut"},{"role":"aut","family":"Rosenberger","display":"Rosenberger, Albert","given":"Albert"},{"role":"aut","given":"Holger","family":"Hänßle","display":"Hänßle, Holger"}],"title":[{"title_sort":"Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification","title":"Dark corner artefact and diagnostic performance of a market-approved neural network for skin cancer classification"}],"relHost":[{"corporate":[{"display":"Deutsche Dermatologische Gesellschaft","role":"aut"}],"language":["ger","eng"],"id":{"zdb":["2099463-1"],"issn":["1610-0387"],"eki":["362755833"],"doi":["10.1111/(ISSN)1610-0387"]},"type":{"bibl":"periodical","media":"Online-Ressource"},"origin":[{"dateIssuedDisp":"2003-","publisherPlace":"Berlin ; Berlin","publisher":"Wiley-Blackwell ; Blackwell","dateIssuedKey":"2003"}],"physDesc":[{"extent":"Online-Ressource"}],"title":[{"subtitle":"JDDG = Journal of the German Society of Dermatology","title":"Journal der Deutschen Dermatologischen Gesellschaft","title_sort":"Journal der Deutschen Dermatologischen Gesellschaft"}],"titleAlt":[{"title":"JDDG"}],"titleTranslated":[{"translated":"Journal of the German Society of Dermatology"}],"part":{"volume":"19","pages":"842-850","text":"19(2021), 6, Seite 842-850","year":"2021","extent":"9","issue":"6"},"disp":"Deutsche Dermatologische GesellschaftJournal der Deutschen Dermatologischen Gesellschaft","pubHistory":["1.2003 -"],"note":["Gesehen am 03.03.10"],"recId":"362755833"}],"origin":[{"dateIssuedKey":"2021","dateIssuedDisp":"2021"}],"id":{"doi":["10.1111/ddg.14384"],"eki":["1780387431"]},"language":["eng"],"type":{"media":"Online-Ressource","bibl":"article-journal"},"name":{"displayForm":["Katharina Sies, Julia K. Winkler, Christine Fink, Felicitas Bardehle, Ferdinand Toberer, Felix K.F. Kommoss, Timo Buhl, Alexander Enk, Albert Rosenberger, Holger A. Haenssle"]},"note":["First published: 10 May 2021","Gesehen am 06.12.2021"],"recId":"1780387431"} | ||
| SRT | |a KOMMOSSKATDARKCORNER2021 | ||