MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1093/annonc/mdy166

Медицинская библиотека · Annals of oncology : official journal of the European Society for Medical Oncology · 2018

Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

Haenssle H A, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A, Kalloo A, Hassen A Ben Hadj, Thomas L, Enk A, Uhlmann L, Reader study level-I and level-II Groups, Alt Christina, Arenbergerova Monika, Bakos Renato, Baltzer Anne, Bertlich Ines, Blum Andreas, Bokor-Billmann Therezia, Bowling Jonathan, Braghiroli Naira, Braun Ralph, Buder-Bakhaya Kristina, Buhl Timo, Cabo Horacio, Cabrijan Leo, Cevic Naciye, Classen Anna, Deltgen David, Fink Christine, Georgieva Ivelina, Hakim-Meibodi Lara-Elena, Hanner Susanne, Hartmann Franziska, Hartmann Julia, Haus Georg, Hoxha Elti, Karls Raimonds, Koga Hiroshi, Kreusch Jürgen, Lallas Aimilios, Majenka Pawel, Marghoob Ash, Massone Cesare, Mekokishvili Lali, Mestel Dominik, Meyer Volker, Neuberger Anna, Nielsen Kari, Oliviero Margaret, Pampena Riccardo, Paoli John, Pawlik Erika, Rao Barbar, Rendon Adriana, Russo Teresa, Sadek Ahmed, Samhaber Kinga, Schneiderbauer Roland, Schweizer Anissa, Toberer Ferdinand, Trennheuser Lukas, Vlahova Lyobomira, Wald Alexander, Winkler Julia, Wölbing Priscila, Zalaudek Iris

Сравнительное исследованиеСтатьяНаблюдательное исследованиеВалидационное исследованиеПеревод пока не подготовлен

Аннотация

BACKGROUND

Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking.

METHODS

Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge.

RESULTS

In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P = 0.19) and specificity to 75.7% (±11.7%, P < 0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P < 0.01) and level-II (75.7%, P < 0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P < 0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge.

CONCLUSIONS

For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification.

CLINICAL TRIAL NUMBER: This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

Для цитирования: Haenssle H A, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A, Kalloo A, Hassen A Ben Hadj, Thomas L, Enk A, Uhlmann L, Reader study level-I and level-II Groups, Alt Christina, Arenbergerova Monika, Bakos Renato, Baltzer Anne, Bertlich Ines, Blum Andreas, Bokor-Billmann Therezia, Bowling Jonathan, Braghiroli Naira, Braun Ralph, Buder-Bakhaya Kristina, Buhl Timo, Cabo Horacio, Cabrijan Leo, Cevic Naciye, Classen Anna, Deltgen David, Fink Christine, Georgieva Ivelina, Hakim-Meibodi Lara-Elena, Hanner Susanne, Hartmann Franziska, Hartmann Julia, Haus Georg, Hoxha Elti, Karls Raimonds, Koga Hiroshi, Kreusch Jürgen, Lallas Aimilios, Majenka Pawel, Marghoob Ash, Massone Cesare, Mekokishvili Lali, Mestel Dominik, Meyer Volker, Neuberger Anna, Nielsen Kari, Oliviero Margaret, Pampena Riccardo, Paoli John, Pawlik Erika, Rao Barbar, Rendon Adriana, Russo Teresa, Sadek Ahmed, Samhaber Kinga, Schneiderbauer Roland, Schweizer Anissa, Toberer Ferdinand, Trennheuser Lukas, Vlahova Lyobomira, Wald Alexander, Winkler Julia, Wölbing Priscila, Zalaudek Iris. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.. Annals of oncology : official journal of the European Society for Medical Oncology. 2018. DOI: 10.1093/annonc/mdy166.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.