Literature DB >> 33423009

Robustness of convolutional neural networks in recognition of pigmented skin lesions.

Roman C Maron1, Sarah Haggenmüller1, Christof von Kalle2, Jochen S Utikal3, Friedegund Meier4, Frank F Gellrich4, Axel Hauschild5, Lars E French6, Max Schlaak7, Kamran Ghoreschi8, Heinz Kutzner9, Markus V Heppt10, Sebastian Haferkamp11, Wiebke Sondermann12, Dirk Schadendorf12, Bastian Schilling13, Achim Hekler1, Eva Krieghoff-Henning1, Jakob N Kather14, Stefan Fröhling15, Daniel B Lipka15, Titus J Brinker16.   

Abstract

BACKGROUND: A basic requirement for artificial intelligence (AI)-based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems.
OBJECTIVE: To quantify to what extent minor image perturbations affect the convolutional neural network (CNN)-mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing).
METHODS: We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes ('brittleness') was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions.
RESULTS: All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor.
CONCLUSIONS: Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic.
Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Entities:  

Keywords:  Artificial intelligence; Deep learning; Dermatology; Machine learning; Melanoma; Neural networks; Nevus; Skin neoplasms

Year:  2021        PMID: 33423009     DOI: 10.1016/j.ejca.2020.11.020

Source DB:  PubMed          Journal:  Eur J Cancer        ISSN: 0959-8049            Impact factor:   9.162


  6 in total

1.  Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge.

Authors:  Marc Combalia; Noel Codella; Veronica Rotemberg; Cristina Carrera; Stephen Dusza; David Gutman; Brian Helba; Harald Kittler; Nicholas R Kurtansky; Konstantinos Liopyris; Michael A Marchetti; Sebastian Podlipnik; Susana Puig; Christoph Rinner; Philipp Tschandl; Jochen Weber; Allan Halpern; Josep Malvehy
Journal:  Lancet Digit Health       Date:  2022-05

2.  Multispectral Imaging Algorithm Predicts Breslow Thickness of Melanoma.

Authors:  Szabolcs Bozsányi; Noémi Nóra Varga; Klára Farkas; András Bánvölgyi; Kende Lőrincz; Ilze Lihacova; Alexey Lihachev; Emilija Vija Plorina; Áron Bartha; Antal Jobbágy; Enikő Kuroli; György Paragh; Péter Holló; Márta Medvecz; Norbert Kiss; Norbert M Wikonkál
Journal:  J Clin Med       Date:  2021-12-30       Impact factor: 4.241

3.  A cell phone app for facial acne severity assessment.

Authors:  Jiaoju Wang; Yan Luo; Zheng Wang; Alphonse Houssou Hounye; Cong Cao; Muzhou Hou; Jianglin Zhang
Journal:  Appl Intell (Dordr)       Date:  2022-07-29       Impact factor: 5.019

4.  Comparison of Convolutional Neural Network Architectures for Robustness Against Common Artefacts in Dermatoscopic Images.

Authors:  Florian Katsch; Christoph Rinner; Philipp Tschandl
Journal:  Dermatol Pract Concept       Date:  2022-07-01

5.  Multi-center verification of the influence of data ratio of training sets on test results of an AI system for detecting early gastric cancer based on the YOLO-v4 algorithm.

Authors:  Tao Jin; Yancai Jiang; Boneng Mao; Xing Wang; Bo Lu; Ji Qian; Hutao Zhou; Tieliang Ma; Yefei Zhang; Sisi Li; Yun Shi; Zhendong Yao
Journal:  Front Oncol       Date:  2022-08-16       Impact factor: 5.738

Review 6.  New Trends in Melanoma Detection Using Neural Networks: A Systematic Review.

Authors:  Dan Popescu; Mohamed El-Khatib; Hassan El-Khatib; Loretta Ichim
Journal:  Sensors (Basel)       Date:  2022-01-10       Impact factor: 3.576

  6 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.