scholarly journals Optical Imaging as Auxiliary Tool in Skin Cancer Diagnosis

10.5772/25465 ◽  
2011 ◽  
Author(s):  
S. Pratavieira ◽  
C. T. ◽  
A. G. ◽  
V.S. Bagnato ◽  
C. Kurachi
Keyword(s):  
Skin Cancer ◽  
Optical Imaging ◽  
Cancer Diagnosis

scholarly journals Detection Accuracy of Collective Intelligence Assessments for Skin Cancer Diagnosis

2015 ◽  
Vol 151 (12) ◽  
pp. 1346 ◽  
Author(s):  
Ralf H. J. M. Kurvers ◽  
Jens Krause ◽  
Giuseppe Argenziano ◽  
Iris Zalaudek ◽  
Max Wolf
Keyword(s):  
Skin Cancer ◽  
Cancer Diagnosis ◽  
Collective Intelligence ◽  
Detection Accuracy

Genomic Approaches to Skin Cancer Diagnosis

2001 ◽  
Vol 137 (11) ◽  
Author(s):  
Boris C. Bastian ◽  
Philip E. LeBoit ◽  
Dan Pinkel
Keyword(s):  
Skin Cancer ◽  
Cancer Diagnosis

Spectral biopsy for skin cancer diagnosis: initial clinical results

2017 ◽  
Author(s):  
Austin J. Moy ◽  
Xu Feng ◽  
Hieu T. M. Nguyen ◽  
Yao Zhang ◽  
Katherine R. Sebastian ◽  
...  
Keyword(s):  
Skin Cancer ◽  
Cancer Diagnosis ◽  
Clinical Results

Using Reflectance Confocal Microscopy in Skin Cancer Diagnosis

2017 ◽  
Vol 35 (4) ◽  
pp. 457-464 ◽  
Author(s):  
Attiya Haroon ◽  
Shahram Shafi ◽  
Babar K. Rao
Keyword(s):  
Skin Cancer ◽  
Confocal Microscopy ◽  
Cancer Diagnosis ◽  
Reflectance Confocal Microscopy

scholarly journals Uncovering and Correcting Shortcut Learning in Machine Learning Models for Skin Cancer Diagnosis

Diagnostics ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 40
Author(s):  
Meike Nauta ◽  
Ricky Walsh ◽  
Adam Dubowski ◽  
Christin Seifert
Keyword(s):  
Machine Learning ◽  
Clinical Practice ◽  
Skin Cancer ◽  
Cancer Diagnosis ◽  
Image Inpainting ◽  
Relevant Information ◽  
Black Box ◽  
Training Dataset ◽  
Learning Models ◽  
Machine Learning Models

Machine learning models have been successfully applied for analysis of skin images. However, due to the black box nature of such deep learning models, it is difficult to understand their underlying reasoning. This prevents a human from validating whether the model is right for the right reasons. Spurious correlations and other biases in data can cause a model to base its predictions on such artefacts rather than on the true relevant information. These learned shortcuts can in turn cause incorrect performance estimates and can result in unexpected outcomes when the model is applied in clinical practice. This study presents a method to detect and quantify this shortcut learning in trained classifiers for skin cancer diagnosis, since it is known that dermoscopy images can contain artefacts. Specifically, we train a standard VGG16-based skin cancer classifier on the public ISIC dataset, for which colour calibration charts (elliptical, coloured patches) occur only in benign images and not in malignant ones. Our methodology artificially inserts those patches and uses inpainting to automatically remove patches from images to assess the changes in predictions. We find that our standard classifier partly bases its predictions of benign images on the presence of such a coloured patch. More importantly, by artificially inserting coloured patches into malignant images, we show that shortcut learning results in a significant increase in misdiagnoses, making the classifier unreliable when used in clinical practice. With our results, we, therefore, want to increase awareness of the risks of using black box machine learning models trained on potentially biased datasets. Finally, we present a model-agnostic method to neutralise shortcut learning by removing the bias in the training dataset by exchanging coloured patches with benign skin tissue using image inpainting and re-training the classifier on this de-biased dataset.

scholarly journals Discovery Radiomics via Deep Multi-Column Radiomic Sequencers for Skin Cancer Detection

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
Mohammad Javad Shafiee ◽  
Alexander Wong
Keyword(s):  
Skin Cancer ◽  
Cancer Detection ◽  
Cancer Diagnosis ◽  
Imaging Data ◽  
Clinical Images ◽  
Skin Cancers ◽  
Cancer Phenotype ◽  
Skin Cancer Detection ◽  
Level Performance ◽  
Medical Imaging Data

While skin cancer is the most diagnosed form of cancer in menand women, with more cases diagnosed each year than all othercancers combined, sufficiently early diagnosis results in very goodprognosis and as such makes early detection crucial. While radiomicshave shown considerable promise as a powerful diagnostictool for significantly improving oncological diagnostic accuracy andefficiency, current radiomics-driven methods have largely rely onpre-defined, hand-crafted quantitative features, which can greatlylimit the ability to fully characterize unique cancer phenotype thatdistinguish it from healthy tissue. Recently, the notion of discoveryradiomics was introduced, where a large amount of custom, quantitativeradiomic features are directly discovered from the wealth ofreadily available medical imaging data. In this study, we presenta novel discovery radiomics framework for skin cancer detection,where we leverage novel deep multi-column radiomic sequencersfor high-throughput discovery and extraction of a large amount ofcustom radiomic features tailored for characterizing unique skincancer tissue phenotype. The discovered radiomic sequencer wastested against 9,152 biopsy-proven clinical images comprising ofdifferent skin cancers such as melanoma and basal cell carcinoma,and demonstrated sensitivity and specificity of 91% and 75%, respectively,thus achieving dermatologist-level performance andhence can be a powerful tool for assisting general practitionersand dermatologists alike in improving the efficiency, consistency,and accuracy of skin cancer diagnosis.

Sign in / Sign up

Export Citation Format

Share Document