FRACTAL MODEL FOR SKIN CANCER DIAGNOSIS USING PROBABILISTIC CLASSIFIERS

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.

Download Full-text

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

Journal of Computational Vision and Imaging Systems ◽

10.15353/vsnl.v3i1.177 ◽

2017 ◽

Vol 3 (1) ◽

Cited By ~ 3

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.

Download Full-text

Android skin cancer detection and classification based on MobileNet v2 model

International Journal of Advances in Intelligent Informatics ◽

10.26555/ijain.v6i2.492 ◽

2020 ◽

Vol 6 (2) ◽

pp. 135

Author(s):

Adi Wibowo ◽

Cahyo Adhi Hartanto ◽

Panji Wisnu Wirawan

Keyword(s):

Image Analysis ◽

Skin Cancer ◽

Object Detection ◽

Cancer Detection ◽

Cancer Diagnosis ◽

Learning Algorithm ◽

Computing Time ◽

Classification Model ◽

Method Accuracy ◽

Skin Cancer Detection

The latest developments in the smartphone-based skin cancer diagnosis application allow simple ways for portable melanoma risk assessment and diagnosis for early skin cancer detection. Due to the trade-off problem (time complexity and error rate) on using a smartphone to run a machine learning algorithm for image analysis, most of the skin cancer diagnosis apps execute the image analysis on the server. In this study, we investigate the performance of skin cancer images detection and classification on android devices using the MobileNet v2 deep learning model. We compare the performance of several aspects; object detection and classification method, computer and android based image analysis, image acquisition method, and setting parameter. Skin cancer actinic Keratosis and Melanoma are used to test the performance of the proposed method. Accuracy, sensitivity, specificity, and running time of the testing methods are used for the measurement. Based on the experiment results, the best parameter for the MobileNet v2 model on android using images from the smartphone camera produces 95% accuracy for object detection and 70% accuracy for classification. The performance of the android app for object detection and classification model was feasible for the skin cancer analysis. Android-based image analysis remains within the threshold of computing time that denotes convenience for the user and has the same performance accuracy with the computer for the high-quality images. These findings motivated the development of disease detection processing on android using a smartphone camera, which aims to achieve real-time detection and classification with high accuracy.

Download Full-text