Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis.

Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis.

Publication date: Aug 17, 2019

Knowing when a machine learning system is not confident about its prediction is crucial in medical domains where safety is critical. Ideally, a machine learning algorithm should make a prediction only when it is highly certain about its competency, and refer the case to physicians otherwise. In this paper, we investigate how Bayesian deep learning can improve the performance of the machine-physician team in the skin lesion classification task. We used the publicly available HAM10000 dataset, which includes samples from seven common skin lesion categories: Melanoma (MEL), Melanocytic Nevi (NV), Basal Cell Carcinoma (BCC), Actinic Keratoses and Intraepithelial Carcinoma (AKIEC), Benign Keratosis (BKL), Dermatofibroma (DF), and Vascular (VASC) lesions. Our experimental results show that Bayesian deep networks can boost the diagnostic performance of the standard DenseNet-169 model from 81.35% to 83.59% without incurring additional parameters or heavy computation. More importantly, a hybrid physician-machine workflow reaches a classification accuracy of 90 % while only referring 35 % of the cases to physicians. The findings are expected to generalize to other medical diagnosis applications. We believe that the availability of risk-aware machine learning methods will enable a wider adoption of machine learning technology in clinical settings.

Mobiny, A., Singh, A., and Van Nguyen, H. Risk-Aware Machine Learning Classifier for Skin Lesion Diagnosis. 23825. 2019 J Clin Med (8):8.

Concepts Keywords
Algorithm Organ systems
Bayesian Neoplasms
Carcinoma Medicine
Deep Learning Actinic keratosis
DF Dermatology
Hybrid Melanocytic nevus
Keratosis Melanoma
MEL Carcinoma
Melanoma RTT
Physician Seborrheic keratosis
Skin Lesion Skin biopsy
Workflow

Semantics

Type Source Name
disease MESH uncertainty
disease DOID Dermatofibroma
disease MESH Dermatofibroma
gene UNIPROT KLB
disease DOID Keratosis
disease MESH Keratosis
disease MESH Intraepithelial Carcinoma
disease MESH Actinic Keratoses
pathway BSID Basal cell carcinoma
disease DOID Basal Cell Carcinoma
disease MESH Basal Cell Carcinoma
disease MESH Melanocytic Nevi
gene UNIPROT RAB8A
drug DRUGBANK Honey
pathway BSID Melanoma
disease DOID Melanoma
disease MESH Melanoma
gene UNIPROT KCNK3
disease MESH Diagnosis

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *