Artificial Intelligence Approach in Melanoma

Curiel‐Lewandrowski, Clara; Novoa, Roberto A.; Berry, Elizabeth; Celebi, M. Emre; Codella, Noel; Giuste, Felipe; Gutman, David; Halpern, Allan C.; Leachman, Sancy A.; Liu, Yuan; Liu, Yun; Reiter, Ofer; Tschandl, Philipp

doi:10.1007/978-1-4614-7147-9_43

Cited by 7 publications

(4 citation statements)

References 148 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Technologies such as two‐dimensional total body imaging or sequential digital dermoscopy highlight concerning lesions and allow change over time to be monitored 40 . Advanced imaging technologies such as three‐dimensional total body photography supported by artificial intelligence, and liquid biomarkers, have the potential to further improve the accuracy of melanoma diagnosis and minimise excision of benign lesions 41–43 . These technology advances could inform a more systematic approach to melanoma screening in the future, but their utility in practice needs, including ensuring equitable access and training of the primary care workforce, requires further evaluation 44–47 .…”

Section: Current Australian Screening Policy and Practicementioning

confidence: 99%

Early detection of melanoma: a consensus report from the Australian Skin and Skin Cancer Research Centre Melanoma Screening Summit

Janda

Cust

Aitken

et al. 2020

Australian and New Zealand Journal of Public Health

View full text Add to dashboard Cite

Introduction: A Melanoma Screening Summit was held in Brisbane, Australia, to review evidence regarding current approaches for early detection of melanomas and explore new opportunities. Results: Formal population‐based melanoma screening is not carried out in Australia, but there is evidence of considerable opportunistic screening as well as early detection. Biopsy rates are rising and most melanomas are now diagnosed when in situ. Based on evidence review and expert opinion, the Summit attendees concluded that there is currently insufficient information in terms of comparative benefits, harms and costs to support change from opportunistic to systematic screening. Assessment of gains in precision and cost‐effectiveness of integrating total body imaging, artificial intelligence algorithms and genetic risk information is required, as well as better understanding of clinical and molecular features of thin fatal melanomas. Conclusions: Research is needed to understand how to further optimise early detection of melanoma in Australia. Integrating risk‐based population stratification and more precise diagnostic tests is likely to improve the balance of benefits and harms of opportunistic screening, pending assessment of cost‐effectiveness. Implications for public health: The Summit Group identified that the personal and financial costs to the community of detecting and treating melanoma are rising, and this may be mitigated by developing and implementing a more systematic process for diagnosing melanoma.

show abstract

Section: Current Australian Screening Policy and Practicementioning

confidence: 99%

Early detection of melanoma: a consensus report from the Australian Skin and Skin Cancer Research Centre Melanoma Screening Summit

Janda

Cust

Aitken

et al. 2020

Australian and New Zealand Journal of Public Health

View full text Add to dashboard Cite

show abstract

“…Despite all the above, there is still a wide improvement margin in developing CAD tools in order to be reliable. Most of the AI works published in the field of skin cancer detection have been focused on melanoma [ 6 , 7 , 8 , 9 ]. On the other hand, works devoted to detecting non-melanoma skin cancer are uncommon in the literature.…”

Section: Introductionmentioning

confidence: 99%

Clinically Inspired Skin Lesion Classification through the Detection of Dermoscopic Criteria for Basal Cell Carcinoma

et al. 2022

View full text Add to dashboard Cite

Background and Objective. Skin cancer is the most common cancer worldwide. One of the most common non-melanoma tumors is basal cell carcinoma (BCC), which accounts for 75% of all skin cancers. There are many benign lesions that can be confused with these types of cancers, leading to unnecessary biopsies. In this paper, a new method to identify the different BCC dermoscopic patterns present in a skin lesion is presented. In addition, this information is applied to classify skin lesions into BCC and non-BCC. Methods. The proposed method combines the information provided by the original dermoscopic image, introduced in a convolutional neural network (CNN), with deep and handcrafted features extracted from color and texture analysis of the image. This color analysis is performed by transforming the image into a uniform color space and into a color appearance model. To demonstrate the validity of the method, a comparison between the classification obtained employing exclusively a CNN with the original image as input and the classification with additional color and texture features is presented. Furthermore, an exhaustive comparison of classification employing different color and texture measures derived from different color spaces is presented. Results. Results show that the classifier with additional color and texture features outperforms a CNN whose input is only the original image. Another important achievement is that a new color cooccurrence matrix, proposed in this paper, improves the results obtained with other texture measures. Finally, sensitivity of 0.99, specificity of 0.94 and accuracy of 0.97 are achieved when lesions are classified into BCC or non-BCC. Conclusions. To the best of our knowledge, this is the first time that a methodology to detect all the possible patterns that can be present in a BCC lesion is proposed. This detection leads to a clinically explainable classification into BCC and non-BCC lesions. In this sense, the classification of the proposed tool is based on the detection of the dermoscopic features that dermatologists employ for their diagnosis.

show abstract

“…Shortcut learning problems [5], which are decision rules that perform well on standard benchmarks but fail when applied to more challenging testing conditions, have recently drawn researchers' attention, as ML systems have been found sharing such common problems with human learning systems. Take a Melanoma (skin cancer) image classification model with deep convolutional neural networks (CNN) [6] as an example, if most of the malignant tumor images used to train the CNN models contain rulers or size markers as shown in Fig. 1, the learning algorithm may learn a shortcut that "ruler denotes skin cancer" [6].…”

Section: Introductionmentioning

confidence: 99%

“…Take a Melanoma (skin cancer) image classification model with deep convolutional neural networks (CNN) [6] as an example, if most of the malignant tumor images used to train the CNN models contain rulers or size markers as shown in Fig. 1, the learning algorithm may learn a shortcut that "ruler denotes skin cancer" [6].…”

Section: Introductionmentioning

confidence: 99%

Towards Model-informed Precision Dosing with Expert-in-the-loop Machine Learning

Kang

Chiu

Lin

et al. 2021

2021 IEEE 22nd International Conference on Information Reuse and Integration for Data Science (IRI)

View full text Add to dashboard Cite

Machine Learning (ML) and its applications have been transforming our lives but it is also creating issues related to the development of fair, accountable, transparent, and ethical Artificial Intelligence. As the ML models are not fully comprehensible yet, it is obvious that we still need humans to be part of algorithmic decision-making processes. In this paper, we consider a ML framework that may accelerate model learning and improve its interpretability by incorporating human experts into the model learning loop. We propose a novel human-in-the-loop ML framework aimed at dealing with learning problems that the cost of data annotation is high and the lack of appropriate data to model the association between the target tasks and the input features. With an application to precision dosing, our experimental results show that the approach can learn interpretable rules from data and may potentially lower experts' workload by replacing data annotation with rule representation editing. The approach may also help remove algorithmic bias by introducing experts' feedback into the iterative model learning process.

show abstract

Artificial Intelligence Approach in Melanoma

Cited by 7 publications

References 148 publications

Early detection of melanoma: a consensus report from the Australian Skin and Skin Cancer Research Centre Melanoma Screening Summit

Early detection of melanoma: a consensus report from the Australian Skin and Skin Cancer Research Centre Melanoma Screening Summit

Clinically Inspired Skin Lesion Classification through the Detection of Dermoscopic Criteria for Basal Cell Carcinoma

Towards Model-informed Precision Dosing with Expert-in-the-loop Machine Learning

Contact Info

Product

Resources

About