Machine Learning in Melanoma Diagnosis. Limitations About to be Overcome

González‐Cruz, Carlos; Jofre, M.A.; Podlipnik, Sebastián; Combalia, Marc; Gareau, Daniel S.; Gamboa, Mauricio Andión; Vallone, María Gabriela; Barragán-Estudillo, Z. Faride; Tamez-Peña, Alejandra Lorena; Montoya, J.; Jesús-Silva, M. América; Carrera, Cristina; Malvehy, Josep; Puig, Susana

doi:10.1016/j.adengl.2019.09.003

Cited by 9 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important limitation is large lesions that do not fit into the field of view of the dermatoscopic camera. In addition, a recent study 78 evaluated the limitations in image selection for ML analysis. Authors found that 66.7% of the LM included in the study showed exclusion criteria, with only 33.3% of them being eligible for ML analysis.…”

Section: Future Directionsmentioning

confidence: 99%

“…Authors found that 66.7% of the LM included in the study showed exclusion criteria, with only 33.3% of them being eligible for ML analysis. 78 Therefore, although ML and CNN will probably play an important role in the future management of LM/LMM, there are still limitations that need to be addressed by the use of larger image datasets that better represent different skin types, include benign lesions as well as images obtained with consumer cameras in a rather uncontrolled manner.…”

Section: Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

<p>Lentigo Maligna: Clinical Presentation and Appropriate Management</p>

Iznardo¹,

Garcia‐Melendo²,

Yélamos³

2020

CCID

View full text Add to dashboard Cite

Section: Future Directionsmentioning

confidence: 99%

Section: Future Directionsmentioning

confidence: 99%

<p>Lentigo Maligna: Clinical Presentation and Appropriate Management</p>

Iznardo¹,

Garcia‐Melendo²,

Yélamos³

2020

CCID

View full text Add to dashboard Cite

“…The accuracy of ML algorithms is difficult to determine when used without any physician input [ 93 , 94 ]. A major limitation of ML is that it is difficult to explain how these algorithms arrive at their conclusions [ 95 ].…”

Section: Discussionmentioning

confidence: 99%

“…This maxim indicates that the quality of the dataset input determines the quality of the output. Therefore, if the data inputs are badly labeled, the outputs of the algorithm will reflect these inaccuracies [ 93 , 94 , 95 ].…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application

Velichko

Huyut

Belyaev

et al. 2022

Sensors

View full text Add to dashboard Cite

Healthcare digitalization requires effective applications of human sensors, when various parameters of the human body are instantly monitored in everyday life due to the Internet of Things (IoT). In particular, machine learning (ML) sensors for the prompt diagnosis of COVID-19 are an important option for IoT application in healthcare and ambient assisted living (AAL). Determining a COVID-19 infected status with various diagnostic tests and imaging results is costly and time-consuming. This study provides a fast, reliable and cost-effective alternative tool for the diagnosis of COVID-19 based on the routine blood values (RBVs) measured at admission. The dataset of the study consists of a total of 5296 patients with the same number of negative and positive COVID-19 test results and 51 routine blood values. In this study, 13 popular classifier machine learning models and the LogNNet neural network model were exanimated. The most successful classifier model in terms of time and accuracy in the detection of the disease was the histogram-based gradient boosting (HGB) (accuracy: 100%, time: 6.39 sec). The HGB classifier identified the 11 most important features (LDL, cholesterol, HDL-C, MCHC, triglyceride, amylase, UA, LDH, CK-MB, ALP and MCH) to detect the disease with 100% accuracy. In addition, the importance of single, double and triple combinations of these features in the diagnosis of the disease was discussed. We propose to use these 11 features and their binary combinations as important biomarkers for ML sensors in the diagnosis of the disease, supporting edge computing on Arduino and cloud IoT service.

show abstract

“…González-Cruz et al [ 11 ] also noted limitations of datasets used in deep learning research for melanoma detection. They analyzed a dataset of 2849 high quality dermoscopic images of skin tumours to determine suitability for machine learning analysis.…”

Section: Introductionmentioning

confidence: 99%

Interpretability of a Deep Learning Based Approach for the Classification of Skin Lesions into Main Anatomic Body Sites

Jaworek-Korjakowska

Brodzicki

Cassidy

et al. 2021

Cancers

View full text Add to dashboard Cite

Over the past few decades, different clinical diagnostic algorithms have been proposed to diagnose malignant melanoma in its early stages. Furthermore, the detection of skin moles driven by current deep learning based approaches yields impressive results in the classification of malignant melanoma. However, in all these approaches, the researchers do not take into account the origin of the skin lesion. It has been observed that the specific criteria for in situ and early invasive melanoma highly depend on the anatomic site of the body. To address this problem, we propose a deep learning architecture based framework to classify skin lesions into the three most important anatomic sites, including the face, trunk and extremities, and acral lesions. In this study, we take advantage of pretrained networks, including VGG19, ResNet50, Xception, DenseNet121, and EfficientNetB0, to calculate the features with an adjusted and densely connected classifier. Furthermore, we perform in depth analysis on database, architecture, and result regarding the effectiveness of the proposed framework. Experiments confirm the ability of the developed algorithms to classify skin lesions into the most important anatomical sites with 91.45% overall accuracy for the EfficientNetB0 architecture, which is a state-of-the-art result in this domain.

show abstract

Machine Learning in Melanoma Diagnosis. Limitations About to be Overcome

Cited by 9 publications

References 7 publications

<p>Lentigo Maligna: Clinical Presentation and Appropriate Management</p>

<p>Lentigo Maligna: Clinical Presentation and Appropriate Management</p>

Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application

Interpretability of a Deep Learning Based Approach for the Classification of Skin Lesions into Main Anatomic Body Sites

Contact Info

Product

Resources

About