Using Deep Learning for Melanoma Detection in Dermoscopy Images

Salido, Julie Ann A.; Ruiz, Conrado

doi:10.18178/ijmlc.2018.8.1.664

Cited by 67 publications

(32 citation statements)

References 14 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another important issue is related to the artifacts observed in clinical or dermoscopic images, such as surgical skin markings, dark corners, gel bubbles, superimposed color charts, overlayed rulers, and occluding hair that can affect image classification by automated algorithms [ 55 ]. Various methods have been reported for the removal of such artifacts and strategies for preprocessing images were described to improve the classification outcomes of DNNs [ 55 , 56 , 57 , 58 ]. Finally, a major point of weakness of our study was the lack of comparison with traditional, hand-designed image descriptors [ 50 , 59 , 60 ].…”

Section: Discussionmentioning

confidence: 99%

Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions

Lucius

All

et al. 2020

Diagnostics

View full text Add to dashboard Cite

This study evaluated whether deep learning frameworks trained in large datasets can help non-dermatologist physicians improve their accuracy in categorizing the seven most common pigmented skin lesions. Open-source skin images were downloaded from the International Skin Imaging Collaboration (ISIC) archive. Different deep neural networks (DNNs) (n = 8) were trained based on a random dataset constituted of 8015 images. A test set of 2003 images was used to assess the classifiers’ performance at low (300 × 224 RGB) and high (600 × 450 RGB) image resolution and aggregated data (age, sex and lesion localization). We also organized two different contests to compare the DNN performance to that of general practitioners by means of unassisted image observation. Both at low and high image resolution, the DNN framework differentiated dermatological images with appreciable performance. In all cases, the accuracy was improved when adding clinical data to the framework. Finally, the least accurate DNN outperformed general practitioners. The physician’s accuracy was statistically improved when allowed to use the output of this algorithmic framework as guidance. DNNs are proven to be high performers as skin lesion classifiers and can improve general practitioner diagnosis accuracy in a routine clinical scenario.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions

Lucius

All

et al. 2020

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Another important issue is related to the artifacts observed in clinical or dermoscopic images, such as surgical skin markings, dark corners, gel bubbles, superimposed color charts, overlayed rulers, and occluding hair that can affect image classification by automated algorithms [51]. Various methods have been reported for the removal of such artifacts and strategies for preprocessing of images were described to improve the classification outcomes of DNNs [51-54].…”

Section: Discussionmentioning

confidence: 99%

Deep neural frameworks improve the accuracy of general practitioners in the classification of pigmented skin lesions

Lucius

All

et al. 2020

Preprint

View full text Add to dashboard Cite

Artificial intelligence can be a key tool in the context of assisting in the diagnosis of dermatological conditions, particularly when performed by general practitioners with limited or no access to high resolution optical equipment. This study evaluates the performance of deep convolutional neural networks (DNNs) in the classification of seven pigmented skin lesions. Additionally, it assesses the improvement ratio in the classification performance when utilized by general practitioners. Open-source skin images were downloaded from the ISIC archive. Different DNNs (n=8) were trained based on a random dataset constituted by 8,015 images. A test set of 2,003 images has been used to assess the classifiers performance at low (300 x 224 RGB) and high (600 x 450 RGB) image resolution and aggregated clinical data (age, sex and lesion localization). We have also organized two different contests to compare the DNNs performance to that of general practitioners by means of unassisted image observation. Both at low and high image resolution, the DNNs framework being trained differentiated dermatological images with appreciable performance. In all cases, accuracy has been improved when adding clinical data to the framework. Finally, the lowest accurate DNN outperformed general practitioners. Physicians accuracy was statistically improved when allowed to use the output of this algorithmic framework as guidance. DNNS are proven to be high performers as skin lesion classifiers. The aim is to include these AI tools in the context of general practitioners whilst improving their diagnosis accuracy in a routine clinical scenario when or where the use of high-resolution equipment is not accessible.

show abstract

“…The justification and challenging groups comprise 1,000 images, without ground truth. In our experimentations, we used 80% of the training traditional of the ISIC 2018 dataset for training and 20% for justification as planned in [21]. In try, ISBI 2017 databases were separated into workout, justification and challenging groups with 2000 images.…”

Section: Methodsmentioning

confidence: 99%

A new swarm intelligence information technique for improving information balancedness on the skin lesions segmentation

Abd

Abdullah

Alkafaji

2020

IJECE

View full text Add to dashboard Cite

Methods of image processing can recognize the images of melanoma lesions border in addition to the disease compared to a skilled dermatologist. New swarm intelligence technique depends on meta-heuristic that is industrialized to resolve composite real problems which are problematic to explain by the available deterministic approaches. For an accurate detection of all segmentation and classification of skin lesions, some dealings should be measured which contain, contrast broadening, irregularity quantity, choice of most optimal features, and so into the world. The price essential for the action of progressive disease cases is identical high and the survival percentage is low. Many electronic dermoscopy classifications are advanced depend on the grouping of form, surface and dye features to facilitate premature analysis of malignance. To overcome this problematic, an effective prototypical for accurate boundary detection and arrangement is obtainable. The projected classical recovers the optimization segment of accuracy in its pre-processing stage, applying contrast improvement of lesion area compared to the contextual. In conclusion, optimized features are future fed into of artifical bee colony (ABC) segmentation. Wide-ranging researches have been supported out on four databases named as, ISBI (2016, 2017, 2018) and PH2. Also, the selection technique outclasses and successfully indifferent the dismissed features. The paper shows a different process for lesions optimal segmentation that could be functional to a variation of images with changed possessions and insufficiencies is planned with multistep pre-processing stage.

show abstract

Using Deep Learning for Melanoma Detection in Dermoscopy Images

Cited by 67 publications

References 14 publications

Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions

Deep Neural Frameworks Improve the Accuracy of General Practitioners in the Classification of Pigmented Skin Lesions

Deep neural frameworks improve the accuracy of general practitioners in the classification of pigmented skin lesions

A new swarm intelligence information technique for improving information balancedness on the skin lesions segmentation

Contact Info

Product

Resources

About