Multi-Class Diagnosis of Skin Lesions Using the Fourier Spectral Information of Images on Additive Color Model by Artificial Neural Network

López-Leyva, Josué Aarón; Guerra-Rosas, Esperanza; Álvarez-Borrego, Josué

doi:10.1109/access.2021.3061873

Cited by 24 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using overall accuracy as a performance measure in an imbalanced dataset leads to a bias towards the majority class instances. Lopez et al [29] developed a 2-layer neural network model for multi-class image classification using Fourier spectral information from red, green, and blue (RGB) color channels. They have reported the accuracy of each class where the maximum accuracy in only one class achieved is 99.33%.…”

Section: B Deep Learning Methodsmentioning

confidence: 99%

“…Moreover, they reported a true positive rate of 83% which is far less than the true positive rate of expert dermatologists, i.e., 90%. • Lopez et al [29] extracted Fourier spectral information from RGB images of Dermofit using a two-layer neural network. This 10-class classification method achieved 99.33% overall accuracy, and 92.21% balanced accuracy.…”

Section: B Benchmark Methodsmentioning

confidence: 99%

“…They have reported their results using overall accuracy, which is not suitable for imbalanced datasets. For Dermofit, to the best of our knowledge, the state-of-theart result for this 10-class skin image classification problem is presented by ANNs [29]. They split the dataset using training (70%), validation (15%) and test (15%) sets.…”

Section: B Comparison With the State-of-the-artsmentioning

confidence: 99%

See 2 more Smart Citations

Automatically Evolving Interpretable Feature Vectors using Genetic Programming for an Ensemble Classifier in Skin Cancer Detection

Ain¹,

Al-Sahaf²,

Xue³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>Early diagnosis of skin cancer saves lives as it can be successfully treated through complete excision. Computer-aided diagnosis methods developed using artificial intelligence techniques help earlier detection and identify hidden causes leading to cancers in skin lesion images. In skin cancer image classification problems, an ensemble of classifiers has demonstrated better classification ability than a single classification algorithm. Traditionally, training an ensemble uses the complete set of original features, where some of these features can be redundant or irrelevant and hence, may not provide useful information in generating good models for ensemble classification. Moreover, newly created features may help improve the classification performance. To address this, existing methods have used feature construction for building an ensemble classifier, which usually creates a fixed number of features that may fit the training data too well, resulting in poor test performance. This study develops a novel classification approach that combines ensemble learning, feature selection, and feature construction utilizing genetic programming (GP) to handle the above limitations. The proposed method automatically evolves variable-length feature vectors consisting GP-selected and GP-constructed features suitable for training an ensemble classifier. The study evaluates the goodness of the proposed method on two benchmark real-world skin image datasets that include dermoscopy and standard camera images. The experimental results reveal that the proposed algorithm significantly outperforms six state-of-the-art convolutional neural network methods, existing GP approaches, and ten commonly used machine learning methods. Furthermore, the study also includes interpreting evolved individuals that highlight important skin cancer characteristics playing a vital role in discriminating images of different cancer classes. This study shows that high classification performance can be achieved at a low cost of computational resources and inference time, and accordingly this method is potentially suitable to be implemented in mobile devices for automated screening of skin lesions and many other malignancies in low resource settings.</p>

show abstract

Section: B Deep Learning Methodsmentioning

confidence: 99%

Section: B Benchmark Methodsmentioning

confidence: 99%

Section: B Comparison With the State-of-the-artsmentioning

confidence: 99%

See 1 more Smart Citation

Automatically Evolving Interpretable Feature Vectors using Genetic Programming for an Ensemble Classifier in Skin Cancer Detection

Ain¹,

Al-Sahaf²,

Xue³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Because ortho-images obtained from a UAV-equipped multispectral sensor are expensive to obtain, a sufficient number of data samples is hard to be expected. Usually one can depend on conventional computer vision approach with the small amount data rather than deep neural networks which have lots of parameters to be adjusted by training [12], [13].…”

Section: Introductionmentioning

confidence: 99%

Detecting Pine Trees Damaged by Wilt Disease Using Deep Learning Techniques Applied to Multi-Spectral Images

2022

View full text Add to dashboard Cite

Pine wilt disease (PWD) is responsible for significant damage to East Asia's pine forests, including those in Korea, Japan, and China. Preventing the spread of wilt disease requires early detection and removal of damaged trees. This paper proposes a method of detecting disease-damaged pines using ortho-images corrected from 5-band multi-spectral images captured by unmanned aviation vehicles. The proposed method relies on a ResNet18 backbone network connected to a modified DenseNet module, classifies the 5-band multispectral (RGB, NIR, Red_Edge) ortho-image patches, and visualizes the results as a heat map. The patch-based classifier was retrained with hard negative examples, after which it achieved 98.66% accuracy, an improvement over the 96.0% accuracy associated with the same method applied to RGB images. The resulting heat map reflects the approximate distribution, and movement of the disease. Disease locations are also predicted by local maximums in the heat map. When the distance between a ground truth and the predicted location is less than visible distance, e.g. about 5m, it is counted as a correct detection. The proposed detection which consists of heat map generation followed by localization achieves Recall of 93.39%, Precision of 88.26%, and F1-score of 90.75%.

show abstract

“…Ruela et al [23] investigate the importance of shape features, concluding that, although shape is relevant for classification, the use of texture and color descriptors is more effective. Beyond texture, shape, and color, other studies indicate a high relevance of spectral features for predictive performance [3,18]. However, the influence of individual features, as well as the effect of the shape-bias on DL-based skin lesion classifiers has not yet been explored.…”

Section: Introductionmentioning

confidence: 99%

Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification

Lucieri

Schmeisser

Balada

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

It is generally believed that the human visual system is biased towards the recognition of shapes rather than textures. This assumption has led to a growing body of work aiming to align deep models' decision-making processes with the fundamental properties of human vision. The reliance on shape features is primarily expected to improve the robustness of these models under covariate shift. In this paper, we revisit the significance of shape-biases for the classification of skin lesion images. Our analysis shows that different skin lesion datasets exhibit varying biases towards individual image features. Interestingly, despite deep feature extractors being inclined towards learning entangled features for skin lesion classification, individual features can still be decoded from this entangled representation. This indicates that these features are still represented in the learnt embedding spaces of the models, but not used for classification. In addition, the spectral analysis of different datasets shows that in contrast to common visual recognition, dermoscopic skin lesion classification, by nature, is reliant on complex feature combinations beyond shape-bias. As a natural consequence, shifting away from the prevalent desire of shape-biasing models can even improve skin lesion classifiers in some cases.

show abstract

Multi-Class Diagnosis of Skin Lesions Using the Fourier Spectral Information of Images on Additive Color Model by Artificial Neural Network

Cited by 24 publications

References 43 publications

Automatically Evolving Interpretable Feature Vectors using Genetic Programming for an Ensemble Classifier in Skin Cancer Detection

Automatically Evolving Interpretable Feature Vectors using Genetic Programming for an Ensemble Classifier in Skin Cancer Detection

Detecting Pine Trees Damaged by Wilt Disease Using Deep Learning Techniques Applied to Multi-Spectral Images

Revisiting the Shape-Bias of Deep Learning for Dermoscopic Skin Lesion Classification

Contact Info

Product

Resources

About