Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms

Rezvantalab, Amirreza; Safigholi, Habib; Karimijeshni, Somayeh

doi:10.48550/arxiv.1810.10348

Cited by 21 publications

(23 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In step (a), a grayscale image is firstly obtained from the input color image represented in L * a * b * color space. Then, the grayscale image is reconverted to a color image using U-Net (Ronneberger, Fischer, and Brox 2015). To supplement, the color information a * b * (chrominance) is predicted based on L * (luminance) information in the L * a * b * color space.…”

Section: -1 Color Anomaly Map Generationmentioning

confidence: 99%

“…Anomaly detection is a technique to identify irregular or unusual patterns in datasets. Especially, anomaly detection for imaging data is a powerful and core technology for various kinds of real-world problems including medical diagnosis (Rezvantalab, Safigholi, and Karimijeshni 2018;Cao et al 2018), plant healthcare (Ferentinos 2018), production quality controls, and disaster detection (Minhas and Zelek 2019;Natarajan, Mao, and Chia 2019). Over the last decade, many researchers have shown great interest in establishment of automatic anomaly detection techniques for a huge image dataset driven by breakthroughs in deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

Katafuchi,

Tokunaga

2021

Preprint

View full text Add to dashboard Cite

The utilization of prior knowledge about anomalies is an essential issue for anomaly detections. Recently, the visual attention mechanism has become a promising way to improve the performance of CNNs for some computer vision tasks. In this paper, we propose a novel model called Layerwise External Attention Network (LEA-Net) for efficient image anomaly detection. The core idea relies on the integration of unsupervised and supervised anomaly detectors via the visual attention mechanism. Our strategy is as follows: (i) Prior knowledge about anomalies is represented as the anomaly map generated by unsupervised learning of normal instances, (ii) The anomaly map is translated to an attention map by the external network, (iii) The attention map is then incorporated into intermediate layers of the anomaly detection network. Notably, this layer-wise external attention can be applied to any CNN model in an end-to-end training manner. For a pilot study, we validate LEA-Net on color anomaly detection tasks. Through extensive experiments on PlantVillage, MVTec AD, and Cloud datasets, we demonstrate that the proposed layer-wise visual attention mechanism consistently boosts anomaly detection performances of an existing CNN model, even on imbalanced datasets. Moreover, we show that our attention mechanism successfully boosts the performance of several CNN models.

show abstract

Section: -1 Color Anomaly Map Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

Katafuchi,

Tokunaga

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Rezvantalab et al [9] uses the HAM10000 along with another dataset and compared four classic CNN architectures: Inception-v3, InceptionResNet-v2, ResNet-152 and DenseNet-201. The best architecture was DenseNet-201.…”

Section: Related Workmentioning

confidence: 99%

A comparative study of convolutional neural networks for classification of pigmented skin lesions

Carmo¹,

Mari²

2021

Anais Do XVII Workshop De Visão Computacional (WVC 2021)

View full text Add to dashboard Cite

Skin cancer is one of the most common types of cancer in Brazil and its incidence rate has increased in recent years. Melanoma cases are more aggressive compared to nonmelanoma skin cancer. Machine learning-based classification algorithms can help dermatologists to diagnose whether skin lesion is melanoma or non-melanoma cancer. We compared four convolutional neural networks architectures (ResNet-50, VGG16, Inception-v3, and DenseNet-121) using different training strategies and validation methods to classify seven classes of skin lesions. The experiments were executed using the HAM10000 dataset which contains 10,015 images of pigmented skin lesions. We considered the test accuracy to determine the best model for each strategy. DenseNet-121 was the best model when trained with fine-tuning and data augmentation, 90% (k-fold crossvalidation). Our results can help to improve the use of machine learning algorithms for classifying pigmented skin lesions.

show abstract

“…Artificial Neural Networks (ANNs) have contributed to a number of impressive success stories in Artificial General Intelligence (AGI) [1]- [5]. However, their superior performance has come at the cost of high computational and memory requirements [6], [7].…”

Section: Introductionmentioning

confidence: 99%

Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding

Datta¹,

Kundu²,

A.³

2021

Preprint

View full text Add to dashboard Cite

Spiking Neural Networks (SNNs) have emerged as an attractive alternative to traditional deep learning frameworks, since they provide higher computational efficiency in event driven neuromorphic hardware. However, the state-of-the-art (SOTA) SNNs suffer from high inference latency, resulting from inefficient input encoding and training techniques. The most widely used input coding schemes, such as Poisson based rate-coding, do not leverage the temporal learning capabilities of SNNs. This paper presents a training framework for low-latency energyefficient SNNs that uses a hybrid encoding scheme at the input layer in which the analog pixel values of an image are directly applied during the first timestep and a novel variant of spike temporal coding is used during subsequent timesteps. In particular, neurons in every hidden layer are restricted to fire at most once per image which increases activation sparsity. To train these hybrid-encoded SNNs, we propose a variant of the gradient descent based spike timing dependent backpropagation (STDB) mechanism using a novel cross entropy loss function based on both the output neurons' spike time and membrane potential. The resulting SNNs have reduced latency and high activation sparsity, yielding significant improvements in computational efficiency. In particular, we evaluate our proposed training scheme on image classification tasks from CIFAR-10 and CIFAR-100 datasets on several VGG architectures. We achieve top-1 accuracy of 66.46% with 5 timesteps on the CIFAR-100 dataset with ∼125× less compute energy than an equivalent standard ANN. Additionally, our proposed SNN performs 5-300× faster inference compared to other state-of-the-art rate or temporally coded SNN models.

show abstract

Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms

Cited by 21 publications

References 0 publications

LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

LEA-Net: Layer-wise External Attention Network for Efficient Color Anomaly Detection

A comparative study of convolutional neural networks for classification of pigmented skin lesions

Training Energy-Efficient Deep Spiking Neural Networks with Single-Spike Hybrid Input Encoding

Contact Info

Product

Resources

About