An EfficientNet-based modified sigmoid transform for enhancing dermatological macro-images of melanoma and nevi skin lesions

BACKGROUND AND OBJECTIVE

During the initial stages, skin lesions may not have sufficient intensity difference or contrast from the background region on dermatological macro-images. The lack of proper light exposure at the time of capturing the image also reduces the contrast. Low contrast between lesion and background regions adversely impacts segmentation. Enhancement techniques for improving the contrast between lesion and background skin on dermatological macro-images are limited in the literature. An EfficientNet-based modified sigmoid transform for enhancing the contrast on dermatological macro-images is proposed to address this issue.

METHODS

A modified sigmoid transform is applied in the HSV color space. The crossover point in the modified sigmoid transform that divides the macro-image into lesion and background is predicted using a modified EfficientNet regressor to exclude manual intervention and subjectivity. The Modified EfficientNet regressor is constructed by replacing the classifier layer in the conventional EfficientNet with a regression layer. Transfer learning is employed to reduce the training time and size of the dataset required to train the modified EfficientNet regressor. For training the modified EfficientNet regressor, a set of value components extracted from the HSV color space representation of the macro-images in the training dataset is fed as input. The corresponding set of ideal crossover points at which the values of Dice similarity coefficient (DSC) between the ground-truth images and the segmented output images obtained from Otsu's thresholding are maximum, is defined as the target.

RESULTS

On images enhanced with the proposed framework, the DSC of segmented results obtained by Otsu's thresholding increased from 0.68 ± 0.34 to 0.81 ± 0.17.

CONCLUSIONS

The proposed algorithm could consistently improve the contrast between lesion and background on a comprehensive set of test images, justifying its applications in automated analysis of dermatological macro-images.

Effective Conversion of a Convolutional Neural Network into a Spiking Neural Network for Image Recognition Tasks

Due to energy efficiency, spiking neural networks (SNNs) have gradually been considered as an alternative to convolutional neural networks (CNNs) in various machine learning tasks. In image recognition tasks, leveraging the superior capability of CNNs, the CNN–SNN conversion is considered one of the most successful approaches to training SNNs. However, previous works assume a rather long inference time period called inference latency to be allowed, while having a trade-off between inference latency and accuracy. One of the main reasons for this phenomenon stems from the difficulty in determining proper a firing threshold for spiking neurons. The threshold determination procedure is called a threshold balancing technique in the CNN–SNN conversion approach. This paper proposes a CNN–SNN conversion method with a new threshold balancing technique that obtains converted SNN models with good accuracy even with low latency. The proposed method organizes the SNN models with soft-reset IF spiking neurons. The threshold balancing technique estimates the thresholds for spiking neurons based on the maximum input current in a layerwise and channelwise manner. The experiment results have shown that our converted SNN models attain even higher accuracy than the corresponding trained CNN model for the MNIST dataset with low latency. In addition, for the Fashion-MNIST and CIFAR-10 datasets, our converted SNNs have shown less conversion loss than other methods in low latencies. The proposed method can be beneficial in deploying efficient SNN models for recognition tasks on resource-limited systems because the inference latency is strongly associated with energy consumption.

X-ray Image Enhancement Based on Nonsubsampled Shearlet Transform and Gradient Domain Guided Filtering

In this paper, we propose an image enhancement algorithm combining non-subsampled shearlet transform and gradient-domain guided filtering to address the problems of low resolution, noise amplification, missing details, and weak edge gradient retention in the X-ray image enhancement process. First, we decompose histogram equalization and nonsubsampled shearlet transform to the original image. We get a low-frequency sub-band and several high-frequency sub-bands. Adaptive gamma correction with weighting distribution is used for the low-frequency sub-band to highlight image contour information and improve the overall contrast of the image. The gradient-domain guided filtering is conducted for the high-frequency sub-bands to suppress image noise and highlight detail and edge information. Finally, we reconstruct all the effectively processed sub-bands by the inverse non-subsampled shearlet transform and obtain the final enhanced image. The experimental results show that the proposed algorithm has good results in X-ray image enhancement, and its objective index also has evident advantages over some classical algorithms.

Low-Light Image Enhancement via the Absorption Light Scattering Model

Low light often leads to poor image visibility, which can easily affect the performance of computer vision algorithms. First, this paper proposes the absorption light scattering model (ALSM), which can be used to reasonably explain the absorbed light imaging process for low-light images. In addition, the absorbing light scattering image obtained via ALSM under a sufficient and uniform illumination can reproduce hidden outlines and details from the low-light image. Then, we identify that the minimum channel of ALSM obtained above exhibits high local similarity. This similarity can be constrained by superpixels, which effectively prevent the use of gradient operations at the edges so that the noise is not amplified quickly during enhancement. Finally, by analyzing the monotonicity between the scene reflection and the atmospheric light or transmittance in ALSM, a new low-light image enhancement method is identified. We replace atmospheric light with inverted atmospheric light to reduce the contribution of atmospheric light in the imaging results. Moreover, a soft jointed mean-standard-deviation (MSD) mechanism is proposed that directly acts on the patches represented by the superpixels. The MSD can obtain a smaller transmittance than that obtained by the minimum strategy, and it can be automatically adjusted according to the information of the image. The experiments on challenging low-light images are conducted to reveal the advantages of our method compared with other powerful techniques.