Illumination-based Transformations Improve Skin Lesion Segmentation in Dermoscopic Images

Lesion segmentation in dermoscopic images significantly enhances the diagnostic performance of AI-based classification models. However, conventional methods often require pixel-level annotations, which are resource-intensive and prone to errors caused by external artifacts, such as hair and skin markings. We propose a hybrid framework called SAM-enhanced YOLO, which integrates the Segment Anything Model (SAM) with You Only Look Once (YOLO) for precise pixel-level segmentation. This method combines YOLO's efficient lesion localization with SAM's advanced zero-shot segmentation capabilities. To further validate the framework, we compared it against traditional methods, including GrabCut and Otsu's thresholding, as well as SAM used without YOLO (SAM-only). For SAM-only, lesion segmentation was initialized at the image center to simulate a typical dermoscopic imaging setup. SAM-enhanced YOLO demonstrated superior segmentation performance, achieving an Intersection over Union (IoU) of 0.738 and an F1-score (the harmonic mean of precision and recall) of 0.833, compared to 0.578 and 0.683 with SAM-only, respectively. This represents a 28% improvement in IoU and a 22% improvement in F1-score compared to SAM-only. The results were consistent across lesion shapes and contrast conditions, with SAM-enhanced YOLO exhibiting the lowest variability and highest robustness among the evaluated methods. By reducing the need for pixel-level annotations and outperforming both standalone SAM and traditional methods, SAM-enhanced YOLO provides a scalable and resource-efficient solution for dermoscopic lesion segmentation. This framework holds significant potential for improving diagnostic workflows in clinical and resource-limited settings.

Recently, the incidence of skin cancer has increased considerably and is seriously threatening human health. Automatic detection of this disease, where early detection is critical to human life, is quite challenging. Factors such as undesirable residues (hair, ruler markers), indistinct boundaries, variable contrast, shape differences, and color differences in the skin lesion images make automatic analysis quite difficult. To overcome these challenges, a highly effective segmentation method based on a fully convolutional network (FCN) is presented in this paper. The proposed improved FCN (iFCN) architecture is used for the segmentation of full-resolution skin lesion images without any pre- or post-processing. It is to support the residual structure of the FCN architecture with spatial information. This situation, which creates a more advanced residual system, enables more precise detection of details on the edges of the lesion, and an analysis independent of skin color can be performed. It offers two contributions: determining the center of the lesion and clarifying the edge details despite the undesirable effects. Two publicly available datasets, the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 Challenge and PH2 datasets, are used to evaluate the performance of the iFCN method. The mean Jaccard index is 78.34%, the mean Dice score is 88.64%, and the mean accuracy value is 95.30% for the proposed method for the ISBI 2017 test dataset. Furthermore, the mean Jaccard index is 87.1%, the mean Dice score is 93.02%, and the mean accuracy value is 96.92% for the proposed method for the PH2 test dataset.

Diagnosis of dermoscopic skin lesions due to skin cancer is the most challenging task for the experienced dermatologists. In this context, dermoscopy is the non-invasive useful method for the detection of skin lesions which are not visible to naked human eye. Among different types of skin cancers, malignant melanoma is the most aggressive and deadliest form of skin cancer. Its diagnosis is crucial if not detected in early stage. This paper mainly aims to present an efficient machine learning approach for the detection of melanoma from dermoscopic images. It detects melanomic skin lesions based upon their discriminating properties. In first step of proposed method, different types of color and texture features are extracted from dermoscopic images based on distinguished structures and varying intensities of melanomic lesions. In second step, extracted features are fed to the classifier to classify melanoma out of dermoscopic images. Paper also focuses on the role of color and texture features in the context of detection of melanomas. Proposed method is tested on publicly available PH2 dataset in terms of accuracy, sensitivity, specificity and Area under ROC curve (AUC). It is observed that good results are achieved using extracted features, hence proving the validity of the proposed system.

Melanoma skin cancer is the most life-threatening and fatal disease among the family of skin cancer diseases. Modern technological developments and research methodologies made it possible to detect and identify this kind of skin cancer more effectively; however, the automated localization and segmentation of skin lesion at earlier stages is still a challenging task due to the low contrast between melanoma moles and skin portion and a higher level of color similarity between melanoma-affected and -nonaffected areas. In this paper, we present a fully automated method for segmenting the skin melanoma at its earliest stage by employing a deep-learning-based approach, namely faster region-based convolutional neural networks (RCNN) along with fuzzy k-means clustering (FKM). Several clinical images are utilized to test the presented method so that it may help the dermatologist in diagnosing this life-threatening disease at its earliest stage. The presented method first preprocesses the dataset images to remove the noise and illumination problems and enhance the visual information before applying the faster-RCNN to obtain the feature vector of fixed length. After that, FKM has been employed to segment the melanoma-affected portion of skin with variable size and boundaries. The performance of the presented method is evaluated on the three standard datasets, namely ISBI-2016, ISIC-2017, and PH2, and the results show that the presented method outperforms the state-of-the-art approaches. The presented method attains an average accuracy of 95.40, 93.1, and 95.6% on the ISIC-2016, ISIC-2017, and PH2 datasets, respectively, which is showing its robustness to skin lesion recognition and segmentation.

Skin lesion segmentation in dermoscopic images is a challenging task in the domain of medical images analysis because of the irregular and blurring edges of the lesion and the presence of various artifacts. Inspired by the successful applications of the generative adversarial network (GAN), we propose a new neural network for the segmentation of skin lesion. Different from the traditional adversarial network, the segmentation network uses encoder-decoder with the dense-residual block which enables the network to be trained more efficiently. It can also establish a direct relationship between adjacent pixels to improve segmentation accuracy. A multi-scale objective loss function is used to utilize deep supervision in multiple layers of the critic network. End point error and Jaccard distance are combined as the content loss function. It can solve the problem of boundary ambiguity and solve the lesion-background imbalance in pixel-level classification for skin lesion segmentation. We finally use a joint loss function including a multi-scale objective loss function, end point error, and Jaccard distance content loss function. The experiment results show that our algorithm is superior to other state-of-the-art algorithms on the ISBI2017 and PH2 datasets.

Semi-automatic segmentation of skin lesions based on superpixels and hybrid texture information.

Semantic segmentation is a fundamental task in image processing and computer vision domains. Therefore, it is a core component of most emerging industry applications such as medical imaging, autonomous driving, and agriculture. The last five years have witnessed a huge growth in the computer vision domain with the introduction of Generative Adversarial Networks (GANs) due to their ability to learn deep representations by a competitive process between two neural networks called the Generator the Discriminator. Neural Architecture Search (NAS) is undergoing a revolution aimed at automating the architectural engineering process. This paper discusses implementing a novel framework for semantic image segmentation called iSegmentor using NAS and GANs. The proposed approach is the first framework that utilizes NAS in GANs for semantic image segmentation to the best of our knowledge. The iSegmentor framework was evaluated using mean Intersection over Union (mIoU) and Mean Pixel Accuracy (MPA) metrics. The iSegmentor was mainly tested and evaluated for the autonomous driving domain. With the analysis of the past five-year literature, Cityscapes and CamVid datasets were chosen. The iSegmentor achieved 81.73 MPA and 71.90 mIoU for the Cityscapes dataset, whereas CamVid achieved 80.41 MPA and 70.63 mIoU. Further, we present future avenues that we identified with the conducted experiments to assist other researchers to extend the research area of NAS in GANs in semantic segmentation.

Skin lesion segmentation has a critical role in the early and accurate diagnosis of skin cancer by computerized systems. However, automatic segmentation of skin lesions in dermoscopic images is a challenging task owing to difficulties including artifacts (hairs, gel bubbles, ruler markers), indistinct boundaries, low contrast and varying sizes and shapes of the lesion images. This paper proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images combining a deep convolutional neural network named as You Only Look Once (YOLO) and the GrabCut algorithm. This method performs lesion segmentation using a dermoscopic image in four steps: 1. Removal of hairs on the lesion, 2. Detection of the lesion location, 3. Segmentation of the lesion area from the background, 4. Post-processing with morphological operators. The method was evaluated on two publicly well-known datasets, that is the PH2 and the ISBI 2017 (Skin Lesion Analysis Towards Melanoma Detection Challenge Dataset). The proposed pipeline model has achieved a 90% sensitivity rate on the ISBI 2017 dataset, outperforming other deep learning-based methods. The method also obtained close results according to the results obtained from other methods in the literature in terms of metrics of accuracy, specificity, Dice coefficient, and Jaccard index.

Automatic lesion segmentation in dermoscopy images is an essential step for computer-aided diagnosis of melanoma. The dermoscopy images exhibits rotational and reflectional symmetry, however, this geometric property has not been encoded in the state-of-the-art convolutional neural networks based skin lesion segmentation methods. In this paper, we present a deeply supervised rotation equivariant network for skin lesion segmentation by extending the recent group rotation equivariant network~\cite{cohen2016group}. Specifically, we propose the G-upsampling and G-projection operations to adapt the rotation equivariant classification network for our skin lesion segmentation problem. To further increase the performance, we integrate the deep supervision scheme into our proposed rotation equivariant segmentation architecture. The whole framework is equivariant to input transformations, including rotation and reflection, which improves the network efficiency and thus contributes to the segmentation performance. We extensively evaluate our method on the ISIC 2017 skin lesion challenge dataset. The experimental results show that our rotation equivariant networks consistently excel the regular counterparts with the same model complexity under different experimental settings. Our best model achieves 77.23\%(JA) on the test dataset, outperforming the state-of-the-art challenging methods and further demonstrating the effectiveness of our proposed deeply supervised rotation equivariant segmentation network. Our best model also outperforms the state-of-the-art challenging methods, which further demonstrate the effectiveness of our proposed deeply supervised rotation equivariant segmentation network.

Skin lesion segmentation is critical in medical image processing, but the segmentation task faces numerous challenges due to the differences in size, color, shape, and texture of skin lesions between patients, as well as the blurring of the boundary between lesions and normal skin. While many models improve segmentation performance by introducing complex modules, their computational resource constraints make applications limited in a clinical setting. To cope with this problem, we propose a lightweight multi-fusion network (LMFUNet) with parameters of only 0.100M and GFLOPs of 0.106. LMFUNet uses an Efficient Multi-scale Feature Extraction block (EMFE) in deep stages, which uses grouping of features by convolution with different dilation rates to reduce model complexity and effectively capture multi-scale features. By using the Multi-level Feature Fusion module (MFF) in skip connections, different levels of information are combined step by step, realizing the first step of fusion of low-level details and high-level contextual information, which helps to accurately localize the lesion area. After MFF, we designed the Spatial-channel Fusion module (SCF). This module further optimizes the fusion of feature information output from MFF in terms of spatial and channel dimensions, significantly enhancing the recognition of lesion boundaries. We did in-depth tests on three public datasets that are typical of others: ISIC2017, ISIC2018 and PH2 datasets. LMFUNet demonstrates superior performance because it excels at segmentation and doesn’t require a lot of computing power.

Skin cancer is the most commonly diagnosed cancer worldwide. It is estimated that there are over 5 million cases of skin cancer are diagnosed in the United States every year. Although less than 5% of all diagnosed skin cancers are melanoma it accounts for over 70% of skin cancer-related deaths. In the past decade, the number of melanoma cancer cases has increased by 53%. Recently, there has been significant work on segmentation and classification of skin lesions via deep learning. However, there is limited work on identifying attributes and clinically-meaningful visual skin lesion patterns from dermoscopic images. In this work, we propose to use conditional GANs for skin lesion segmentation and attribute detection and use these attributes to improve skin lesion classification. The proposed conditional GAN framework can generate segmentation and attribute masks from RGB dermoscopic images. The adversarial-image-to-image translation style architecture forces the generator to learn both local and global features. The Markovian discriminator classifies pairs of image and segmentation labels as being real or fake. Unlike previous approaches, such an architecture not only learns the mapping from dermoscopic images image to segmentation and attribute masks but also learns an optimal loss function to train such a mapping. We demonstrate that the such an approach significantly improves the Jaccard index for segmentation (with a 0.65 threshold) up to 0.893. Fusing the lesion attributes for classification of lesions yields a higher accuracy compared to those without predicted attributes.

Automated skin lesion segmentation is essential to assist doctors in diagnosis. Most methods focus on lesion segmentation of dermoscopy images, while a few focus on clinical images. Nearly all the existing methods tackle the binary segmentation problem as to distinguish lesion parts from normal skin parts, and are designed for diseases with localized solitary skin lesion. Besides, the characteristics of both the dermoscopy images and the clinical images are four-fold: (1) Only one skin lesion exists in the image. (2) The skin lesion mostly appears in the center of the image. (3) The backgrounds are similar between different images of same modality. (4) The resolution of images isn’t high, with an average of about \(1500\times 1200\) in several popular datasets. In contrast, this paper focuses on a four-class segmentation task for Cutaneous T-cell lymphomas (CTCL), an extremely aggressive skin disease with three visually similar kinds of lesions. For the first time, we collect a new dataset, which only contains clinical images captured from different body areas of human. The main characteristics of these images differ from all the existing images in four aspects: (1) Multiple skin lesion parts exist in each image. (2) The skin lesion parts are widely scattered in different areas of the image. (3) The background of the images has a large variety. (4) All the images have high resolutions, with an average of \(3255 \times 2535\). According to the characteristics and difficulties of CTCL, we design a new Multi Knowledge Learning Network (MKLN). The experimental results demonstrate the superiority of our method, which meet the clinical needs.

The effective segmentation of lesion(s) from dermoscopic skin images assists the Computer-Aided Diagnosis (CAD) systems in improving the diagnosing rate of skin cancer. The results of the existing skin lesion segmentation techniques are not up to the mark for dermoscopic images with artifacts like varying size corner borders with color similar to lesion(s) and/or hairs having low contrast with surrounding background. To improve the results of the existing skin lesion segmentation techniques for such kinds of dermoscopic images, an effective skin lesion segmentation method is proposed in this research work. The proposed method searches for the presence of corner borders in the given dermoscopc image and removes them if found otherwise it starts searching for the presence of hairs on it and eliminate them if present. Next, it enhances the resultant image using state-of-the-art image enhancement method and segments lesion from it using machine learning technique namely, GrabCut method. The proposed method was tested on PH2 and ISIC 2018 datasets containing 200 images each and its accuracy was measured with two evaluation metrics, i.e., Jaccard index, and Dice index. The evaluation results show that our proposed skin lesion segmentation method obtained Jaccard Index of 0.77, 0.80 and Dice index of 0.87, 0.82 values on PH2, and ISIC2018 datasets, respectively, which are better than state-of-the-art skin lesion segmentation techniques.

Segmentation of skin lesion images using discrete wavelet transform

Multiclass skin lesion localization and classification using deep learning based features fusion and selection framework for smart healthcare