Hair Segmentation and Removal in Dermoscopic Images Using Deep Learning

Skin-CAD: Explainable deep learning classification of skin cancer from dermoscopic images by feature selection of dual high-level CNNs features and transfer learning

Image Denoising is a consistent problem from long period of time and still a challenging task for researchers. There evolved many techniques for image denoising which involves filtering techniques in spatial domain, Transform techniques in transform domain (Sekhar et al. in IRECOS 10(10):1012–1017, 2015 [1]), and more recently evolutionary computing tools (ECT) and genetic algorithms proved more effective in denoising of images. There are many ECT available which can be applied for denoising problem (Sekhar et al. in JGIM 25(4) 2017, [2]). In this paper we made an attempt to Denoise both color and grayscale images by applying a new ECT which emerged out with more efficient results. Peak Signal to noise ratio (PSNR), Structural Similarity Index Metric (SSIM), Mean Structural Similarity Index Metric (MSSIM), etc., are considered in this paper as Image quality Assessment metrics. Comparison of proposed method is also compared with state-of-the-art techniques.

An effectively perceptual preprocessing filter method will reduce the sequence’s perceptually insignificant details, which can help to alleviate the video coding’s pressure and benefit the coding results. In this paper, a perceptual rate distortion optimization based preprocessing filter algorithm is presented to achieve better video compression performance. The proposed algorithm employs an adaptively temporal filter with the rate SSIM (Structure Similarity Index Metric) based optimization constraint to produces optimal filter parameters. The evaluation results confirm that the proposed video filter algorithm has achieved reliable rate-visual quality improvements with -4.35% and -2.96% SSIM based BD-Rate performance gain on JM18.3 and HM16.9, respectively. Additionally, the subjective quality comparison results show that our algorithm has reduced significant bits with negligible visual difference for both the experiments on JM18.3 and HM16.9.

Noise Removal in medical images is a requisite pre-processing step for medical image analysis. In this paper, we present three deep learning architectures: Convolutional Auto-encoders, U-Net and a Double U-Net architecture utilizing convolution layers for medical Image De-noising. We use PSNR(Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index Metric) to compare the results of the networks.In our experiments, the variant of the U-Net architecture implemented performed better than the two architectures in terms of its SSIM.

Given the potential risk of motion artifacts, acquisition time reduction is desirable in pediatric 99m Tc-dimercaptosuccinic acid (DMSA) scintigraphy. The aim of this study was to evaluate the performance of predicted full-acquisition-time images from short-acquisition-time pediatric 99m Tc-DMSA planar images with only 1/5th acquisition time using deep learning in terms of image quality and quantitative renal uptake measurement accuracy. One hundred and fifty-five cases that underwent pediatric 99m Tc-DMSA planar imaging as dynamic data for 10min were retrospectively collected for the development of three deep learning models (DnCNN, Win5RB, and ResUnet), and the generation of full-time images from short-time images. We used the normalized mean squared error (NMSE), peak signal-to-noise ratio (PSNR), and structural similarity index metrics (SSIM) to evaluate the accuracy of the predicted full-time images. In addition, the renal uptake of 99m Tc-DMSA was calculated, and the difference in renal uptake from the reference full-time images was assessed using scatter plots with Pearson correlation and Bland-Altman plots. The predicted full-time images from the deep learning models showed a significant improvement in image quality compared to the short-time images with respect to the reference full-time images. In particular, the predicted full-time images obtained by ResUnet showed the lowest NMSE (0.4 [0.4-0.5] %) and the highest PSNR (55.4 [54.7-56.1] dB) and SSIM (0.997 [0.995-0.997]). For renal uptake, an extremely high correlation was achieved in all short-time and three predicted full-time images (R2 >0.999 for all). The Bland-Altman plots showed the lowest bias (-0.10) of renal uptake in ResUnet, while short-time images showed the lowest variance (95% confidence interval: -0.14, 0.45) of renal uptake. Our proposed method is capable of producing images that are comparable to the original full-acquisition-time images, allowing for a reduction of acquisition time/injected dose in pediatric 99m Tc-DMSA planar imaging.

This research paper explores the rising interest in utilising deep learning methods, specifically Convolution Neural Network (CNN), to improve the reconstruction of Compressively Sampled Magnetic Resonance Imaging (CS MRI) images from under-sampled data. By training deep learning architectures on extensive data sets of paired under sampled and fully sampled MR images, these models aim to capture intricate patterns and structures, ultimately enhancing the accuracy of MR image reconstructions. A novel deep learning model is proposed dubbed as “Deep Iterative Shrinkage Thresholding Algorithm-Compressed Sensing Network” (DISTA-CSNet), specifically designed for efficient recovery of CS MRI. Our model showcases impressive results with only 20 epochs and can be effortlessly trained on diverse datasets. To ensure robustness across different datasets, the dropouts are incorporated into the model, evident from testing results. The trained DISTA-CSNet exhibits remarkable performance in recovering CS MRI from various data sets, surpassing several advanced deep learning techniques with changing compression ratios consistently. The proposed model demonstrates significant enhancements in both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics, affirming the efficacy of our proposed model. The capability of our DISTA-CSNet in accurately reconstructing CS MRI images from 5-fold undersampled data shows promise in improving medical imaging applications and advancing the field of compressed sensing MRI.

Skin conditions are becoming increasingly prevalent, and many of these ailments carry concealed risks that can elevate the likelihood of developing skin cancer. Given the low quality of images associated with such conditions, diagnosing these diseases traditionally required advanced medical expertise and specialized equipment. Furthermore, manually detecting skin disorders is often subjective, time-consuming, and demands considerable human effort. This highlights the need for an automated, computer-assisted system capable of diagnosing skin conditions without human intervention. To achieve this, Deep Learning techniques, particularly Convolutional Neural Networks (CNNs), will be employed to classify skin diseases using dermoscopic images. The dataset for this study comes from the MNIST HAM10000 collection, which contains 10,015 images and was made available by the International Skin Imaging Collaboration (ISIC). The data is divided into seven categories, including skin cancer. For image classification, a pre-trained CNN model will be utilized. One key challenge is the imbalanced nature of the dataset. To mitigate this, data augmentation techniques were applied, helping to reduce class imbalance and ensure that classification accuracy across categories was not dominated by the majority class.

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.

Style transfer is an optimizing technique that aims to blend style of input image to content image. Deep neural networks have previously surpassed humans in tasks such as object identification and detection. Deep neural networks, on the contrary, had been lagging behind in generating higher quality creative products until lately. This article introduces deep-learning techniques, which are vital in accomplishing human characteristics and open up a new world of prospects. The system employs a pre-trained CNN so that the styles of the provided image is transferred to the content image to generate high quality stylized image. The designed systems effectiveness is evaluated based on Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index Metrics (SSIM), it is noticed that the designed method effectively maintains the structural and textural information of the cover image.

Skin cancer is a common and deadly cancer. Dermoscopy is an effective tool for the observation of abnormal skin pigmentation. However, dermoscopy images are extremely complex and present great challenges for diagnosis. Therefore, we proposed a classification method based on the ensemble of individual advantage and group decision in dermoscopy images, including the ensemble strategy of group decision, the ensemble strategy of maximizing individual advantage, and the ensemble strategy of block-integrated voting. We used generative adversarial networks (GANs) to create a balanced sample space to better train convolutional neural networks (CNNs). Through transfer learning, the pre-training CNNs were used for fine-tuning, then the effects of different CNNs on the classification of different categories of dermoscopy images were compared, and the CNNs with better classification effect were selected for the ensemble of different strategies. This study is based on the ISIC 2018 dataset and ISIC 2019 dataset. Compared with the different individual CNNs and the frameworks, the proposed ensemble strategies achieve a better improvement in the evaluation criteria.

The aim was to improve single-photon emission computed tomography (SPECT) quality for sparsely acquired 111In projections by adding deep learning generated synthetic intermediate projections (SIPs). Method: The recently constructed deep convolutional network for generating synthetic intermediate projections (CUSIP) was used for improving 20 sparsely acquired 111In-octreotide SPECTs. Reconstruction was performed with 120 (120P) or 30 (30P) projections, or 120 projections with 90 SIPs generated from 30 projections (30–120SIP). The SPECT reconstructions were performed with attenuation, scatter and collimator response corrections. Postfiltered 30P reconstructed SPECT was also analyzed. Image quality were quantitatively evaluated with root-mean-square error, peak signal-to-noise ratio and structural similarity index metrics. Result: The 30–120SIP reconstructed SPECT had statistically significant improved image quality parameters compared to 30P reconstructed SPECT with and without post filtering. The images visual appearance was similar to slightly filtered 120P SPECTs. Thereby, substantial acquisition time reduction with SIPs seems possible without image quality degradation.

This article presents a convolutional neural network (CNN)-based deep-learning (DL) model, inspired from UNet with a series of encoder and decoder units with skip connections, for the simulation of microwave–plasma interaction. The microwave propagation characteristics in complex plasma medium pertaining to transmission, absorption, and reflection primarily depend on the ratio of electromagnetic (EM) wave frequency and electron plasma frequency, and the plasma density profile. The scattering of a plane EM wave with fixed frequency (1 GHz) and amplitude incident on a plasma medium with different Gaussian density profiles (in the range of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1 \times10^{17}$ </tex-math></inline-formula> <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$- 1\times 10^{22} {\text {m}^{-3}}$ </tex-math></inline-formula> ) have been considered. The training data associated with microwave–plasma interaction has been generated using 2-D finite-difference time-domain (FDTD)-based simulations. The trained DL model is then used to reproduce the scattered electric field values for the 1-GHz incident microwave on different plasma profiles with an error margin of less than 2%. We propose a complete DL-based pipeline to train, validate, and evaluate the model. We compare the results of the network, using various metrics like structural similarity index metric (SSIM) index, average percent error, and mean square error, with the physical data obtained from well-established FDTD-based EM solvers. To the best of our knowledge, this is the first effort toward exploring a DL-based approach for the simulation of complex microwave–plasma interaction. The DL technique proposed in this work is significantly fast when compared to the existing computational techniques and can be used as a new, prospective, and alternative computational approach for investigating microwave–plasma interaction in a real-time scenario.

Skin cancer is one of the most lethal types of cancer worldwide. There are different types of cancer but the most dangerous one is melanoma. In US alone, 1 out of 5 people will develop skin cancer by the age of 70 and more than 2 people die of skin cancer every hour. Taking these facts under consideration, early detection of skin cancer is crucial, and many lives could be saved. Deep learning technologies are proven to be of great aid in early detection. In this master thesis, different convolutional neural networks will be presented and tested on HAM10000 dataset of ISIC challenge dataset of 2018, containing 10.000 images of skin lesion from seven different classes. Neural networks will be trained on a portion of the dataset and then tested in new images. The convolutional networks used are Densenet201, Inception V3 and an Ensemble model of the previous two. Lastly, an application is developed which uses by default a convolutional network defined by the user. The user is able to feed an image in the application and a result out of the seven classes predefined will be presented.

Skin cancer has emerged as a grave health concern leading to significant mortality rates. Diagnosis of this disease traditionally relies on specialist dermatologists who interpret dermoscopy images using the ABCD rule. However, the integration of computer-aided diagnosis technologies is gaining popularity as a means to assist clinicians in accurate skin cancer diagnosis, overcoming potential challenges associated with human error. The objective of this research is to develop a robust system for the detection of skin cancer by employing machine learning algorithms for skin lesion classification and detection. The proposed system utilizes Convolutional Neural Network (CNN), a highly accurate and efficient deep learning technique well-suited for image classification tasks. By using the power of CNN, this system effectively classifies various skin diseases in dermoscopic images associated with skin cancer The MNIST HAM10000 dataset, comprising 10015 images, serves as the foundation for this study. The dataset encompasses seven distinct skin diseases falling within the realm of skin cancer. In this study, diverse transfer learning methods were used and evaluated to enhance the performance of the system. By comparing and analyzing these approaches the highest accuracy rate was obtained using the MobileNetV2 model with a rate of 80.79% accuracy.

Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The system shows great potential in facilitating the initial screening of skin cancer patients, empowering healthcare professionals to make timely decisions regarding patient referrals to dermatologists or specialists for further diagnosis and appropriate treatment. Our advanced adaptive fine-tuned CNN approach for automatic skin cancer diagnosis offers a valuable tool for efficient and accurate early detection. By leveraging DL and transfer learning techniques, the system has the possible to transform skin cancer diagnosis and improve patient outcomes.