PAD-UFES-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones

Over the past few years, different Computer-Aided Diagnosis (CAD) systems have been proposed to tackle skin lesion analysis. Most of these systems work only for dermoscopy images since there is a strong lack of public clinical images archive available to evaluate the aforementioned CAD systems. To fill this gap, we release a skin lesion benchmark composed of clinical images collected from smartphone devices and a set of patient clinical data containing up to 21 features. The dataset consists of 1373 patients, 1641 skin lesions, and 2298 images for six different diagnostics: three skin diseases and three skin cancers. In total, 58.4% of the skin lesions are biopsy-proven, including 100% of the skin cancers. By releasing this benchmark, we aim to support future research and the development of new tools to assist clinicians to detect skin cancer.

Realistic hair simulator for skin lesion images: A novel benchemarking tool

Automated skin lesion analysis is one of the trending fields that has gained attention among the dermatologists and health care practitioners. Skin lesion restoration is an essential pre-processing step for lesion enhancements for accurate automated analysis and diagnosis by both dermatologists and computer-aided diagnosis tools. Hair occlusion is one of the most popular artifacts in dermatoscopic images. It can negatively impact the skin lesions diagnosis by both dermatologists and automated computer diagnostic tools. Digital hair removal is a non-invasive method for image enhancement for decrease the hair-occlusion artifact in previously captured images. Several hair removal methods were proposed for skin delineation and removal without standardized benchmarking techniques. Manual annotation is one of the main challenges that hinder the validation of these proposed methods on a large number of images or against benchmarking datasets for comparison purposes. In the presented work, we propose a photo-realistic hair simulator based on context-aware image synthesis using image-to-image translation techniques via conditional adversarial generative networks for generation of different hair occlusions in skin images, along with ground-truth mask for hair location. Hair-occluded image is synthesized using the latent structure of any input hair-free image by deep encoding the input image into a latent vector of features. The locations of required hair are highlighted using white pixels on the input image. Then, these deep encoded features are used to reconstruct the synthetic highly realistic hair-occluded image. Besides, we explored using three loss functions including L₁-norm, L₂-norm and structural similarity index (SSIM) to maximize the image synthesis visual quality. For the evaluation of the generated samples, the t-SNE feature mapping and Bland-Altman test are used as visualization tools for the experimental results. The results show the superior performance of our proposed method compared to previous methods for hair synthesis with plausible colours and preserving the integrity of the lesion texture. The proposed method can be used to generate benchmarking datasets for comparing the performance of digital hair removal methods. The code is available online at: https://github.com/attiamohammed/realhair.

Simple and Accurate Border Detection Algorithm for Melanoma Computer Aided Diagnosis

The interest of the scientific community for computer aided skin lesion analysis and characterization has been increased during the last years for the growing incidence of melanoma among cancerous pathologies. The detection of melanoma in its early stage is essential for prognosis improvement and for guaranteeing a high five-year relative survival rate of patients. The clinical diagnosis of skin lesions is challenging and not trivial since it depends on human vision and physician experience and expertise. Therefore, a computer method that makes an accurate extraction of important details of skin lesion image can assist dermatologists in cancer detection. In particular, the border detection is a critical computer vision issue owing to the wide range of lesion shapes, sizes, colours and skin texture types. In this paper, an automatic and effective pigmented skin lesion segmentation method in dermoscopic image is presented. The proposed procedure is adopted to extract a mask of the lesion region without the adoption of other signal processing procedures for image improvement. A quantitative experimental evaluation has been performed on a publicly available database. The achieved results show the method validity and its high robustness towards irregular boundaries, smooth transition between lesion and skin, noise and artifact presence.

Feature Selection of Non-Dermoscopic Skin Lesion Images for Nevus and Melanoma Classification

(1) Background: In this research, we aimed to identify and validate a set of relevant features to distinguish between benign nevi and melanoma lesions. (2) Methods: Two datasets with 70 melanomas and 100 nevi were investigated. The first one contained raw images. The second dataset contained images preprocessed for noise removal and uneven illumination reduction. Further, the images belonging to both datasets were segmented, followed by extracting features considered in terms of form/shape and color such as asymmetry, eccentricity, circularity, asymmetry of color distribution, quadrant asymmetry, fast Fourier transform (FFT) normalization amplitude, and 6th and 7th Hu’s moments. The FFT normalization amplitude is an atypical feature that is computed as a Fourier transform descriptor and focuses on geometric signatures of skin lesions using the frequency domain information. The receiver operating characteristic (ROC) curve and area under the curve (AUC) were employed to ascertain the relevance of the selected features and their capability to differentiate between nevi and melanoma. (3) Results: The ROC curves and AUC were employed for all experiments and selected features. A comparison in terms of the accuracy and AUC was performed, and an evaluation of the performance of the analyzed features was carried out. (4) Conclusions: The asymmetry index and eccentricity, together with F6 Hu’s invariant moment, were fairly competent in providing a good separation between malignant melanoma and benign lesions. Also, the FFT normalization amplitude feature should be exploited due to showing potential in classification.

Diagnostic techniques for improved segmentation, feature extraction, and classification of malignant melanoma

A typical diagnosis of malignant melanoma involves three major steps: segmentation of a lesion from the input color image, feature extraction from the separated lesion, and classification to distinguish malignant from benign melanomas based on features obtained. We suggest new methods for segmentation, feature extraction, and classification compared. We replaced edge-imfill method with U-Otsu method for segmentation, the previous features with new features for the criteria ABCD (asymmetry, border irregularity, color variegation, diameter) criteria, and the median thresholding with weighted receiver operating characteristic thresholding for classification. We used 88 melanoma images and expert's segmentation. All the three steps in the suggested method were compared with the steps in the previous method, with respect to sensitivity, specificity, and accuracy of the 88 samples. For segmentation, the previous and the suggested segmentations were also compared assuming the skin cancer expert's segmentation as a ground truth. All three steps resulted in remarkable improvement in the suggested method.

The Ethics of Machine Learning in Medical Sciences: Where Do We Stand Today?

Advances in Machine Learning and availability of state-of-the-art computational resources, along with digitized healthcare data, have set the stage for extensive application of artificial intelligence in the realm of diagnosis, prognosis, clinical decision support, personalized treatment options, drug development, and the field of biomedicine. Here, we discuss the application of Machine Learning algorithms in patient healthcare and dermatological domains along with the ethical complexities that are involved. In scientific studies, ethical challenges were initially not addressed proportionally (as assessed by keyword counts in PubMed) and just more recently (since 2016) this has started to improve. Few pioneering countries have created regulatory guidelines around how to respect matters of (1) privacy, (2) fairness, (3) accountability, (4) transparency and (5) conflict of interest when developing novel medical Machine Learning applications. While there is a strong promise of emerging medical applications to ultimately benefit both the patients and the medical practitioners, it is important to raise awareness on the five key ethical issues and incorporate them into medical practice in the near future.

Using content-based image retrieval of dermoscopic images for interpretation and education: A pilot study

BACKGROUND

Dermoscopic content-based image retrieval (CBIR) systems provide a set of visually similar dermoscopic (magnified and illuminated) skin images with a pathology-confirmed diagnosis for a given dermoscopic query image of a skin lesion. Although recent advances in machine learning have spurred novel CBIR algorithms, we have few insights into how end users interact with CBIRs and to what extent CBIRs can be useful for education and image interpretation.

MATERIALS AND METHODS

We developed an interactive user interface for a CBIR system with dermoscopic images as a decision support tool and investigated users' interactions and decisions with the system. We performed a pilot experiment with 14 non-medically trained users for a given set of annotated dermoscopic images.

RESULTS

Our pilot showed that the number of correct classifications and users' confidence levels significantly increased with the CBIR interface compared with a non-CBIR interface, although the timing also increased significantly. The users found the CBIR interface of high educational value, engaging and easy to use.

CONCLUSION

Overall, users became more accurate, found the CBIR approach provided a useful decision aid, and had educational value for learning about skin conditions.

Gabor wavelet-based deep learning for skin lesion classification

Skin cancer cases are increasing and becoming one of the main problems worldwide. Skin cancer is known as a malignant type of skin lesion, and early detection and treatment are necessary. Malignant melanoma and seborrheic keratosis are known as common skin lesion types. A fast and accurate medical diagnosis of these lesions is crucial. In this study, a novel Gabor wavelet-based deep convolutional neural network is proposed for the detection of malignant melanoma and seborrheic keratosis. The proposed method is based on the decomposition of input images into seven directional sub-bands. Seven sub-band images and the input image are used as inputs to eight parallel CNNs to generate eight probabilistic predictions. Decision fusion based on the sum rule is utilized to classify the skin lesion. Gabor based approach provides directional decomposition where each sub-band gives isolated decisions that can be fused for improved overall performance. The results show that the proposed method outperforms alternative methods in the literature developed for skin cancer detection.

Skin cancer detection by deep learning and sound analysis algorithms: A prospective clinical study of an elementary dermoscope

Background

Skin cancer (SC), especially melanoma, is a growing public health burden. Experimental studies have indicated a potential diagnostic role for deep learning (DL) algorithms in identifying SC at varying sensitivities. Previously, it was demonstrated that diagnostics by dermoscopy are improved by applying an additional sonification (data to sound waves conversion) layer on DL algorithms. The aim of the study was to determine the impact of image quality on accuracy of diagnosis by sonification employing a rudimentary skin magnifier with polarized light (SMP).

Methods

Dermoscopy images acquired by SMP were processed by a first deep learning algorithm and sonified. Audio output was further analyzed by a different secondary DL. Study criteria outcomes of SMP were specificity and sensitivity, which were further processed by a F2-score, i.e. applying a twice extra weight to sensitivity over positive predictive values.

Findings

Patients (n = 73) fulfilling inclusion criteria were referred to biopsy. SMP analysis metrics resulted in a receiver operator characteristic curve AUC's of 0.814 (95% CI, 0.798–0.831). SMP achieved a F2-score sensitivity of 91.7%, specificity of 41.8% and positive predictive value of 57.3%. Diagnosing the same set of patients' lesions by an advanced dermoscope resulted in a F2-score sensitivity of 89.5%, specificity of 57.8% and a positive predictive value of 59.9% (P=NS).

Interpretation

DL processing of dermoscopic images followed by sonification results in an accurate diagnostic output for SMP, implying that the quality of the dermoscope is not the major factor influencing DL diagnosis of skin cancer. Present system might assist all healthcare providers as a feasible computer-assisted detection system.

Fund

Bostel Technologies.

Trial Registration clinicaltrials.gov Identifier: NCT03362138