Novel Approaches for Diagnosing Melanoma Skin Lesions Through Supervised and Deep Learning Algorithms

Recognition of Cutaneous Melanoma on Digitized Histopathological Slides via Artificial Intelligence Algorithm

Increasing incidence of skin cancer combined with a shortage of dermatopathologists has increased the workload of pathology departments worldwide. In addition, the high intraobserver and interobserver variability in the assessment of melanocytic skin lesions can result in underestimated or overestimated diagnosis of melanoma. Thus, the development of new techniques for skin tumor diagnosis is essential to assist pathologists to standardize diagnoses and plan accurate patient treatment. Here, we describe the development of an artificial intelligence (AI) system that recognizes cutaneous melanoma from histopathological digitalized slides with clinically acceptable accuracy. Whole-slide digital images from 100 formalin-fixed paraffin-embedded primary cutaneous melanoma were used to train a convolutional neural network (CNN) based on a pretrained Inception-ResNet-v2 to accurately and automatically differentiate tumoral areas from healthy tissue. The CNN was trained by using 60 digital slides in which regions of interest (ROIs) of tumoral and healthy tissue were extracted by experienced dermatopathologists, while the other 40 slides were used as test datasets. A total of 1377 patches of healthy tissue and 2141 patches of melanoma were assessed in the training/validation set, while 791 patches of healthy tissue and 1122 patches of pathological tissue were evaluated in the test dataset. Considering the classification by expert dermatopathologists as reference, the trained deep net showed high accuracy (96.5%), sensitivity (95.7%), specificity (97.7%), F₁ score (96.5%), and a Cohen’s kappa of 0.929. Our data show that a deep learning system can be trained to recognize melanoma samples, achieving accuracies comparable to experienced dermatopathologists. Such an approach can offer a valuable aid in improving diagnostic efficiency when expert consultation is not available, as well as reducing interobserver variability. Further studies in larger data sets are necessary to verify whether the deep learning algorithm allows subclassification of different melanoma subtypes.

Artificial Intelligence in Cutaneous Oncology

Skin cancer, previously known to be a common disease in Western countries, is becoming more common in Asian countries. Skin cancer differs from other carcinomas in that it is visible to our eyes. Although skin biopsy is essential for the diagnosis of skin cancer, decisions regarding whether or not to conduct a biopsy are made by an experienced dermatologist. From this perspective, it is easy to obtain and store photos using a smartphone, and artificial intelligence technologies developed to analyze these photos can represent a useful tool to complement the dermatologist's knowledge. In addition, the universal use of dermoscopy, which allows for non-invasive inspection of the upper dermal level of skin lesions with a usual 10-fold magnification, adds to the image storage and analysis techniques, foreshadowing breakthroughs in skin cancer diagnosis. Current problems include the inaccuracy of the available technology and resulting legal liabilities. This paper presents a comprehensive review of the clinical applications of artificial intelligence and a discussion on how it can be implemented in the field of cutaneous oncology.

Skin Lesion Segmentation Using Stochastic Region-Merging and Pixel-Based Markov Random Field

Markov random field (MRF) theory has achieved great success in image segmentation. Researchers have developed various methods based on MRF theory to solve skin lesions segmentation problems such as pixel-based MRF model, stochastic region-merging approach, symmetric MRF model, etc. In this paper, the proposed method seeks to provide a complement to the advantages of the pixel-based MRF model and stochastic region-merging approach. This is in order to overcome shortcomings of the pixel-based MRF model, because of various challenges that affect the skin lesion segmentation results such as irregular and fuzzy border, noisy and artifacts presence, and low contrast between lesions. The strength of the proposed method lies in the aspect of combining the benefits of the pixel-based MRF model and the stochastic region-merging by decomposing the likelihood function into the multiplication of stochastic region-merging likelihood function and the pixel likelihood function. The proposed method was evaluated on bench marked available datasets, PH2 and ISIC. The proposed method achieves Dice coefficients of 89.65 % on PH2 and 88.34 % on ISIC datasets respectively.

Artificial intelligence for clinical decision support in neurology

Artificial intelligence is one of the most exciting methodological shifts in our era. It holds the potential to transform healthcare as we know it, to a system where humans and machines work together to provide better treatment for our patients. It is now clear that cutting edge artificial intelligence models in conjunction with high-quality clinical data will lead to improved prognostic and diagnostic models in neurological disease, facilitating expert-level clinical decision tools across healthcare settings. Despite the clinical promise of artificial intelligence, machine and deep-learning algorithms are not a one-size-fits-all solution for all types of clinical data and questions. In this article, we provide an overview of the core concepts of artificial intelligence, particularly contemporary deep-learning methods, to give clinician and neuroscience researchers an appreciation of how artificial intelligence can be harnessed to support clinical decisions. We clarify and emphasize the data quality and the human expertise needed to build robust clinical artificial intelligence models in neurology. As artificial intelligence is a rapidly evolving field, we take the opportunity to iterate important ethical principles to guide the field of medicine is it moves into an artificial intelligence enhanced future.

A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images

Skin lesion border irregularity is considered an important clinical feature for the early diagnosis of melanoma, representing the B feature in the ABCD rule. In this article we propose an automated approach for skin lesion border irregularity detection. The approach involves extracting the skin lesion from the image, detecting the skin lesion border, measuring the border irregularity, training a Convolutional Neural Network and Gaussian naive Bayes ensemble, to the automatic detection of border irregularity, which results in an objective decision on whether the skin lesion border is considered regular or irregular. The approach achieves outstanding results, obtaining an accuracy, sensitivity, specificity, and F-score of 93.6%, 100%, 92.5% and 96.1%, respectively.

Artificial Intelligence Applications in Dermatology: Where Do We Stand?

Artificial intelligence (AI) has become a progressively prevalent Research Topic in medicine and is increasingly being applied to dermatology. There is a need to understand this technology's progress to help guide and shape the future for medical care providers and recipients. We reviewed the literature to evaluate the types of publications on the subject, the specific dermatological topics addressed by AI, and the most challenging barriers to its implementation. A substantial number of original articles and commentaries have been published to date and only few detailed reviews exist. Most AI applications focus on differentiating between benign and malignant skin lesions, however; others exist pertaining to ulcers, inflammatory skin diseases, allergen exposure, dermatopathology, and gene expression profiling. Applications commonly analyze and classify images, however, other tools such as risk assessment calculators are becoming increasingly available. Although many applications are technologically feasible, important implementation barriers have been identified including systematic biases, difficulty of standardization, interpretability, and acceptance by physicians and patients alike. This review provides insight into future research needs and possibilities. There is a strong need for clinical investigation in dermatology providing evidence of success overcoming the identified barriers. With these research goals in mind, an appropriate role for AI in dermatology may be achieved in not so distant future.

Characterizing the role of dermatologists in developing artificial intelligence for assessment of skin cancer: A systematic review

BACKGROUND

The use of artificial intelligence (AI) for skin cancer assessment has been an emerging topic in dermatology. Leadership of dermatologists is necessary in defining how these technologies fit into clinical practice.

OBJECTIVE

To characterize the evolution of AI in skin cancer assessment and characterize the involvement of dermatologists in developing these technologies.

METHODS

An electronic literature search was performed using PubMed by searching machine learning or artificial intelligence combined with skin cancer or melanoma. Articles were included if they used AI for screening and diagnosis of skin cancer using data sets consisting of dermoscopic images or photographs of gross lesions.

RESULTS

Fifty-one articles were included, and 41% of these had dermatologists included as authors. Articles that included dermatologists described algorithms built with more images versus articles that did not include dermatologists (mean, 12,111 vs 660 images, respectively). In terms of underlying technology, AI used for skin cancer assessment has followed trends in the field of image recognition.

LIMITATIONS

This review focused on models described in the medical literature and did not account for those described elsewhere.

CONCLUSIONS

Greater involvement of dermatologists is needed in thinking through issues in data collection, data set biases, and applications of technology. Dermatologists can provide access to large, diverse data sets that are increasingly important for building these models.

Risk factors influencing survival of acellular porcine corneal stroma in infectious keratitis: a prospective clinical study

Background

A worldwide lack of donor corneas demands the bioengineered corneas be developed as an alternative. The primary objective of the current study was to evaluate the efficacy of acellular porcine corneal stroma (APCS) transplantation in various types of infectious keratitis and identify risk factors that may increase APCS graft failure.

Methods

In this prospective interventional study, 39 patients with progressive infectious keratitis underwent therapeutic lamellar keratoplasty using APCS and were followed up for 12 months. Data collected for analysis included preoperative characteristics, visual acuity, graft survival and complications. Graft survival was evaluated by the Kaplan–Meier method and compared with the log-rank test.

Results

The percentage of eyes that had a visual acuity of 20/40 or better increased from 10.3% preoperatively to 51.2% at 12 months postoperatively. Twelve patients (30.8%) experienced graft failure within the follow-up period. The primary reasons given for graft failure was noninfectious graft melting (n = 5), and the other causes included recurrence of primary infection (n = 4) and extensive graft neovascularization (n = 3). No graft rejection was observed during the follow-up period. A higher relative risk (RR) of graft failure was associated with herpetic keratitis (RR = 8.0, P = 0.046) and graft size larger than 8 mm (RR = 6.5, P < 0.001).

Conclusions

APCS transplantation is an alternative treatment option for eyes with medically unresponsive infectious keratitis. Despite the efficacy of therapeutic lamellar keratoplasty with APCS, to achieve a good prognosis, restriction of surgical indications, careful selection of patients and postoperative management must be emphasized.

Trial registration Prospective Study of Deep Anterior Lamellar Keratoplasty Using Acellular Porcine Cornea, NCT03105466. Registered 31 August 2016, ClinicalTrails.gov

Systematic review of machine learning for diagnosis and prognosis in dermatology

Background: Software systems using artificial intelligence for medical purposes have been developed in recent years. The success of deep neural networks (DNN) in 2012 in the image recognition challenge ImageNet LSVRC 2010 fueled expectations of the potential for using such systems in dermatology.Objective: To evaluate the ways in which machine learning has been utilized in dermatology to date and provide an overview of the findings in current literature on the subject.Methods: We conducted a systematic review of existing literature, identifying the literature through a systematic search of the PubMed database. Two doctors assessed screening and eligibility with respect to pre-determined inclusion and exclusion criteria.Results: A total of 2175 publications were identified, and 64 publications were included. We identified eight major categories where machine learning tools were tested in dermatology. Most systems involved image recognition tools that were primarily aimed at binary classification of malignant melanoma (MM). Short system descriptions and results of all included systems are presented in tables.Conclusions: We present a complete overview of artificial intelligence implemented in dermatology. Impressive outcomes were reported in all of the identified eight categories, but head-to-head comparison proved difficult. The many areas of dermatology where we identified machine learning tools indicate the diversity of machine learning.

Classification of Carotid Artery Intima Media Thickness Ultrasound Images with Deep Learning

Cerebrovascular accident due to carotid artery disease is the most common cause of death in developed countries following heart disease and cancer. For a reliable early detection of atherosclerosis, Intima Media Thickness (IMT) measurement and classification are important. A new method for decision support purpose for the classification of IMT was proposed in this study. Ultrasound images are used for IMT measurements. Images are classified and evaluated by experts. This is a manual procedure, so it causes subjectivity and variability in the IMT classification. Instead, this article proposes a methodology based on artificial intelligence methods for IMT classification. For this purpose, a deep learning strategy with multiple hidden layers has been developed. In order to create the proposed model, convolutional neural network algorithm, which is frequently used in image classification problems, is used. 501 ultrasound images from 153 patients were used to test the model. The images are classified by two specialists, then the model is trained and tested on the images, and the results are explained. The deep learning model in the study achieved an accuracy of 89.1% in the IMT classification with 89% sensitivity and 88% specificity. Thus, the assessments in this paper have shown that this methodology performs reasonable results for IMT classification.

Convolutional Neural Network Approach to Classify Skin Lesions Using Reflectance Confocal Microscopy

We propose an approach based on a convolutional neural network to classify skin lesions using the reflectance confocal microscopy (RCM) mosaics. Skin cancers are the most common type of cancers and a correct, early diagnosis significantly lowers both morbidity and mortality. RCM is an in-vivo non-invasive screening tool that produces virtual biopsies of skin lesions but its proficient and safe use requires hard to obtain expertise. Therefore, it may be useful to have an additional tool to aid diagnosis. The proposed network is based on the ResNet architecture. The dataset consists of 429 RCM mosaics and is divided into 3 classes: melanoma, basal cell carcinoma, and benign naevi with the ground-truth confirmed by a histopathological examination. The test set classification accuracy was 87%, higher than the accuracy achieved by medical, confocal users. The results show that the proposed classification system can be a useful tool to aid in early, noninvasive melanoma detection.

Segmented and Non-Segmented Skin Lesions Classification Using Transfer Learning and Adaptive Moment Learning Rate Technique Using Pretrained Convolutional Neural Network

A skin lesion is a very severe problem, especially in coastal countries. Early detection by a highly reliable classification of skin lesion causes a great reduction in the mortality rate. Recognition of melanoma is a complicated issue due to the high degree of visual similarities between melanoma and non-melanoma lesions. Various studies are carried out to overcome this problem and to obtain accurate screening of skin lesion, where the most recent method for segmenting and classifying the lesion is based on a deep learning algorithm. In this paper, (GoogleNet) and (AlexNet) are employed with transfer learning and optimization gradient descent adaptive momentum learning rate (ADAM). The proposed method is applied on Archive International Skin Imaging Collaboration (ISIC) database to classify images into three main classes (benign, melanoma, seborrheic keratosis) under the two scenarios; segmented and non-segmented lesion images. The overall accuracy of the non-segmented classification database is 92.2% and 89.8% for the non-segmented dataset. Utilizing optimization algorithm (ADAM) leads to a significant improvement in the classification results when they are compared with previous studies.

Classification of skin lesions using transfer learning and augmentation with Alex-net

Skin cancer is one of most deadly diseases in humans. According to the high similarity between melanoma and nevus lesions, physicians take much more time to investigate these lesions. The automated classification of skin lesions will save effort, time and human life. The purpose of this paper is to present an automatic skin lesions classification system with higher classification rate using the theory of transfer learning and the pre-trained deep neural network. The transfer learning has been applied to the Alex-net in different ways, including fine-tuning the weights of the architecture, replacing the classification layer with a softmax layer that works with two or three kinds of skin lesions, and augmenting dataset by fixed and random rotation angles. The new softmax layer has the ability to classify the segmented color image lesions into melanoma and nevus or into melanoma, seborrheic keratosis, and nevus. The three well-known datasets, MED-NODE, Derm (IS & Quest) and ISIC, are used in testing and verifying the proposed method. The proposed DCNN weights have been fine-tuned using the training and testing dataset from ISIC in addition to 10-fold cross validation for MED-NODE and DermIS—DermQuest. The accuracy, sensitivity, specificity, and precision measures are used to evaluate the performance of the proposed method and the existing methods. For the datasets, MED-NODE, Derm (IS & Quest) and ISIC, the proposed method has achieved accuracy percentages of 96.86%, 97.70%, and 95.91% respectively. The performance of the proposed method has outperformed the performance of the existing classification methods of skin cancer.

Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis

BACKGROUND

Application of deep-learning technology to skin cancer classification can potentially improve the sensitivity and specificity of skin cancer screening, but the number of training images required for such a system is thought to be extremely large.

OBJECTIVES

To determine whether deep-learning technology could be used to develop an efficient skin cancer classification system with a relatively small dataset of clinical images.

METHODS

A deep convolutional neural network (DCNN) was trained using a dataset of 4867 clinical images obtained from 1842 patients diagnosed with skin tumours at the University of Tsukuba Hospital from 2003 to 2016. The images consisted of 14 diagnoses, including both malignant and benign conditions. Its performance was tested against 13 board-certified dermatologists and nine dermatology trainees.

RESULTS

The overall classification accuracy of the trained DCNN was 76·5%. The DCNN achieved 96·3% sensitivity (correctly classified malignant as malignant) and 89·5% specificity (correctly classified benign as benign). Although the accuracy of malignant or benign classification by the board-certified dermatologists was statistically higher than that of the dermatology trainees (85·3% ± 3·7% and 74·4% ± 6·8%, P < 0·01), the DCNN achieved even greater accuracy, as high as 92·4% ± 2·1% (P < 0·001).

CONCLUSIONS

We have developed an efficient skin tumour classifier using a DCNN trained on a relatively small dataset. The DCNN classified images of skin tumours more accurately than board-certified dermatologists. Collectively, the current system may have capabilities for screening purposes in general medical practice, particularly because it requires only a single clinical image for classification.

Machine learning-based diagnosis of melanoma using macro images

Cancer bears a poisoning threat to human society. Melanoma, the skin cancer, originates from skin layers and penetrates deep into subcutaneous layers. There exists an extensive research in melanoma diagnosis using dermatoscopic images captured through a dermatoscope. While designing a diagnostic model for general handheld imaging systems is an emerging trend, this article proposes a computer-aided decision support system for macro images captured by a general-purpose camera. General imaging conditions are adversely affected by nonuniform illumination, which further affects the extraction of relevant information. To mitigate it, we process an image to define a smooth illumination surface using the multistage illumination compensation approach, and the infected region is extracted using the proposed multimode segmentation method. The lesion information is numerated as a feature set comprising geometry, photometry, border series, and texture measures. The redundancy in feature set is reduced using information theory methods, and a classification boundary is modeled to distinguish benign and malignant samples using support vector machine, random forest, neural network, and fast discriminative mixed-membership-based naive Bayesian classifiers. Moreover, the experimental outcome is supported by hypothesis testing and boxplot representation for classification losses. The simulation results prove the significance of the proposed model that shows an improved performance as compared with competing arts.

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

Highlights

We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.

Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.

The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls.

Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way.

Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC).

Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM).

Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier.

Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.