Deep Learning Approaches Towards Skin Lesion Segmentation and Classification from Dermoscopic Images - A Review

Exploring the feasibility of an artificial intelligence based clinical decision support system for cutaneous melanoma detection in primary care - a mixed method study

Objective: Skin examination to detect cutaneous melanomas is commonly performed in primary care. In recent years, clinical decision support systems (CDSS) based on artificial intelligence (AI) have been introduced within several diagnostic fields.Setting: This study employs a variety of qualitative and quantitative methodologies to investigate the feasibility of an AI-based CDSS to detect cutaneous melanoma in primary care.Subjects and Design: Fifteen primary care physicians (PCPs) underwent near-live simulations using the CDSS on a simulated patient, and subsequent individual semi-structured interviews were explored with a hybrid thematic analysis approach. Additionally, twenty-five PCPs performed a reader study (diagnostic assessment on the basis of image interpretation) of 18 dermoscopic images, both with and without help from AI, investigating the value of adding AI support to a PCPs decision. Perceived instrument usability was rated on the System Usability Scale (SUS).Results: From the interviews, the importance of trust in the CDSS emerged as a central concern. Scientific evidence supporting sufficient diagnostic accuracy of the CDSS was expressed as an important factor that could increase trust. Access to AI decision support when evaluating dermoscopic images proved valuable as it formally increased the physician's diagnostic accuracy. A mean SUS score of 84.8, corresponding to 'good' usability, was measured.Conclusion: AI-based CDSS might play an important future role in cutaneous melanoma diagnostics, provided sufficient evidence of diagnostic accuracy and usability supporting its trustworthiness among the users.

Finetuning of GLIDE stable diffusion model for AI-based text-conditional image synthesis of dermoscopic images

Background

The development of artificial intelligence (AI)-based algorithms and advances in medical domains rely on large datasets. A recent advancement in text-to-image generative AI is GLIDE (Guided Language to Image Diffusion for Generation and Editing). There are a number of representations available in the GLIDE model, but it has not been refined for medical applications.

Methods

For text-conditional image synthesis with classifier-free guidance, we have fine-tuned GLIDE using 10,015 dermoscopic images of seven diagnostic entities, including melanoma and melanocytic nevi. Photorealistic synthetic samples of each diagnostic entity were created by the algorithm. Following this, an experienced dermatologist reviewed 140 images (20 of each entity), with 10 samples originating from artificial intelligence and 10 from original images from the dataset. The dermatologist classified the provided images according to the seven diagnostic entities. Additionally, the dermatologist was asked to indicate whether or not a particular image was created by AI. Further, we trained a deep learning model to compare the diagnostic results of dermatologist versus machine for entity classification.

Results

The results indicate that the generated images possess varying degrees of quality and realism, with melanocytic nevi and melanoma having higher similarity to real images than other classes. The integration of synthetic images improved the classification performance of the model, resulting in higher accuracy and precision. The AI assessment showed superior classification performance compared to dermatologist.

Conclusion

Overall, the results highlight the potential of synthetic images for training and improving AI models in dermatology to overcome data scarcity.

An Effective Skin Cancer Classification Mechanism via Medical Vision Transformer

Skin Cancer (SC) is considered the deadliest disease in the world, killing thousands of people every year. Early SC detection can increase the survival rate for patients up to 70%, hence it is highly recommended that regular head-to-toe skin examinations are conducted to determine whether there are any signs or symptoms of SC. The use of Machine Learning (ML)-based methods is having a significant impact on the classification and detection of SC diseases. However, there are certain challenges associated with the accurate classification of these diseases such as a lower detection accuracy, poor generalization of the models, and an insufficient amount of labeled data for training. To address these challenges, in this work we developed a two-tier framework for the accurate classification of SC. During the first stage of the framework, we applied different methods for data augmentation to increase the number of image samples for effective training. As part of the second tier of the framework, taking into consideration the promising performance of the Medical Vision Transformer (MVT) in the analysis of medical images, we developed an MVT-based classification model for SC. This MVT splits the input image into image patches and then feeds these patches to the transformer in a sequence structure, like word embedding. Finally, Multi-Layer Perceptron (MLP) is used to classify the input image into the corresponding class. Based on the experimental results achieved on the Human Against Machine (HAM10000) datasets, we concluded that the proposed MVT-based model achieves better results than current state-of-the-art techniques for SC classification.

Superpixel-Oriented Label Distribution Learning for Skin Lesion Segmentation

Lesion segmentation is a critical task in skin cancer analysis and detection. When developing deep learning-based segmentation methods, we need a large number of human-annotated labels to serve as ground truth for model-supervised learning. Due to the complexity of dermatological images and the subjective differences of different dermatologists in decision-making, the labels in the segmentation target boundary region are prone to produce uncertain labels or error labels. These labels may lead to unsatisfactory performance of dermoscopy segmentation. In addition, the model trained by the errored one-hot label may be overconfident, which can lead to arbitrary prediction and model overfitting. In this paper, a superpixel-oriented label distribution learning method is proposed. The superpixels formed by the simple linear iterative cluster (SLIC) algorithm combine one-hot labels constraint and define a distance function to convert it into a soft probability distribution. Referring to the model structure of knowledge distillation, after Superpixel-oriented label distribution learning, we get soft labels with structural prior information. Then the soft labels are transferred as new knowledge to the lesion segmentation network for training. Ours method on ISIC 2018 datasets achieves an Dice coefficient reaching 84%, sensitivity 79.6%, precision 80.4%, improved by 19.3%, 8.6% and 2.5% respectively in comparison with the results of U-Net. We also evaluate our method on the tasks of skin lesion segmentation via several general neural network architectures. The experiments show that ours method improves the performance of network image segmentation and can be easily integrated into most existing deep learning architectures.

Deep learning-based automatic assessment of radiation dermatitis in nasopharyngeal carcinoma (NPC) patients

PURPOSE

Radiation dermatitis (RD) is a common, unpleasant side-effect of patients receiving radiotherapy. In clinical practice, the severity of RD is graded manually through visual inspection, which is labor-intensive and often leads to large inter-rater variations. To overcome these shortcomings, this study aims to develop an automatic RD assessment based on deep learning (DL) techniques, which could efficiently assist the RD severity classification in clinical application.

METHODS

A total of 1205 photographs of the head and neck region were collected from nasopharyngeal carcinoma (NPC) patients undergoing radiotherapy. The severity of RD in these photographs was graded by five qualified assessors based on the Radiation Therapy Oncology Group (RTOG) guidance. An end-to-end RD grading framework was developed by combining a DL-based segmentation network and a DL-based RD severity classifier, which are used for segmenting the neck region from the camera-captured photographs and grading, respectively. U-Net was used for segmentation and another convolutional neural network (CNN) classifier (DenseNet-121) was applied to RD severity classification. Dice Similarity Coefficient (DSC) was used to evaluate the performance of segmentation. Severity classification was evaluated by several metrics, including overall accuracy, precision, recall, and F1-score.

RESULTS

Results of segmentation showed that the averaged DSCs were 91.2% and 90.8% for front and side view, respectively. For RD severity classification, the overall accuracy of test photographs was 83.0%. Our method accurately classified 90.5% of Grade 0, 67.2% of Grade 1, 93.8% of Grade 2, and 100% of Above Grade 2 cases. The overall prediction performance was comparable with human assessors. There was no significant difference in accuracy when using manually or automatically segmented regions (p = 0.683).

CONCLUSION

We have successfully demonstrated a DL-based method for automatic assessment of RD severity in NPC patients. This method holds great potential for efficient and effective assessing and monitoring of RD in NPC patients.

Imtidad: A Reference Architecture and a Case Study on Developing Distributed AI Services for Skin Disease Diagnosis over Cloud, Fog and Edge

Several factors are motivating the development of preventive, personalized, connected, virtual, and ubiquitous healthcare services. These factors include declining public health, increase in chronic diseases, an ageing population, rising healthcare costs, the need to bring intelligence near the user for privacy, security, performance, and costs reasons, as well as COVID-19. Motivated by these drivers, this paper proposes, implements, and evaluates a reference architecture called Imtidad that provides Distributed Artificial Intelligence (AI) as a Service (DAIaaS) over cloud, fog, and edge using a service catalog case study containing 22 AI skin disease diagnosis services. These services belong to four service classes that are distinguished based on software platforms (containerized gRPC, gRPC, Android, and Android Nearby) and are executed on a range of hardware platforms (Google Cloud, HP Pavilion Laptop, NVIDIA Jetson nano, Raspberry Pi Model B, Samsung Galaxy S9, and Samsung Galaxy Note 4) and four network types (Fiber, Cellular, Wi-Fi, and Bluetooth). The AI models for the diagnosis include two standard Deep Neural Networks and two Tiny AI deep models to enable their execution at the edge, trained and tested using 10,015 real-life dermatoscopic images. The services are evaluated using several benchmarks including model service value, response time, energy consumption, and network transfer time. A DL service on a local smartphone provides the best service in terms of both energy and speed, followed by a Raspberry Pi edge device and a laptop in fog. The services are designed to enable different use cases, such as patient diagnosis at home or sending diagnosis requests to travelling medical professionals through a fog device or cloud. This is the pioneering work that provides a reference architecture and such a detailed implementation and treatment of DAIaaS services, and is also expected to have an extensive impact on developing smart distributed service infrastructures for healthcare and other sectors.

Characterizing Malignant Melanoma Clinically Resembling Seborrheic Keratosis Using Deep Knowledge Transfer

Simple Summary

Malignant melanomas (MMs) with aypical clinical presentation constitute a diagnostic pitfall, and false negatives carry the risk of a diagnostic delay and improper disease management. Among the most common, challenging presentation forms of MMs are those that clinically resemble seborrheic keratosis (SK). On the other hand, SK may mimic melanoma, producing ‘false positive overdiagnosis’ and leading to needless excisions. The evolving efficiency of deep learning algorithms in image recognition and the availability of large image databases have accelerated the development of advanced computer-aided systems for melanoma detection. In the present study, we used image data from the International Skin Image Collaboration archive to explore the capacity of deep knowledge transfer in the challenging diagnostic task of the atypical skin tumors of MM and SK.

Abstract

Malignant melanomas resembling seborrheic keratosis (SK-like MMs) are atypical, challenging to diagnose melanoma cases that carry the risk of delayed diagnosis and inadequate treatment. On the other hand, SK may mimic melanoma, producing a ‘false positive’ with unnecessary lesion excisions. The present study proposes a computer-based approach using dermoscopy images for the characterization of SΚ-like MMs. Dermoscopic images were retrieved from the International Skin Imaging Collaboration archive. Exploiting image embeddings from pretrained convolutional network VGG16, we trained a support vector machine (SVM) classification model on a data set of 667 images. SVM optimal hyperparameter selection was carried out using the Bayesian optimization method. The classifier was tested on an independent data set of 311 images with atypical appearance: MMs had an absence of pigmented network and had an existence of milia-like cysts. SK lacked milia-like cysts and had a pigmented network. Atypical MMs were characterized with a sensitivity and specificity of 78.6% and 84.5%, respectively. The advent of deep learning in image recognition has attracted the interest of computer science towards improved skin lesion diagnosis. Open-source, public access archives of skin images empower further the implementation and validation of computer-based systems that might contribute significantly to complex clinical diagnostic problems such as the characterization of SK-like MMs.

Application of deep learning in image recognition and diagnosis of gastric cancer

In recent years, artificial intelligence has been extensively applied in the diagnosis of gastric cancer based on medical imaging. In particular, using deep learning as one of the mainstream approaches in image processing has made remarkable progress. In this paper, we also provide a comprehensive literature survey using four electronic databases, PubMed, EMBASE, Web of Science, and Cochrane. The literature search is performed until November 2020. This article provides a summary of the existing algorithm of image recognition, reviews the available datasets used in gastric cancer diagnosis and the current trends in applications of deep learning theory in image recognition of gastric cancer. covers the theory of deep learning on endoscopic image recognition. We further evaluate the advantages and disadvantages of the current algorithms and summarize the characteristics of the existing image datasets, then combined with the latest progress in deep learning theory, and propose suggestions on the applications of optimization algorithms. Based on the existing research and application, the label, quantity, size, resolutions, and other aspects of the image dataset are also discussed. The future developments of this field are analyzed from two perspectives including algorithm optimization and data support, aiming to improve the diagnosis accuracy and reduce the risk of misdiagnosis.

A Probabilistic-Based Deep Learning Model for Skin Lesion Segmentation

The analysis and detection of skin cancer diseases from skin lesion have always been tedious when done manually. The complex nature of skin lesion images is one of the key reasons for this. The skin lesion images contain noise and artifacts such as hairs, oil and bubbles, blood vessels, and skin lines. They also have variegated colors, low contrast, and irregular borders. Various computational approaches have been designed in the past for aiding in the detection and diagnosis of skin cancer diseases using skin lesion images. The existing techniques have been limited due to the interference of the aforementioned features of skin lesion. Recently, machine learning techniques, in particular the deep learning techniques have been used for the detection of skin cancer. However, they are still limited to the fuzzy and irregular borders of skin lesion images coupled with the low contrast that exists between the diseased lesion and healthy tissues. In this paper, we utilized a probabilistic model for the enhancement of a fully convolutional network-based deep learning system to analyze and segment skin lesion images. The probabilistic model employs an efficient mean-field approximate probabilistic inference approach with a fully connected conditional random field that utilizes a Gaussian kernel. The probabilistic model further performs a refinement of skin lesion borders. The whole framework is tested and evaluated on publicly available skin lesion image datasets of ISBI 2017 and PH2. The system achieved a better performance, having an accuracy of 98%.

A hierarchical three-step superpixels and deep learning framework for skin lesion classification

Skin cancer is one of the most common and dangerous cancer that exists worldwide. Malignant melanoma is one of the most dangerous skin cancer types has a high mortality rate. An estimated 196,060 melanoma cases will be diagnosed in 2020 in the USA. Many computerized techniques are presented in the past to diagnose skin lesions, but they are still failing to achieve significant accuracy. To improve the existing accuracy, we proposed a hierarchical framework based on two-dimensional superpixels and deep learning. First, we enhance the contrast of original dermoscopy images by fusing local and global enhanced images. The entire enhanced images are utilized in the next step to segmentation skin lesions using three-step superpixel lesion segmentation. The segmented lesions are mapped over the whole enhanced dermoscopy images and obtained only segmented color images. Then, a deep learning model (ResNet-50) is applied to these mapped images and learned features through transfer learning. The extracted features are further optimized using an improved grasshopper optimization algorithm, which is later classified through the Naïve Bayes classifier. The proposed hierarchical method has been evaluated on three datasets (Ph2, ISBI2016, and HAM1000), consisting of three, two, and seven skin cancer classes. On these datasets, our method achieved an accuracy of 95.40%, 91.1%, and 85.50%, respectively. The results show that this method can be helpful for the classification of skin cancer with improved accuracy.

CNN-based transfer learning-BiLSTM network: A novel approach for COVID-19 infection detection

Coronavirus disease 2019 (COVID-2019), which emerged in Wuhan, China in 2019 and has spread rapidly all over the world since the beginning of 2020, has infected millions of people and caused many deaths. For this pandemic, which is still in effect, mobilization has started all over the world, and various restrictions and precautions have been taken to prevent the spread of this disease. In addition, infected people must be identified in order to control the infection. However, due to the inadequate number of Reverse Transcription Polymerase Chain Reaction (RT-PCR) tests, Chest computed tomography (CT) becomes a popular tool to assist the diagnosis of COVID-19. In this study, two deep learning architectures have been proposed that automatically detect positive COVID-19 cases using Chest CT X-ray images. Lung segmentation (preprocessing) in CT images, which are given as input to these proposed architectures, is performed automatically with Artificial Neural Networks (ANN). Since both architectures contain AlexNet architecture, the recommended method is a transfer learning application. However, the second proposed architecture is a hybrid structure as it contains a Bidirectional Long Short-Term Memories (BiLSTM) layer, which also takes into account the temporal properties. While the COVID-19 classification accuracy of the first architecture is 98.14%, this value is 98.70% in the second hybrid architecture. The results prove that the proposed architecture shows outstanding success in infection detection and, therefore this study contributes to previous studies in terms of both deep architectural design and high classification success.