A survey, review, and future trends of skin lesion segmentation and classification

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 155, P. 106624 - 106624

Published: Feb. 1, 2023

The Computer-aided Diagnosis or Detection (CAD) approach for skin lesion analysis is an emerging field of research that has the potential to alleviate burden and cost cancer screening. Researchers have recently indicated increasing interest in developing such CAD systems, with intention providing a user-friendly tool dermatologists reduce challenges encountered associated manual inspection. This article aims provide comprehensive literature survey review total 594 publications (356 segmentation 238 classification) published between 2011 2022. These articles are analyzed summarized number different ways contribute vital information regarding methods development systems. include relevant essential definitions theories, input data (dataset utilization, preprocessing, augmentations, fixing imbalance problems), method configuration (techniques, architectures, module frameworks, losses), training tactics (hyperparameter settings), evaluation criteria. We intend investigate variety performance-enhancing approaches, including ensemble post-processing. also discuss these dimensions reveal their current trends based on utilization frequencies. In addition, we highlight primary difficulties evaluating classification systems using minimal datasets, as well solutions difficulties. Findings, recommendations, disclosed inform future automated robust system analysis.

Language: Английский

---

An Interpretable Skin Cancer Classification Using Optimized Convolutional Neural Network for a Smart Healthcare System

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 41003 - 41018

Published: Jan. 1, 2023

Skin cancer is a prevalent form of malignancy globally, and its early accurate diagnosis critical for patient survival. Clinical evaluation skin lesions essential, but it faces challenges such as long waiting times subjective interpretations. Deep learning techniques have been developed to tackle these assist dermatologists in making more diagnoses. Prompt treatment vital prevent progression potentially life-threatening consequences. The use deep algorithms can improve the speed accuracy diagnosis, leading earlier detection treatment. Additionally, reduce workload healthcare professionals, allowing them concentrate on complex cases. goal this study was develop reliable (DL) prediction models classification; (i) deal with typical severe class imbalance problem, which arises because skin-affected patients' significantly smaller than healthy class; (ii) interpret model output better understand decision-making mechanism (iii) Propose an End-to-End smart system through android application. In comparison examination six well-known classifiers, effectiveness proposed DL technique explored terms metrics relating both generalization capability classification accuracy. A used HAM10000 dataset optimized CNN identify seven forms cancer. trained using two optimization functions (Adam RMSprop) three activation (Relu, Swish, Tanh). Furthermore, XAI-based lesion developed, incorporating Grad-CAM Grad-CAM++ explain model's decisions. This help doctors make informed diagnoses their stages, 82% 0.47% loss

Language: Английский

---

Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey

IEEE Internet of Things Journal, Journal Year: 2023, Volume and Issue: 10(16), P. 14764 - 14779

Published: June 20, 2023

Artificial intelligence (AI) and machine learning (ML) are widely employed to make the solutions more accurate autonomous in many smart intelligent applications Internet of Things (IoT). In these IoT applications, performance accuracy AI/ML models main concerns; however, transparency, interpretability, responsibility models' decisions often neglected. Moreover, AI/ML-supported next-generation there is a need for reliable, transparent, explainable systems. particular, regardless whether simple or complex, how decision made, which features affect decision, their adoption interpretation by people experts crucial issues. Also, typically perceive unpredictable opaque AI outcomes with skepticism, reduces proliferation applications. To that end, (XAI) has emerged as promising research topic allows ante-hoc post-hoc functioning stages black-box be understandable, interpretable. this article, we provide an in-depth systematic review recent studies use XAI scope domain. We classify according methodology application areas. Additionally, highlight challenges open issues future directions lead researchers investigations.

Language: Английский

---

Explainable deep inherent learning for multi-classes skin lesion classification

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 159, P. 111624 - 111624

Published: April 19, 2024

Language: Английский

---

An effective multiclass skin cancer classification approach based on deep convolutional neural network

Cluster Computing, Journal Year: 2024, Volume and Issue: unknown

Published: June 17, 2024

Abstract Skin cancer is one of the most dangerous types due to its immediate appearance and possibility rapid spread. It arises from uncontrollably growing cells, rapidly dividing cells in area body, invading other bodily tissues, spreading throughout body. Early detection helps prevent progress reaching critical levels, reducing risk complications need for more aggressive treatment options. Convolutional neural networks (CNNs) revolutionize skin diagnosis by extracting intricate features images, enabling an accurate classification lesions. Their role extends early detection, providing a powerful tool dermatologists identify abnormalities their nascent stages, ultimately improving patient outcomes. This study proposes novel deep convolutional network (DCNN) approach classifying The proposed DCNN model evaluated using two unbalanced datasets, namely HAM10000 ISIC-2019. compared with transfer learning models, including VGG16, VGG19, DenseNet121, DenseNet201, MobileNetV2. Its performance assessed four widely used evaluation metrics: accuracy, recall, precision, F1-score, specificity, AUC. experimental results demonstrate that outperforms (DL) models utilized these datasets. achieved highest accuracy ISIC-2019 $$98.5\%$$ 98.5 % $$97.1\%$$ 97.1 , respectively. These show how competitive successful overcoming problems caused class imbalance raising accuracy. Furthermore, demonstrates superior performance, particularly excelling terms recent studies utilize same which highlights robustness effectiveness DCNN.

Language: Английский

---

Unlocking the black box: an in-depth review on interpretability, explainability, and reliability in deep learning

Neural Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 18, 2024

Language: Английский

---

Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review

International Journal of Medical Informatics, Journal Year: 2024, Volume and Issue: 193, P. 105689 - 105689

Published: Nov. 4, 2024

Language: Английский

---

Improving Plant Disease Classification With Deep-Learning-Based Prediction Model Using Explainable Artificial Intelligence

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 100005 - 100014

Published: Jan. 1, 2024

Plant diseases can have profound effects on the economy, impacting both local and global scales. These lead to substantial losses in agricultural productivity, affecting crop yields quality. In this context, deep learning algorithms are widely acknowledged as effective solutions. However, use of these black-box approaches raises concerns about trust interpreting validating decisions generated by models. This study proposes an explainable artificial intelligence (XAI) based plant disease classification system classify identify distinct ailments with improved accuracy. The correctly identifies 38 different accuracy, precision, recall 99.69%, 98.27%, 98.26%, respectively. predictions subjected additional analysis employing interpretable model-agnostic explanations (LIME) framework produce visual aligning prior beliefs adhering established best practices explanations. will serve a promising avenue for revolutionizing detection, fostering informed decision-making, ultimately contributing food security.

Language: Английский

---

Interpretable machine learning for dermatological disease detection: Bridging the gap between accuracy and explainability

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 179, P. 108919 - 108919

Published: July 23, 2024

Language: Английский

---

SkinLesNet: Classification of Skin Lesions and Detection of Melanoma Cancer Using a Novel Multi-Layer Deep Convolutional Neural Network

Cancers, Journal Year: 2023, Volume and Issue: 16(1), P. 108 - 108

Published: Dec. 24, 2023

Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure sunlight. Although can appear any part of human body, accounts for significant proportion all new diagnoses worldwide. There are substantial obstacles precise diagnosis and classification lesions because morphological variety indistinguishable characteristics across malignancies. Recently, deep learning models have been used in field image-based skin-lesion demonstrated diagnostic efficiency par with dermatologists. To increase accuracy lesions, cutting-edge multi-layer convolutional neural network termed SkinLesNet was built this study. The dataset study extracted from PAD-UFES-20 augmented. PAD-UFES-20-Modified includes three common forms lesions: seborrheic keratosis, nevus, melanoma. comprehensively assess SkinLesNet’s performance, its evaluation expanded beyond dataset. Two additional datasets, HAM10000 ISIC2017, were included, compared widely ResNet50 VGG16 models. This broader confirmed effectiveness, as it consistently outperformed both benchmarks datasets.

Language: Английский

---