XSE-TomatoNet: An Explainable AI based Tomato Leaf Disease Classification Method Using EfficientNetB0 with Squeeze-and-Excitation Blocks and Multi-Scale Feature Fusion

MethodsX, Journal Year: 2025, Volume and Issue: unknown, P. 103159 - 103159

Published: Jan. 1, 2025

Language: Английский

---

An Extensive Investigation into the Use of Machine Learning Tools and Deep Neural Networks for the Recognition of Skin Cancer: Challenges, Future Directions, and a Comprehensive Review

Symmetry, Journal Year: 2024, Volume and Issue: 16(3), P. 366 - 366

Published: March 18, 2024

Skin cancer poses a serious risk to one’s health and can only be effectively treated with early detection. Early identification is critical since skin has higher fatality rate, it expands gradually different areas of the body. The rapid growth automated diagnosis frameworks led combination diverse machine learning, deep computer vision algorithms for detecting clinical samples atypical lesion specimens. Automated methods recognizing that use learning techniques are discussed in this article: convolutional neural networks, and, general, artificial networks. recognition symmetries key point dealing image datasets; hence, developing appropriate architecture as improve performance release capacities network. current study emphasizes need an method identify lesions reduce amount time effort required diagnostic process, well novel aspect using based on analysis concludes underlying research directions future, which will assist better addressing difficulties encountered human recognition. By highlighting drawbacks advantages prior techniques, authors hope establish standard future domain diagnostics.

Language: Английский

---

Skin-lesion segmentation using boundary-aware segmentation network and classification based on a mixture of convolutional and transformer neural networks

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: March 10, 2025

Background Skin cancer is one of the most prevalent cancers worldwide. In clinical domain, skin lesions such as melanoma detection are still a challenge due to occlusions, poor contrast, image quality, and similarities between lesions. Deep-/machine-learning methods used for early, accurate, efficient Therefore, we propose boundary-aware segmentation network (BASNet) model comprising prediction residual refinement modules. Materials The module works like U-Net densely supervised by an encoder decoder. A hybrid loss function used, which has potential help in domain dermatology. BASNet handles these challenges providing robust outcomes, even suboptimal imaging environments. This leads accurate early diagnosis, improved treatment workflows. We further compact convolutional transformer (CCTM) based on convolution transformers classification. was designed selected number layers hyperparameters having two convolutions, transformers, 64 projection dimensions, tokenizer, position embedding, sequence pooling, MLP, batch size, heads, 0.1 stochastic depth, 0.001 learning rate, 0.0001 weight decay, 100 epochs. Results CCTM evaluated six skin-lesion datasets, namely MED-NODE, PH2, ISIC-2019, ISIC-2020, HAM10000, DermNet achieving over 98% accuracy. Conclusion proposed holds significant domain. Its ability combine local feature extraction global context understanding makes it ideal tasks medical analysis disease diagnosis.

Language: Английский

---

An Innovative Approach for Early Dermatological Diagnostics Skin Cancer Detection Using Advanced Deep Learning Techniques

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 437 - 445

Published: Jan. 1, 2025

Language: Английский

---

A Transfer Learning and Feature Ranking-based Feature Extraction Approach for Enhancing Skin Lesion Classification

Published: Feb. 9, 2024

This study investigates skin lesion classification through feature fusion, focusing on transfer learning-based extraction for improved model discernment. Utilizing VGG16, ResNet, and EfficientNet B0, the research ranks features using methods like weights, RFE, correlation-based techniques, LASSO regression, gradient boosting, variance thresholding. The approach aims to enhance diagnostic precision by combining diverse essential accurate classification. Assessing HAM 10000 BCN 20000 datasets, evaluates impact of ranking performance. Results consistently demonstrate that ranked sets outperform initial across classifiers (KNN, SVM, CNN) both datasets. Notably, CNN excels with from RFE applied fused learning networks.

Language: Английский

---

Cutting-edge Dermatological Advances using Deep Learning for Precise Skin Cancer Classification

Published: May 3, 2024

This research paper presents a novel approach using Convolutional Neural Network (CNN) to accurately identify skin cancer based on prompts. The technique utilises dataset acquired from the ISIC Archive, comprising of 1800 photographs benign moles and 1497 pictures malignant moles. study aims improve automated classification by employing deep learning model, recognising critical significance visual diagnostics in detection cancer. 14-step involves essential steps such as importing data, labelling categories, normalising constructing model Keras with TensorFlow backend access. dataset's balanced design facilitates precise evaluation, leading an exceptional accuracy precision score 92.7%. underscores importance early cancer, stressing practical use developed approach. In addition, implementation ResNet50 architecture is examined, which significantly improves performance model. Networks (CNNs) visually discerning lesions demonstrates their efficacy potential for solutions aid expeditious accurate identification

Language: Английский

---

Feature Extraction with Automated Scale Selection in Skin Cancer Image Classification: A Genetic Programming Approach

Proceedings of the Genetic and Evolutionary Computation Conference, Journal Year: 2024, Volume and Issue: unknown, P. 1363 - 1372

Published: July 8, 2024

Language: Английский

---

Exploring Genetic Programming Models in Computer-Aided Diagnosis of Skin Cancer Images

2022 IEEE Congress on Evolutionary Computation (CEC), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 8

Published: June 30, 2024

Language: Английский

---

Autonomous Data Augmentation and Melanoma Detection Using a Combination of Classical and Deep-Learning‏ Techniques

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

---

Multimodal Hybrid Approach for Fine-Grained Classification of Diverse Dermatological Conditions

Published: May 17, 2024

Language: Английский

---