1
|
Lawal M, Yi D. Polar contrast attention and skip cross-channel aggregation for efficient learning in U-Net. Comput Biol Med 2024; 181:109047. [PMID: 39182369 DOI: 10.1016/j.compbiomed.2024.109047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/2024] [Revised: 07/31/2024] [Accepted: 08/18/2024] [Indexed: 08/27/2024]
Abstract
The performance of existing lesion semantic segmentation models has shown a steady improvement with the introduction of mechanisms like attention, skip connections, and deep supervision. However, these advancements often come at the expense of computational requirements, necessitating powerful graphics processing units with substantial video memory. Consequently, certain models may exhibit poor or non-existent performance on more affordable edge devices, such as smartphones and other point-of-care devices. To tackle this challenge, our paper introduces a lesion segmentation model with a low parameter count and minimal operations. This model incorporates polar transformations to simplify images, facilitating faster training and improved performance. We leverage the characteristics of polar images by directing the model's focus to areas most likely to contain segmentation information, achieved through the introduction of a learning-efficient polar-based contrast attention (PCA). This design utilizes Hadamard products to implement a lightweight attention mechanism without significantly increasing model parameters and complexities. Furthermore, we present a novel skip cross-channel aggregation (SC2A) approach for sharing cross-channel corrections, introducing Gaussian depthwise convolution to enhance nonlinearity. Extensive experiments on the ISIC 2018 and Kvasir datasets demonstrate that our model surpasses state-of-the-art models while maintaining only about 25K parameters. Additionally, our proposed model exhibits strong generalization to cross-domain data, as confirmed through experiments on the PH2 dataset and CVC-Polyp dataset. In addition, we evaluate the model's performance in a mobile setting against other lightweight models. Notably, our proposed model outperforms other advanced models in terms of IoU and Dice score, and running time.
Collapse
Affiliation(s)
- Mohammed Lawal
- Department of Computing Science, University of Aberdeen, Aberdeen, AB24 3UE, United Kingdom
| | - Dewei Yi
- Department of Computing Science, University of Aberdeen, Aberdeen, AB24 3UE, United Kingdom.
| |
Collapse
|
2
|
Fan C, Zhu Z, Peng B, Xuan Z, Zhu X. EAAC-Net: An Efficient Adaptive Attention and Convolution Fusion Network for Skin Lesion Segmentation. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01223-6. [PMID: 39147886 DOI: 10.1007/s10278-024-01223-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/11/2024] [Revised: 07/13/2024] [Accepted: 07/31/2024] [Indexed: 08/17/2024]
Abstract
Accurate segmentation of skin lesions in dermoscopic images is of key importance for quantitative analysis of melanoma. Although existing medical image segmentation methods significantly improve skin lesion segmentation, they still have limitations in extracting local features with global information, do not handle challenging lesions well, and usually have a large number of parameters and high computational complexity. To address these issues, this paper proposes an efficient adaptive attention and convolutional fusion network for skin lesion segmentation (EAAC-Net). We designed two parallel encoders, where the efficient adaptive attention feature extraction module (EAAM) adaptively establishes global spatial dependence and global channel dependence by constructing the adjacency matrix of the directed graph and can adaptively filter out the least relevant tokens at the coarse-grained region level, thus reducing the computational complexity of the self-attention mechanism. The efficient multiscale attention-based convolution module (EMA⋅C) utilizes multiscale attention for cross-space learning of local features extracted from the convolutional layer to enhance the representation of richly detailed local features. In addition, we designed a reverse attention feature fusion module (RAFM) to enhance the effective boundary information gradually. To validate the performance of our proposed network, we compared it with other methods on ISIC 2016, ISIC 2018, and PH2 public datasets, and the experimental results show that EAAC-Net has superior segmentation performance under commonly used evaluation metrics.
Collapse
Affiliation(s)
- Chao Fan
- School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou City, Henan Province, China
- Key Laboratory of Grain Information Processing and Control, Ministry of Education, Zhengzhou City, Henan Province, China
| | - Zhentong Zhu
- School of Information Science and Engineering, Henan University of Technology, Henan Province, Post Code, Zhengzhou City, 450001, China.
| | - Bincheng Peng
- School of Information Science and Engineering, Henan University of Technology, Henan Province, Post Code, Zhengzhou City, 450001, China
| | - Zhihui Xuan
- School of Information Science and Engineering, Henan University of Technology, Henan Province, Post Code, Zhengzhou City, 450001, China
| | - Xinru Zhu
- School of Information Science and Engineering, Henan University of Technology, Henan Province, Post Code, Zhengzhou City, 450001, China
| |
Collapse
|
3
|
Attallah O. Skin-CAD: Explainable deep learning classification of skin cancer from dermoscopic images by feature selection of dual high-level CNNs features and transfer learning. Comput Biol Med 2024; 178:108798. [PMID: 38925085 DOI: 10.1016/j.compbiomed.2024.108798] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2024] [Revised: 05/30/2024] [Accepted: 06/19/2024] [Indexed: 06/28/2024]
Abstract
Skin cancer (SC) significantly impacts many individuals' health all over the globe. Hence, it is imperative to promptly identify and diagnose such conditions at their earliest stages using dermoscopic imaging. Computer-aided diagnosis (CAD) methods relying on deep learning techniques especially convolutional neural networks (CNN) can effectively address this issue with outstanding outcomes. Nevertheless, such black box methodologies lead to a deficiency in confidence as dermatologists are incapable of comprehending and verifying the predictions that were made by these models. This article presents an advanced an explainable artificial intelligence (XAI) based CAD system named "Skin-CAD" which is utilized for the classification of dermoscopic photographs of SC. The system accurately categorises the photographs into two categories: benign or malignant, and further classifies them into seven subclasses of SC. Skin-CAD employs four CNNs of different topologies and deep layers. It gathers features out of a pair of deep layers of every CNN, particularly the final pooling and fully connected layers, rather than merely depending on attributes from a single deep layer. Skin-CAD applies the principal component analysis (PCA) dimensionality reduction approach to minimise the dimensions of pooling layer features. This also reduces the complexity of the training procedure compared to using deep features from a CNN that has a substantial size. Furthermore, it combines the reduced pooling features with the fully connected features of each CNN. Additionally, Skin-CAD integrates the dual-layer features of the four CNNs instead of entirely depending on the features of a single CNN architecture. In the end, it utilizes a feature selection step to determine the most important deep attributes. This helps to decrease the general size of the feature set and streamline the classification process. Predictions are analysed in more depth using the local interpretable model-agnostic explanations (LIME) approach. This method is used to create visual interpretations that align with an already existing viewpoint and adhere to recommended standards for general clarifications. Two benchmark datasets are employed to validate the efficiency of Skin-CAD which are the Skin Cancer: Malignant vs. Benign and HAM10000 datasets. The maximum accuracy achieved using Skin-CAD is 97.2 % and 96.5 % for the Skin Cancer: Malignant vs. Benign and HAM10000 datasets respectively. The findings of Skin-CAD demonstrate its potential to assist professional dermatologists in detecting and classifying SC precisely and quickly.
Collapse
Affiliation(s)
- Omneya Attallah
- Department of Electronics and Communications Engineering, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandri, 21937, Egypt; Wearables, Biosensing, and Biosignal Processing Laboratory, Arab Academy for Science, Technology and Maritime Transport, Alexandria, 21937, Egypt.
| |
Collapse
|
4
|
Pacal I, Alaftekin M, Zengul FD. Enhancing Skin Cancer Diagnosis Using Swin Transformer with Hybrid Shifted Window-Based Multi-head Self-attention and SwiGLU-Based MLP. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024:10.1007/s10278-024-01140-8. [PMID: 38839675 DOI: 10.1007/s10278-024-01140-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/26/2024] [Revised: 05/07/2024] [Accepted: 05/08/2024] [Indexed: 06/07/2024]
Abstract
Skin cancer is one of the most frequently occurring cancers worldwide, and early detection is crucial for effective treatment. Dermatologists often face challenges such as heavy data demands, potential human errors, and strict time limits, which can negatively affect diagnostic outcomes. Deep learning-based diagnostic systems offer quick, accurate testing and enhanced research capabilities, providing significant support to dermatologists. In this study, we enhanced the Swin Transformer architecture by implementing the hybrid shifted window-based multi-head self-attention (HSW-MSA) in place of the conventional shifted window-based multi-head self-attention (SW-MSA). This adjustment enables the model to more efficiently process areas of skin cancer overlap, capture finer details, and manage long-range dependencies, while maintaining memory usage and computational efficiency during training. Additionally, the study replaces the standard multi-layer perceptron (MLP) in the Swin Transformer with a SwiGLU-based MLP, an upgraded version of the gated linear unit (GLU) module, to achieve higher accuracy, faster training speeds, and better parameter efficiency. The modified Swin model-base was evaluated using the publicly accessible ISIC 2019 skin dataset with eight classes and was compared against popular convolutional neural networks (CNNs) and cutting-edge vision transformer (ViT) models. In an exhaustive assessment on the unseen test dataset, the proposed Swin-Base model demonstrated exceptional performance, achieving an accuracy of 89.36%, a recall of 85.13%, a precision of 88.22%, and an F1-score of 86.65%, surpassing all previously reported research and deep learning models documented in the literature.
Collapse
Affiliation(s)
- Ishak Pacal
- Department of Computer Engineering, Igdir University, 76000, Igdir, Turkey
| | - Melek Alaftekin
- Department of Computer Engineering, Igdir University, 76000, Igdir, Turkey
| | - Ferhat Devrim Zengul
- Department of Health Services Administration, The University of Alabama at Birmingham, Birmingham, AL, USA.
- Center for Integrated System, School of Engineering, The University of Alabama at Birmingham, Birmingham, AL, USA.
- Department of Biomedical Informatics and Data Science, School of Medicine, The University of Alabama, Birmingham, USA.
| |
Collapse
|
5
|
Khan MA, Hamza A, Shabaz M, Kadry S, Rubab S, Bilal MA, Akbar MN, Kesavan SM. Multiclass skin lesion classification using deep learning networks optimal information fusion. DISCOVER APPLIED SCIENCES 2024; 6:300. [DOI: 10.1007/s42452-024-05998-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/15/2024] [Accepted: 05/27/2024] [Indexed: 08/25/2024]
Abstract
AbstractA serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin lesions with less effort, dermatologists are increasingly turning to machine learning (ML) techniques and computer-aided diagnostic (CAD) systems. This paper proposes a computerized method for multiclass lesion classification using a fusion of optimal deep-learning model features. The dataset used in this work, ISIC2018, is imbalanced; therefore, augmentation is performed based on a few mathematical operations. After that, two pre-trained deep learning models (DarkNet-19 and MobileNet-V2) have been fine-tuned and trained on the selected dataset. After training, features are extracted from the average pool layer and optimized using a hybrid firefly optimization technique. The selected features are fused in two ways: (i) original serial approach and (ii) proposed threshold approach. Machine learning classifiers are used to classify the chosen features at the end. Using the ISIC2018 dataset, the experimental procedure produced an accuracy of 89.0%. Whereas, 87.34, 87.57, and 87.45 are sensitivity, precision, and F1 score respectively. At the end, comparison is also conducted with recent techniques, and it shows the proposed method shows improved accuracy along with other performance measures.
Collapse
|
6
|
Buruiană A, Şerbănescu MS, Pop B, Gheban BA, Georgiu C, Crişan D, Crişan M. Automated cutaneous squamous cell carcinoma grading using deep learning with transfer learning. ROMANIAN JOURNAL OF MORPHOLOGY AND EMBRYOLOGY = REVUE ROUMAINE DE MORPHOLOGIE ET EMBRYOLOGIE 2024; 65:243-250. [PMID: 39020538 PMCID: PMC11384044 DOI: 10.47162/rjme.65.2.10] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/19/2024]
Abstract
INTRODUCTION Histological grading of cutaneous squamous cell carcinoma (cSCC) is crucial for prognosis and treatment decisions, but manual grading is subjective and time-consuming. AIM This study aimed to develop and validate a deep learning (DL)-based model for automated cSCC grading, potentially improving diagnostic accuracy (ACC) and efficiency. MATERIALS AND METHODS Three deep neural networks (DNNs) with different architectures (AlexNet, GoogLeNet, ResNet-18) were trained using transfer learning on a dataset of 300 histopathological images of cSCC. The models were evaluated on their ACC, sensitivity (SN), specificity (SP), and area under the curve (AUC). Clinical validation was performed on 60 images, comparing the DNNs' predictions with those of a panel of pathologists. RESULTS The models achieved high performance metrics (ACC>85%, SN>85%, SP>92%, AUC>97%) demonstrating their potential for objective and efficient cSCC grading. The high agreement between the DNNs and pathologists, as well as among different network architectures, further supports the reliability and ACC of the DL models. The top-performing models are publicly available, facilitating further research and potential clinical implementation. CONCLUSIONS This study highlights the promising role of DL in enhancing cSCC diagnosis, ultimately improving patient care.
Collapse
Affiliation(s)
- Alexandra Buruiană
- Department of Medical Informatics and Biostatistics, University of Medicine and Pharmacy of Craiova, Romania;
| | | | | | | | | | | | | |
Collapse
|
7
|
Tang X, Rashid Sheykhahmad F. Boosted dipper throated optimization algorithm-based Xception neural network for skin cancer diagnosis: An optimal approach. Heliyon 2024; 10:e26415. [PMID: 38449650 PMCID: PMC10915520 DOI: 10.1016/j.heliyon.2024.e26415] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/01/2024] [Revised: 02/10/2024] [Accepted: 02/13/2024] [Indexed: 03/08/2024] Open
Abstract
Skin cancer is a prevalent form of cancer that necessitates prompt and precise detection. However, current diagnostic methods for skin cancer are either invasive, time-consuming, or unreliable. Consequently, there is a demand for an innovative and efficient approach to diagnose skin cancer that utilizes non-invasive and automated techniques. In this study, a unique method has been proposed for diagnosing skin cancer by employing an Xception neural network that has been optimized using Boosted Dipper Throated Optimization (BDTO) algorithm. The Xception neural network is a deep learning model capable of extracting high-level features from skin dermoscopy images, while the BDTO algorithm is a bio-inspired optimization technique that can determine the optimal parameters and weights for the Xception neural network. To enhance the quality and diversity of the images, the ISIC dataset is utilized, a widely accepted benchmark system for skin cancer diagnosis, and various image preprocessing and data augmentation techniques were implemented. By comparing the method with several contemporary approaches, it has been demonstrated that the method outperforms others in detecting skin cancer. The method achieves an average precision of 94.936%, an average accuracy of 94.206%, and an average recall of 97.092% for skin cancer diagnosis, surpassing the performance of alternative methods. Additionally, the 5-fold ROC curve and error curve have been presented for the data validation to showcase the superiority and robustness of the method.
Collapse
Affiliation(s)
- Xiaofei Tang
- School of Computer Science and Software Engineering, University of Science and Technology Liaoning, Anshan, 114051, Liaoning, China
| | - Fatima Rashid Sheykhahmad
- Ardabil Branch, Islamic Azad University, Ardabil, Iran
- College of Technical Engineering, The Islamic University, Najaf, Iraq
| |
Collapse
|
8
|
Pan X, Mu Y, Ma C, He Q. TFCNet: A texture-aware and fine-grained feature compensated polyp detection network. Comput Biol Med 2024; 171:108144. [PMID: 38382386 DOI: 10.1016/j.compbiomed.2024.108144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 01/14/2024] [Accepted: 02/12/2024] [Indexed: 02/23/2024]
Abstract
PURPOSE Abnormal tissue detection is a prerequisite for medical image analysis and computer-aided diagnosis and treatment. The use of neural networks (CNN) to achieve accurate detection of intestinal polyps is beneficial to the early diagnosis and treatment of colorectal cancer. Currently, image detection models using multi-scale feature processing perform well in polyp detection. However, these methods do not fully consider the misalignment of information in the process of feature scale change, resulting in the loss of fine-grained features, and eventually cause the missed and false detection of targets. METHOD To solve this problem, a texture-aware and fine-grained feature compensated polyp detection network (TFCNet) is proposed in this paper. Firstly, design Texture Awareness Module (TAM) to excavate the rich texture information from the low-level layers and utilize high-level semantic information for background suppression, thereby capturing purer fine-grained features. Secondly, the Texture Feature Enhancement Module (TFEM) is designed to enhance the low-level texture information in TAM, and the enhanced texture features were fused with the high-level features. By making full use of the low-level texture features and multi-scale context information, the semantic consistency and integrity of the features were ensured. Finally, the Residual Pyramid Splittable Attention Module (RPSA) is designed to balance the loss of channel information caused by skip connections, and further improve the detection performance of the network. RESULTS Experimental results on 4 datasets demonstrate that the TFCNet network outperforms existing methods. Particularly, on the large dataset PolypSets, the mAP@0.5-0.95 has been improved to 88.9%. On the small datasets CVC-ClinicDB and Kvasir, the mAP@0.5-0.95 is increased by 2% and 1.6%, respectively, compared to the baseline, showcasing a significant superiority over competing methods.
Collapse
Affiliation(s)
- Xiaoying Pan
- Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an, 710121, China; School of Computer Science & Technology, Xi'an University of Post & Telecommunications, Xi'an, 710121, China.
| | - Yaya Mu
- Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an, 710121, China; School of Computer Science & Technology, Xi'an University of Post & Telecommunications, Xi'an, 710121, China
| | - Chenyang Ma
- Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an, 710121, China; School of Computer Science & Technology, Xi'an University of Post & Telecommunications, Xi'an, 710121, China
| | - Qiqi He
- Shanxi Key Laboratory of Network Data Analysis and Intelligent Processing, Xi'an, 710121, China; School of Computer Science & Technology, Xi'an University of Post & Telecommunications, Xi'an, 710121, China
| |
Collapse
|
9
|
Kumar Lilhore U, Simaiya S, Sharma YK, Kaswan KS, Rao KBVB, Rao VVRM, Baliyan A, Bijalwan A, Alroobaea R. A precise model for skin cancer diagnosis using hybrid U-Net and improved MobileNet-V3 with hyperparameters optimization. Sci Rep 2024; 14:4299. [PMID: 38383520 PMCID: PMC10881962 DOI: 10.1038/s41598-024-54212-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Accepted: 02/09/2024] [Indexed: 02/23/2024] Open
Abstract
Skin cancer is a frequently occurring and possibly deadly disease that necessitates prompt and precise diagnosis in order to ensure efficacious treatment. This paper introduces an innovative approach for accurately identifying skin cancer by utilizing Convolution Neural Network architecture and optimizing hyperparameters. The proposed approach aims to increase the precision and efficacy of skin cancer recognition and consequently enhance patients' experiences. This investigation aims to tackle various significant challenges in skin cancer recognition, encompassing feature extraction, model architecture design, and optimizing hyperparameters. The proposed model utilizes advanced deep-learning methodologies to extract complex features and patterns from skin cancer images. We enhance the learning procedure of deep learning by integrating Standard U-Net and Improved MobileNet-V3 with optimization techniques, allowing the model to differentiate malignant and benign skin cancers. Also substituted the crossed-entropy loss function of the Mobilenet-v3 mathematical framework with a bias loss function to enhance the accuracy. The model's squeeze and excitation component was replaced with the practical channel attention component to achieve parameter reduction. Integrating cross-layer connections among Mobile modules has been proposed to leverage synthetic features effectively. The dilated convolutions were incorporated into the model to enhance the receptive field. The optimization of hyperparameters is of utmost importance in improving the efficiency of deep learning models. To fine-tune the model's hyperparameter, we employ sophisticated optimization methods such as the Bayesian optimization method using pre-trained CNN architecture MobileNet-V3. The proposed model is compared with existing models, i.e., MobileNet, VGG-16, MobileNet-V2, Resnet-152v2 and VGG-19 on the "HAM-10000 Melanoma Skin Cancer dataset". The empirical findings illustrate that the proposed optimized hybrid MobileNet-V3 model outperforms existing skin cancer detection and segmentation techniques based on high precision of 97.84%, sensitivity of 96.35%, accuracy of 98.86% and specificity of 97.32%. The enhanced performance of this research resulted in timelier and more precise diagnoses, potentially contributing to life-saving outcomes and mitigating healthcare expenditures.
Collapse
Affiliation(s)
- Umesh Kumar Lilhore
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | - Sarita Simaiya
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | - Yogesh Kumar Sharma
- Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfield, Vaddeswaram, Guntur, AP, India
| | - Kuldeep Singh Kaswan
- School of Computing Science and Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India
| | - K B V Brahma Rao
- Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Greenfield, Vaddeswaram, Guntur, AP, India
| | - V V R Maheswara Rao
- Departmentt of Computer Science and Engineering, Shri Vishnu Engineering College for Women (A), Bhimavaram, India
| | - Anupam Baliyan
- Department of Computer Science and Engineering, Chandigarh University, Mohali, Punjab, 140413, India
| | | | - Roobaea Alroobaea
- Department of Computer Science, College of Computers and Information Technology, Taif University, P. O. Box 11099, 21944, Taif, Saudi Arabia
| |
Collapse
|