The Role of Machine Learning and Deep Learning Approaches for the Detection of Skin Cancer

Mazhar, Tehseen; Haq, Inayatul; Ditta, Allah; Mohsan, Syed Agha Hassnain; Rehman, Faisal; Zafar, Imran; Gansau, Jualang Azlan; Goh, Lucky Poh Wah

doi:10.3390/healthcare11030415

Cited by 34 publications

(19 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed work performs better when compare with other CNN models that were recently published. We noticed that, the AUC score of 0.912 higher than the result in [17], 4% higher than the work carried out in [18] and 5% higher when compared with [19].…”

Section: Comparison Between Existing Methodscontrasting

confidence: 54%

DeepSkin: A Deep Learning Approach for Skin Cancer Classification

Gururaj,

Manju,

Nagarjun

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Skin cancer is one of the most rapidly spreading illnesses in the world and because of the limited resources available. Early detection of skin cancer is crucial accurate diagnosis of skin cancer identification for preventive approach in general. Detecting skin cancer at an early stage is challenging for dermatologists, as well in recent years, both supervised and unsupervised learning tasks have made extensive use of deep learning. One of these models, Convolutional Neural Networks (CNN), has surpassed all others in object detection and classification tests. The dataset is screened from MNIST: HAM10000 which consists of seven different types of skin lesions with the sample size of 10015 is used for the experimentation. The data pre-processing techniques like sampling, dull razor and segmentation using autoencoder and decoder is employed. Transfer learning techniques like DenseNet169 and Resnet 50 were used to train the model to obtain the results.

show abstract

Section: Comparison Between Existing Methodscontrasting

confidence: 54%

DeepSkin: A Deep Learning Approach for Skin Cancer Classification

Gururaj,

Manju,

Nagarjun

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Cancer is a multifaceted ailment that has the potential to impact any anatomical structure, and it is the result of a combination of genotypic, environmental, and lifestyle determinants (Pandya et al, 2021;Mazhar et al, 2023). Although cancer may manifest in any individual, specific predisposing factors, such as advanced age, familial history, and exposure to carcinogenic substances, can augment the likelihood of developing the disease.…”

Section: Introductionmentioning

confidence: 99%

Amomum subulatum: A treasure trove of anti-cancer compounds targeting TP53 protein using in vitro and in silico techniques

Ali¹,

Noreen

Qamar³

et al. 2023

Front. Chem.

Self Cite

View full text Add to dashboard Cite

Cancer is a primary global health concern, and researchers seek innovative approaches to combat the disease. Clinical bioinformatics and high-throughput proteomics technologies provide powerful tools to explore cancer biology. Medicinal plants are considered effective therapeutic agents, and computer-aided drug design (CAAD) is used to identify novel drug candidates from plant extracts. The tumour suppressor protein TP53 is an attractive target for drug development, given its crucial role in cancer pathogenesis. This study used a dried extract of Amomum subulatum seeds to identify phytocompounds targeting TP53 in cancer. We apply qualitative tests to determine its phytochemicals (Alkaloid, Tannin, Saponin, Phlobatinin, and Cardic glycoside), and found that alkaloid composed of 9.4% ± 0.04% and Saponin 1.9% ± 0.05% crude chemical constituent. In the results of DPPH Analysis Amomum subulatum Seeds founded antioxidant activity, and then we verified via observing methanol extract (79.82%), BHT (81.73%), and n-hexane extract (51.31%) found to be positive. For Inhibition of oxidation, we observe BHT is 90.25%, and Methanol (83.42%) has the most significant proportion of linoleic acid oxidation suppression. We used diverse bioinformatics approaches to evaluate the effect of A. subulatum seeds and their natural components on TP53. Compound-1 had the best pharmacophore match value (53.92), with others ranging from 50.75 to 53.92. Our docking result shows the top three natural compounds had the highest binding energies (−11.10 to −10.3 kcal/mol). The highest binding energies (−10.9 to −9.2 kcal/mol) compound bonded to significant sections in the target protein’s active domains with TP53. Based on virtual screening, we select top phytocompounds for targets which highly fit based on pharmacophore score and observe these compounds exhibited potent antioxidant activity and inhibited cancer cell inflammation in the TP53 pathway. Molecular Dynamics (MD) simulations indicated that the ligand was bound to the protein with some significant conformational changes in the protein structure. This study provides novel insights into the development of innovative drugs for the treatment of cancer disorders.

show abstract

“…The researchers discovered that image determination does not diminish sensitivity, specificity, or accuracy when other features are present. Study [ 58 ] focuses on how DL-driven recordkeeping systems help doctors discover skin cancer early and how machinery helps doctors provide quality care. While different and effective augmentation approaches are used, training images improve CNN design accuracy, sensitivity, and specificity.…”

Section: Related Workmentioning

confidence: 99%

An Improved Skin Lesion Classification Using a Hybrid Approach with Active Contour Snake Model and Lightweight Attention-Guided Capsule Networks

Behara,

Bhero,

Agee

2024

Diagnostics

View full text Add to dashboard Cite

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diagnosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obstacles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate classification. As such, skilled clinicians often struggle to differentiate benign moles from early malignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to experience difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification that combines snake models of active contour (AC) segmentation, ResNet50 for feature extraction, and a capsule network with a fusion of lightweight attention mechanisms to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimination, and improve accuracy. We employed the stochastic gradient descent (SGD) optimization algorithm to optimize the model’s parameters. The proposed model is implemented on publicly available datasets, namely, HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated dermatological diagnosis and provide a helpful tool for medical practitioners.

show abstract

The Role of Machine Learning and Deep Learning Approaches for the Detection of Skin Cancer

Cited by 34 publications

References 53 publications

DeepSkin: A Deep Learning Approach for Skin Cancer Classification

DeepSkin: A Deep Learning Approach for Skin Cancer Classification

Amomum subulatum: A treasure trove of anti-cancer compounds targeting TP53 protein using in vitro and in silico techniques

An Improved Skin Lesion Classification Using a Hybrid Approach with Active Contour Snake Model and Lightweight Attention-Guided Capsule Networks

Contact Info

Product

Resources

About