Skin lesion analysis towards melanoma detection using optimized deep learning network

Sukanya, S. T.; Jerine, S.

doi:10.1007/s11042-023-14454-6

Cited by 4 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-neighbourhood pixels and its two adjacent pixels (either horizontal or vertical pixels) are compared with the center pixel, as graphically presented in Figure 4. The output of the LTriDP descriptor 𝐹𝑒 𝐿𝑇𝑟𝑖𝐷𝑃 is mathematically expressed in (7). Here, a feature level fusion is carried out for combining 2048 feature vectors of the ResNet-50 model, and 4982 feature vectors of LTriDP descriptor which are lastly passed to the normalized stacked LSTM network for skin lesion classification.…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Furthermore, several handcrafted feature extraction techniques are used to extract image properties like color, texture and shape. The traditional techniques have a high semantic gap among extracted features, further leading to the curse of the dimensionality problem [7]. Even though the conventional machine and deep learning models offer adequate outcomes, they are ineffective in achieving satisfactory results, especially when the dataset is limited [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate detection of melanoma skin cancer using fuzzy based SegNet model and normalized stacked LSTM network

Chembian,

Sankar,

Koteeswaran

et al. 2024

IJEECS

View full text Add to dashboard Cite

Early detection of melanoma skin cancer (MSC) is critical in order to prevent deaths from fatal skin cancer. Even though the modern research methods are effective in identifying and detecting skin cancer, it is a challenging task due to a higher level of color similarity between melanoma non-affected areas and affected areas, and a lower contrast between the skin portions and melanoma moles. For highlighting the aforementioned problems, an efficient automated system is proposed for an early diagnosis of MSC. Firstly, dermoscopic images are collected from two benchmark datasets namely, international skin imaging collaboration (ISIC)-2017 and PH2. Next, skin lesions are segmented from dermoscopic images by implementing a fuzzy based SegNet model which is a combination of both deep fuzzy clustering algorithm and the SegNet model. Then, hybrid feature extraction (ResNet-50 model and local tri-directional pattern (LTriDP) descriptor) is performed to capture the features from segmented skin lesions. These features are given into the normalized stacked long short-term memory (LSTM) network to categorize the classes of skin lesions. The empirical evaluation reveals that the proposed normalized stacked LSTM network achieves 98.98% and 98.97% of accuracy respectively on the ISIC2017 and PH2 datasets, and these outcomes are more impressive than those of the conventional detection models.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Accurate detection of melanoma skin cancer using fuzzy based SegNet model and normalized stacked LSTM network

Chembian,

Sankar,

Koteeswaran

et al. 2024

IJEECS

View full text Add to dashboard Cite

show abstract

“…Deep learning (DL) techniques have successfully detected and classified cancer diseases in medical imaging [22,23]. For the skin cancer classification, DL techniques give promising results that reveal its importance in medical imaging [24].…”

Section: Introductionmentioning

confidence: 99%

MSRNet: Multiclass Skin Lesion Recognition Using Additional Residual Block Based Fine-Tuned Deep Models Information Fusion and Best Feature Selection

Bibi,

Khan,

Shah

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Cancer is one of the leading significant causes of illness and chronic disease worldwide. Skin cancer, particularly melanoma, is becoming a severe health problem due to its rising prevalence. The considerable death rate linked with melanoma requires early detection to receive immediate and successful treatment. Lesion detection and classification are more challenging due to many forms of artifacts such as hairs, noise, and irregularity of lesion shape, color, irrelevant features, and textures. In this work, we proposed a deep-learning architecture for classifying multiclass skin cancer and melanoma detection. The proposed architecture consists of four core steps: image preprocessing, feature extraction and fusion, feature selection, and classification. A novel contrast enhancement technique is proposed based on the image luminance information. After that, two pre-trained deep models, DarkNet-53 and DensNet-201, are modified in terms of a residual block at the end and trained through transfer learning. In the learning process, the Genetic algorithm is applied to select hyperparameters. The resultant features are fused using a two-step approach named serial-harmonic mean. This step increases the accuracy of the correct classification, but some irrelevant information is also observed. Therefore, an algorithm is developed to select the best features called marine predator optimization (MPA) controlled Reyni Entropy. The selected features are finally classified using machine learning classifiers for the final classification. Two datasets, ISIC2018 and ISIC2019, have been selected for the experimental process. On these datasets, the obtained maximum accuracy of 85.4% and 98.80%, respectively. To prove the effectiveness of the proposed methods, a detailed comparison is conducted with several recent techniques and shows the proposed framework outperforms.

show abstract

CACBL-Net: a lightweight skin cancer detection system for portable diagnostic devices using deep learning based channel attention and adaptive class balanced focal loss function

Agrawal,

Gupta,

Jalal

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Skin lesion analysis towards melanoma detection using optimized deep learning network

Cited by 4 publications

References 34 publications

Accurate detection of melanoma skin cancer using fuzzy based SegNet model and normalized stacked LSTM network

Accurate detection of melanoma skin cancer using fuzzy based SegNet model and normalized stacked LSTM network

MSRNet: Multiclass Skin Lesion Recognition Using Additional Residual Block Based Fine-Tuned Deep Models Information Fusion and Best Feature Selection

CACBL-Net: a lightweight skin cancer detection system for portable diagnostic devices using deep learning based channel attention and adaptive class balanced focal loss function

Contact Info

Product

Resources

About