Skin Lesion Classification Using Pre-Trained DenseNet201 Deep Neural Network

Jasil, S. P. Godlin; Ulagamuthalvi, V.

doi:10.1109/icspc51351.2021.9451818

Cited by 11 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A single-modality large-scale dataset, including a total of 64699 images, was used to calculate the performance of the CAD method. Similarly, Jasil et al [16] and Çakmak et al [17] utilized different CNNs for skin lesion classification tasks. In [16], a pretrained CNN, named DenseNet201 [28], was employed to classify dermoscopy images into one of seven different classes of skin lesions.…”

Section: A Image-based Methods (2d Models)mentioning

confidence: 99%

“…Similarly, Jasil et al [16] and Çakmak et al [17] utilized different CNNs for skin lesion classification tasks. In [16], a pretrained CNN, named DenseNet201 [28], was employed to classify dermoscopy images into one of seven different classes of skin lesions. A single-modality limited dataset, including a total of 3091 images, was used to validate the method.…”

Section: A Image-based Methods (2d Models)mentioning

confidence: 99%

“…Later, Çakmak et al [17] used a lightweight CNN, named NASNetMobile [29], for melanoma detection from dermoscopy images. They considered a larger dataset (including a total of 10015 images) than that of [16]. In the context of diabetic retinopathy (DR), Gambhir et al [18] proposed a severity classification CAD method that was able to detect and distinguish DR into different severity levels.…”

Section: A Image-based Methods (2d Models)mentioning

confidence: 99%

“…Compared to various image-based classification methods, our proposed 2D-CNN model (MDF-RN) shows better results. Jasil et al [16] proposed a CAD method based on DenseNet201 [16], which showed comparable results and ranked it as the second-best method among other image-based models. However, our proposed MDF-RN model outperformed [16] in terms of quantitative as well as computational performance.…”

Section: Comparisonmentioning

confidence: 99%

“…Jasil et al [16] proposed a CAD method based on DenseNet201 [16], which showed comparable results and ranked it as the second-best method among other image-based models. However, our proposed MDF-RN model outperformed [16] in terms of quantitative as well as computational performance. In detail, our MDF-RN model outperformed DenseNet201 (used by Jasil et al [16]) with average gains of 0.64%, 0.75%, 0.85%, 0.66%, and 0.39% in terms of ACC, F1, PRE, REC, and AUC, respectively.…”

Section: Comparisonmentioning

confidence: 99%

See 4 more Smart Citations

Volumetric Model Genesis in Medical Domain for the Analysis of Multimodality 2-D/3-D Data Based on the Aggregation of Multilevel Features

Owais

Cho

Park

2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

The automatic and accurate classification of medical imaging data has potential applications in computer-aided disease diagnosis, prognosis, and treatment. However, it remains a challenge to optimize recent deep learning algorithms in medical domain for the accurate classification of large-scale 3D volumetric data. To address these challenges, we propose an efficient deep volumetric classification network based on the aggregation of multilevel deep features for accurate classification of large-scale medical 2D/3D imaging data. To perform a detailed quantitative analysis of our method, 26 different datasets were fused to construct a single large-scale multimodal database that comprises a total of seventy different classes, including 151,095 data samples. Additionally, 15 different baseline methods were configured under the same experimental protocol for volumetric model genesis and extensive performance comparison with our method. The experimental results of our method exhibited promising performance as area under the curve of 93.66% and outperformed various state-of-the-art methods.

show abstract