ScarNet: Development and Validation of a Novel Deep CNN Model for Acne Scar Classification With a New Dataset

Junayed, Masum Shah; Islam, Md Baharul; Jeny, Afsana Ahsan; Sadeghzadeh, Arezoo; Biswas, Topu; Shah, A. F. M. Shahen

doi:10.1109/access.2021.3138021

Cited by 28 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The effectiveness of our ensemble classifier is assessed and compared to three pre-trained models (DenseNet201, and the proposed CNN model using the Receiver Operating Characteristic (ROC) Curve (Junayed et al, 2021a) to ascertain how well it performs in Fig. 8.…”

Section: Results and Comparisonmentioning

confidence: 99%

Deep Neural Network-Based Ensemble Model for Eye Diseases Detection and Classification

Jeny¹,

Junayed²,

Islam

2023

Image Anal Stereol

View full text Add to dashboard Cite

Fundus images are the principal tool for observing and recognizing a wide range of ophthalmological abnormalities. The automatic and robust methods based on color fundus images are urgently needed since few symptoms are observable in the early stages of the disease. Experts must manually evaluate images to detect diseases for screening procedures to be effective. Due to the complexity of the screening procedure and the shortage of experienced personnel, developing successful screening-based treatments is costly. Although existing automated approaches strive to address these issues, they cannot handle a wide range of diseases and real-world circumstances. We design an automated deep learning-based ensemble method to detect and classify eye diseases from fundus images to address the abovementioned problems. A deep CNN-based model is proposed in the ensemble method that incorporates a mix of 20 layers, including the activation, optimization, and loss functions. The contrast-limited adaptive histogram equalization (CLAHE) and Gaussian filter are utilized in the pre-processing step to get more explicit images and eliminate noise. To avoid overfitting in the training phase, augmentation techniques are applied. Three pre-trained CNN models, including VGG16, DenseNet201, and ResNet50, are employed to compare and assess the efficiency of the proposed CNN model. Experimental results demonstrate that the ensemble approach outperforms recent approaches, which is comparatively state-of-art in the ODIR publicly available dataset.

show abstract

Section: Results and Comparisonmentioning

confidence: 99%

Deep Neural Network-Based Ensemble Model for Eye Diseases Detection and Classification

Jeny¹,

Junayed²,

Islam

2023

Image Anal Stereol

View full text Add to dashboard Cite

show abstract

“…Mengacu pada beberapa penelitian terkait klasifikasi data pada penelitian sebelumnya, [14][15][16][17][18][19][20] metrik evaluasi menjadi parameter yang penting untuk mengukur performa dari model yang…”

Section: Performance Evaluation Metricsunclassified

Perbandingan Kemampuan Klasifikasi Citra X-ray Paru-paru menggunakan Transfer Learning ResNet-50 dan VGG-16

Berliani,

Rahardja,

Septiana

2023

J. Med. Health

View full text Add to dashboard Cite

Di masa pandemi Covid-19, foto rontgen menjadi umum digunakan untuk memeriksa pasien diduga Covid-19. Pada citra x-ray paru-paru yang terkena Covid-19 ditemukan adanya bercak putih atau flek. Namun, paru-paru yang memiliki flek ini tidak selalu disebabkan oleh Covid-19. Tujuan penelitian ini adalah untuk mengklasifikasikan beberapa jenis penyakit paru-paru dari citra x-ray, yaitu paru-paru dengan Covid-19, paru-paru dengan pneumonia, dan paru-paru yang memiliki flek dibandingkan dengan yang normal. Proses klasifikasi data pada penelitian ini dilakukan dengan membandingkan dua model yaitu CNN VGG-16 dan ResNet-50 dengan model yang telah dilatih sebelumnya. Metrik evaluasi yang digunakan dalam penelitian ini terdiri dari akurasi, presisi, sensitivitas, spesifisitas, skor F1, dan kecepatan waktu inferensi. Hasil menunjukkan bahwa VGG-16 lebih unggul dari ResNet-50 dalam hal kecepatan inferensi namun tidak dalam hal metrik evaluasi lainnya. Perubahan parameter juga menunjukkan hasil yang berbeda, epoch 200 adalah nilai optimal. Untuk mendapatkan hasil yang optimal diperlukan finetuning dengan menyesuaikan kondisi data yang digunakan. Sebagai simpulan, VGG-16 memiliki kemampuan klasifikasi yang lebih baik dibandingkan ResNet-50, namun perlu terus dikembangkan dengan memperbanyak data klinis yang aktual.

show abstract

“…According to numerous studies from ImageNet's large-scale visual recognition challenge, the most sophisticated CNN has outperformed humans on object-classification tasks. [6][7][8] Due to its exceptional performance over traditional methods, deep CNN-based learning is also frequently utilized in skin disease classification, 9,10 lesion localization, and segmentation tasks, [11][12][13][14] A majority of these tasks showed a high standard of accuracy, making automatic skin disease screening achievable.…”

Section: Introductionmentioning

confidence: 99%

Few-Shot Classification with Multiscale Feature Fusion for Clinical Skin Disease Diagnosis

Chen,

Liu,

Yang

2024

CCID

View full text Add to dashboard Cite

Introduction: Skin disease is one of the most common diseases and can affect people of all ages and races. However, the diagnosis of skin diseases via observation is a highly challenging task for both doctors and patients, and would benefit from the use of an intelligent system. Building a large benchmark with professional dermatologists is resource-intensive, and we believe that few-shot learning (FSL) methods would be helpful in solving the problem of annotated data scarcity. In this paper, we propose CDD-Net (Context Feature Fusion and Dual Attention Dermatology Net), a plug-in module for FSL clinical skin disease classification. Methods: Current FSL methods used in skin disease classification are limited to nonuniversal approaches and few disease classes. Our CDD-Net has a flexible structure, including a context feature-fusion module and dual-attention module to extract discriminating texture feature and emphasize contributive regions and channels. The context feature-fusion module localizes discriminatory texture details of skin lesions by integrating features from different layers, while the dual-attention module highlights discriminative regions via channel-wise and pixel-wise depictions based on weight vectors and restrains the contributions of irrelevant areas. We also present Derm104, a new clinical skin disease data benchmark that has significant coverage of rare diseases and reliable annotation between primary species and subspecies for better validation of our approach. Results: Our experiments validated the versatility of CDD-Net for different FSL methods and achieved an improvement in accuracy of up to 9.14 percentage points compared with the vanilla network, which can be considered state of the art. The ablation study also showed that the dual-attention module and context feature-fusion module worked efficiently in CDD-Net.

show abstract

ScarNet: Development and Validation of a Novel Deep CNN Model for Acne Scar Classification With a New Dataset

Cited by 28 publications

References 49 publications

Deep Neural Network-Based Ensemble Model for Eye Diseases Detection and Classification

Deep Neural Network-Based Ensemble Model for Eye Diseases Detection and Classification

Perbandingan Kemampuan Klasifikasi Citra X-ray Paru-paru menggunakan Transfer Learning ResNet-50 dan VGG-16

Few-Shot Classification with Multiscale Feature Fusion for Clinical Skin Disease Diagnosis

Contact Info

Product

Resources

About