International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 02 | Feb 2026
p-ISSN: 2395-0072
www.irjet.net
“Diagnosing Melanoma Using Convolutional Neural Network” Prof. Shruthi Rampure1, Keerti2 1Professor, Dept. of Master of computer Application, VTU, Kalaburagi, Karnataka, India 2 Student, Dept. of Master of computer Application, VTU, Kalaburagi, Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
ABSTARCT-Accurate identification of melanoma in
has highlighted significant advancements in medical image analysis. The study evaluated advanced architectures such as convolutional neural networks, transfer learning models, and hybrid frameworks for accurate lesion classification. It demonstrated that deep learning techniques achieve high diagnostic accuracy by extracting complex visual features directly from large-scale datasets. The importance of preprocessing, data augmentation, and optimized training strategies in enhancing model performance and generalization was also emphasized. A major contribution of the work is the systematic identification of current challenges, including class imbalance and limited annotated medical datasets. Overall, the study provides a strong foundation for developing reliable, scalable, and clinically applicable AI-based melanoma detection systems. [3]
dermoscopic images is critical for early diagnosis of skin cancer and prevention of disease progression. Reliable classification of malignant and benign lesions assists clinicians in making informed diagnostic decisions and reducing unnecessary biopsies. This research presents a deep learning– based automated melanoma detection system using dermoscopic images collected from publicly available datasets. A structured classification pipeline is developed using a pretrained convolutional neural network with transfer learning for feature extraction and classification. The network architecture is customized by modifying the final layers for binary classification. Model training is performed using binary cross-entropy loss and optimized using the Adam optimizer. Experimental results demonstrate reliable classification performance and highlight the potential of automated melanoma detection systems as supportive tools for dermatologists.
An advanced deep learning–based framework has been developed to improve melanoma classification by addressing the challenge of class imbalance in dermoscopic image datasets. The study integrates convolutional neural network architectures with data balancing strategies such as augmentation and resampling to enhance classification performance. By mitigating the effects of imbalanced training data, the proposed approach significantly improves model accuracy and reduces misclassification of malignant lesions. The research demonstrates that optimized data distribution and feature learning contribute to more reliable and consistent diagnostic outcomes. A key achievement of the work is the successful enhancement of melanoma detection performance through effective handling of dataset imbalance. This contribution provides a strong foundation for developing robust and clinically reliable automated skin cancer detection systems. [4]
Key Words: Melanoma detection, dermoscopic images, convolutional neural networks, deep learning, transfer learning.
1. INTRODUCTION A deep learning–based framework for automated skin lesion analysis is presented to enhance melanoma detection from dermoscopic images. The study employs convolutional neural network architectures to perform integrated tasks such as lesion segmentation, feature representation, and classification within a unified system. By utilizing datadriven feature learning instead of conventional handcrafted methods, the model effectively captures complex morphological and textural characteristics of skin lesions. Emphasis is placed on preprocessing and precise lesion boundary extraction to improve feature quality and diagnostic performance. Experimental evaluation on large dermoscopic datasets demonstrates improved classification accuracy and model robustness. The proposed approach supports efficient and scalable implementation for computer-aided dermatological diagnosis. Its architecture enables consistent performance across varied imaging conditions and reduces dependence on manual interpretation. This work contributes to the development of reliable and clinically applicable automated melanoma detection systems. [2]
A deep convolutional neural network framework with residual learning has been introduced to enhance the classification of skin lesions from dermoscopic images. The study employs residual network architecture to address challenges such as vanishing gradients and performance degradation in deep neural models. By enabling efficient feature propagation and deeper network training, the proposed model improves the extraction of complex visual characteristics associated with skin cancer. Image preprocessing and augmentation techniques were incorporated to strengthen model generalization and classification accuracy. A key achievement of this work is the significant improvement in diagnostic performance compared to conventional deep learning approaches. The study demonstrates the effectiveness of residual learning–
A comprehensive review of deep learning approaches for automated skin cancer detection using dermoscopic images
© 2026, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 641