e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
SKIN CANCER CLASSIFICATION USING DEEP LEARNING
C. S. N. Durga*1, R. Nandan Reddy*2, N. Anshith Varma*3, Bureboina Vamshi*4
*1Assistant Professor, Department Of Computer Science And Engineering Malla Reddy College Of
Engineering & Technology Hyderabad, India.
*2,3,4Final Year Student, Department Of Computer Science And Engineering Malla Reddy College Of
Engineering & Technology Hyderabad, India.
ABSTRACT
Due to the limited availability of resources, skin cancer is one of the most quickly spreading diseases in the
globe. Identification of skin cancer through an accurate diagnosis is essential for a preventative approach in
general. Dermatologists struggle to detect skin cancer at an early stage, and 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. To enhance the model's performance, transfer
learning is employed by leveraging pre-trained neural network weights on a large-scale image dataset. Fine-
tuning is performed to adapt the network to the specific characteristics of dermatoscopic images. The model is
trained and validated on a comprehensive dataset, and its performance is evaluated using various metrics such
as sensitivity, specificity, and accuracy.
Results demonstrate the efficacy of the proposed deep learning model in accurately classifying skin lesions. The
system exhibits a high level of sensitivity and specificity, outperforming traditional methods and showcasing its
potential as a valuable tool for dermatologists and healthcare professionals in the early diagnosis of skin
cancer. Furthermore, the model's interpretability is explored through attention mechanisms, providing insights
into the regions of interest contributing to the classification decision.
Because of the lack of resources, skin cancer is one of the diseases that is spreading the fastest in the world.
Accurate diagnosis of skin cancer identification is essential for early detection in order to implement preventive
measures more broadly. Dermatologists find it difficult to identify skin cancer in its early stages, and deep
learning has been used extensively in both supervised and unsupervised learning tasks in recent years. In tests
of object detection and classification, Convolutional Neural Networks (CNN), one of these models, has
outperformed the others.
I. INTRODUCTION
A tumor is formed when healthy cells begin to change and grow out of control. Both cancerous and
noncancerous tumors are conceivable. Malignant tumors are those that have the potential to grow and spread
to other areas of the body. A benign tumor may form, but it does not usually spread. Skin cancer is the result of
abnormal skin cell growth. It is the most prevalent cancer nowadays and occurs everywhere. Every year,
various forms of melanomas are thought to cause more than 3.5 million cases to be discovered. This number
exceeds the sum of cases of lung, bone, and colon cancers. In reality, a person with melanoma dies every 57
seconds. When cancer is detected in dermoscopy images in advance, the survival percentage is significantly
boosted. Therefore, accurate automatic skin excrescence discovery will undoubtedly help pathologists become
more skilled and productive. The purpose of the dermoscopy technique is to improve each melanoma patient’s
performance. Noninvasive skin imaging technique dermoscopy uses a magnified and lighted picture of the
affected skin area to increase visibility of the spots, therefore reducing facial reflection. Skin cancer early
detection is still a prized possession. It’s difficult to tell if a skin lesion is benign or malignant because they all
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[1]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
seem similar. The sun’s harmful ultraviolet (UV) rays and the usage of UV tanning beds are the two most
common causes of skin cancer. It is particularly difficult for dermatologists to distinguish between melanoma
and non-melanoma lesions because of the low degree of difference between lesions and skin. The main problem
of similar opinion is largely dependent on private judgment and is scarcely reproducible. With the help of
robotization using operation of deep literacy helps the case to get the early opinion report and grounded on the
report case can consult dermatologists for treatment. An early diagnosis of skin cancer is crucial and has
limited number of available treatment options. Accurate evaluation and the capacity to accurately identify skin
cancer are critical components of a skin cancer prevention approach. Even in literacy tasks that are
unsupervised, deep literacy has been widely adopted. Object detection and bracket tasks have been dominated
by Convolutional Neural Networks (CNN). As a result, trained end-to-end in a controlled environment, CNNs
eliminate the need for humans to manually create feature sets. The use of Convolutional Neural Networks
(CNNs) to categorize lesions in skin cancer in recent years has outperformed skilled mortal specialists.
II. LITERATURE REVIEW
2.1 Detection of skin cancer using CNN algorithm:
https://www.sciencedirect.com/science/article/abs/pii/S0933365719301460
ABSTRACT: arly detection of skin cancer is very important and can prevent some skin cancers, such as focal
cell carcinoma and melanoma. Although there are several reasons that have bad impacts on the detection
precision. Recently, the utilization of image processing and machine vision in medical applications is increasing.
In this paper, a new image processing based method has been proposed for the early detection of skin cancer.
The method utilizes an optimal Convolutional neural network (CNN) for this purpose. In this paper, improved
whale optimization algorithm is utilized for optimizing the CNN. For evaluation of the proposed method, it is
compared with some different methods on two different datasets. Simulation results show that the proposed
method has superiority toward the other compared methods.
2.2 Skin lesion classification based on deep convolutional neural networks architectures:
https://www.researchgate.net/publication/
350529813_Skin_Lesion_Classification_Based_on_Deep_Convolutional_Neural_Networks_Architectures
ABSTRACT: Skin cancer is among the primary cancer types that manifest due to various dermatological
disorders, which may be further classified into several types based on morphological features, color, structure,
and texture. The mortality rate of patients who have skin cancer is contingent on preliminary and rapid
detection and diagnosis of malignant skin cancer cells. Limitations in current dermoscopic images, including
shadow, artifact, and noise, affect image quality, which may hamper detection effort. Attempts to overcome
these challenges have been made by analyzing the images using deep learning neural networks to perform skin
cancer detection. In this paper, the authors review the state-of-the-art in authoritative deep learning concepts
pertinent to skin cancer detection and classification.
2.3 Skin cancer classification using image processing and machine learning:
https://www.researchgate.net/publication/
350935822_Skin_Cancer_Classification_Using_Image_Processing_and_Machine_Learning
ABSTRACT: one of the most rapidly spreading cancers among various other types of cancers known to humans
is skin cancer. Melanoma is the worst and the most dangerous type of skin cancer that appears usually on the
skin surface and then extends deeper into the layers of skin. However, if diagnosed at an early stage; the
survival rate of Melanoma patients is 96% with simple and economical treatments. The conventional method of
diagnosing Melanoma involves expert dermatologists, equipment, and Biopsies. To avoid the expensive
diagnosis, and to assist dermatologists, the field of machine learning has proven to provide state of the art
solutions for skin cancer detection at an earlier stage with high accuracy. In this paper, a method for skin lesion
classification and segmentation as benign or malignant is proposed using image processing and machine
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[2]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
learning. A novel method of contrast stretching of dermoscopic images based on the methods of mean values
and standard deviation of pixels is proposed. Then the OTSU thresholding algorithm is applied for image
segmentation. After the segmentation, features including Gray level Co-occurrence Matrix (GLCM) features for
texture identification, the histogram of oriented gradients (HOG) object, and color identification features are
extracted from the segmented images. Principal component analysis (PCA) reduction of HOG features is
performed for dimensionality reduction. Synthetic minority oversampling technique (SMOTE) sampling is
performed to deal with the class imbalance problem. The feature vector is then standardized and scaled. A
novel approach of feature selection based on the wrapper method is proposed before classification. Classifiers
including Quadratic Discriminant, SVM (Medium Gaussian), and Random Forest are used for classification. The
proposed approach is verified on the publicly accessible dataset of ISIC-ISBI 2016. Maximum accuracy is
achieved using the Random Forest classifier. The classification accuracy of the proposed system with the
Random Forest classifier on ISIC-ISBI 2016 is 93.89%.The proposed approach of contrast stretching before the
segmentation gives satisfactory results of segmentation. Further, the proposed wrapper-based approach of
feature selection in combination with the Random Forest classifier gives promising results as compared to
other commonly used classifiers.
III. METHODOLOGY
We proposed a Convolutional Neural Networks (CNN), it 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. We employed the data pre-
processing techniques like sampling, dull razor and segmentation using autoencoder and decoder. Transfer
learning techniques like DenseNet169 and Resnet 50 were used to train the model to obtain the results. We
compare performance of the both transfer learning models by using the undersampling and oversampling
techniques.
format.
Figure 1: Dull razor implementation
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[3]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
Figure 2: Dull razor implementation
Figure 3: Architecture of DenseNet-169
IV. RESULTS AND DISCUSSION
The results and discussion may be combined into a common section or obtainable separately. They may also be
broken into subsets with short, revealing captions. An easy way to comply with the conference paper
formatting requirements is to use this document as a template and simply type your text into it. This section
should be typed in character size 10pt Times New Roman.
Table 1. Test Cases
SN. INPUT If available If not available
1 User signup User is registered into
the web application and No process
details get stored.
2 User login User get login into the
No process
application
3 Submit Input The predicted result is
No process
for prediction displayed to user
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[4]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
Figure 2: Graph
F
igure 3: Result screen
V. CONCLUSION
Skin cancer is one of the illnesses that is spreading the quickest on the earth. Skin cancer is mostly brought on
by a person’s vulnerability to the sun’s UV radiation. Given the limited resources available, early identification
of skin cancer is essential. Accurate diagnosis and identification viability are generally essential for skin cancer
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[5]
e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering
Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:06/Issue:03/March-2024 Impact Factor- 7.868
www.irjmets.com
prevention strategies. Additionally, dermatologists have trouble seeing skin cancer in its early stages. The use
of deep learning for both supervised and unsupervised applications has increased significantly in recent years.
Convolutional Neural Networks (CNNs) are one of these models that have excelled in object identification and
classification tasks (CNN). The dataset is filtered from MNIST: HAM10000, which has a sample size of 10015
and includes seven different types of skin lesions. Data preprocessing methods include sampling, segmentation
using an autoencoder and decoder, and dull razor. The model was trained using transfer learning methods like
DenseNet169 and Resnet 50. Different ratios were used for the training and assessment, including 80:20, 70:30,
and 40:60. When undersampling and oversampling were compared, DenseNet169’s undersampling technique
produced accuracy of 91.2% with a f1-measure of 91.7% and Resnet50’s oversampling technique produced
accuracy of 83% with a f1-measure of 84%. The future extension of this study includes increasing forecast
accuracy through parameter tuning.
VI. REFERENCES
[1] Y. C. Lee, S.-H. Jung, and H.-H. Won, ‘‘WonDerM: Skin lesion classification with fine-tuned neural networks,’’
2018, arXiv:1808.03426.
[2] U. Jamil, M. U. Akram, S. Khalid, S. Abbas, and K. Saleem, ‘‘Computer based melanocytic and nevus image
enhancement and segmentation,’’ BioMed Res. Int., vol. 2016, pp. 1–13, Jan. 2016.
[3] A. Mahbod, G. Schaefer, C. Wang, R. Ecker, and I. Ellinge, ‘‘Skin lesion classification using hybrid deep neural
networks,’’ in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), May 2019, pp. 1229–1233.
[4] K. Pai and A. Giridharan, ‘‘Convolutional neural networks for classifying skin lesions,’’ in Proc. TENCON
IEEE Region 10 Conf. (TENCON), Oct. 2019, pp. 1794–1796.
[5] A. S. Shete, A. S. Rane, P. S. Gaikwad, and M. H. Patil, ‘‘Detection of skin cancer using CNN algorithm,’’ Int. J.,
vol. 6, no. 5, pp. 1–4, 2021.
[6] [M. Vidya and M. V. Karki, ‘‘Skin cancer detection using machine learning techniques,’’ in Proc. IEEE Int.
Conf. Electron., Comput. Commun. Technol. (CONECCT), Jul. 2020, pp. 1–5.
[7] H. Nahata and S. P. Singh, ‘‘Deep learning solutions for skin cancer detection and diagnosis,’’ in Machine
Learning with Health Care Perspective. Cham, Switzerland: Springer, 2020, pp. 159–182.
[8] P. Wighton, T. K. Lee, H. Lui, D. I. McLean, and M. S. Atkins, ‘‘Generalizing common tasks in automated skin
lesion diagnosis,’’ IEEE Trans. Inf. Technol. Biomed., vol. 15, no. 4, pp. 622–629, Jul. 2011.
[9] J. Saeed and S. Zeebaree, ‘‘Skin lesion classification based on deep convolutional neural networks
architectures,’’ J. Appl. Sci. Technol. Trends, vol. 2, no. 1, pp. 41–51, Mar. 2021.
[10] Y. Li, A. Esteva, B. Kuprel, R. Novoa, J. Ko, and S. Thrun, ‘‘Skin cancer detection and tracking using data
synthesis and deep learning,’’ 2016, arXiv:1612.01074.
[11] V. Badrinarayanan, A. Kendall, and R. Cipolla, ‘‘SegNet: A deep convolutional encoder–decoder
architecture for image segmentation,’’ IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 12, pp. 2481–
2495, Dec. 2017.
[12] P. Tschandl, C. Rosendahl, and H. Kittler, ‘‘The HAM10000 dataset, a large collection of multi-source
dermatoscopic images of common pigmented skin lesions,’’ Sci. Data, vol. 5, no. 1, pp. 1–9, Aug. 2018.
[13] K. M. Hosny, M. A. Kassem, and M. M. Foaud, ‘‘Skin cancer classification using deep learning and
transfer learning,’’ in Proc. 9th Cairo Int. Biomed. Eng. Conf. (CIBEC), Dec. 2018, pp. 90–93.
[14] A. Javaid, M. Sadiq, and F. Akram, ‘‘Skin cancer classification using image processing and machine
learning,’’ in Proc. Int. Bhurban Conf. Appl. Sci. Technol. (IBCAST), Jan. 2021, pp. 439–444.
[15] R. Ashraf, I. Kiran, T. Mahmood, A. U. R. Butt, N. Razzaq, and Z. Farooq, ‘‘An efficient technique for skin
cancer classification using deep learning,’’ in Proc. IEEE 23rd Int. Multitopic Conf. (INMIC), Nov. 2020, pp.
1–5.
www.irjmets.com @International Research Journal of Modernization in Engineering,
Technology and Science
[6]
