Deep Learning Based Skin Lesion Segmentation and Classification of Melanoma Using Support Vector Machine (SVM)

R. D. Seeja, A. Suresh

Asian Pacific Journal of Cancer Prevention 2019 article cited by 156

Source Open-access PDF More in Medicine & Health

importance 6/10 ai assisted Cutaneous Melanoma Detection and Management dermatology stage: research

Problem

Improving early diagnosis of melanoma by automatically segmenting skin lesions and classifying them as melanoma or benign on dermoscopy images.

Why it matters

Early detection of melanoma can assist medical experts and improve patient outcomes.

What the AI did

A CNN U-Net segmented lesions; color, texture and shape features were extracted and fed to SVM, Random Forest, KNN and Naive Bayes classifiers for diagnosis.

Results

Dice coefficient 77.5% for segmentation; SVM classifier achieved 85.19% accuracy.

Impact

Prototype achieved moderate classification accuracy on the study dataset; no clinical or external validation stated.

Record

Venue	Asian Pacific Journal of Cancer Prevention
Published	2019
Work type	article
Authors	R. D. Seeja, A. Suresh
Citations	156 (OpenAlex, at import time)
References	22
Model or method	CNN U-Net with SVM/RF/KNN/NB classifiers
Organization	not stated in source
Primary source	https://doi.org/10.31557/apjcp.2019.20.5.1555
Open access	gold
Keywords	melanoma, dermoscopy, segmentation, U-Net, SVM, classification

Importance rating

6 / 10

significant — thousands to millions affected

Early melanoma diagnosis on dermoscopy images to assist medical experts; meaningful clinical benefit implied but no scale or outcome evidence stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Medicine & Health

#	Paper	Year	Citations	Importance
1	Multimodal deep learning of fundus abnormalities and traditional risk factors for cardiovascular risk prediction Yeong Chan Lee, Jiho Cha, Injeong Shim, Woong‐Yang Park, Se Woong Kang...	2023	107	10
2	Reliable Tuberculosis Detection Using Chest X-Ray With Deep Learning, Segmentation and Visualization Tawsifur Rahman, Amith Abdullah Khandakar, Muhammad Abdul Kadir, Khand...	2020	651	10
3	A comparative analysis of machine learning classifiers for stroke prediction: A predictive analytics approach Nitish Biswas, Khandaker Mohammad Mohi Uddin, Sarreha Tasmin Rikta, Sa...	2022	116	10
4	Cardiovascular Disease Diagnosis from DXA Scan and Retinal Images Using Deep Learning Hamada R. H. Al-Absi, Mohammad Tariqul Islam, Mahmoud Ahmed Refaee, Mu...	2022	89	10
5	Proteomics and Machine Learning Approaches Reveal a Set of Prognostic Markers for COVID-19 Severity With Drug Repurposing Potential Kruthi Suvarna, Deeptarup Biswas, Medha Gayathri J. Pai, Arup Acharjee...	2021	76	10