kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Determining Important Features for Melanoma Classification Through Feature Selection
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Bestämma Betydande Attribut för Klassificering av Melanom Genom Attributselektion (Swedish)
Abstract [en]

Skin cancer is a common disease and malignant melanoma is the most dangerous form of it. Although dangerous, the survival rate of melanoma patients is high if the diagnosis is made at an early stage. Computer aided diagnostics has been shown to have potential in accurately diagnosing the disease utilizing machine learning. Thus, machine learning algorithms can be used to effectively classify a skin lesions as either benign or malignant. These algorithms can be made more accurate and efficient by applying feature selection since it decreases the dimensionality of the feature space. The aim of this study is to apply feature selection on four different classifiers to compare morphological and SIFT features in order to determine which features are important for classifying melanoma. The results show that morphological features in general had a higher importance than the SIFT features, although this varied between different classifiers. Furthermore, forward selection was more effective than backward selection in terms of accuracy for three out of the four classifiers. Lastly, two morphological features were significantly more important than the other features. The most effective feature measured the compactness of the lesion and the second most described the contrast between the lesion and the surrounding skin in terms of the color red.

Abstract [sv]

Hudcancer är en vanlig sjukdom och malignt melanom är den farligaste formen av hudcancer. Trots att formen är farlig så är sannolikheten att en patient kan botas från sjukdomen hög om diagnosen sker i ett tidigt stadium. Datordriven diagnostisering har visat sig kunna effektivt diagnostisera sjukdomen med hög säkerhet genom att tillämpa maskininlärning. På så vis kan maskininlärningsalgoritmer användas för att klassificera hudutslag som godartade eller inte. Dessa algoritmer kan effektiviseras genom att utföra attributurvalsmetoder då det minskar antalet dimensioner som behöver beräknas. Syftet med denna studie är att undersöka vilka attribut som är viktiga för klassificeringen. Detta gjordes genom att tillämpa attributurvalsmetoderna Sekventiell Framåt- och Bakåtselektion på fyra olika maskininlärningsalgoritmer med indata i form av morfologiska och SIFT-attribut. Resultaten visar att morfologiska attribut generellt föredrogs i större utsträckning än SIFT-attribut, detta varierade dock mellan olika klassificeringsmodeller. Vidare var Framåtselektion mer effektiv än Bakåtselektion sett till träffsäkerhet för tre av klassificeringsmodellerna. Slutligen var två attribut mer effektiva än de andra. Det mest effektiva attributet beskrev utslagens kompakthet och den andra beskrev kontrasten mellan utslagen och huden runtomkring med avseende på den röda färgen.

Place, publisher, year, edition, pages
2023. , p. 40
Series
TRITA-EECS-EX ; 2023:315
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-330861OAI: oai:DiVA.org:kth-330861DiVA, id: diva2:1779223
Supervisors
Examiners
Available from: 2023-08-01 Created: 2023-07-03 Last updated: 2023-08-01Bibliographically approved

Open Access in DiVA

fulltext(690 kB)182 downloads
File information
File name FULLTEXT01.pdfFile size 690 kBChecksum SHA-512
b999caf38c79231df6ae0be2854f23fee31ba6956c5920b2672a09675dbbcc31950cbbbeb597db609b6297f60c6767503f628b2bbc7e599d12ae20489f1a82b5
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 182 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 723 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf