Sökning: id:"swepub:oai:lup.lub.lu.se:fa155e4d-70b5-4d49-9c63-c9f96dc5f086" >
Automatic diagnosis of melanoma using hyperspectral data and GoogLeNet
-
- Hirano, Ginji (författare)
- Kindai University
-
- Nemoto, Mitsutaka (författare)
- Kindai University
-
- Kimura, Yuichi (författare)
- Kindai University
-
visa fler...
-
- Kiyohara, Yoshio (författare)
- Shizuoka Cancer Center
-
- Koga, Hiroshi (författare)
- Shinshu University Hospital
-
- Yamazaki, Naoya (författare)
- National Cancer Center Hospital, Japan
-
- Christensen, Gustav (författare)
- Lund University,Lunds universitet,Dermatologi och venereologi, Lund,Sektion III,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Dermatology and Venereology (Lund),Section III,Department of Clinical Sciences, Lund,Faculty of Medicine
-
- Ingvar, Christian (författare)
- Lund University,Lunds universitet,Dermatologi och venereologi, Lund,Sektion III,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Dermatology and Venereology (Lund),Section III,Department of Clinical Sciences, Lund,Faculty of Medicine
-
- Nielsen, Kari (författare)
- Lund University,Lunds universitet,Dermatologi och venereologi, Lund,Sektion III,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,LUCC: Lunds universitets cancercentrum,Övriga starka forskningsmiljöer,Dermatology and Venereology (Lund),Section III,Department of Clinical Sciences, Lund,Faculty of Medicine,LUCC: Lund University Cancer Centre,Other Strong Research Environments
-
- Nakamura, Atsushi (författare)
- Waseda University
-
- Sota, Takayuki (författare)
- Waseda University
-
- Nagaoka, Takashi (författare)
- Kindai University
-
visa färre...
-
(creator_code:org_t)
- 2020-06-25
- Engelska 7 s.
-
Ingår i: Skin Research and Technology. - : Wiley. - 0909-752X .- 1600-0846. ; 26:6, s. 891-897
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Background: Melanoma is a type of superficial tumor. As advanced melanoma has a poor prognosis, early detection and therapy are essential to reduce melanoma-related deaths. To that end, there is a need to develop a quantitative method for diagnosing melanoma. This paper reports the development of such a diagnostic system using hyperspectral data (HSD) and a convolutional neural network, which is a type of machine learning. Materials and Methods: HSD were acquired using a hyperspectral imager, which is a type of spectrometer that can simultaneously capture information about wavelength and position. GoogLeNet pre-trained with Imagenet was used to model the convolutional neural network. As many CNNs (including GoogLeNet) have three input channels, the HSD (involving 84 channels) could not be input directly. For that reason, a “Mini Network” layer was added to reduce the number of channels from 84 to 3 just before the GoogLeNet input layer. In total, 619 lesions (including 278 melanoma lesions and 341 non-melanoma lesions) were used for training and evaluation of the network. Results and Conclusion: The system was evaluated by 5-fold cross-validation, and the results indicate sensitivity, specificity, and accuracy of 69.1%, 75.7%, and 72.7% without data augmentation, 72.3%, 81.2%, and 77.2% with data augmentation, respectively. In future work, it is intended to improve the Mini Network and to increase the number of lesions.
Ämnesord
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Cancer och onkologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Cancer and Oncology (hsv//eng)
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Dermatologi och venereologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Dermatology and Venereal Diseases (hsv//eng)
Nyckelord
- deep learning
- GoogLeNet
- hyperspectral imager
- melanoma
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)