Skin pattern analysis for lesion classification using local isotropy

Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature...

Full description

Saved in:

Bibliographic Details
Published in:	Skin research and technology Vol. 17; no. 2; pp. 206 - 212
Main Authors:	She, Zhishun, Excell, Peter S.
Format:	Journal Article
Language:	English
Published:	Oxford, UK Blackwell Publishing Ltd 01.05.2011
Subjects:	Dermoscopy - instrumentation Dermoscopy - methods Diagnosis, Differential Humans Image Interpretation, Computer-Assisted - instrumentation Image Interpretation, Computer-Assisted - methods lesion classification local isotropy melanoma Melanoma - classification Melanoma - pathology Models, Theoretical Neoplasms - classification Neoplasms - pathology Pattern Recognition, Automated - methods Photophobia Skin - pathology Skin Neoplasms - classification Skin Neoplasms - pathology skin pattern texture analysis
ISSN:	0909-752X, 1600-0846, 1600-0846
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption. Methods: The skin pattern was extracted from WLC skin images by high‐pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier. Results: A set of images of malignant melanoma and benign naevi was analysed. A one‐dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two‐dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three‐dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96. Conclusion: The experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions.
AbstractList	Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption. Methods: The skin pattern was extracted from WLC skin images by high‐pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier. Results: A set of images of malignant melanoma and benign naevi was analysed. A one‐dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two‐dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three‐dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96. Conclusion: The experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions. The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption. The skin pattern was extracted from WLC skin images by high-pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier. A set of images of malignant melanoma and benign naevi was analysed. A one-dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two-dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three-dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96. The experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions. The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption.BACKGROUND/PURPOSEThe observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption.The skin pattern was extracted from WLC skin images by high-pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier.METHODSThe skin pattern was extracted from WLC skin images by high-pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier.A set of images of malignant melanoma and benign naevi was analysed. A one-dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two-dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three-dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96.RESULTSA set of images of malignant melanoma and benign naevi was analysed. A one-dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two-dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three-dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96.The experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions.CONCLUSIONThe experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions. Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption on simply captured white light optical clinical (WLC) skin images could be a useful contribution to a diagnostic feature set. Previous work, which generated a flow field of skin pattern using a measurement of local line direction and intensity, was encouraging. The aim of this paper is to investigate the possibility of extracting new features using local isotropy metrics to quantify the skin pattern disruption. Methods: The skin pattern was extracted from WLC skin images by high‐pass filtering. A local tensor matrix was computed. The local isotropy was measured by the condition number of the local tensor matrix. The difference of this measure over the lesion and normal skin areas, combined with the local line direction and the ABCD features, was used as a lesion classifier. Results: A set of images of malignant melanoma and benign naevi was analysed. A one‐dimensional scatter plot showed the potential of a local isotropy metric, showing an area of 0.70 under the receiver operating characteristic (ROC) curve. A two‐dimensional scatter plot, combined with the local line direction, indicated enhancement of the classification performance, showing an area of 0.89 under the ROC curve. A three‐dimensional scatter plot combined with the local line direction and the ABCD features, using principal component analysis, demonstrated excellent separation of benign and malignant lesions. An ROC plot for this case enclosed an area of 0.96. Conclusion: The experimental results show that the local isotropy metric has a potential to increase lesion classifier accuracy. Combined with the local line direction and the ABCD features, it is very promising as a method to distinguish malignant melanoma from benign lesions.
Author	She, Zhishun Excell, Peter S.
Author_xml	– sequence: 1 givenname: Zhishun surname: She fullname: She, Zhishun organization: Institute of Arts, Science & Technology, Glyndwr University, University of Wales, Wrexham, UK – sequence: 2 givenname: Peter S. surname: Excell fullname: Excell, Peter S. organization: Institute of Arts, Science & Technology, Glyndwr University, University of Wales, Wrexham, UK
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/21208289$$D View this record in MEDLINE/PubMed
BookMark	eNqNkE9P3DAQxa2Kqiy0X6HKjVMW20n8R0JILVBaiRYEVMtt5DgT5MUbL3ZW3f32JCxw6Alfxp55v2fN2yM7XeiQkIzRKRvO4XzKBKU5VaWYcjp0KS1VNV1_IJO3wQ6ZUE11Lit-t0v2UppTSivNik9klzNOFVd6Qk5vHlyXLU3fY-wy0xm_SS5lbYiZx-RCl1lvUnKts6Yfn6vkuvvMB2t85lLoY1huPpOPrfEJv7zUffL3x9ntyc_84vL818m3i9yWklU5Mi4bq5qWC2ssrW3daKOlFdpK0Q4tLGopUEhTNnXZNqLVDKuSI9assEoU--Rg67uM4XGFqYeFSxa9Nx2GVQJVaa6ZkmpQfn1RruoFNrCMbmHiBl4XHwTHW4GNIaWILVjXP2_YR-M8MApj0jCHMVAYA4UxaXhOGtaDgfrP4PWPd6BHW_Sf87h5Nwc317fDZcDzLe5Sj-s33MQHELKQFcz-nMOMst-zq-vvcFc8ARWvpg8
CitedBy_id	crossref_primary_10_1016_j_compbiomed_2023_106624 crossref_primary_10_1109_TBME_2014_2348323 crossref_primary_10_1016_j_artmed_2012_08_002 crossref_primary_10_32604_cmc_2022_023178
Cites_doi	10.1007/978-1-4613-9777-9 10.1111/j.1600-0846.2009.00383.x 10.1016/0734-189X(87)90043-0 10.1109/TIT.1972.1054863 10.1016/B0-12-227240-4/00132-5 10.1034/j.1600-0846.2003.00044.x 10.1111/j.1600-0846.2007.00181.x 10.1109/51.232345 10.1007/978-1-4471-1925-8_4 10.1111/j.1600-0846.2009.00413.x 10.3322/caac.20006 10.1034/j.1600-0846.2000.006004183.x 10.1034/j.1600-0846.2003.00370.x 10.1016/0141-5425(92)90057-R
ContentType	Journal Article
Copyright	2010 John Wiley & Sons A/S 2010 John Wiley & Sons A/S.
Copyright_xml	– notice: 2010 John Wiley & Sons A/S – notice: 2010 John Wiley & Sons A/S.
DBID	BSCLL AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1111/j.1600-0846.2010.00485.x
DatabaseName	Istex CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic CrossRef
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Engineering
EISSN	1600-0846
EndPage	212
ExternalDocumentID	21208289 10_1111_j_1600_0846_2010_00485_x SRT485 ark_67375_WNG_W01MWPRB_X
Genre	article Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- .3N .GA .Y3 05W 0R~ 10A 123 1OB 1OC 24P 31~ 36B 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52R 52S 52T 52U 52V 52W 52X 53G 5HH 5LA 5VS 66C 702 7PT 7X7 8-0 8-1 8-3 8-4 8-5 8FI 8FJ 8UM 930 A01 A03 AAESR AAEVG AAKAS AAMMB AANHP AAONW AAZKR ABCQN ABCUV ABDBF ABEML ABJNI ABPVW ABUWG ACAHQ ACBWZ ACCMX ACGFS ACIWK ACMXC ACPOU ACPRK ACRPL ACSCC ACUHS ACXQS ACYXJ ADBBV ADEOM ADIYS ADIZJ ADKYN ADMGS ADNMO ADOZA ADPDF ADXAS ADZCM ADZMN AEFGJ AEGXH AEIMD AENEX AFBPY AFEBI AFGKR AFKRA AFRAH AFZJQ AGQPQ AGXDD AHEFC AHMBA AIACR AIDQK AIDYY AIQQE AIURR ALAGY ALMA_UNASSIGNED_HOLDINGS AMBMR AMYDB ASPBG ATUGU AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BENPR BFHJK BHBCM BMXJE BROTX BRXPI BSCLL BY8 CAG CCPQU COF CS3 CYRXZ D-6 D-7 D-E D-F DC6 DCZOG DPXWK DR2 DRFUL DRMAN DRSTM EAD EAP EBC EBD EBS EJD EMB EMK EMOBN ESX EX3 F00 F01 F04 FEDTE FUBAC FYUFA FZ0 G-S G.N GODZA H.X HF~ HMCUK HVGLF HZI HZ~ IHE IX1 J0M K48 KBYEO LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MK4 MRFUL MRMAN MRSTM MSFUL MSMAN MSSTM MXFUL MXMAN MXSTM N04 N05 N9A NF~ O66 O9- OIG OK1 OVD OVEED P2P P2W P2X P2Z P4B P4D PALCI PHGZM PQQKQ Q.N Q11 QB0 R.K RIWAO RJQFR ROL RPM RX1 SAMSI SUPJJ SV3 TEORI TUS UB1 UKHRP W8V W99 WBKPD WHWMO WIH WIJ WIK WOHZO WOW WQJ WVDHM WXI WXSBR XG1 YFH ZZTAW ~IA ~WT ALUQN AAYXX CITATION O8X AAHHS ACCFJ AEEZP AEQDE AIWBW AJBDE CGR CUY CVF ECM EIF NPM 7X8
ID	FETCH-LOGICAL-c4715-e127dc8df26cac0bcbd9a97c69c76fcace3b76e67a4db4fd6f91e542eeb13c863
IEDL.DBID	DRFUL
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000288906900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0909-752X 1600-0846
IngestDate	Sat Sep 27 19:20:17 EDT 2025 Thu Apr 03 06:57:59 EDT 2025 Sat Nov 29 02:17:31 EST 2025 Tue Nov 18 21:36:22 EST 2025 Sun Sep 21 06:26:12 EDT 2025 Tue Nov 11 03:32:38 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
Language	English
License	http://onlinelibrary.wiley.com/termsAndConditions#vor 2010 John Wiley & Sons A/S.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c4715-e127dc8df26cac0bcbd9a97c69c76fcace3b76e67a4db4fd6f91e542eeb13c863
Notes	ArticleID:SRT485 ark:/67375/WNG-W01MWPRB-X istex:39B242BCF4AE42D2867DC0A054DC3A679B2F77F6 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PMID	21208289
PQID	859291878
PQPubID	23479
PageCount	7
ParticipantIDs	proquest_miscellaneous_859291878 pubmed_primary_21208289 crossref_citationtrail_10_1111_j_1600_0846_2010_00485_x crossref_primary_10_1111_j_1600_0846_2010_00485_x wiley_primary_10_1111_j_1600_0846_2010_00485_x_SRT485 istex_primary_ark_67375_WNG_W01MWPRB_X
PublicationCentury	2000
PublicationDate	May 2011
PublicationDateYYYYMMDD	2011-05-01
PublicationDate_xml	– month: 05 year: 2011 text: May 2011
PublicationDecade	2010
PublicationPlace	Oxford, UK
PublicationPlace_xml	– name: Oxford, UK – name: England
PublicationTitle	Skin research and technology
PublicationTitleAlternate	Skin Res Technol
PublicationYear	2011
Publisher	Blackwell Publishing Ltd
Publisher_xml	– name: Blackwell Publishing Ltd
References	Golub GH, Loan CFV Matrix computations. Baltimore, MD: Johns Hopkins University Press, 1989. Setaro M, Sparavigna A. Irregularity skin index (ISI): a tool to evaluate skin surface texture. Skin Res Technol 2001; 7: 159-163. She Z, Fish PJ. Analysis of skin line pattern for lesion classification. Skin Res Technol 2003; 9: 73-80. Sparavigna A, Marazzato R. An image-processing analysis of skin textures. Skin Res Technol 2010; 16: 161-167. Round AJ, Duller AWG, Fish PJ. Lesion classification using skin patterning. Skin Res Technol 2000; 6: 183-192. Hall PN. Clinical diagnosis of melanoma. Diagnosis and management of melanoma in clinical practice. New York, NY: Springer-Verlag, 1992: 35-52. Rao AR. A taxonomy for texture description and identification. Berlin: Spring-Verlag, 1990. Foley DH. Consideration of sample and feature size. IEEE Trans Info Theory 1972; 18: 618-626. Mark R. Roxburgh's common skin diseases. London: Chapman and Hall Medical, 1993. Tabatabaie K, Esteki A, Toossi P. Extration of skin lesion texture features based on independent component analysis. Skin Res Technol 2009; 15: 433-439. Durg A, Stoecker WV, Cookson JP, Umbaugh SE, Moss RH. Identification of variegated colouring in skin tumours. IEEE Eng Med Biol 1993; 12: 71-74. Schmid-Saugeon P. Symmetry axis computation for almost-symmetrical and asymmetrical objects: application to pigmented skin lesions. Med Image Anal 2000; 4: 269-282. Bigun J. Vision with direction: a systematic introduction to image processing and computer vision. Berlin: Springer, 2006. Kass M, Witkin A. Analyzing oriented patterns. Comput Vis Graph Image Process 1987; 37: 362-385. Jemal A, Siegel R, Ward E, Hao Y, Xu J, Thun MJ. Cancer statistics, 2009. CA Cancer J Clin 2009; 59: 225-249. Mackie RM. An illustrated guide to the recognition of early malignant melanoma. Blackwood Pillans & Wilson Ltd. Edinburgh and Department of Dermatology, University of Glasgow, UK: Edinburgh, 1986. Claridge E, Hall PN, Keffe M, Allen JP. Shape analysis for classification of malignant melanoma. J Biomed Eng 1992; 14: 229-234. Wilhelm K, Elsnor P, Berardesca E. Bioengineering of the skin: skin surface imaging and analysis. Boca Raton, FL: CRC Press Inc, 1997. Theodoridis S, Koutroumbas K. Pattern recognition. San Diego, CA: Academic Press, 2003. She Z, Liu Y, Damato A. Combination of features from skin pattern and ABCD analysis for lesion classification. Skin Res Technol 2007; 13: 25-33. Deshabhoina SV, Umbaugh SE, Stoecker WV, Moss RH, Srinivasan SK. Melanoma and seborrheic keratosis differentiation using texture features. Skin Res Technol 2003; 9: 348-356. 1993; 12 2010; 16 2001; 7 2000; 6 1990 2000; 4 2003; 9 1986 1997 2006 1992; 14 1993 1992 2003 1972; 18 2007; 13 2009; 59 2009; 15 1987; 37 1989 e_1_2_7_5_2 e_1_2_7_4_2 e_1_2_7_2_2 e_1_2_7_9_2 e_1_2_7_8_2 Wilhelm K (e_1_2_7_11_2) 1997 e_1_2_7_19_2 e_1_2_7_17_2 Bigun J. (e_1_2_7_18_2) 2006 e_1_2_7_16_2 Schmid‐Saugeon P. (e_1_2_7_6_2) 2000; 4 e_1_2_7_15_2 e_1_2_7_14_2 e_1_2_7_12_2 e_1_2_7_22_2 e_1_2_7_10_2 e_1_2_7_21_2 Mackie RM. (e_1_2_7_3_2) 1986 e_1_2_7_20_2 Setaro M (e_1_2_7_7_2) 2001; 7 Mark R. (e_1_2_7_13_2) 1993 Golub GH (e_1_2_7_23_2) 1989
References_xml	– reference: Rao AR. A taxonomy for texture description and identification. Berlin: Spring-Verlag, 1990. – reference: She Z, Liu Y, Damato A. Combination of features from skin pattern and ABCD analysis for lesion classification. Skin Res Technol 2007; 13: 25-33. – reference: Kass M, Witkin A. Analyzing oriented patterns. Comput Vis Graph Image Process 1987; 37: 362-385. – reference: Bigun J. Vision with direction: a systematic introduction to image processing and computer vision. Berlin: Springer, 2006. – reference: Theodoridis S, Koutroumbas K. Pattern recognition. San Diego, CA: Academic Press, 2003. – reference: Jemal A, Siegel R, Ward E, Hao Y, Xu J, Thun MJ. Cancer statistics, 2009. CA Cancer J Clin 2009; 59: 225-249. – reference: Schmid-Saugeon P. Symmetry axis computation for almost-symmetrical and asymmetrical objects: application to pigmented skin lesions. Med Image Anal 2000; 4: 269-282. – reference: Sparavigna A, Marazzato R. An image-processing analysis of skin textures. Skin Res Technol 2010; 16: 161-167. – reference: Mackie RM. An illustrated guide to the recognition of early malignant melanoma. Blackwood Pillans & Wilson Ltd. Edinburgh and Department of Dermatology, University of Glasgow, UK: Edinburgh, 1986. – reference: She Z, Fish PJ. Analysis of skin line pattern for lesion classification. Skin Res Technol 2003; 9: 73-80. – reference: Tabatabaie K, Esteki A, Toossi P. Extration of skin lesion texture features based on independent component analysis. Skin Res Technol 2009; 15: 433-439. – reference: Mark R. Roxburgh's common skin diseases. London: Chapman and Hall Medical, 1993. – reference: Hall PN. Clinical diagnosis of melanoma. Diagnosis and management of melanoma in clinical practice. New York, NY: Springer-Verlag, 1992: 35-52. – reference: Golub GH, Loan CFV Matrix computations. Baltimore, MD: Johns Hopkins University Press, 1989. – reference: Setaro M, Sparavigna A. Irregularity skin index (ISI): a tool to evaluate skin surface texture. Skin Res Technol 2001; 7: 159-163. – reference: Claridge E, Hall PN, Keffe M, Allen JP. Shape analysis for classification of malignant melanoma. J Biomed Eng 1992; 14: 229-234. – reference: Round AJ, Duller AWG, Fish PJ. Lesion classification using skin patterning. Skin Res Technol 2000; 6: 183-192. – reference: Deshabhoina SV, Umbaugh SE, Stoecker WV, Moss RH, Srinivasan SK. Melanoma and seborrheic keratosis differentiation using texture features. Skin Res Technol 2003; 9: 348-356. – reference: Foley DH. Consideration of sample and feature size. IEEE Trans Info Theory 1972; 18: 618-626. – reference: Durg A, Stoecker WV, Cookson JP, Umbaugh SE, Moss RH. Identification of variegated colouring in skin tumours. IEEE Eng Med Biol 1993; 12: 71-74. – reference: Wilhelm K, Elsnor P, Berardesca E. Bioengineering of the skin: skin surface imaging and analysis. Boca Raton, FL: CRC Press Inc, 1997. – year: 1986 – volume: 14 start-page: 229 year: 1992 end-page: 234 article-title: Shape analysis for classification of malignant melanoma publication-title: J Biomed Eng – start-page: 35 year: 1992 end-page: 52 – volume: 18 start-page: 618 year: 1972 end-page: 626 article-title: Consideration of sample and feature size publication-title: IEEE Trans Info Theory – volume: 16 start-page: 161 year: 2010 end-page: 167 article-title: An image‐processing analysis of skin textures publication-title: Skin Res Technol – volume: 37 start-page: 362 year: 1987 end-page: 385 article-title: Analyzing oriented patterns publication-title: Comput Vis Graph Image Process – year: 2006 – volume: 13 start-page: 25 year: 2007 end-page: 33 article-title: Combination of features from skin pattern and ABCD analysis for lesion classification publication-title: Skin Res Technol – year: 1989 – year: 2003 – volume: 4 start-page: 269 year: 2000 end-page: 282 article-title: Symmetry axis computation for almost‐symmetrical and asymmetrical objects publication-title: application to pigmented skin lesions – year: 1997 – volume: 6 start-page: 183 year: 2000 end-page: 192 article-title: Lesion classification using skin patterning publication-title: Skin Res Technol – volume: 15 start-page: 433 year: 2009 end-page: 439 article-title: Extration of skin lesion texture features based on independent component analysis publication-title: Skin Res Technol – volume: 9 start-page: 73 year: 2003 end-page: 80 article-title: Analysis of skin line pattern for lesion classification publication-title: Skin Res Technol – volume: 9 start-page: 348 year: 2003 end-page: 356 article-title: Melanoma and seborrheic keratosis differentiation using texture features publication-title: Skin Res Technol – volume: 12 start-page: 71 year: 1993 end-page: 74 article-title: Identification of variegated colouring in skin tumours publication-title: IEEE Eng Med Biol – volume: 59 start-page: 225 year: 2009 end-page: 249 article-title: Cancer statistics, 2009 publication-title: CA Cancer J Clin – year: 1990 – volume: 7 start-page: 159 year: 2001 end-page: 163 article-title: Irregularity skin index (ISI) publication-title: a tool to evaluate skin surface texture – year: 1993 – ident: e_1_2_7_16_2 doi: 10.1007/978-1-4613-9777-9 – ident: e_1_2_7_10_2 doi: 10.1111/j.1600-0846.2009.00383.x – volume-title: An illustrated guide to the recognition of early malignant melanoma year: 1986 ident: e_1_2_7_3_2 – ident: e_1_2_7_15_2 doi: 10.1016/0734-189X(87)90043-0 – volume: 7 start-page: 159 year: 2001 ident: e_1_2_7_7_2 article-title: Irregularity skin index (ISI) publication-title: a tool to evaluate skin surface texture – ident: e_1_2_7_19_2 – ident: e_1_2_7_20_2 doi: 10.1109/TIT.1972.1054863 – ident: e_1_2_7_21_2 doi: 10.1016/B0-12-227240-4/00132-5 – ident: e_1_2_7_9_2 doi: 10.1034/j.1600-0846.2003.00044.x – ident: e_1_2_7_22_2 doi: 10.1111/j.1600-0846.2007.00181.x – volume-title: Matrix computations year: 1989 ident: e_1_2_7_23_2 – ident: e_1_2_7_5_2 doi: 10.1109/51.232345 – ident: e_1_2_7_12_2 doi: 10.1007/978-1-4471-1925-8_4 – ident: e_1_2_7_8_2 doi: 10.1111/j.1600-0846.2009.00413.x – volume-title: Bioengineering of the skin: skin surface imaging and analysis year: 1997 ident: e_1_2_7_11_2 – ident: e_1_2_7_2_2 doi: 10.3322/caac.20006 – ident: e_1_2_7_14_2 doi: 10.1034/j.1600-0846.2000.006004183.x – volume: 4 start-page: 269 year: 2000 ident: e_1_2_7_6_2 article-title: Symmetry axis computation for almost‐symmetrical and asymmetrical objects publication-title: application to pigmented skin lesions – ident: e_1_2_7_17_2 doi: 10.1034/j.1600-0846.2003.00370.x – ident: e_1_2_7_4_2 doi: 10.1016/0141-5425(92)90057-R – volume-title: Roxburgh's common skin diseases year: 1993 ident: e_1_2_7_13_2 – volume-title: Vision with direction: a systematic introduction to image processing and computer vision year: 2006 ident: e_1_2_7_18_2
SSID	ssj0005913
Score	1.9400258
Snippet	Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of... Background/purpose: The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of... The observation that skin pattern tends to be disrupted by malignant skin lesions, but not by benign ones suggests that measurements of skin pattern disruption...
SourceID	proquest pubmed crossref wiley istex
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	206
SubjectTerms	Dermoscopy - instrumentation Dermoscopy - methods Diagnosis, Differential Humans Image Interpretation, Computer-Assisted - instrumentation Image Interpretation, Computer-Assisted - methods lesion classification local isotropy melanoma Melanoma - classification Melanoma - pathology Models, Theoretical Neoplasms - classification Neoplasms - pathology Pattern Recognition, Automated - methods Photophobia Skin - pathology Skin Neoplasms - classification Skin Neoplasms - pathology skin pattern texture analysis
Title	Skin pattern analysis for lesion classification using local isotropy
URI	https://api.istex.fr/ark:/67375/WNG-W01MWPRB-X/fulltext.pdf https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fj.1600-0846.2010.00485.x https://www.ncbi.nlm.nih.gov/pubmed/21208289 https://www.proquest.com/docview/859291878
Volume	17
WOSCitedRecordID	wos000288906900011&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVWIB databaseName: Wiley Online Library Full Collection 2020 customDbUrl: eissn: 1600-0846 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0005913 issn: 0909-752X databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1bT9swFD7a2mliD2OwwbIx5Ae0t0y5-fbIrdvDqFAHat4sx3YmBEqrtkzs33PspIVKPKBpb1EkW8m55HyxP38H4CC1LtOZ0ZhpvPBHcjDn0PUxFq-c58xYkbTNJvhwKMpSnnf8J38WptWHWC24-cwI32uf4Lqaryc5S4IuKVsytApBvyGe7GcYxkUP-iejweXPB8KHbJsly0TGnGblOq_nybnWilXf2_3uKSS6DmxDZRps_s93egdvO3xKDtuA2oIXrtmGN49UC7fh9Vm3H_8eTnzvLjINGp0N0Z3ACUEgTG6cX4cjxqNzT0cKEUA8zf43CQWUXM0ni9lk-vcDXA5OL45_xF1fhthgKaOxSzNujbB1xow2SWUqK7XkhknDWY23XF5x5hjXha2K2rJapo4WmcO6kBvB8h3oNZPGfUQHpNbgB5baWrCCUiEkow4nyo2rqjxJIuBLByjTiZb73hk36tHPC5pMeZMpbzIVTKbuIkhXI6etcMczxnwNPl4N0LNrT3zjVI2H39U4Sc_G56MjVUZAlkGgMB39Hotu3OR2rgRFvJkKLiLYbYNjNRmCBK8XKCOgIQae_Vjq1-gCLz7947jPsNEuhHuW5h70FrNb9wVemT-Lq_lsH17yUux3uXIPZpoO_g
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Zb9NAEB6hBHE8cJTLnPuAeDPytdcjUEIRSVSFVMnbyt5do4rKiZIUlX_PzNoJjdSHCvFmWZqVPYfn8-zsNwBvU-ezMrMlRpos6EgOxhyaPsbklctcWKeSdtiEHI_VfK6Pu3FAdBam5YfYFdwoMsL3mgKcCtL7US6SQEwqti1aheLvEVD2C_Qq3oP-4WRwMvzb8aHback60bHk2Xy_sefKtfayVZ8Uf3EVFN1HtiE1De7_15d6APc6hMo-tC71EG745gDuXuItPIBbo25H_hEc0vQutgwsnQ0rO4oThlCYnXmqxDFL-JwakoIPMGq0_8FCCmWn68VmtVj-fgwng8_TT0dxN5khtpjMeOzTTDqrXJ0JW9qkspXTpZZWaCtFjbd8XknhhSwLVxW1E7VOPS8yj5kht0rkT6DXLBr_DC2QOoufWO5qJQrOldKCe1wot76q8iSJQG4tYGxHW07TM87Mpd8XVJkhlRlSmQkqMxcRpDvJZUvdcQ2Zd8HIO4Fy9ZNa3yQ3s_EXM0vS0ex48tHMI2BbLzAYkLTLUjZ-cb42iiPiTJVUETxtvWO3GMIEYgzUEfDgBNd-LPN9MsWL5_8o9wZuH01HQzP8Ov72Au60ZXHq2XwJvc3q3L-Cm_bX5nS9et2FzB9OPxIG
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9NAEB6hBlVwoFAomPLYA-Jm5Ne-jtA0gGijKLRKbit7d40qKidKUlT-PTNrJzRSDxXiZlnalT0zn-fz7uw3AO9S57MysyUiTRZ0JAcxh66PMXnlMhfWqaRtNiGHQzWd6lHXDojOwrT6EJsFN0JG-F4TwP3c1dsoF0kQJhXrEq1C8Q9IKHsF1wJR2uuPB-cnfys-dNstWSc6ljybbhf23DrXVrbqkeGvb6Oi28w2pKbB3n99qcfwqGOo7GMbUk_gnm_24eEN3cJ92D3tduSfQp-6d7F5UOlsWNlJnDCkwuzS00ocs8TPqSApxACjQvsfLKRQdrGcrRaz-e9ncD44Pjv6EnedGWKLyYzHPs2ks8rVmbClTSpbOV1qaYW2UtR4y-eVFF7IsnBVUTtR69TzIvOYGXKrRH4AO82s8S_QA6mz-Inlrlai4FwpLbjHiXLrqypPkgjk2gPGdrLl1D3j0tz4fUGTGTKZIZOZYDJzHUG6GTlvpTvuMOZ9cPJmQLn4SaVvkpvJ8LOZJOnpZDT-ZKYRsHUUGAQk7bKUjZ9dLY3iyDhTJVUEz9vo2EyGNIEUA3UEPATBnR_LfB-f4cXLfxz3FnZH_YE5-Tr8dggP2lVxKtl8BTurxZV_Dfftr9XFcvGmQ8wfvCkRgQ
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Skin+pattern+analysis+for+lesion+classification+using+local+isotropy&rft.jtitle=Skin+research+and+technology&rft.au=She%2C+Zhishun&rft.au=Excell%2C+Peter+S&rft.date=2011-05-01&rft.eissn=1600-0846&rft.volume=17&rft.issue=2&rft.spage=206&rft_id=info:doi/10.1111%2Fj.1600-0846.2010.00485.x&rft_id=info%3Apmid%2F21208289&rft.externalDocID=21208289
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0909-752X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0909-752X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0909-752X&client=summon