A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists
Purpose In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system...
Gespeichert in:
| Veröffentlicht in: | International journal for computer assisted radiology and surgery 2017-05, Vol.12 (5), p.767-776 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 776 |
|---|---|
| container_issue | 5 |
| container_start_page | 767 |
| container_title | International journal for computer assisted radiology and surgery |
| container_volume | 12 |
| creator | Kawagishi, Masami Chen, Bin Furukawa, Daisuke Sekiguchi, Hiroyuki Sakai, Koji Kubo, Takeshi Yakami, Masahiro Fujimoto, Koji Sakamoto, Ryo Emoto, Yutaka Aoyama, Gakuto Iizuka, Yoshio Nakagomi, Keita Yamamoto, Hiroyuki Togashi, Kaori |
| description | Purpose
In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system using derived imaging findings based on calculated image features, in which the system only requires few user operations. The purpose of this study is to check whether calculated image features (CFT) or derived imaging findings (DFD) can represent information in imaging findings annotated by radiologists (AFD).
Methods
We calculate 2282 image features and derive 39 imaging findings by using information on a nodule position and its type (solid or ground-glass). These image features are categorized into shape features, texture features and imaging findings-specific features. Each imaging finding is derived based on each corresponding classifier using random forest. To check whether CFT or DFD can represent information in AFD, under an assumption that the accuracies of classifiers are the same if information included in input is the same, we constructed classifiers by using various types of information (CTT, DFD and AFD) and compared accuracies on an inferred diagnosis of a nodule. We employ SVM with RBF kernel as classifier to infer a diagnosis name.
Results
Accuracies of classifiers using DFD, CFT, AFD and CFT
+
AFD were 0.613, 0.577, 0.773 and 0.790, respectively. Concordance rates between DFD and AFD of shape findings, texture findings and surrounding findings were 0.644, 0.871 and 0.768, respectively.
Conclusions
The results suggest that CFT and AFD are similar information and CFT represent only a portion of AFD. Particularly, CFT did not contain shape information in AFD. In order to decrease an interaction of radiologists, a development of a method which overcomes these problems is necessary. |
| doi_str_mv | 10.1007/s11548-017-1554-0 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1876814397</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1895658904</sourcerecordid><originalsourceid>FETCH-LOGICAL-c508t-b7d7c9de1b0a40a219d0055c496c278188ba20798c6125ae6c7d7df56f35743d3</originalsourceid><addsrcrecordid>eNp1kU2L1jAUhYMozof-ADcScOOmmrRJk7obBr9gwI2uy22Slgxt8pqbIO8Pm_9n3uk4iODqhnOfc5JwCHnF2TvOmHqPnEuhG8ZVw6UUDXtCzrnuedOLdnj6eObsjFwg3jImpOrkc3LW6lbLrtPn5O6KYi72SONMTdwOJbvUgLfOUuthCRE90jkmeijrFgOkIw3RltV9uMcheYyBTi7_ci5QswKin72B7KsMxpQExjukBX1YqIHVlBVyTfcbLI7ODnJJdQ9hl07U7IOt8ySGmO_p6UgTWB_XuHjM-II8m2FF9_JhXpIfnz5-v_7S3Hz7_PX66qYxkuncTMoqM1jHJwaCQcsHy5iURgy9aZXmWk_QMjVo0_NWgutNNdhZ9nMnlehsd0ne7rmHFH8Wh3ncPBq3rhBcLDhyrXrNRTeoir75B72NJYX6ukoNspd6YKJSfKdMiojJzeMh1W-n48jZeOp03Dsda6fjqdORVc_rh-Qybc4-Ov6UWIF2B7CuwuLSX1f_N_U3Raawpg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1895658904</pqid></control><display><type>article</type><title>A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists</title><source>MEDLINE</source><source>Springer Nature - Complete Springer Journals</source><creator>Kawagishi, Masami ; Chen, Bin ; Furukawa, Daisuke ; Sekiguchi, Hiroyuki ; Sakai, Koji ; Kubo, Takeshi ; Yakami, Masahiro ; Fujimoto, Koji ; Sakamoto, Ryo ; Emoto, Yutaka ; Aoyama, Gakuto ; Iizuka, Yoshio ; Nakagomi, Keita ; Yamamoto, Hiroyuki ; Togashi, Kaori</creator><creatorcontrib>Kawagishi, Masami ; Chen, Bin ; Furukawa, Daisuke ; Sekiguchi, Hiroyuki ; Sakai, Koji ; Kubo, Takeshi ; Yakami, Masahiro ; Fujimoto, Koji ; Sakamoto, Ryo ; Emoto, Yutaka ; Aoyama, Gakuto ; Iizuka, Yoshio ; Nakagomi, Keita ; Yamamoto, Hiroyuki ; Togashi, Kaori</creatorcontrib><description>Purpose
In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system using derived imaging findings based on calculated image features, in which the system only requires few user operations. The purpose of this study is to check whether calculated image features (CFT) or derived imaging findings (DFD) can represent information in imaging findings annotated by radiologists (AFD).
Methods
We calculate 2282 image features and derive 39 imaging findings by using information on a nodule position and its type (solid or ground-glass). These image features are categorized into shape features, texture features and imaging findings-specific features. Each imaging finding is derived based on each corresponding classifier using random forest. To check whether CFT or DFD can represent information in AFD, under an assumption that the accuracies of classifiers are the same if information included in input is the same, we constructed classifiers by using various types of information (CTT, DFD and AFD) and compared accuracies on an inferred diagnosis of a nodule. We employ SVM with RBF kernel as classifier to infer a diagnosis name.
Results
Accuracies of classifiers using DFD, CFT, AFD and CFT
+
AFD were 0.613, 0.577, 0.773 and 0.790, respectively. Concordance rates between DFD and AFD of shape findings, texture findings and surrounding findings were 0.644, 0.871 and 0.768, respectively.
Conclusions
The results suggest that CFT and AFD are similar information and CFT represent only a portion of AFD. Particularly, CFT did not contain shape information in AFD. In order to decrease an interaction of radiologists, a development of a method which overcomes these problems is necessary.</description><identifier>ISSN: 1861-6410</identifier><identifier>EISSN: 1861-6429</identifier><identifier>DOI: 10.1007/s11548-017-1554-0</identifier><identifier>PMID: 28285338</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Adolescent ; Adult ; Aged ; Aged, 80 and over ; Algorithms ; Biopsy ; Child ; Child, Preschool ; Classifiers ; Computer Imaging ; Computer Science ; Diagnosis ; Diagnosis, Computer-Assisted - methods ; Female ; Health Informatics ; Humans ; Image classification ; Imaging ; Infant ; Infant, Newborn ; Lung Neoplasms - diagnostic imaging ; Male ; Mathematical analysis ; Medicine ; Medicine & Public Health ; Middle Aged ; Neoplasm Metastasis ; Observer Variation ; Original Article ; Pattern Recognition and Graphics ; Radiographic Image Interpretation, Computer-Assisted - methods ; Radiologists ; Radiology ; Radiology - methods ; Reproducibility of Results ; Solitary Pulmonary Nodule - diagnostic imaging ; Support Vector Machine ; Surgery ; Texture ; Tomography, X-Ray Computed - methods ; Vision ; Young Adult</subject><ispartof>International journal for computer assisted radiology and surgery, 2017-05, Vol.12 (5), p.767-776</ispartof><rights>CARS 2017</rights><rights>Copyright Springer Science & Business Media 2017</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c508t-b7d7c9de1b0a40a219d0055c496c278188ba20798c6125ae6c7d7df56f35743d3</citedby><cites>FETCH-LOGICAL-c508t-b7d7c9de1b0a40a219d0055c496c278188ba20798c6125ae6c7d7df56f35743d3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11548-017-1554-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11548-017-1554-0$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,776,780,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/28285338$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Kawagishi, Masami</creatorcontrib><creatorcontrib>Chen, Bin</creatorcontrib><creatorcontrib>Furukawa, Daisuke</creatorcontrib><creatorcontrib>Sekiguchi, Hiroyuki</creatorcontrib><creatorcontrib>Sakai, Koji</creatorcontrib><creatorcontrib>Kubo, Takeshi</creatorcontrib><creatorcontrib>Yakami, Masahiro</creatorcontrib><creatorcontrib>Fujimoto, Koji</creatorcontrib><creatorcontrib>Sakamoto, Ryo</creatorcontrib><creatorcontrib>Emoto, Yutaka</creatorcontrib><creatorcontrib>Aoyama, Gakuto</creatorcontrib><creatorcontrib>Iizuka, Yoshio</creatorcontrib><creatorcontrib>Nakagomi, Keita</creatorcontrib><creatorcontrib>Yamamoto, Hiroyuki</creatorcontrib><creatorcontrib>Togashi, Kaori</creatorcontrib><title>A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists</title><title>International journal for computer assisted radiology and surgery</title><addtitle>Int J CARS</addtitle><addtitle>Int J Comput Assist Radiol Surg</addtitle><description>Purpose
In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system using derived imaging findings based on calculated image features, in which the system only requires few user operations. The purpose of this study is to check whether calculated image features (CFT) or derived imaging findings (DFD) can represent information in imaging findings annotated by radiologists (AFD).
Methods
We calculate 2282 image features and derive 39 imaging findings by using information on a nodule position and its type (solid or ground-glass). These image features are categorized into shape features, texture features and imaging findings-specific features. Each imaging finding is derived based on each corresponding classifier using random forest. To check whether CFT or DFD can represent information in AFD, under an assumption that the accuracies of classifiers are the same if information included in input is the same, we constructed classifiers by using various types of information (CTT, DFD and AFD) and compared accuracies on an inferred diagnosis of a nodule. We employ SVM with RBF kernel as classifier to infer a diagnosis name.
Results
Accuracies of classifiers using DFD, CFT, AFD and CFT
+
AFD were 0.613, 0.577, 0.773 and 0.790, respectively. Concordance rates between DFD and AFD of shape findings, texture findings and surrounding findings were 0.644, 0.871 and 0.768, respectively.
Conclusions
The results suggest that CFT and AFD are similar information and CFT represent only a portion of AFD. Particularly, CFT did not contain shape information in AFD. In order to decrease an interaction of radiologists, a development of a method which overcomes these problems is necessary.</description><subject>Adolescent</subject><subject>Adult</subject><subject>Aged</subject><subject>Aged, 80 and over</subject><subject>Algorithms</subject><subject>Biopsy</subject><subject>Child</subject><subject>Child, Preschool</subject><subject>Classifiers</subject><subject>Computer Imaging</subject><subject>Computer Science</subject><subject>Diagnosis</subject><subject>Diagnosis, Computer-Assisted - methods</subject><subject>Female</subject><subject>Health Informatics</subject><subject>Humans</subject><subject>Image classification</subject><subject>Imaging</subject><subject>Infant</subject><subject>Infant, Newborn</subject><subject>Lung Neoplasms - diagnostic imaging</subject><subject>Male</subject><subject>Mathematical analysis</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Middle Aged</subject><subject>Neoplasm Metastasis</subject><subject>Observer Variation</subject><subject>Original Article</subject><subject>Pattern Recognition and Graphics</subject><subject>Radiographic Image Interpretation, Computer-Assisted - methods</subject><subject>Radiologists</subject><subject>Radiology</subject><subject>Radiology - methods</subject><subject>Reproducibility of Results</subject><subject>Solitary Pulmonary Nodule - diagnostic imaging</subject><subject>Support Vector Machine</subject><subject>Surgery</subject><subject>Texture</subject><subject>Tomography, X-Ray Computed - methods</subject><subject>Vision</subject><subject>Young Adult</subject><issn>1861-6410</issn><issn>1861-6429</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp1kU2L1jAUhYMozof-ADcScOOmmrRJk7obBr9gwI2uy22Slgxt8pqbIO8Pm_9n3uk4iODqhnOfc5JwCHnF2TvOmHqPnEuhG8ZVw6UUDXtCzrnuedOLdnj6eObsjFwg3jImpOrkc3LW6lbLrtPn5O6KYi72SONMTdwOJbvUgLfOUuthCRE90jkmeijrFgOkIw3RltV9uMcheYyBTi7_ci5QswKin72B7KsMxpQExjukBX1YqIHVlBVyTfcbLI7ODnJJdQ9hl07U7IOt8ySGmO_p6UgTWB_XuHjM-II8m2FF9_JhXpIfnz5-v_7S3Hz7_PX66qYxkuncTMoqM1jHJwaCQcsHy5iURgy9aZXmWk_QMjVo0_NWgutNNdhZ9nMnlehsd0ne7rmHFH8Wh3ncPBq3rhBcLDhyrXrNRTeoir75B72NJYX6ukoNspd6YKJSfKdMiojJzeMh1W-n48jZeOp03Dsda6fjqdORVc_rh-Qybc4-Ov6UWIF2B7CuwuLSX1f_N_U3Raawpg</recordid><startdate>20170501</startdate><enddate>20170501</enddate><creator>Kawagishi, Masami</creator><creator>Chen, Bin</creator><creator>Furukawa, Daisuke</creator><creator>Sekiguchi, Hiroyuki</creator><creator>Sakai, Koji</creator><creator>Kubo, Takeshi</creator><creator>Yakami, Masahiro</creator><creator>Fujimoto, Koji</creator><creator>Sakamoto, Ryo</creator><creator>Emoto, Yutaka</creator><creator>Aoyama, Gakuto</creator><creator>Iizuka, Yoshio</creator><creator>Nakagomi, Keita</creator><creator>Yamamoto, Hiroyuki</creator><creator>Togashi, Kaori</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20170501</creationdate><title>A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists</title><author>Kawagishi, Masami ; Chen, Bin ; Furukawa, Daisuke ; Sekiguchi, Hiroyuki ; Sakai, Koji ; Kubo, Takeshi ; Yakami, Masahiro ; Fujimoto, Koji ; Sakamoto, Ryo ; Emoto, Yutaka ; Aoyama, Gakuto ; Iizuka, Yoshio ; Nakagomi, Keita ; Yamamoto, Hiroyuki ; Togashi, Kaori</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c508t-b7d7c9de1b0a40a219d0055c496c278188ba20798c6125ae6c7d7df56f35743d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Adolescent</topic><topic>Adult</topic><topic>Aged</topic><topic>Aged, 80 and over</topic><topic>Algorithms</topic><topic>Biopsy</topic><topic>Child</topic><topic>Child, Preschool</topic><topic>Classifiers</topic><topic>Computer Imaging</topic><topic>Computer Science</topic><topic>Diagnosis</topic><topic>Diagnosis, Computer-Assisted - methods</topic><topic>Female</topic><topic>Health Informatics</topic><topic>Humans</topic><topic>Image classification</topic><topic>Imaging</topic><topic>Infant</topic><topic>Infant, Newborn</topic><topic>Lung Neoplasms - diagnostic imaging</topic><topic>Male</topic><topic>Mathematical analysis</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Middle Aged</topic><topic>Neoplasm Metastasis</topic><topic>Observer Variation</topic><topic>Original Article</topic><topic>Pattern Recognition and Graphics</topic><topic>Radiographic Image Interpretation, Computer-Assisted - methods</topic><topic>Radiologists</topic><topic>Radiology</topic><topic>Radiology - methods</topic><topic>Reproducibility of Results</topic><topic>Solitary Pulmonary Nodule - diagnostic imaging</topic><topic>Support Vector Machine</topic><topic>Surgery</topic><topic>Texture</topic><topic>Tomography, X-Ray Computed - methods</topic><topic>Vision</topic><topic>Young Adult</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kawagishi, Masami</creatorcontrib><creatorcontrib>Chen, Bin</creatorcontrib><creatorcontrib>Furukawa, Daisuke</creatorcontrib><creatorcontrib>Sekiguchi, Hiroyuki</creatorcontrib><creatorcontrib>Sakai, Koji</creatorcontrib><creatorcontrib>Kubo, Takeshi</creatorcontrib><creatorcontrib>Yakami, Masahiro</creatorcontrib><creatorcontrib>Fujimoto, Koji</creatorcontrib><creatorcontrib>Sakamoto, Ryo</creatorcontrib><creatorcontrib>Emoto, Yutaka</creatorcontrib><creatorcontrib>Aoyama, Gakuto</creatorcontrib><creatorcontrib>Iizuka, Yoshio</creatorcontrib><creatorcontrib>Nakagomi, Keita</creatorcontrib><creatorcontrib>Yamamoto, Hiroyuki</creatorcontrib><creatorcontrib>Togashi, Kaori</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>International journal for computer assisted radiology and surgery</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kawagishi, Masami</au><au>Chen, Bin</au><au>Furukawa, Daisuke</au><au>Sekiguchi, Hiroyuki</au><au>Sakai, Koji</au><au>Kubo, Takeshi</au><au>Yakami, Masahiro</au><au>Fujimoto, Koji</au><au>Sakamoto, Ryo</au><au>Emoto, Yutaka</au><au>Aoyama, Gakuto</au><au>Iizuka, Yoshio</au><au>Nakagomi, Keita</au><au>Yamamoto, Hiroyuki</au><au>Togashi, Kaori</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists</atitle><jtitle>International journal for computer assisted radiology and surgery</jtitle><stitle>Int J CARS</stitle><addtitle>Int J Comput Assist Radiol Surg</addtitle><date>2017-05-01</date><risdate>2017</risdate><volume>12</volume><issue>5</issue><spage>767</spage><epage>776</epage><pages>767-776</pages><issn>1861-6410</issn><eissn>1861-6429</eissn><abstract>Purpose
In our previous study, we developed a computer-aided diagnosis (CADx) system using imaging findings annotated by radiologists. The system, however, requires radiologists to input many imaging findings. In order to reduce such an interaction of radiologists, we further developed a CADx system using derived imaging findings based on calculated image features, in which the system only requires few user operations. The purpose of this study is to check whether calculated image features (CFT) or derived imaging findings (DFD) can represent information in imaging findings annotated by radiologists (AFD).
Methods
We calculate 2282 image features and derive 39 imaging findings by using information on a nodule position and its type (solid or ground-glass). These image features are categorized into shape features, texture features and imaging findings-specific features. Each imaging finding is derived based on each corresponding classifier using random forest. To check whether CFT or DFD can represent information in AFD, under an assumption that the accuracies of classifiers are the same if information included in input is the same, we constructed classifiers by using various types of information (CTT, DFD and AFD) and compared accuracies on an inferred diagnosis of a nodule. We employ SVM with RBF kernel as classifier to infer a diagnosis name.
Results
Accuracies of classifiers using DFD, CFT, AFD and CFT
+
AFD were 0.613, 0.577, 0.773 and 0.790, respectively. Concordance rates between DFD and AFD of shape findings, texture findings and surrounding findings were 0.644, 0.871 and 0.768, respectively.
Conclusions
The results suggest that CFT and AFD are similar information and CFT represent only a portion of AFD. Particularly, CFT did not contain shape information in AFD. In order to decrease an interaction of radiologists, a development of a method which overcomes these problems is necessary.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><pmid>28285338</pmid><doi>10.1007/s11548-017-1554-0</doi><tpages>10</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1861-6410 |
| ispartof | International journal for computer assisted radiology and surgery, 2017-05, Vol.12 (5), p.767-776 |
| issn | 1861-6410 1861-6429 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1876814397 |
| source | MEDLINE; Springer Nature - Complete Springer Journals |
| subjects | Adolescent Adult Aged Aged, 80 and over Algorithms Biopsy Child Child, Preschool Classifiers Computer Imaging Computer Science Diagnosis Diagnosis, Computer-Assisted - methods Female Health Informatics Humans Image classification Imaging Infant Infant, Newborn Lung Neoplasms - diagnostic imaging Male Mathematical analysis Medicine Medicine & Public Health Middle Aged Neoplasm Metastasis Observer Variation Original Article Pattern Recognition and Graphics Radiographic Image Interpretation, Computer-Assisted - methods Radiologists Radiology Radiology - methods Reproducibility of Results Solitary Pulmonary Nodule - diagnostic imaging Support Vector Machine Surgery Texture Tomography, X-Ray Computed - methods Vision Young Adult |
| title | A study of computer-aided diagnosis for pulmonary nodule: comparison between classification accuracies using calculated image features and imaging findings annotated by radiologists |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T20%3A27%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20study%20of%20computer-aided%20diagnosis%20for%20pulmonary%20nodule:%20comparison%20between%20classification%20accuracies%20using%20calculated%20image%20features%20and%20imaging%20findings%20annotated%20by%20radiologists&rft.jtitle=International%20journal%20for%20computer%20assisted%20radiology%20and%20surgery&rft.au=Kawagishi,%20Masami&rft.date=2017-05-01&rft.volume=12&rft.issue=5&rft.spage=767&rft.epage=776&rft.pages=767-776&rft.issn=1861-6410&rft.eissn=1861-6429&rft_id=info:doi/10.1007/s11548-017-1554-0&rft_dat=%3Cproquest_cross%3E1895658904%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1895658904&rft_id=info:pmid/28285338&rfr_iscdi=true |