DOI: 10.1118/1.2207129. Computer‐aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours

Computer‐aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours

10.1118/1.2207129

Crossref journal-article

Wiley

Medical Physics (311)

Abstract

We are developing a computer‐aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three‐dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two‐dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface, (2) 3D curvature, which imposes a smoothness constraint in the direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray‐level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run‐length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave‐one‐case‐out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve of . Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.

Bibliography

Way, T. W., Hadjiiski, L. M., Sahiner, B., Chan, H., Cascade, P. N., Kazerooni, E. A., Bogot, N., & Zhou, C. (2006). Computerâaided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours. Medical Physics, 33(7Part1), 2323â2337. Portico.

Authors 8

Ted W. Way (first)
Lubomir M. Hadjiiski (additional)
Berkman Sahiner (additional)
Heang‐Ping Chan (additional)
Philip N. Cascade (additional)
Ella A. Kazerooni (additional)
Naama Bogot (additional)
Chuan Zhou (additional)

References 56 Referenced 177

“American Cancer Society www.cancer.org2005 ” “Cancer Facts & Figures2005.”
10.1148/radiology.214.1.r00ja1473
10.1016/S0140‐6736(99)06093‐6
10.1148/radiol.2223010490
10.1148/radiology.201.3.8939234
10.1378/chest.122.1.15
10.1016/S0140‐6736(97)08229‐9
10.1054/bjoc.2000.1531
10.1148/radiol.2351041662
10.1148/radiol.2263020036
10.1148/radiol.2203001282
10.1148/radiographics.19.5.g99se181303
10.1109/42.974919
10.1148/radiology.197.2.7480683
10.1109/34.368173
10.1109/TMI.2004.830802
10.1109/TMI.2004.834618
10.1118/1.1515762
10.1148/radiol.2261011708
10.1148/radiol.2372041461
10.1148/radiol.2253011376
10.1148/radiol.2361041286
10.1109/42.932744
10.1016/S0895-6111(98)00017-2
10.1118/1.1580485
10.1118/1.598603
10.1016/j.acra.2005.01.018
10.1118/1.1573210
10.1109/23.708321
10.2214/ajr.183.5.1831209
10.1118/1.1543575
10.1109/TMI.2005.852048
10.1148/radiol.2323032035
10.1118/1.597829
10.1007/BF00133570
10.1016/1049‐9660(92)90003‐L
10.1088/0031‐9155/42/9/013
10.1109/42.974922
10.1016/1049‐9660(91)90028‐N
T. W.Way B.Sahiner L.Hadjiiski H.‐P.Chan N.Bogot P.Cascade E.Kazerooni andJ. A.Fessler “Segmentation of pulmonary nodules with 3D active contour model for computer‐aided diagnosis ” in “Radiological Society of North America Scientific Assembly and Annual Meeting Program ” Oakbrook IL: RSNA 2003. Chicago IL November 30–December 5.
10.1109/TMI.2003.817785
10.1148/radiology.186.2.8421743
10.1148/radiographics.20.1.g00ja0343
10.1148/radiology.160.2.3726106
10.1016/0149-936X(81)90075-8
10.1118/1.598228
10.1016/S0146-664X(75)80008-6
10.1016/0167-8655(91)80014-2
10.1088/0031‐9155/40/5/010
10.1080/00401706.1962.10490033 / Technometrics / “Sequential application of simplex designs in optimization and evolutionary operation,” by Spendley W. (1962)
10.1097/00004424-198609000-00009
10.1088/0031‐9155/43/10/014
10.1118/1.1737492
10.1002/(SICI)1097-0258(19980515)17:9<1033::AID-SIM784>3.0.CO;2-Z
10.1378/chest.123.1_suppl.89S
10.1164/ajrccm.162.3.9812152

Dates

Type	When
Created	19 years, 1 month ago (July 12, 2006, 6:29 p.m.)
Deposited	1 year, 10 months ago (Oct. 3, 2023, 1:25 p.m.)
Indexed	4 weeks, 2 days ago (July 25, 2025, 6:17 a.m.)
Issued	19 years, 2 months ago (June 19, 2006)
Published	19 years, 2 months ago (June 19, 2006)
Published Online	19 years, 2 months ago (June 19, 2006)
Published Print	19 years, 1 month ago (July 1, 2006)

Funders 0

None

BibTeX

@article{Way_2006, title={Computer‐aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours}, volume={33}, ISSN={2473-4209}, url={http://dx.doi.org/10.1118/1.2207129}, DOI={10.1118/1.2207129}, number={7Part1}, journal={Medical Physics}, publisher={Wiley}, author={Way, Ted W. and Hadjiiski, Lubomir M. and Sahiner, Berkman and Chan, Heang‐Ping and Cascade, Philip N. and Kazerooni, Ella A. and Bogot, Naama and Zhou, Chuan}, year={2006}, month=jun, pages={2323–2337} }

JSON

{
  "indexed": {
    "date-parts": [
      [
        2025,
        7,
        25
      ]
    ],
    "date-time": "2025-07-25T10:17:42Z",
    "timestamp": 1753438662068
  },
  "reference-count": 56,
  "publisher": "Wiley",
  "issue": "7Part1",
  "license": [
    {
      "start": {
        "date-parts": [
          [
            2006,
            6,
            19
          ]
        ],
        "date-time": "2006-06-19T00:00:00Z",
        "timestamp": 1150675200000
      },
      "content-version": "vor",
      "delay-in-days": 0,
      "URL": "http://onlinelibrary.wiley.com/termsAndConditions#vor"
    }
  ],
  "content-domain": {
    "domain": [],
    "crossmark-restriction": false
  },
  "published-print": {
    "date-parts": [
      [
        2006,
        7
      ]
    ]
  },
  "abstract": "<jats:p>We are developing a computer\u2010aided diagnosis (CAD) system to classify malignant and benign lung nodules found on CT scans. A fully automated system was designed to segment the nodule from its surrounding structured background in a local volume of interest (VOI) and to extract image features for classification. Image segmentation was performed with a three\u2010dimensional (3D) active contour (AC) method. A data set of 96 lung nodules (44 malignant, 52 benign) from 58 patients was used in this study. The 3D AC model is based on two\u2010dimensional AC with the addition of three new energy components to take advantage of 3D information: (1) 3D gradient, which guides the active contour to seek the object surface, (2) 3D curvature, which imposes a smoothness constraint in the <jats:inline-graphic xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"graphic/mp7129-math-0001.png\" xlink:title=\"urn:x-wiley:0094-2405:media:mp7129:mp7129-math-0001\" /> direction, and (3) mask energy, which penalizes contours that grow beyond the pleura or thoracic wall. The search for the best energy weights in the 3D AC model was guided by a simplex optimization method. Morphological and gray\u2010level features were extracted from the segmented nodule. The rubber band straightening transform (RBST) was applied to the shell of voxels surrounding the nodule. Texture features based on run\u2010length statistics were extracted from the RBST image. A linear discriminant analysis classifier with stepwise feature selection was designed using a second simplex optimization to select the most effective features. Leave\u2010one\u2010case\u2010out resampling was used to train and test the CAD system. The system achieved a test area under the receiver operating characteristic curve <jats:inline-graphic xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"graphic/mp7129-math-0002.png\" xlink:title=\"urn:x-wiley:0094-2405:media:mp7129:mp7129-math-0002\" /> of <jats:inline-graphic xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"graphic/mp7129-math-0003.png\" xlink:title=\"urn:x-wiley:0094-2405:media:mp7129:mp7129-math-0003\" />. Our preliminary results indicate that use of the 3D AC model and the 3D texture features surrounding the nodule is a promising approach to the segmentation and classification of lung nodules with CAD. The segmentation performance of the 3D AC model trained with our data set was evaluated with 23 nodules available in the Lung Image Database Consortium (LIDC). The lung nodule volumes segmented by the 3D AC model for best classification were generally larger than those outlined by the LIDC radiologists using visual judgment of nodule boundaries.</jats:p>",
  "DOI": "10.1118/1.2207129",
  "type": "journal-article",
  "created": {
    "date-parts": [
      [
        2006,
        7,
        12
      ]
    ],
    "date-time": "2006-07-12T22:29:20Z",
    "timestamp": 1152743360000
  },
  "page": "2323-2337",
  "source": "Crossref",
  "is-referenced-by-count": 177,
  "title": "Computer\u2010aided diagnosis of pulmonary nodules on CT scans: Segmentation and classification using 3D active contours",
  "prefix": "10.1002",
  "volume": "33",
  "author": [
    {
      "given": "Ted W.",
      "family": "Way",
      "sequence": "first",
      "affiliation": []
    },
    {
      "given": "Lubomir M.",
      "family": "Hadjiiski",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Berkman",
      "family": "Sahiner",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Heang\u2010Ping",
      "family": "Chan",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Philip N.",
      "family": "Cascade",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Ella A.",
      "family": "Kazerooni",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Naama",
      "family": "Bogot",
      "sequence": "additional",
      "affiliation": []
    },
    {
      "given": "Chuan",
      "family": "Zhou",
      "sequence": "additional",
      "affiliation": []
    }
  ],
  "member": "311",
  "published-online": {
    "date-parts": [
      [
        2006,
        6,
        19
      ]
    ]
  },
  "reference": [
    {
      "key": "e_1_2_9_2_1",
      "unstructured": "\u201cAmerican Cancer Society www.cancer.org2005 \u201d \u201cCancer Facts & Figures2005.\u201d"
    },
    {
      "key": "e_1_2_9_3_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiology.214.1.r00ja1473"
    },
    {
      "key": "e_1_2_9_4_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0140\u20106736(99)06093\u20106"
    },
    {
      "key": "e_1_2_9_5_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2223010490"
    },
    {
      "key": "e_1_2_9_6_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiology.201.3.8939234"
    },
    {
      "key": "e_1_2_9_7_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1378/chest.122.1.15"
    },
    {
      "key": "e_1_2_9_8_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0140\u20106736(97)08229\u20109"
    },
    {
      "key": "e_1_2_9_9_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1054/bjoc.2000.1531"
    },
    {
      "key": "e_1_2_9_10_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2351041662"
    },
    {
      "key": "e_1_2_9_11_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2263020036"
    },
    {
      "key": "e_1_2_9_12_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2203001282"
    },
    {
      "key": "e_1_2_9_13_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiographics.19.5.g99se181303"
    },
    {
      "key": "e_1_2_9_14_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/42.974919"
    },
    {
      "key": "e_1_2_9_15_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiology.197.2.7480683"
    },
    {
      "key": "e_1_2_9_16_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/34.368173"
    },
    {
      "key": "e_1_2_9_17_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/TMI.2004.830802"
    },
    {
      "key": "e_1_2_9_18_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/TMI.2004.834618"
    },
    {
      "key": "e_1_2_9_19_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.1515762"
    },
    {
      "key": "e_1_2_9_20_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2261011708"
    },
    {
      "key": "e_1_2_9_21_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2372041461"
    },
    {
      "key": "e_1_2_9_22_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2253011376"
    },
    {
      "key": "e_1_2_9_23_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2361041286"
    },
    {
      "key": "e_1_2_9_24_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/42.932744"
    },
    {
      "key": "e_1_2_9_25_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0895-6111(98)00017-2"
    },
    {
      "key": "e_1_2_9_26_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.1580485"
    },
    {
      "key": "e_1_2_9_27_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.598603"
    },
    {
      "key": "e_1_2_9_28_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/j.acra.2005.01.018"
    },
    {
      "key": "e_1_2_9_29_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.1573210"
    },
    {
      "key": "e_1_2_9_30_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/23.708321"
    },
    {
      "key": "e_1_2_9_31_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.2214/ajr.183.5.1831209"
    },
    {
      "key": "e_1_2_9_32_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.1543575"
    },
    {
      "key": "e_1_2_9_33_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/TMI.2005.852048"
    },
    {
      "key": "e_1_2_9_34_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiol.2323032035"
    },
    {
      "key": "e_1_2_9_35_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.597829"
    },
    {
      "key": "e_1_2_9_36_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1007/BF00133570"
    },
    {
      "key": "e_1_2_9_37_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/1049\u20109660(92)90003\u2010L"
    },
    {
      "key": "e_1_2_9_38_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1088/0031\u20109155/42/9/013"
    },
    {
      "key": "e_1_2_9_39_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/42.974922"
    },
    {
      "key": "e_1_2_9_40_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/1049\u20109660(91)90028\u2010N"
    },
    {
      "key": "e_1_2_9_41_1",
      "unstructured": "T. W.Way B.Sahiner L.Hadjiiski H.\u2010P.Chan N.Bogot P.Cascade E.Kazerooni andJ. A.Fessler \u201cSegmentation of pulmonary nodules with 3D active contour model for computer\u2010aided diagnosis \u201d in \u201cRadiological Society of North America Scientific Assembly and Annual Meeting Program \u201d Oakbrook IL: RSNA 2003. Chicago IL November 30\u2013December 5."
    },
    {
      "key": "e_1_2_9_42_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1109/TMI.2003.817785"
    },
    {
      "key": "e_1_2_9_43_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiology.186.2.8421743"
    },
    {
      "key": "e_1_2_9_44_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiographics.20.1.g00ja0343"
    },
    {
      "key": "e_1_2_9_45_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1148/radiology.160.2.3726106"
    },
    {
      "key": "e_1_2_9_46_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/0149-936X(81)90075-8"
    },
    {
      "key": "e_1_2_9_47_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.598228"
    },
    {
      "key": "e_1_2_9_48_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/S0146-664X(75)80008-6"
    },
    {
      "key": "e_1_2_9_49_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1016/0167-8655(91)80014-2"
    },
    {
      "key": "e_1_2_9_50_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1088/0031\u20109155/40/5/010"
    },
    {
      "key": "e_1_2_9_51_1",
      "doi-asserted-by": "crossref",
      "first-page": "441",
      "DOI": "10.1080/00401706.1962.10490033",
      "article-title": "\u201cSequential application of simplex designs in optimization and evolutionary operation,\u201d",
      "volume": "4",
      "author": "Spendley W.",
      "year": "1962",
      "journal-title": "Technometrics"
    },
    {
      "key": "e_1_2_9_52_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1097/00004424-198609000-00009"
    },
    {
      "key": "e_1_2_9_53_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1088/0031\u20109155/43/10/014"
    },
    {
      "key": "e_1_2_9_54_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1118/1.1737492"
    },
    {
      "key": "e_1_2_9_55_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1002/(SICI)1097-0258(19980515)17:9<1033::AID-SIM784>3.0.CO;2-Z"
    },
    {
      "key": "e_1_2_9_56_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1378/chest.123.1_suppl.89S"
    },
    {
      "key": "e_1_2_9_57_1",
      "doi-asserted-by": "publisher",
      "DOI": "10.1164/ajrccm.162.3.9812152"
    }
  ],
  "container-title": "Medical Physics",
  "original-title": [],
  "language": "en",
  "link": [
    {
      "URL": "https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1118%2F1.2207129",
      "content-type": "application/pdf",
      "content-version": "vor",
      "intended-application": "text-mining"
    },
    {
      "URL": "https://api.wiley.com/onlinelibrary/tdm/v1/articles/10.1118%2F1.2207129",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "text-mining"
    },
    {
      "URL": "https://aapm.onlinelibrary.wiley.com/doi/pdf/10.1118/1.2207129",
      "content-type": "unspecified",
      "content-version": "vor",
      "intended-application": "similarity-checking"
    }
  ],
  "deposited": {
    "date-parts": [
      [
        2023,
        10,
        3
      ]
    ],
    "date-time": "2023-10-03T17:25:15Z",
    "timestamp": 1696353915000
  },
  "score": 1,
  "resource": {
    "primary": {
      "URL": "https://aapm.onlinelibrary.wiley.com/doi/10.1118/1.2207129"
    }
  },
  "subtitle": [],
  "short-title": [],
  "issued": {
    "date-parts": [
      [
        2006,
        6,
        19
      ]
    ]
  },
  "references-count": 56,
  "journal-issue": {
    "issue": "7Part1",
    "published-print": {
      "date-parts": [
        [
          2006,
          7
        ]
      ]
    }
  },
  "alternative-id": [
    "10.1118/1.2207129"
  ],
  "URL": "http://dx.doi.org/10.1118/1.2207129",
  "relation": {},
  "ISSN": [
    "0094-2405",
    "2473-4209"
  ],
  "subject": [],
  "container-title-short": "Medical Physics",
  "published": {
    "date-parts": [
      [
        2006,
        6,
        19
      ]
    ]
  }
}