Performance of a computer-aided digital dermoscopic image analyzer for melanoma detection in 1,076 pigmented skin lesion biopsies

被引:7
|
作者
Del Rosario, Francis [1 ]
Farahi, Jessica M. [1 ]
Drendel, Jesse [2 ]
Buntinx-Krieg, Talayesa [3 ]
Caravaglio, Joseph [3 ]
Domozych, Renee [3 ]
Chapman, Stephanie [4 ]
Braunberger, Taylor [5 ]
Dellavalle, Robert P. [1 ]
Norris, David A. [1 ]
Fathi, Ramin [1 ]
Alkousakis, Theodore [1 ]
机构
[1] Univ Colorado, Sch Med, Aurora, CO USA
[2] Colorado State Univ, Ft Collins, CO 80523 USA
[3] Univ Cent Florida, Coll Med, Orlando, FL 32816 USA
[4] Michigan State Univ, Coll Human Med, Grand Rapids, MI USA
[5] Univ North Dakota, Sch Med, Grand Forks, ND USA
关键词
computer-aided diagnosis; diagnostic accuracy; digital dermoscopy; image analysis; melanoma; pigmented skin lesions; screening; skin cancer; test sensitivity; EPILUMINESCENCE MICROSCOPY; DIFFERENTIAL-DIAGNOSIS; SYSTEM; CLASSIFICATION; MULTICENTER; INSTRUMENTS; CLINICIAN; VS;
D O I
10.1016/j.jaad.2017.01.049
中图分类号
R75 [皮肤病学与性病学];
学科分类号
100206 ;
摘要
Background: Digital dermoscopic image analysis of pigmented skin lesions (PSLs) has become increasingly popular, despite its unclear clinical utility. Unbiased, high-powered studies investigating the efficacy of commercially available systems are limited. Objective: To investigate the diagnostic performance of the FotoFinder Mole-Analyzer in assessing PSLs for cutaneous melanoma. Methods: In this 15-year retrospective study, the histopathologies of 1076 biopsied PSLs among a total of 2500 imaged PSLs were collected. The biopsied PSLs were categorized as benign or malignant (cutaneous melanoma) based on histopathology. Analyzer scores (0-1.00) for these PSLs were obtained and grouped according to histopathology. Results: At an optimized cutoff score of 0.50, a sensitivity of 56% and a specificity of 74% were achieved. The area under the receiver operating characteristics curve was 0.698, indicating poor accuracy as a diagnostic tool. Limitations: This study had a retrospective design and involved only a single institution. Conclusion: Our study reveals a low sensitivity of the scoring function of this digital dermoscopic image analyzer for detecting cutaneous melanomas. Physicians must apply keen clinical judgment when using such devices in the screening of suspicious PSLs.
引用
收藏
页码:927 / +
页数:14
相关论文
共 45 条
  • [1] Pigmented Skin Lesion Biopsies After Computer-Aided Multispectral Digital Skin Lesion Analysis
    Winkelmann, Richard R.
    Tucker, Natalie
    White, Richard
    Rigel, Darrell S.
    JOURNAL OF THE AMERICAN OSTEOPATHIC ASSOCIATION, 2015, 115 (11): : 666 - 669
  • [2] Performance of a computer-aided digital dermoscopic image analyzer for the diagnosis of cutaneous melanoma: A retrospective study comparing 1098 pigmented skin lesions' severity scores with known histopathologies
    Mounessa, Jessica
    del Rosario, Francis
    Fathi, Ramin
    Alkousakis, Theodore
    Norris, David
    Drendel, Jesse
    Chapman, Stephanie
    Domozych, Renee
    Caravaglio, Joseph
    JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2017, 76 (06) : AB194 - AB194
  • [3] Computer-Aided Detection of Lung Nodules: Influence of the Image Reconstruction Kernel for Computer-Aided Detection Performance
    Hwang, Jiyoung
    Chung, Myung Jin
    Bae, Younga
    Shin, Kyung Min
    Jeong, Sun Young
    Lee, Kyung Soo
    JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 2010, 34 (01) : 31 - 34
  • [4] Intelligent content-based dermoscopic image retrieval with relevance feedback for computer-aided melanoma diagnosis
    Belattar K.
    Mostefai S.
    Draa A.
    1600, IGI Global (10): : 85 - 108
  • [5] Computer aided Melanoma skin cancer detection using Image Processing
    Jain, Shivangi
    Jagtap, Vandana
    Pise, Nitin
    INTERNATIONAL CONFERENCE ON COMPUTER, COMMUNICATION AND CONVERGENCE (ICCC 2015), 2015, 48 : 735 - 740
  • [6] The positive impact of providing information from a computer-aided multispectral digital skin lesion analysis system on melanoma biopsy sensitivity
    Rigel, Darrell
    Cockerell, Clay
    Yoo, Jane
    Robinson, June
    Roy, Mrinalini
    White, Richard
    JOURNAL OF THE AMERICAN ACADEMY OF DERMATOLOGY, 2012, 66 (04) : AB148 - AB148
  • [7] Impact of Image Quality on the Performance of Computer-Aided Detection of Pulmonary Embolism
    Wittenberg, Rianne
    Peters, Joost F.
    Sonnemans, Jeroen J.
    Bipat, Shandra
    Prokop, Mathias
    Schaefer-Prokop, Cornelia M.
    AMERICAN JOURNAL OF ROENTGENOLOGY, 2011, 196 (01) : 95 - 101
  • [8] Differences in the Known Cellular Composition of Benign Pigmented Skin Lesions Reflected in Computer-Aided Image Analysis
    Choi, Jae Woo
    Ryu, Hyeong Ho
    Byun, Sang Young
    Youn, Sang Woong
    ANNALS OF DERMATOLOGY, 2014, 26 (03) : 314 - 320
  • [9] Improvement in detection of pulmonary nodules: Digital image processing and computer-aided diagnosis
    MacMahon, H
    RADIOGRAPHICS, 2000, 20 (04) : 1169 - 1177
  • [10] Advanced Deep Learning Models for Melanoma Diagnosis in Computer-Aided Skin Cancer Detection
    Kaur, Ranpreet
    Gholamhosseini, Hamid
    Linden, Maria
    SENSORS, 2025, 25 (03)