Radiomic and Artificial Intelligence Analysis with Textural Metrics Extracted by Contrast-Enhanced Mammography and Dynamic Contrast Magnetic Resonance Imaging to Detect Breast Malignant Lesions

被引:18
作者
Fusco, Roberta [1 ]
Di Bernardo, Elio [1 ]
Piccirillo, Adele [2 ]
Rubulotta, Maria Rosaria [3 ]
Petrosino, Teresa [3 ]
Barretta, Maria Luisa [3 ]
Raso, Mauro Mattace [3 ]
Vallone, Paolo [3 ]
Raiano, Concetta [3 ]
Di Giacomo, Raimondo [4 ]
Siani, Claudio [4 ]
Avino, Franca [4 ]
Scognamiglio, Giosue [5 ]
Di Bonito, Maurizio [5 ]
Granata, Vincenza [3 ]
Petrillo, Antonella [3 ]
机构
[1] Igea SpA, Med Oncolody Div, I-80013 Naples, Italy
[2] Univ Napoli Federico II, Dept Elect Engn & Informat Technol, I-80125 Naples, Italy
[3] Ist Nazl Tumori IRCCS Fdn G Pascale, Radiol Div, I-80131 Naples, Italy
[4] Ist Nazl Tumori IRCCS Fdn G Pascale, Senol Surg Div, I-80131 Naples, Italy
[5] Ist Nazl Tumori IRCCS Fdn G Pascale, Pathol Div, I-80131 Naples, Italy
关键词
contrast-enhanced mammography; magnetic resonance imaging; image enhancement; contrast media; radiomics; artificial intelligence; SPECTRAL MAMMOGRAPHY; DIAGNOSTIC PERFORMANCE; MR-IMAGES; DCE-MRI; CANCER; CLASSIFICATION; PREDICTION; SELECTION; FEATURES; PATTERN;
D O I
10.3390/curroncol29030159
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Purpose:The purpose of this study was to discriminate between benign and malignant breast lesions through several classifiers using, as predictors, radiomic metrics extracted from CEM and DCE-MRI images. In order to optimize the analysis, balancing and feature selection procedures were performed. Methods: Fifty-four patients with 79 histo-pathologically proven breast lesions (48 malignant lesions and 31 benign lesions) underwent both CEM and DCE-MRI. The lesions were retrospectively analyzed with radiomic and artificial intelligence approaches. Forty-eight textural metrics were extracted, and univariate and multivariate analyses were performed: non-parametric statistical test, receiver operating characteristic (ROC) and machine learning classifiers. Results: Considering the single metrics extracted from CEM, the best predictors were KURTOSIS (area under ROC curve (AUC) = 0.71) and SKEWNESS (AUC = 0.71) calculated on late MLO view. Considering the features calculated from DCE-MRI, the best predictors were RANGE (AUC = 0.72), ENERGY (AUC = 0.72), ENTROPY (AUC = 0.70) and GLN (gray-level nonuniformity) of the gray-level run-length matrix (AUC = 0.72). Considering the analysis with classifiers and an unbalanced dataset, no significant results were obtained. After the balancing and feature selection procedures, higher values of accuracy, specificity and AUC were reached. The best performance was obtained considering 18 robust features among all metrics derived from CEM and DCE-MRI, using a linear discriminant analysis (accuracy of 0.84 and AUC = 0.88). Conclusions: Classifiers, adjusted with adaptive synthetic sampling and feature selection, allowed for increased diagnostic performance of CEM and DCE-MRI in the differentiation between benign and malignant lesions.
引用
收藏
页码:1947 / 1966
页数:20
相关论文
共 64 条
  • [1] Feature extraction and classification of breast cancer on dynamic magnetic resonance imaging using artificial neural network
    Abdolmaleki, P
    Buadu, LD
    Naderimansh, H
    [J]. CANCER LETTERS, 2001, 171 (02) : 183 - 191
  • [2] Textural Kinetics: A Novel Dynamic Contrast-Enhanced (DCE)-MRI Feature for Breast Lesion Classification
    Agner, Shannon C.
    Soman, Salil
    Libfeld, Edward
    McDonald, Margie
    Thomas, Kathleen
    Englander, Sarah
    Rosen, Mark A.
    Chin, Deanna
    Nosher, John
    Madabhushi, Anant
    [J]. JOURNAL OF DIGITAL IMAGING, 2011, 24 (03) : 446 - 463
  • [3] Potential of Noncontrast Magnetic Resonance Imaging With Diffusion-Weighted Imaging in Characterization of Breast Lesions Intraindividual Comparison With Dynamic Contrast-Enhanced Magnetic Resonance Imaging
    Baltzer, Pascal A. T.
    Bickel, Hubert
    Spick, Claudio
    Wengert, Georg
    Woitek, Ramona
    Kapetas, Panagiotis
    Clauser, Paola
    Helbich, Thomas H.
    Pinker, Katja
    [J]. INVESTIGATIVE RADIOLOGY, 2018, 53 (04) : 229 - 235
  • [4] CT-derived radiomic features to discriminate histologic characteristics of pancreatic neuroendocrine tumors
    Benedetti, Giulia
    Mori, Martina
    Panzeri, Marta Maria
    Barbera, Maurizio
    Palumbo, Diego
    Sini, Carla
    Muffatti, Francesca
    Andreasi, Valentina
    Steidler, Stephanie
    Doglioni, Claudio
    Partelli, Stefano
    Manzoni, Marco
    Falconi, Massimo
    Fiorino, Claudio
    De Cobelli, Francesco
    [J]. RADIOLOGIA MEDICA, 2021, 126 (06): : 745 - 760
  • [5] Digital breast tomosynthesis (DBT): recommendations from the Italian College of Breast Radiologists (ICBR) by the Italian Society of Medical Radiology (SIRM) and the Italian Group for Mammography Screening (GISMa)
    Bernardi, Daniela
    Belli, Paolo
    Benelli, Eva
    Brancato, Beniamino
    Bucchi, Lauro
    Calabrese, Massimo
    Carbonaro, Luca A.
    Caumo, Francesca
    Cavallo-Marincola, Beatrice
    Clauser, Paola
    Fedato, Chiara
    Frigerio, Alfonso
    Galli, Vania
    Giordano, Livia
    Rossi, Paolo Giorgi
    Golinelli, Paola
    Morrone, Doralba
    Mariscotti, Giovanna
    Martincich, Laura
    Montemezzi, Stefania
    Naldoni, Carlo
    Paduos, Adriana
    Panizza, Pietro
    Pediconi, Federica
    Querci, Fiammetta
    Rizzo, Antonio
    Saguatti, Gianni
    Tagliafico, Alberto
    Trimboli, Rubina M.
    Zappa, Marco
    Zuiani, Chiara
    Sardanelli, Francesco
    [J]. RADIOLOGIA MEDICA, 2017, 122 (10): : 723 - 730
  • [6] Bruce P. C., 2020, Practical statistics for data scientists: 50+ essential concepts using R and Python, VSecond
  • [7] Recommendations for breast imaging follow-up of women with a previous history of breast cancer: position paper from the Italian Group for Mammography Screening (GISMa) and the Italian College of Breast Radiologists (ICBR) by SIRM
    Bucchi, Lauro
    Belli, Paolo
    Benelli, Eva
    Bernardi, Daniela
    Brancato, Beniamino
    Calabrese, Massimo
    Carbonaro, Luca A.
    Caumo, Francesca
    Cavallo-Marincola, Beatrice
    Clauser, Paola
    Fedato, Chiara
    Frigerio, Alfonso
    Galli, Vania
    Giordano, Livia
    Golinelli, Paola
    Mariscotti, Giovanna
    Martincich, Laura
    Montemezzi, Stefania
    Morrone, Doralba
    Naldoni, Carlo
    Paduos, Adriana
    Panizza, Pietro
    Pediconi, Federica
    Querci, Fiammetta
    Rizzo, Antonio
    Saguatti, Gianni
    Tagliafico, Alberto
    Trimboli, Rubina M.
    Zuiani, Chiara
    Sardanelli, Francesco
    [J]. RADIOLOGIA MEDICA, 2016, 121 (12): : 891 - 896
  • [8] Radiomic analysis of the optic nerve at the first episode of acute optic neuritis: an indicator of optic nerve pathology and a predictor of visual recovery?
    Cellina, Michaela
    Pirovano, Marta
    Ciocca, Matteo
    Gibelli, Daniele
    Floridi, Chiara
    Oliva, Giancarlo
    [J]. RADIOLOGIA MEDICA, 2021, 126 (05): : 698 - 706
  • [9] A synthetic neighborhood generation based ensemble learning for the imbalanced data classification
    Chen, Zhi
    Lin, Tao
    Xia, Xin
    Xu, Hongyan
    Ding, Sha
    [J]. APPLIED INTELLIGENCE, 2018, 48 (08) : 2441 - 2457
  • [10] An update in musculoskeletal tumors: from quantitative imaging to radiomics
    Chianca, Vito
    Albano, Domenico
    Messina, Carmelo
    Vincenzo, Gabriele
    Rizzo, Stefania
    Del Grande, Filippo
    Sconfienza, Luca Maria
    [J]. RADIOLOGIA MEDICA, 2021, 126 (08): : 1095 - 1105