Rami N Al-Rohil1, Jessica L Moore2, Nathan Heath Patterson2,3, Sarah Nicholson2, Nico Verbeeck4, Marc Claesen4, Jameelah Z Muhammad2, Richard M Caprioli2,3, Jeremy L Norris2,3, Sara Kantrow5, Margaret Compton6, Jason Robbins5, Ahmed K Alomari7. 1. Departments of Pathology and Dermatology, Duke University School of Medicine, Durham, North Carolina, USA. 2. Frontier Diagnostics, LLC, Nashville, Tennessee, USA. 3. Mass Spectrometry Research Center, Department of Biochemistry, Vanderbilt University, Nashville, Tennessee, USA. 4. Aspect Analytics NV, Genk, Belgium. 5. Pathology Associates of Saint Thomas, Nashville, Tennessee, USA. 6. Department of Pathology, Microbiology, and Immunology, Vanderbilt University Medical Center, Nashville, Tennessee, USA. 7. Departments of Pathology and Dermatology, Indiana University School of Medicine, Indianapolis, Indiana, USA.
Abstract
BACKGROUND: The definitive diagnosis of melanocytic neoplasia using solely histopathologic evaluation can be challenging. Novel techniques that objectively confirm diagnoses are needed. This study details the development and validation of a melanoma prediction model from spatially resolved multivariate protein expression profiles generated by imaging mass spectrometry (IMS). METHODS: Three board-certified dermatopathologists blindly evaluated 333 samples. Samples with triply concordant diagnoses were included in this study, divided into a training set (n = 241) and a test set (n = 92). Both the training and test sets included various representative subclasses of unambiguous nevi and melanomas. A prediction model was developed from the training set using a linear support vector machine classification model. RESULTS: We validated the prediction model on the independent test set of 92 specimens (75 classified correctly, 2 misclassified, and 15 indeterminate). IMS detects melanoma with a sensitivity of 97.6% and a specificity of 96.4% when evaluating each unique spot. IMS predicts melanoma at the sample level with a sensitivity of 97.3% and a specificity of 97.5%. Indeterminate results were excluded from sensitivity and specificity calculations. CONCLUSION: This study provides evidence that IMS-based proteomics results are highly concordant to diagnostic results obtained by careful histopathologic evaluation from a panel of expert dermatopathologists.
BACKGROUND: The definitive diagnosis of melanocytic neoplasia using solely histopathologic evaluation can be challenging. Novel techniques that objectively confirm diagnoses are needed. This study details the development and validation of a melanoma prediction model from spatially resolved multivariate protein expression profiles generated by imaging mass spectrometry (IMS). METHODS: Three board-certified dermatopathologists blindly evaluated 333 samples. Samples with triply concordant diagnoses were included in this study, divided into a training set (n = 241) and a test set (n = 92). Both the training and test sets included various representative subclasses of unambiguous nevi and melanomas. A prediction model was developed from the training set using a linear support vector machine classification model. RESULTS: We validated the prediction model on the independent test set of 92 specimens (75 classified correctly, 2 misclassified, and 15 indeterminate). IMS detects melanoma with a sensitivity of 97.6% and a specificity of 96.4% when evaluating each unique spot. IMS predicts melanoma at the sample level with a sensitivity of 97.3% and a specificity of 97.5%. Indeterminate results were excluded from sensitivity and specificity calculations. CONCLUSION: This study provides evidence that IMS-based proteomics results are highly concordant to diagnostic results obtained by careful histopathologic evaluation from a panel of expert dermatopathologists.
Authors: R P Braun; D Gutkowicz-Krusin; H Rabinovitz; A Cognetta; R Hofmann-Wellenhof; V Ahlgrimm-Siess; D Polsky; M Oliviero; I Kolm; P Googe; R King; V G Prieto; L French; A Marghoob; M Mihm Journal: Dermatology Date: 2012-03-20 Impact factor: 5.366
Authors: Domenico Taverna; Federica Boraldi; Giorgio De Santis; Richard M Caprioli; Daniela Quaglino Journal: Bone Date: 2015-01-13 Impact factor: 4.398
Authors: Nathan Heath Patterson; Michael Tuck; Adam Lewis; Alexis Kaushansky; Jeremy L Norris; Raf Van de Plas; Richard M Caprioli Journal: Anal Chem Date: 2018-10-16 Impact factor: 6.986
Authors: Loren E Clarke; M B Warf; Darl D Flake; Anne-Renee Hartman; Steven Tahan; Christopher R Shea; Pedram Gerami; Jane Messina; Scott R Florell; Richard J Wenstrup; Kristen Rushton; Kirstin M Roundy; Colleen Rock; Benjamin Roa; Kathryn A Kolquist; Alexander Gutin; Steven Billings; Sancy Leachman Journal: J Cutan Pathol Date: 2015-04-13 Impact factor: 1.587