Your browser doesn't support javascript.
loading
Evaluation of an Integrated Spectroscopy and Classification Platform for Point-of-Care Core Needle Biopsy Assessment: Performance Characteristics from Ex Vivo Renal Mass Biopsies.
Keshavamurthy, Krishna Nand; Dylov, Dmitry V; Yazdanfar, Siavash; Patel, Dharam; Silk, Tarik; Silk, Mikhail; Jacques, Frederick; Petre, Elena N; Gonen, Mithat; Rekhtman, Natasha; Ostroverkhov, Victor; Scher, Howard I; Solomon, Stephen B; Durack, Jeremy C.
Afiliación
  • Keshavamurthy KN; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Dylov DV; Skolkovo Institute of Science and Technology, Moscow, Russia.
  • Yazdanfar S; Corning Incorporated, Corning, New York.
  • Patel D; Novartis Pharmaceutical Corporation, East Hanover, New Jersey.
  • Silk T; New York University Langone Medical Center, New York, New York.
  • Silk M; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Jacques F; Montefiore Medical Center, New York, New York.
  • Petre EN; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Gonen M; Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Rekhtman N; Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Ostroverkhov V; GE Global Research, Niskayuna, New York.
  • Scher HI; Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Solomon SB; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York.
  • Durack JC; Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, New York. Electronic address: jcdurack@gmail.com.
J Vasc Interv Radiol ; 33(11): 1408-1415.e3, 2022 11.
Article en En | MEDLINE | ID: mdl-35940363
PURPOSE: To evaluate a transmission optical spectroscopy instrument for rapid ex vivo assessment of core needle cancer biopsies (CNBs) at the point of care. MATERIALS AND METHODS: CNBs from surgically resected renal tumors and nontumor regions were scanned on their sampling trays with a custom spectroscopy instrument. After extracting principal spectral components, machine learning was used to train logistic regression, support vector machines, and random decision forest (RF) classifiers on 80% of randomized and stratified data. The algorithms were evaluated on the remaining 20% of the data set held out during training. Binary classification (tumor/nontumor) was performed based on a decision threshold. Multinomial classification was also performed to differentiate between the subtypes of renal cell carcinoma (RCC) and account for potential confounding effects from fat, blood, and necrotic tissue. Classifiers were compared based on sensitivity, specificity, and positive predictive value (PPV) relative to a histopathologic standard. RESULTS: A total of 545 CNBs from 102 patients were analyzed, yielding 5,583 spectra after outlier exclusion. At the individual spectra level, the best performing algorithm was RF with sensitivities of 96% and 92% and specificities of 90% and 89%, for the binary and multiclass analyses, respectively. At the full CNB level, RF algorithm also showed the highest sensitivity and specificity (93% and 91%, respectively). For RCC subtypes, the highest sensitivity and PPV were attained for clear cell (93.5%) and chromophobe (98.2%) subtypes, respectively. CONCLUSIONS: Ex vivo spectroscopy imaging paired with machine learning can accurately characterize renal mass CNB at the time of tissue acquisition.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Carcinoma de Células Renales / Neoplasias Renales Tipo de estudio: Clinical_trials / Prognostic_studies Límite: Humans Idioma: En Revista: J Vasc Interv Radiol Asunto de la revista: ANGIOLOGIA / RADIOLOGIA Año: 2022 Tipo del documento: Article Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Carcinoma de Células Renales / Neoplasias Renales Tipo de estudio: Clinical_trials / Prognostic_studies Límite: Humans Idioma: En Revista: J Vasc Interv Radiol Asunto de la revista: ANGIOLOGIA / RADIOLOGIA Año: 2022 Tipo del documento: Article Pais de publicación: Estados Unidos