Nityanand Miskin1, Lei Qin2, Shanna A Matalon3, Sree H Tirumani4, Francesco Alessandrino3,2, Stuart G Silverman3, Atul B Shinagare3,2. 1. Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis Street, Boston, MA, 02115, USA. nmiskin@partners.org. 2. Department of Imaging, Dana-Farber Cancer Institute, Harvard Medical School, 450 Brookline Avenue, Boston, MA, 02215, USA. 3. Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis Street, Boston, MA, 02115, USA. 4. Department of Radiology, University Hospital Cleveland Medical Center, 11100 Euclid Avenue, Cleveland, OH, 44106, USA.
Abstract
PURPOSE: To create a CT texture-based machine learning algorithm that distinguishes benign from potentially malignant cystic renal masses as defined by the Bosniak Classification version 2019. METHODS: In this IRB-approved, HIPAA-compliant study, 4,454 adult patients underwent renal mass protocol CT or CT urography from January 2011 to June 2018. Of these, 257 cystic renal masses were included in the final study cohort. Each mass was independently classified using Bosniak version 2019 by three radiologists, resulting in 185 benign (Bosniak I or II) and 72 potentially malignant (Bosniak IIF, III or IV) masses. Six texture features: mean, standard deviation, mean of positive pixels, entropy, skewness, kurtosis were extracted using commercial software TexRAD (Feedback PLC, Cambridge, UK). Random forest (RF), logistic regression (LR), and support vector machine (SVM) machine learning algorithms were implemented to classify cystic renal masses into the two groups and tested with tenfold cross validations. RESULTS: Higher mean, standard deviation, mean of positive pixels, entropy, skewness were statistically associated with the potentially malignant group (P ≤ 0.0015 each). Sensitivity, specificity, positive predictive value, negative predictive value, and area under curve of RF model was 0.67, 0.91, 0.75, 0.88, 0.88; of LR model was 0.63, 0.93, 0.78, 0.86, 0.90, and of SVM model was 0.56, 0.91, 0.71, 0.84, 0.89, respectively. CONCLUSION: Three CT texture-based machine learning algorithms demonstrated high discriminatory capability in distinguishing benign from potentially malignant cystic renal masses as defined by the Bosniak Classification version 2019. If validated, CT texture-based machine learning algorithms may help reduce interreader variability when applying the Bosniak classification.
PURPOSE: To create a CT texture-based machine learning algorithm that distinguishes benign from potentially malignant cystic renal masses as defined by the Bosniak Classification version 2019. METHODS: In this IRB-approved, HIPAA-compliant study, 4,454 adult patients underwent renal mass protocol CT or CT urography from January 2011 to June 2018. Of these, 257 cystic renal masses were included in the final study cohort. Each mass was independently classified using Bosniak version 2019 by three radiologists, resulting in 185 benign (Bosniak I or II) and 72 potentially malignant (Bosniak IIF, III or IV) masses. Six texture features: mean, standard deviation, mean of positive pixels, entropy, skewness, kurtosis were extracted using commercial software TexRAD (Feedback PLC, Cambridge, UK). Random forest (RF), logistic regression (LR), and support vector machine (SVM) machine learning algorithms were implemented to classify cystic renal masses into the two groups and tested with tenfold cross validations. RESULTS: Higher mean, standard deviation, mean of positive pixels, entropy, skewness were statistically associated with the potentially malignant group (P ≤ 0.0015 each). Sensitivity, specificity, positive predictive value, negative predictive value, and area under curve of RF model was 0.67, 0.91, 0.75, 0.88, 0.88; of LR model was 0.63, 0.93, 0.78, 0.86, 0.90, and of SVM model was 0.56, 0.91, 0.71, 0.84, 0.89, respectively. CONCLUSION: Three CT texture-based machine learning algorithms demonstrated high discriminatory capability in distinguishing benign from potentially malignant cystic renal masses as defined by the Bosniak Classification version 2019. If validated, CT texture-based machine learning algorithms may help reduce interreader variability when applying the Bosniak classification.
Authors: Hendrik Van Poppel; Luigi Da Pozzo; Walter Albrecht; Vsevolod Matveev; Aldo Bono; Andrzej Borkowski; Marc Colombel; Laurence Klotz; Eila Skinner; Thomas Keane; Sandrine Marreaud; Sandra Collette; Richard Sylvester Journal: Eur Urol Date: 2010-12-22 Impact factor: 20.096
Authors: Maxine Sun; Rodolphe Thuret; Firas Abdollah; Giovanni Lughezzani; Jan Schmitges; Zhe Tian; Shahrokh F Shariat; Francesco Montorsi; Jean-Jacques Patard; Paul Perrotte; Pierre I Karakiewicz Journal: Eur Urol Date: 2010-10-28 Impact factor: 20.096
Authors: Maxine Sun; Quoc-Dien Trinh; Marco Bianchi; Jens Hansen; Nawar Hanna; Firas Abdollah; Shahrokh F Shariat; Alberto Briganti; Francesco Montorsi; Paul Perrotte; Pierre I Karakiewicz Journal: Eur Urol Date: 2011-12-03 Impact factor: 20.096