Emine Acar1,2, Asım Leblebici2, Berat Ender Ellidokuz3, Yasemin Başbınar4,5, Gamze Çapa Kaya6. 1. 1Department of Nuclear Medicine, Ataturk Training and Research Hospital, İzmir Kâtip Celebi University, Izmir, Turkey. 2. 2Department of Translational Oncology, Institute of Health Sciences, Dokuz Eylul University, Izmir, Turkey. 3. 3Department of Gastroenterology,Faculty of Medicine, Dokuz Eylul University, Izmır, Turkey. 4. 4Department of Translational Oncology, Institute of Oncology, Dokuz Eylul University, Izmir, Turkey. 5. 5Dokuz Eylul University, Personalized Medicine and Pharmacogenomics Research Center, Izmir, Turkey. 6. 6Department of Nuclear Medicine, Faculty of Medicine, Dokuz Eylul University, Izmir, Turkey.
Abstract
OBJECTIVE: Using CT texture analysis and machine learning methods, this study aims to distinguish the lesions imaged via 68Ga-prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/CT as metastatic and completely responded in patients with known bone metastasis and who were previously treated. METHODS: We retrospectively reviewed the 68Ga-PSMA PET/CT images of 75 patients after treatment, who were previously diagnosed with prostate cancer and had known bone metastasis. A texture analysis was performed on the metastatic lesions showing PSMA expression and completely responded sclerotic lesions without PSMA expression through CT images. Textural features were compared in two groups. Thus, the distinction of metastasis/completely responded lesions and the most effective parameters in this issue were determined by using various methods [decision tree, discriminant analysis, support vector machine (SVM), k-nearest neighbor (KNN), ensemble classifier] in machine learning. RESULTS: In 28 of the 35 texture analysis findings, there was a statistically significant difference between the two groups. The Weighted KNN method had the highest accuracy and area under the curve, has been chosen as the best model. The weighted KNN algorithm was succeeded to differentiate sclerotic lesion from metastasis or completely responded lesions with 0.76 area under the curve. GLZLM_SZHGE and histogram-based kurtosis were found to be the most important parameters in differentiating metastatic and completely responded sclerotic lesions. CONCLUSIONS: Metastatic lesions and completely responded sclerosis areas in CT images, as determined by 68Ga-PSMA PET, could be distinguished with good accuracy using texture analysis and machine learning (Weighted KNN algorithm) in prostate cancer. ADVANCES IN KNOWLEDGE: Our findings suggest that, with the use of newly emerging software, CT imaging can contribute to identifying the metastatic lesions in prostate cancer.
OBJECTIVE: Using CT texture analysis and machine learning methods, this study aims to distinguish the lesions imaged via 68Ga-prostate-specific membrane antigen (PSMA) positron emission tomography (PET)/CT as metastatic and completely responded in patients with known bone metastasis and who were previously treated. METHODS: We retrospectively reviewed the 68Ga-PSMA PET/CT images of 75 patients after treatment, who were previously diagnosed with prostate cancer and had known bone metastasis. A texture analysis was performed on the metastatic lesions showing PSMA expression and completely responded sclerotic lesions without PSMA expression through CT images. Textural features were compared in two groups. Thus, the distinction of metastasis/completely responded lesions and the most effective parameters in this issue were determined by using various methods [decision tree, discriminant analysis, support vector machine (SVM), k-nearest neighbor (KNN), ensemble classifier] in machine learning. RESULTS: In 28 of the 35 texture analysis findings, there was a statistically significant difference between the two groups. The Weighted KNN method had the highest accuracy and area under the curve, has been chosen as the best model. The weighted KNN algorithm was succeeded to differentiate sclerotic lesion from metastasis or completely responded lesions with 0.76 area under the curve. GLZLM_SZHGE and histogram-based kurtosis were found to be the most important parameters in differentiating metastatic and completely responded sclerotic lesions. CONCLUSIONS: Metastatic lesions and completely responded sclerosis areas in CT images, as determined by 68Ga-PSMA PET, could be distinguished with good accuracy using texture analysis and machine learning (Weighted KNN algorithm) in prostate cancer. ADVANCES IN KNOWLEDGE: Our findings suggest that, with the use of newly emerging software, CT imaging can contribute to identifying the metastatic lesions in prostate cancer.
Authors: Axel Heidenreich; Patrick J Bastian; Joaquim Bellmunt; Michel Bolla; Steven Joniau; Theodor van der Kwast; Malcolm Mason; Vsevolod Matveev; Thomas Wiegel; F Zattoni; Nicolas Mottet Journal: Eur Urol Date: 2013-10-06 Impact factor: 20.096
Authors: Wolfgang P Fendler; Matthias Eiber; Mohsen Beheshti; Jamshed Bomanji; Francesco Ceci; Steven Cho; Frederik Giesel; Uwe Haberkorn; Thomas A Hope; Klaus Kopka; Bernd J Krause; Felix M Mottaghy; Heiko Schöder; John Sunderland; Simon Wan; Hans-Jürgen Wester; Stefano Fanti; Ken Herrmann Journal: Eur J Nucl Med Mol Imaging Date: 2017-06 Impact factor: 9.236
Authors: Lucas Frighetto-Pereira; Rangaraj Mandayam Rangayyan; Guilherme Augusto Metzner; Paulo Mazzoncini de Azevedo-Marques; Marcello Henrique Nogueira-Barbosa Journal: Comput Biol Med Date: 2016-04-12 Impact factor: 4.589
Authors: Matteo Ferro; Ottavio de Cobelli; Gennaro Musi; Francesco Del Giudice; Giuseppe Carrieri; Gian Maria Busetto; Ugo Giovanni Falagario; Alessandro Sciarra; Martina Maggi; Felice Crocetto; Biagio Barone; Vincenzo Francesco Caputo; Michele Marchioni; Giuseppe Lucarelli; Ciro Imbimbo; Francesco Alessandro Mistretta; Stefano Luzzago; Mihai Dorin Vartolomei; Luigi Cormio; Riccardo Autorino; Octavian Sabin Tătaru Journal: Ther Adv Urol Date: 2022-07-04
Authors: Simon K B Spohn; Alisa S Bettermann; Fabian Bamberg; Matthias Benndorf; Michael Mix; Nils H Nicolay; Tobias Fechter; Tobias Hölscher; Radu Grosu; Arturo Chiti; Anca L Grosu; Constantinos Zamboglou Journal: Theranostics Date: 2021-07-06 Impact factor: 11.556