Article
Radiology, Nuclear Medicine & Medical Imaging
Haoxin Zheng, Qi Miao, Yongkai Liu, Steven S. Raman, Fabien Scalzo, Kyunghyun Sung
Summary: This study retrospectively reviewed 330 patients with negative prostate mpMRI results and used a machine learning approach to predict prostate biopsy results. The model, utilizing radiomics and clinical features, demonstrated high performance in predicting negative prostate biopsy results, helping to stratify patients who may avoid prostate biopsy.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2022)
Review
Medicine, General & Internal
Hamide Nematollahi, Masoud Moslehi, Fahimeh Aminolroayaei, Maryam Maleki, Daryoush Shahbazi-Gahrouei
Summary: Prostate cancer, the second leading cause of cancer-related death in men, can be effectively detected and graded using artificial intelligence and machine learning techniques, particularly with multiparametric MRI. This review study compares the diagnostic performance of different supervised machine learning algorithms and finds that deep learning, random forest, and logistic regression algorithms have the best performance in prostate cancer diagnosis and prediction. These findings highlight the potential of supervised machine learning in improving the accuracy and effectiveness of prostate cancer detection and prevention.
Article
Oncology
Catarina Dinis Fernandes, Annekoos Schaap, Joan Kant, Petra van Houdt, Hessel Wijkstra, Elise Bekers, Simon Linder, Andries M. Bergman, Uulke van der Heide, Massimo Mischi, Wilbert Zwart, Federica Eduati, Simona Turco
Summary: Prostate cancer is a global health burden and multi-parametric magnetic resonance imaging is recommended for diagnosis. By studying imaging characteristics and genomic information from tumor biopsies, it may be possible to non-invasively detect aggressive tumor characteristics. This study found significant correlations between imaging features and tumor aggressiveness, as well as links between diagnostic images and genomic information of the tumors.
Article
Oncology
Chuan Zhou, Yun-Feng Zhang, Sheng Guo, Dong Wang, Hao-Xuan Lv, Xiao-Ni Qiao, Rong Wang, De-Hui Chang, Li-Ming Zhao, Feng-Hai Zhou
Summary: This study aimed to predict the Ki-67 expression status and Gleason Scores (GS) in prostate cancer (PCa) patients through the construction and verification of MRI-based radiomics signatures. The results showed that the radiomics features were closely correlated with Ki-67 expression and GS, and had good predictive performance. These findings have important implications for clinical decision-making.
Article
Oncology
Elena Bertelli, Laura Mercatelli, Chiara Marzi, Eva Pachetti, Michela Baccini, Andrea Barucci, Sara Colantonio, Luca Gherardini, Lorenzo Lattavo, Maria Antonietta Pascali, Simone Agostini, Vittorio Miele
Summary: Prostate cancer is the most common male malignancy and assessing its aggressiveness is crucial for patient management. This study aimed to develop and validate machine learning/deep learning frameworks on multiparametric MRI data to characterize prostate cancers. The results showed that the machine learning/deep learning frameworks trained on T2w images performed well and could assist in diagnosing and managing prostate cancer, reducing inter-reader variability.
FRONTIERS IN ONCOLOGY
(2022)
Article
Oncology
Alistair D. R. Grey, Rebecca Scott, Bina Shah, Peter Acher, Sidath Liyanage, Menelaos Pavlou, Rumana Omar, Frank Chinegwundoh, Prasad Patki, Taimur T. Shah, Sami Hamid, Maneesh Ghei, Kayleigh Gilbert, Diane Campbell, Chris Brew-Graves, Nimalan Arumainayagam, Alex Chapman, Laura McLeavy, Angeliki Karatziou, Zayneb Alsaadi, Tom Collins, Alex Freeman, David Eldred-Evans, Mariana Bertoncelli-Tanaka, Henry Tam, Navin Ramachandran, Sanjeev Madaan, Mathias Winkler, Manit Arya, Mark Emberton, Hashim U. Ahmed
Summary: Multiparametric ultrasound has slightly lower ability to detect clinically significant prostate cancer compared to multiparametric MRI, but it would result in more patients being referred for a biopsy. For patients at risk of prostate cancer who cannot undergo multiparametric MRI, multiparametric ultrasound can be considered as the first test.
Article
Medicine, General & Internal
Huiyong Zhang, Jin Ji, Zhe Liu, Huiru Lu, Chong Qian, Chunmeng Wei, Shaohua Chen, Wenhao Lu, Chengbang Wang, Huan Xu, Yalong Xu, Xi Chen, Xing He, Zuheng Wang, Xiaodong Zhao, Wen Cheng, Xingfa Chen, Guijian Pang, Guopeng Yu, Yue Gu, Kangxian Jiang, Bin Xu, Junyi Chen, Bin Xu, Xuedong Wei, Ming Chen, Rui Chen, Jiwen Cheng, Fubo Wang
Summary: This study aimed to establish a quick and economic tool to improve the detection of clinically significant prostate cancer (csPCa) based on routinely performed clinical examinations through an automated machine learning platform (AutoML). The results showed that the Prostate Cancer Artificial Intelligence Diagnostic System (PCAIDS) had good diagnostic performance in discriminating csPCa and had a higher net benefit compared to PSA or fPSA/tPSA.
Article
Radiology, Nuclear Medicine & Medical Imaging
Alexander Ushinsky, Michelle Bardis, Justin Glavis-Bloom, Edward Uchio, Chanon Chantaduly, Michael Nguyentat, Daniel Chow, Peter D. Chang, Roozbeh Houshyar
Summary: In this study, a deep learning approach using convolutional neural networks was used for automatic segmentation of prostate organs from mpMRI, achieving high accuracy in segmentation and correlation with prostate volume. Further research is needed to explore pattern recognition for lesion localization and quantification.
AMERICAN JOURNAL OF ROENTGENOLOGY
(2021)
Article
Oncology
Carmen Herrero Vicent, Xavier Tudela, Paula Moreno Ruiz, Victor Pedralva, Ana Jimenez Pastor, Daniel Ahicart, Silvia Rubio Novella, Isabel Meneu, Angela Montes Albuixech, Miguel Angel Santamaria, Maria Fonfria, Almudena Fuster-Matanzo, Santiago Olmos Anton, Eduardo Martinez de Duenas
Summary: This study aimed to evaluate whether imaging features (perfusion/diffusion imaging biomarkers + radiomic features) extracted from pre-treatment multiparametric MRIs can predict pCR to NAC, alone or in combination with clinical data. The results showed that a combination of imaging features and clinical variables improved pCR prediction compared to models only including imaging or clinical data, with an accuracy of 91.5%.
Article
Radiology, Nuclear Medicine & Medical Imaging
Haoxin Zheng, Qi Miao, Yongkai Liu, Sohrab Afshari Mirak, Melina Hosseiny, Fabien Scalzo, Steven S. Raman, Kyunghyun Sung
Summary: A radiomics-based machine learning approach was used to predict lymph node invasion (LNI) in patients with prostate cancer (PCa). The proposed integrative radiomics model (IRM) showed superior performance in predicting LNI compared to pre-existing nomograms. This model could potentially help identify PCa patients who can safely avoid extended pelvic lymph node dissection (ePLND) and reduce unnecessary surgeries.
EUROPEAN RADIOLOGY
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Florent L. Besson, Brice Fernandez, Sylvain Faure, Olaf Mercier, Andrei Seferian, Sacha Mussot, Antonin Levy, Florence Parent, Sophie Bulifon, Xavier Jais, David Montani, Delphine Mitilian, Elie Fadel, David Planchard, Maria-Rosa Ghigna-Bellinzoni, Claude Comtat, Vincent Lebon, Emmanuel Durand
Summary: This study developed a multiparametric imaging framework for NSCLC using PET/MRI, which successfully revealed the PET/MRI characteristics of tumors through Gaussian mixture model-based clustering and machine learning. The features showed high accuracy and low mean discrepancy at both the whole data set and individual tumor levels.
CLINICAL NUCLEAR MEDICINE
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Heejong Kim, Daniel J. A. Margolis, Himanshu Nagar, Mert R. Sabuncu
Summary: By utilizing multiparametric magnetic resonance imaging (mpMRI) combined with deep learning models, early detection and localization of prostate cancer can be achieved. The mpMRI model with T2-ADC-DWI sequence achieved a high AUC score of 0.90 in the test set, slightly outperforming the model using Ktrans instead of DWI. The study demonstrates that convolutional neural networks incorporating multiple pulse sequences show high performance for detecting clinically significant prostate cancer.
ACADEMIC RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lili Xu, Gumuyang Zhang, Daming Zhang, Jiahui Zhang, Xiaoxiao Zhang, Xin Bai, Li Chen, Ru Jin, Li Mao, Xiuli Li, Hao Sun, Zhengyu Jin
Summary: In this study, a deep learning-based tool was developed to automatically segment the whole prostate on T2WI and DWI. The tool showed good performance on T2WI and feasible results on DWI with fine-tuning. It had better segmentation results in the prostate midgland.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Lili Xu, Gumuyang Zhang, Daming Zhang, Jiahui Zhang, Xiaoxiao Zhang, Xin Bai, Li Chen, Ru Jin, Li Mao, Xiuli Li, Hao Sun, Zhengyu Jin
Summary: This study aimed to develop and evaluate a clinically applicable deep learning-based tool for automatic whole prostate segmentation on T2WI and DWI. The segmentation tool showed good and robust performance, especially in the prostate midgland, and fine-tuning might be needed for different scanners.
QUANTITATIVE IMAGING IN MEDICINE AND SURGERY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Jeroen Bleker, Christian Roest, Derya Yakar, Henkjan Huisman, Thomas C. Kwee
Summary: This study investigates the impact of image resampling on the performance of multicenter radiomics artificial intelligence in prostate MRI. The recommended 2D resampling configuration is isotropic resampling with T2W at 0.5 mm (Bspline interpolation) and DWI at 2 mm (nearest neighbor interpolation). For the 3D radiomics, isotropic resampling with T2W at 0.8 mm (linear interpolation) and DWI at 2.5 mm (nearest neighbor interpolation) is recommended.
JOURNAL OF MAGNETIC RESONANCE IMAGING
(2023)
Article
Urology & Nephrology
Xavier Bonet, Marco Oderda, Davide Campobasso, Jean-Luc Hoepffner
Summary: This case report describes a rare case of a 29-year-old male with a history of WT who presented with a prostatic mass, which was later diagnosed as PER. The diagnostic and therapeutic journey of this case highlights the importance of considering the possibility of prostatic sarcoma, especially in patients with a history of WT.
Article
Endocrinology & Metabolism
Marco Oderda, Simone Albisinni, Daniel Benamran, Giorgio Calleris, Mauro Ciccariello, Alessandro Dematteis, Romain Diamand, Jean-Luc Descotes, Gaelle Fiard, Valerio Forte, Alessandro Giacobbe, Alessandro Marquis, Giancarlo Marra, Aurel Messas, Giovanni Muto, Alexandre Peltier, Leire Rius, Giuseppe Simone, Thierry Roumeguere, Riccardo Faletti, Paolo Gontero
Summary: The addition of systematic biopsies to targeted biopsies can increase the detection rate of prostate cancer, especially for clinically significant cases. There is some discordance between mpMRI findings and fusion biopsy results in terms of cancer location.
Article
Health Care Sciences & Services
Ludovica Borsoi, Oriana Ciani, Giuseppe Fornarini, Marco Oderda, Alessandro Sciarra, Damir Vetrini, Irene Luccarini
Summary: This study estimated the direct healthcare costs of nmCRPC in Italy based on a mixed-methods approach. Delaying metastases may be a reasonable goal also from an economic standpoint. These findings can inform decision-making about treatments at the juncture between non-metastatic and metastatic prostate cancer disease.
INTERNATIONAL JOURNAL OF TECHNOLOGY ASSESSMENT IN HEALTH CARE
(2023)
Article
Oncology
Giancarlo Marra, Francesco Soria, Federica Peretti, Marco Oderda, Charles Dariane, Marc-Olivier Timsit, Julien Branchereau, Oussama Hedli, Benoit Mesnard, Derya Tilki, Jonathon Olsburgh, Meghana Kulkarni, Veeru Kasivisvanathan, Cedric Lebacle, Oscar Rodriguez-Faba, Alberto Breda, Timo Soeterik, Giorgio Gandaglia, Paola Todeschini, Luigi Biancone, Paolo Gontero
Summary: Currently, there is limited and conflicting evidence regarding the management of prostate cancer in renal transplant recipients. This study aimed to assess the differences in treatment and natural history of prostate cancer in renal transplant recipients. The study found that prostate cancer in renal transplant recipients is not aggressive and has similar outcomes to non-renal transplant recipients. However, renal transplant recipients have a significant risk of non-prostate cancer-related death. Therefore, aggressive upfront management of prostate cancer in most renal transplant recipients should be avoided.
Review
Urology & Nephrology
Marco Oderda, Oscar Bertetto, Giulia Barbera, Giorgio Calleris, Marco Falcone, Claudia Filippini, Alessandro Marquis, Giancarlo Marra, Gabriele Montefusco, Federica Peretti, Paolo Gontero
Summary: This study aimed to evaluate the appropriateness of androgen deprivation therapy (ADT) prescription and related adverse events in a referral center for prostate cancer. The results showed that most ADT prescriptions followed the European Association of Urology (EAU) guidelines, but a proportion of patients did not receive appropriate treatment according to the guidelines, exposing them to unnecessary side effects.
Article
Urology & Nephrology
Marco Oderda, Antonio Amato, Jean de la Rosette, Steve Doizi, Vincent Estrade, Marco Falcone, Ben Grey, Bodo Knudsen, Jonathon Olsburgh, Amelia Pietropaolo, Nick Rukin, Omidreza Sedigh, Alhamri Saeed, Bhaskar K. Somani, Paolo Gontero
Summary: The aim of this study was to evaluate the costs and criticalities of stent removals performed with Isiris-alpha (R) in different hospitals and health systems, as compared to other DJ removal procedures. The main factor affecting costs was the occupancy of the Endoscopic Room (EnR)/ Operatory Room (OR). Isiris-alpha (R) showed significant cost benefit in institutions where DJ removal is routinely performed in EnR/OR, leading to improved organization and efficiency.
Article
Medicine, General & Internal
Guido Rovera, Serena Grimaldi, Marco Oderda, Monica Finessi, Valentina Giannini, Roberto Passera, Paolo Gontero, Desiree Deandreis
Summary: This study aimed to test the feasibility of using machine learning for intraoperative lymph-nodal segmentation. A machine learning-based approach was developed using open-source Python libraries, showing promising results compared to manual segmentation. This machine learning method also holds promise for facilitating semi-quantitative analysis of PET/CT images in the operating room.
Meeting Abstract
Urology & Nephrology
Marco Oderda, Serena Grimaldi, Giorgio Calleris, Daniele D'Agate, Federico Lavagno, Alessandro Marquis, Giancarlo Marra, Desiree Deandreis, Paolo Gontero
JOURNAL OF UROLOGY
(2023)
Meeting Abstract
Urology & Nephrology
Daniele D'Agate, Giorgio Calleris, Marco Allasia, Marco Oderda, Alessandro Marquis, Giancarlo Marra, Federico Vitiello, Federico Lavagno, Matteo de Bellis, Gabriele Montefusco, Francesco Bracco, Paolo Gontero
JOURNAL OF UROLOGY
(2023)
Article
Urology & Nephrology
Giancarlo Marra, Giorgio Calleris, Emilia Massari, Elena Vissio, Luca Molinaro, Paola Cassoni, Daniele D'Agate, Marco Oderda, Massimo Valerio, Yannick Raskin, Steven Joniau, Mauro Papotti, Paolo Gontero
Summary: This study reviewed the pathology of recurrent prostate cancer in 41 patients who underwent sRP surgery at a single center between 2007 and 2021. The results showed that most cases had tumors located near the apex of the prostate, with positive margins, extraprostatic extension, and apical involvement.
EUROPEAN UROLOGY OPEN SCIENCE
(2023)
Article
Urology & Nephrology
Olivier Windisch, Daniel Benamran, Charles Dariane, Martina Martins Favre, Mehdi Djouhri, Maxime Chevalier, Benedicte Guillaume, Marco Oderda, Marco Gatti, Riccardo Faletti, Valentin Colinet, Yolene Lefebvre, Sylvain Bodard, Romain Diamand, Gaelle Fiard
Summary: PI-QUAL <3 is associated with higher rate of disease upstaging, lower detection rates of PI-RADS 5 lesions and suspicious lesions, and lower detection rates of extraprostatic extension.
EUROPEAN UROLOGY OPEN SCIENCE
(2023)
Article
Urology & Nephrology
Michael Baboudjian, Alberto Breda, Thierry Roumeguere, Alessandro Uleri, Jean-Baptiste Roche, Alae Touzani, Vito Lacetera, Jean-Baptiste Beauval, Romain Diamand, Guiseppe Simone, Olivier Windisch, Daniel Benamran, Alexandre Fourcade, Gaelle Fiard, Camille Durand-Labrunie, Mathieu Roumiguie, Francesco Sanguedolce, Marco Oderda, Eric Barret, Gaelle Fromont, Charles Dariane, Anne-Laure Charvet, Bastien Gondran-Tellier, Cyrille Bastide, Eric Lechevallier, Joan Palou, Alain Ruffion, Roderick C. N. Van der Bergh, Alexandre Peltier, Guillaume Ploussard
Summary: The purpose of this study is to develop new selection criteria for active surveillance in intermediate-risk prostate cancer patients. A retrospective study was conducted on patients from 14 referral centers who underwent pre-biopsy mpMRI, image-guided biopsies, and radical prostatectomy. The results showed that PI-RADS score, PSA density, and clinical T stage were the most informative risk factors for classifying patients according to their risk of adverse features. Expanding the active surveillance criteria to include certain risk clusters can increase the number of eligible patients without increasing the risk of adverse pathological features.
WORLD JOURNAL OF UROLOGY
(2023)
Article
Oncology
Marco Oderda, Giorgio Calleris, Daniele D'Agate, Marco Falcone, Riccardo Faletti, Marco Gatti, Giancarlo Marra, Alessandro Marquis, Paolo Gontero
Summary: This pilot study aimed to assess the feasibility of intraoperative 3D-TRUS-mpMRI elastic fusion imaging in guiding robotic-assisted radical prostatectomy and evaluate its impact on surgical strategy. The results showed that intraoperative 3D modeling was feasible in all patients and led to a change in surgical strategy in some cases. Intraoperative 3D-TRUS-mpMRI modeling can help maximize functional outcomes without increasing the risk of positive surgical margins.
Article
Urology & Nephrology
Marco Oderda, Anastasios Asimakopoulos, Valerio Batetta, Andrea Bosio, Ettore Dalmasso, Ivano Morra, Eugenia Vercelli, Paolo Gontero
Summary: This study compared the functionality, risk of infections, and costs between disposable and reusable cystoscopes for in-office ureteral stent removal. The results showed that the disposable cystoscope outperformed the reusable device in terms of visual quality, maneuverability, grasper functionality, and procedure quality. The procedure time was shorter with the disposable cystoscope, but it was more expensive. There were no significant differences in postoperative bacteriuria or symptomatic UTIs between the two groups.
WORLD JOURNAL OF UROLOGY
(2023)
Article
Pediatrics
Marcello Della Corte, Elisa Cerchia, Marco Oderda, Paola Quarello, Franca Fagioli, Paolo Gontero, Simona Gerocarni Nappo
Summary: This case report presents a prechemotherapy transperitoneal robot-assisted partial nephrectomy (RAPN) for a unilateral, non-syndromic Wilms tumor in a child. The patient showed no tumor recurrence during a 28-month follow-up period.