Article
Surgery
Nasseh Hashemi, Morten Bo Sondergaard Svendsen, Flemming Bjerrum, Sten Rasmussen, Martin G. G. Tolsgaard, Mikkel Lonborg Friis
Summary: As the use of robot-assisted surgery (RAS) increases, there is a need for new methods of assessing the qualifications of new surgeons without relying on expert surgeons. Computer-based automation and artificial intelligence (AI) are potential alternatives to expert-based surgical assessment, but there are currently no standard protocols or methods for preparing data and implementing AI in the clinical setting.
SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Nikita Sushentsev, Leonardo Rundo, Luis Abrego, Zonglun Li, Tatiana Nazarenko, Anne Y. Warren, Vincent J. Gnanapragasam, Evis Sala, Alexey Zaikin, Tristan Barrett, Oleg Blyuss
Summary: In this study, a time series radiomics predictive model was developed using a long short-term memory recurrent neural network. The model analyzed longitudinal changes in tumor-derived radiomic features and serial PSA density to predict histopathological tumor progression in prostate cancer patients on active surveillance. The model outperformed conventional models and achieved comparable performance to expert-performed serial MRI analysis.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Guiqin Liu, Shihang Pan, Rui Zhao, Huang Zhou, Jie Chen, Xiang Zhou, Jianrong Xu, Yan Zhou, Wei Xue, Guangyu Wu
Summary: An AI model was developed for prostate segmentation and PCa detection, and the added value of AI-based CAD was explored compared to conventional PI-RADS assessment. The study included patients who underwent prostate biopsies and multiparametric MRI in multiple centers and tested the reliability of different CAD methods. The diagnostic performance, consistency, and efficiency of radiologists and AI-based CAD were compared.
EUROPEAN RADIOLOGY
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Fajin Dong, Ruilian She, Chen Cui, Siyuan Shi, Xuqiao Hu, Jieying Zeng, Huaiyu Wu, Jinfeng Xu, Yun Zhang
Summary: The study investigated the effectiveness of using DenseNet models to classify breast lesions, with results showing AUC of 0.899 and 0.869 for two models using coarse and fine ROIs of ultrasound images. The models demonstrated high accuracy and specificity, with DL model capturing ROE resembling physicians' considerations. This proposed ROE-based metric system can aid in understanding AI decision-making and potentially be integrated into early screening or patient triage during breast ultrasound examinations.
EUROPEAN RADIOLOGY
(2021)
Article
Multidisciplinary Sciences
Yoshiko Bamba, Shimpei Ogawa, Michio Itabashi, Shingo Kameoka, Takahiro Okamoto, Masakazu Yamamoto
Summary: This study utilized convolutional neural networks to recognize and evaluate the accuracy of forceps types in surgical videos obtained during colorectal surgeries, demonstrating the potential for achieving high accuracy in forceps recognition.
SCIENTIFIC REPORTS
(2021)
Review
Medicine, Research & Experimental
Liliana David, Stefan L. Popa, Maria Barsan, Lucian Muresan, Abdulrahman Ismaiel, Luminita C. Popa, Lacramioara Perju-Dumbrava, Mihaela Fadgyas Stanculete, Dan L. Dumitrascu
Summary: This study conducted a comparative analysis of traditional nursing techniques and autonomous robotic applications for managing patients with advanced dementia. The findings revealed that autonomous robotic applications are a feasible and cost-efficient solution for patients with advanced stages of dementia, benefiting both patients and the healthcare system.
EXPERIMENTAL AND THERAPEUTIC MEDICINE
(2022)
Article
Surgery
Pieter De Backer, Jennifer A. Eckhoff, Jente Simoens, Dolores T. Mueller, Charlotte Allaeys, Heleen Creemers, Amelie Hallemeesch, Kenzo Mestdagh, Charles Van Praet, Charlotte Debbaut, Karel Decaestecker, Christiane J. Bruns, Ozanan Meireles, Alexandre Mottrie, Hans F. Fuchs
Summary: This study explores the requirements and methods of instrument annotation in surgical video and imaging data, and successfully implements a bottom-up approach for team annotation in two types of surgeries, laying the foundation for future AI projects in instrument detection, segmentation, and pose estimation.
SURGICAL ENDOSCOPY AND OTHER INTERVENTIONAL TECHNIQUES
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Hee Jeong Kim, Hak Hee Kim, Ki Hwan Kim, Woo Jung Choi, Eun Young Chae, Hee Jung Shin, Joo Hee Cha, Woo Hyun Shim
Summary: This study retrospectively analyzed mammography using an artificial intelligence (AI) software and found that AI provided added value in the detection of mammographically occult breast cancers. The clinicopathologic characteristics of the AI-detected cancers were also determined.
INSIGHTS INTO IMAGING
(2022)
Article
Radiology, Nuclear Medicine & Medical Imaging
Francesca Marturano, Priscilla Guglielmo, Andrea Bettinelli, Fabio Zattoni, Giacomo Novara, Alessandra Zorz, Matteo Sepulcri, Michele Gregianin, Marta Paiusco, Laura Evangelista
Summary: Radiomic analysis can assist in predicting biochemical recurrence in intermediate and high-risk prostate cancer patients. Combining clinical data with radiomic features improves the accuracy of prediction.
EUROPEAN RADIOLOGY
(2023)
Article
Surgery
Yanzhe Liu, Shang Zhao, Gong Zhang, Xiuping Zhang, Minggen Hu, Xuan Zhang, Chenggang Li, S. Kevin Zhou, Rong Liu
Summary: The study constructed a multigranularity temporal annotation dataset and developed a deep learning-based automated model for multilevel overall and effective surgical workflow recognition. The research demonstrated a fairly higher accuracy in multilevel effective surgical workflow recognition when under-effective frames were removed. This study could contribute to the development of autonomous robotic surgery.
INTERNATIONAL JOURNAL OF SURGERY
(2023)
Review
Surgery
Elif Bilgic, Andrew Gorgy, Alison Yang, Michelle Cwintal, Hamed Ranjbar, Kalin Kahla, Dheeksha Reddy, Kexin Li, Helin Ozturk, Eric Zimmermann, Andrea Quaiattini, Samira Abbasgholizadeh-Rahimi, Dan Poenaru, Jason M. Harley
Summary: This scoping review aims to explore the current and future roles of Artificial Intelligence (AI) in surgical education. The study found that AI applications in the simulation setting were commonly used for assessing and classifying technical skills. Future directions include increasing sample size, using balanced data, and utilizing AI for feedback provision.
AMERICAN JOURNAL OF SURGERY
(2022)
Review
Surgery
Elif Bilgic, Andrew Gorgy, Alison Yang, Michelle Cwintal, Hamed Ranjbar, Kalin Kahla, Dheeksha Reddy, Kexin Li, Helin Ozturk, Eric Zimmermann, Andrea Quaiattini, Samira Abbasgholizadeh-Rahimi, Dan Poenaru, Jason M. Harley
Summary: This scoping review explores the roles of AI in surgical education, showing that AI is widely used in simulation settings and mainly focuses on skills assessment and classification. Future directions include increasing sample size, using balanced data, and utilizing AI to provide feedback.
AMERICAN JOURNAL OF SURGERY
(2022)
Article
Automation & Control Systems
Wenbo Zheng, Lan Yan, Wenwen Zhang, Liwei Ouyang, Ding Wen
Summary: Metaverse is the fusion of cyber-physical-social intelligence, and it becomes the core property of the metaverse. The education domain leads to the birth of the education metaverse, and this article explores smart services in this domain by addressing learning scene, technical framework, and initial expansion. The learning scene in the education metaverse consists of the learner, time, space, and learning events, and a data-knowledge-driven group intelligence framework is proposed to transform data into knowledge and integrate intelligence with knowledge. The application of this framework includes transaction and management services, and it promotes future research in this field.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2023)
Review
Oncology
Thomas M. Ward, Pietro Mascagni, Amin Madani, Nicolas Padoy, Silvana Perretta, Daniel A. Hashimoto
Summary: Surgical data science aims to enhance the quality and value of interventional healthcare by capturing, organizing, analyzing, and modeling procedural data. With advancements in artificial intelligence, SDS can unlock augmented and automated coaching, feedback, assessment, and decision support in surgery.
JOURNAL OF SURGICAL ONCOLOGY
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Yu Ding, Jingyu Zhang, Weitao Zhuang, Zhen Gao, Kaiming Kuang, Dan Tian, Cheng Deng, Hansheng Wu, Rixin Chen, Guojie Lu, Gang Chen, Paolo Mendogni, Marcello Migliore, Min-Woong Kang, Ryu Kanzaki, Yong Tang, Jiancheng Yang, Qiuling Shi, Guibin Qiao
Summary: A new pulmonary nodule diagnostic model was constructed in this study, which showed high diagnostic efficiency, non-invasiveness, and simplicity in measurement. By combining the 7-AAB panel, AI diagnostic system, and other clinical features, the model demonstrated good diagnostic performance in distinguishing lung nodules, especially those with diameters ≤ 2 cm.
EUROPEAN RADIOLOGY
(2023)
Letter
Biochemistry & Molecular Biology
Giovanni E. Cacciamani, Timothy N. Chu, Daniel I. Sanford, Andre Abreu, Vinay Duddalwar, Assad Oberai, C. -C. Jay Kuo, Xiaoxuan Liu, Alastair K. Denniston, Baptiste Vasey, Peter McCulloch, Robert F. Wolff, Sue Mallett, John Mongan, Charles E. Kahn, Viknesh Sounderajah, Ara Darzi, Philipp Dahm, Karel G. M. Moons, Eric Topol, Gary S. Collins, David Moher, Inderbir S. Gill, Andrew J. Hung
Article
Oncology
Richard Mateo Mora, Alireza Ghoreifi, Seyedeh-Sanam Ladi-Seyedian, Farshad Sheybaee Moghaddam, Jie Cai, Gus Miranda, Monish Aron, Anne Schuckman, Mihir Desai, Inderbir Gill, Siamak Daneshmand, Hooman Djaladat
Summary: This study evaluated the perioperative and functional outcomes of radical cystectomy and urinary diversion in patients with a single kidney compared to those with double kidneys. The results showed that patients with a single kidney had a longer length of hospital stay and greater decline in glomerular filtration rate, but similar rates of complications, readmission, and mortality compared to patients with double kidneys. Continent urinary diversion in single kidney patients was as safe as in double kidney patients.
UROLOGIC ONCOLOGY-SEMINARS AND ORIGINAL INVESTIGATIONS
(2023)
Article
Oncology
Sina Sobhani, Muhannad Alsyouf, Hamed Ahmadi, Alireza Ghoreifi, Wenhao Yu, Giovanni Cacciamani, Gus Miranda, Jie Cai, Sumeet Bhanvadia, Anne Schuckman, Monish Aron, Inderbir Gill, Siamak Daneshmand, Mihir Desai, Hooman Djaladat
Summary: This study aimed to evaluate the incidence and predictors of early postoperative acute kidney injury (EP-AKI) following radical cystectomy and its association with postoperative outcomes. The results showed that EP-AKI was associated with postoperative complications, longer hospital stay, and higher readmission rates. Perioperative blood transfusion and continent diversion were identified as independent predictors of EP-AKI.
UROLOGIC ONCOLOGY-SEMINARS AND ORIGINAL INVESTIGATIONS
(2023)
Article
Urology & Nephrology
Sina Sobhani, Alireza Ghoreifi, Antoin Douglawi, Hamed Ahmadi, Gus Miranda, Jie Cai, Monish Aron, Anne Schuckman, Mihir Desai, Inderbir Gill, Siamak Daneshmand, Hooman Djaladat
Summary: The study aims to evaluate the perioperative mortality and contributing variables among patients who underwent radical cystectomy (RC) for bladder cancer in recent decades, with comparison between modern and premodern eras. The study found that the 90-day mortality rate for RC is approaching five percent, with infectious, pulmonary, and cardiac complications as the leading mortality causes. Older age, higher comorbidity, blood transfusion, and pathological lymph node involvement are independently associated with 90-day mortality.
INTERNATIONAL BRAZ J UROL
(2023)
Review
Surgery
Tamir N. Sholklapper, Jorge Ballon, Aref S. Sayegh, Anibal La Riva, Laura C. Perez, Sherry Huang, Michael Eppler, Gregg Nelson, Giovanni Marchegiani, Robert Hinchliffe, Luca Gordini, Marc Furrer, Michael J. Brenner, Salome Dell-Kuster, Chandra Shekhar Biyani, Nader Francis, Haytham M. A. Kaafarani, Matthias Siepe, Des Winter, Julie A. Sosa, Francesco Bandello, Robert Siemens, Jochen Walz, Alberto Briganti, Christian Gratzke, Andre L. Abreu, Mihir M. Desai, Rene Sotelo, Riaz Agha, Keith D. Lillemoe, Steven Wexner, Gary S. Collins, Inderbir Gill, Giovanni E. Cacciamani
Summary: This study assesses the prevalence and typology of perioperative adverse event reporting guidelines among surgery and anesthesiology journals. Results show that 46.5% of the queried journals recommend surgical adverse event reporting. Journals in the surgery, urology, and anesthesia categories are most likely to recommend reporting; those in the top SJR quartiles and based in Western Europe, North America, and the Middle East are also more likely to recommend.
INTERNATIONAL JOURNAL OF SURGERY
(2023)
Article
Oncology
Felix Preisser, Reha-Baris Incesu, Pawel Rajwa, Marcin Chlosta, Mohamed Ahmed, Andre Luis Abreu, Giovanni Cacciamani, Luis Ribeiro, Alexander Kretschmer, Thilo Westhofen, Joseph A. Smith, Markus Graefen, Giorgio Calleris, Yannic Raskin, Paolo Gontero, Steven Joniau, Rafael Sanchez-Salas, Shahrokh F. Shariat, Inderbir Gill, Robert Jeffrey Karnes, Paul Cathcart, Henk van der Poel, Giancarlo Marra, Derya Tilki
Summary: Lymph node invasion is a poor prognostic factor for salvage prostatectomy patients. This study found that lymph node invasion significantly affects the oncologic outcomes after salvage prostatectomy. On the other hand, there is no benefit for lymph node dissection during salvage prostatectomy. These findings highlight the importance of cautious selection of lymph node dissection and strict postoperative monitoring for salvage prostatectomy patients with lymph node invasion.
Review
Urology & Nephrology
Sriram Deivasigamani, Srinath Kotamarti, Ardeshir R. Rastinehad, Rafael Sanchez Salas, J. J. M. C. H. de la Rosette, Herbert Lepor, Peter Pinto, Hashim U. Ahmed, Inderbir Gill, Laurence Klotz, Samir S. Taneja, Mark Emberton, Nathan Lawrentschuk, James Wysock, John F. Feller, Sebastien Crouzet, M. Praveen Kumar, Denis Seguier, Eric S. Adams, Zoe Michael, Andre Abreu, Kae Jack Tay, John F. Ward, Katsuto Shinohara, Aaron E. Katz, Arnauld Villers, Joseph L. Chin, Phillip D. Stricker, Eduard Baco, Petr Macek, Ardalan E. Ahmad, Peter K. F. Chiu, E. David Crawford, Craig G. Rogers, Jurgen J. Futterer, Soroush Rais-Bahrami, Cary N. Robertson, Boris Hadaschik, Giancarlo Marra, Massimo Valerio, Kian Tai, Veeru Kasivisvanathan, Wei Phin Tan, Derek Lomas, Jochen Walz, Gustavo Cardoso Guimaraes, Nikos I. Mertziotis, Ezequiel Becher, Antonio Finelli, Ali Kasraeian, Amir H. Lebastchi, Anup Vora, Mark A. Rosen, Baris Bakir, Rohit Arcot, Samuel Yee, Christopher Netsch, Xiaosong Meng, Theo M. de Reijke, Yu Guang Tan, Stefano Regusci, Tavya G. R. Benjamin, Ruben Olivares, Mohamed Noureldin, Fernando J. Bianco, Arjun Sivaraman, Fernando J. Kim, Robert W. Given, Shawn Dason, Tyler J. Sheetz, Sunao Shoji, Ariel Schulman, Peter Royce, Taimur T. Shah, Stephen Scionti, Georg Salomon, Pilar Laguna, Rafael Tourinho-Barbosa, Alireza Aminsharifi, Xavier Cathelineau, Paolo Gontero, Armando Stabile, Jeremy Grummet, Leila Ledbetter, Margaret Graton, J. Stephen Jones, Thomas J. Polascik
Summary: This article summarizes the mid-to long-term oncological and functional outcomes of whole-gland cryoablation and high-intensity focused ultrasound (HIFU) in patients with localized prostate cancer. The study found that these minimally invasive treatments can be offered as primary treatment options, with nearly equivalent oncological and toxicity outcomes, as well as excellent control of urinary continence.
Article
Urology & Nephrology
Giovanni E. Cacciamani, Andrew Chen, Inderbir S. Gill, Andrew J. J. Hung
Summary: This Perspective highlights the ethical challenges and proposed principles for the use of artificial intelligence (AI) in urology. AI has greatly benefited medical practice by improving patient workflow and diagnostic accuracy, but ethical issues such as patient safety, cybersecurity, and transparency need to be addressed. The authors recommend ethical principles to guide healthcare professionals, patients, and regulators in the responsible use of AI.
NATURE REVIEWS UROLOGY
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
T. Yin, T. Zhao, S. Cen, X. Lei, D. Hwang, S. Hajian, M. Desai, I. Gill, V. Duddalwar, B. A. Varghese
Summary: Morphological metrics like fractal dimension (FD) have been proven to be valuable in diagnosing and predicting various cancers. The lack of procedural consensus in fractal techniques may hinder the generalizability of results across different studies. This study investigates the variations of FD in renal masses derived from Computed Tomography (CT) using different fractal analysis implementations.
18TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Alexander Te-Wei Shieh, Steven Yong Cen, Bino Varghese, Darryl Hwa Hwang, Xiaomeng Lei, Kirthika Gurumurthy, Imran Siddiqi, Manju Aron, Inderbir Gill, William Dean Wallace, Vinay Anant Duddalwar
Summary: This study investigates the correlation between radiomic features extracted from CT imaging and tumor immune microenvironment (TIME) measurements from multiplex immunohistochemistry (mIHC) analysis. The findings show a significant correlation between these radiomic features and the levels of PD-L1 expression and CD8(+)PD-1(+) T cell to CD8(+) T cell ratio.
18TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS
(2023)
Article
Urology & Nephrology
Arnauld Villers, Denis Seguier, Philippe Puech, Georges-Pascal Haber, Mihir M. Desai, Sebastien Crouzet, Xavier Leroy, Julien Labreuche, Inderbir S. Gill, Jonathan Olivier
Summary: This report describes the long-term outcomes of robotic-assisted anterior partial prostatectomy (APP) for anteriorly located tumors. The results show that continence and erectile function were well preserved, and the cancer recurrence rate was 62.7%. Overall, this surgical procedure has good functional outcomes and acceptable oncological results, but there is a risk of recurrence.
EUROPEAN UROLOGY OPEN SCIENCE
(2023)
Letter
Multidisciplinary Sciences
Giovanni E. Cacciamani, Inderbir S. Gill, Gary S. Collins
Article
Urology & Nephrology
Alireza Ghoreifi, Masatomo Kaneko, Samuel Peretsman, Atsuko Iwata, Jessica Brooks, Aliasger Shakir, Dordaneh Sugano, Jie Cai, Giovanni Cacciamani, Daniel Park, Amir H. Lebastchi, Osamu Ukimura, Duke Bahn, Inderbir Gill, Andre Luis Abreu
Summary: This study aimed to evaluate the treatment decision satisfaction and regret among patients who underwent focal therapy (FT) for localized prostate cancer. The results showed that FT is well accepted by patients with a low regret rate. Factors that affect treatment regret include higher post-treatment prostate-specific antigen (PSA) levels, presence of cancer on follow-up biopsy, bothersome postoperative urinary symptoms, and impotence.
EUROPEAN UROLOGY OPEN SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Wenzheng Hu, Zhengping Che, Ning Liu, Mingyang Li, Jian Tang, Changshui Zhang, Jianqiang Wang
Summary: In this article, a novel channel pruning method based on class-aware trace ratio optimization () is proposed to reduce computational burden and accelerate model inference. Experimental results demonstrate that achieves higher accuracy with similar computation cost or lower computation cost with similar accuracy than other state-of-the-art channel pruning algorithms. Furthermore, it is suitable to prune efficient networks adaptively for various classification subtasks, enhancing handy deployment and usage of deep networks in real-world applications.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Yushuo Guan, Ning Liu, Pengyu Zhao, Zhengping Che, Kaigui Bian, Yanzhi Wang, Jian Tang
Summary: This article introduces a channel pruning method for neural networks based on differentiable annealing indicator search (DAIS), which can automatically search for an effective pruned model with given constraints on computation overhead. DAIS relaxes the binarized channel indicators to be continuous and jointly learns both indicators and model parameters through bi-level optimization. DAIS also proposes an annealing-based procedure and various regularizations to control the pruning sparsity and improve model performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)