Search

Your search keyword '"Meakin, James"' showing total 29 results
Start Over Author "Meakin, James"
29 results on '"Meakin, James"'

1. A Robust Ensemble Algorithm for Ischemic Stroke Lesion Segmentation: Generalizability and Clinical Utility Beyond the ISLES Challenge

Author

de la Rosa, Ezequiel, Reyes, Mauricio, Liew, Sook-Lei, Hutton, Alexandre, Wiest, Roland, Kaesmacher, Johannes, Hanning, Uta, Hakim, Arsany, Zubal, Richard, Valenzuela, Waldo, Robben, David, Sima, Diana M., Anania, Vincenzo, Brys, Arne, Meakin, James A., Mickan, Anne, Broocks, Gabriel, Heitkamp, Christian, Gao, Shengbo, Liang, Kongming, Zhang, Ziji, Siddiquee, Md Mahfuzur Rahman, Myronenko, Andriy, Ashtari, Pooya, Van Huffel, Sabine, Jeong, Hyun-su, Yoon, Chi-ho, Kim, Chulhong, Huo, Jiayu, Ourselin, Sebastien, Sparks, Rachel, Clèrigues, Albert, Oliver, Arnau, Lladó, Xavier, Chalcroft, Liam, Pappas, Ioannis, Bertels, Jeroen, Heylen, Ewout, Moreau, Juliette, Hatami, Nima, Frindel, Carole, Qayyum, Abdul, Mazher, Moona, Puig, Domenec, Lin, Shao-Chieh, Juan, Chun-Jung, Hu, Tianxi, Boone, Lyndon, Goubran, Maged, Liu, Yi-Jui, Wegener, Susanne, Kofler, Florian, Ezhov, Ivan, Shit, Suprosanna, Petzsche, Moritz R. Hernandez, Menze, Bjoern, Kirschke, Jan S., and Wiestler, Benedikt

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Diffusion-weighted MRI (DWI) is essential for stroke diagnosis, treatment decisions, and prognosis. However, image and disease variability hinder the development of generalizable AI algorithms with clinical value. We address this gap by presenting a novel ensemble algorithm derived from the 2022 Ischemic Stroke Lesion Segmentation (ISLES) challenge. ISLES'22 provided 400 patient scans with ischemic stroke from various medical centers, facilitating the development of a wide range of cutting-edge segmentation algorithms by the research community. Through collaboration with leading teams, we combined top-performing algorithms into an ensemble model that overcomes the limitations of individual solutions. Our ensemble model achieved superior ischemic lesion detection and segmentation accuracy on our internal test set compared to individual algorithms. This accuracy generalized well across diverse image and disease variables. Furthermore, the model excelled in extracting clinical biomarkers. Notably, in a Turing-like test, neuroradiologists consistently preferred the algorithm's segmentations over manual expert efforts, highlighting increased comprehensiveness and precision. Validation using a real-world external dataset (N=1686) confirmed the model's generalizability. The algorithm's outputs also demonstrated strong correlations with clinical scores (admission NIHSS and 90-day mRS) on par with or exceeding expert-derived results, underlining its clinical relevance. This study offers two key findings. First, we present an ensemble algorithm (https://github.com/Tabrisrei/ISLES22_Ensemble) that detects and segments ischemic stroke lesions on DWI across diverse scenarios on par with expert (neuro)radiologists. Second, we show the potential for biomedical challenge outputs to extend beyond the challenge's initial objectives, demonstrating their real-world clinical applicability.

Published
2024

2. The STOIC2021 COVID-19 AI challenge: applying reusable training methodologies to private data

Author

Boulogne, Luuk H., Lorenz, Julian, Kienzle, Daniel, Schon, Robin, Ludwig, Katja, Lienhart, Rainer, Jegou, Simon, Li, Guang, Chen, Cong, Wang, Qi, Shi, Derik, Maniparambil, Mayug, Muller, Dominik, Mertes, Silvan, Schroter, Niklas, Hellmann, Fabio, Elia, Miriam, Dirks, Ine, Bossa, Matias Nicolas, Berenguer, Abel Diaz, Mukherjee, Tanmoy, Vandemeulebroucke, Jef, Sahli, Hichem, Deligiannis, Nikos, Gonidakis, Panagiotis, Huynh, Ngoc Dung, Razzak, Imran, Bouadjenek, Reda, Verdicchio, Mario, Borrelli, Pasquale, Aiello, Marco, Meakin, James A., Lemm, Alexander, Russ, Christoph, Ionasec, Razvan, Paragios, Nikos, van Ginneken, Bram, and Dubois, Marie-Pierre Revel

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Challenges drive the state-of-the-art of automated medical image analysis. The quantity of public training data that they provide can limit the performance of their solutions. Public access to the training methodology for these solutions remains absent. This study implements the Type Three (T3) challenge format, which allows for training solutions on private data and guarantees reusable training methodologies. With T3, challenge organizers train a codebase provided by the participants on sequestered training data. T3 was implemented in the STOIC2021 challenge, with the goal of predicting from a computed tomography (CT) scan whether subjects had a severe COVID-19 infection, defined as intubation or death within one month. STOIC2021 consisted of a Qualification phase, where participants developed challenge solutions using 2000 publicly available CT scans, and a Final phase, where participants submitted their training methodologies with which solutions were trained on CT scans of 9724 subjects. The organizers successfully trained six of the eight Final phase submissions. The submitted codebases for training and running inference were released publicly. The winning solution obtained an area under the receiver operating characteristic curve for discerning between severe and non-severe COVID-19 of 0.815. The Final phase solutions of all finalists improved upon their Qualification phase solutions.HSUXJM-TNZF9CHSUXJM-TNZF9C

Published
2023

3. Velocity‐selective arterial spin labeling perfusion MRI: A review of the state of the art and recommendations for clinical implementation

Author

Qin, Qin, Alsop, David C, Bolar, Divya S, Hernandez‐Garcia, Luis, Meakin, James, Liu, Dapeng, Nayak, Krishna S, Schmid, Sophie, Osch, Matthias JP, Wong, Eric C, Woods, Joseph G, Zaharchuk, Greg, Zhao, Moss Y, Zun, Zungho, Guo, Jia, and Group, the ISMRMPerfusion Study

Subjects
Engineering, Biomedical Engineering, Biomedical Imaging, Neurosciences, Cerebrovascular Circulation, Magnetic Resonance Angiography, Magnetic Resonance Imaging, Perfusion, Spin Labels, arterial spin labeling, arterial transit delay, cerebral blood flow, perfusion, velocity selective arterial spin labeling, velocity selectivity, ISMRMPerfusion Study Group, Nuclear Medicine & Medical Imaging, Biomedical engineering
Abstract

This review article provides an overview of the current status of velocity-selective arterial spin labeling (VSASL) perfusion MRI and is part of a wider effort arising from the International Society for Magnetic Resonance in Medicine (ISMRM) Perfusion Study Group. Since publication of the 2015 consensus paper on arterial spin labeling (ASL) for cerebral perfusion imaging, important advancements have been made in the field. The ASL community has, therefore, decided to provide an extended perspective on various aspects of technical development and application. Because VSASL has the potential to become a principal ASL method because of its unique advantages over traditional approaches, an in-depth discussion was warranted. VSASL labels blood based on its velocity and creates a magnetic bolus immediately proximal to the microvasculature within the imaging volume. VSASL is, therefore, insensitive to transit delay effects, in contrast to spatially selective pulsed and (pseudo-) continuous ASL approaches. Recent technical developments have improved the robustness and the labeling efficiency of VSASL, making it a potentially more favorable ASL approach in a wide range of applications where transit delay effects are of concern. In this review article, we (1) describe the concepts and theoretical basis of VSASL; (2) describe different variants of VSASL and their implementation; (3) provide recommended parameters and practices for clinical adoption; (4) describe challenges in developing and implementing VSASL; and (5) describe its current applications. As VSASL continues to undergo rapid development, the focus of this review is to summarize the fundamental concepts of VSASL, describe existing VSASL techniques and applications, and provide recommendations to help the clinical community adopt VSASL.

Published
2022

4. The STOIC2021 COVID-19 AI challenge: Applying reusable training methodologies to private data

Author

Boulogne, Luuk H., Lorenz, Julian, Kienzle, Daniel, Schön, Robin, Ludwig, Katja, Lienhart, Rainer, Jégou, Simon, Li, Guang, Chen, Cong, Wang, Qi, Shi, Derik, Maniparambil, Mayug, Müller, Dominik, Mertes, Silvan, Schröter, Niklas, Hellmann, Fabio, Elia, Miriam, Dirks, Ine, Bossa, Matías Nicolás, Berenguer, Abel Díaz, Mukherjee, Tanmoy, Vandemeulebroucke, Jef, Sahli, Hichem, Deligiannis, Nikos, Gonidakis, Panagiotis, Huynh, Ngoc Dung, Razzak, Imran, Bouadjenek, Reda, Verdicchio, Mario, Borrelli, Pasquale, Aiello, Marco, Meakin, James A., Lemm, Alexander, Russ, Christoph, Ionasec, Razvan, Paragios, Nikos, van Ginneken, Bram, and Revel, Marie-Pierre

Published
2024
Full Text
View/download PDF

5. Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study

Author

Saha, Anindo, Bosma, Joeran S., Twilt, Jasper J., van Ginneken, Bram, Noordman, Constant R., Slootweg, Ivan, Roest, Christian, Fransen, Stefan J., Sunoqrot, Mohammed R.S., Bathen, Tone F., Rouw, Dennis, Immerzeel, Jos, Geerdink, Jeroen, van Run, Chris, Groeneveld, Miriam, Meakin, James, Karagöz, Ahmet, Bône, Alexandre, Routier, Alexandre, Marcoux, Arnaud, Abi-Nader, Clément, Li, Cynthia Xinran, Feng, Dagan, Alis, Deniz, Karaarslan, Ercan, Ahn, Euijoon, Nicolas, François, Sonn, Geoffrey A., Bhattacharya, Indrani, Kim, Jinman, Shi, Jun, Jahanandish, Hassan, An, Hong, Kan, Hongyu, Oksuz, Ilkay, Qiao, Liang, Rohé, Marc-Michel, Yergin, Mert, Khadra, Mohamed, Şeker, Mustafa E., Kartal, Mustafa S., Debs, Noëlie, Fan, Richard E., Saunders, Sara, Soerensen, Simon J.C., Moroianu, Stefania, Vesal, Sulaiman, Yuan, Yuan, Malakoti-Fard, Afsoun, Mačiūnien, Agnė, Kawashima, Akira, de Sousa Machadov, Ana M.M. de M.G., Moreira, Ana Sofia L., Ponsiglione, Andrea, Rappaport, Annelies, Stanzione, Arnaldo, Ciuvasovas, Arturas, Turkbey, Baris, de Keyzer, Bart, Pedersen, Bodil G., Eijlers, Bram, Chen, Christine, Riccardo, Ciabattoni, Courrech Staal, Ewout F.W., Jäderling, Fredrik, Langkilde, Fredrik, Aringhieri, Giacomo, Brembilla, Giorgio, Son, Hannah, Vanderlelij, Hans, Raat, Henricus P.J., Pikūnienė, Ingrida, Macova, Iva, Schoots, Ivo, Caglic, Iztok, Zawaideh, Jeries P., Wallström, Jonas, Bittencourt, Leonardo K., Khurram, Misbah, Choi, Moon H., Takahashi, Naoki, Tan, Nelly, Franco, Paolo N., Gutierrez, Patricia A., Thimansson, Per Erik, Hanus, Pieter, Puech, Philippe, Rau, Philipp R., de Visschere, Pieter, Guillaume, Ramette, Cuocolo, Renato, Falcão, Ricardo O., van Stiphout, Rogier S.A., Girometti, Rossano, Briediene, Ruta, Grigienė, Rūta, Gitau, Samuel, Withey, Samuel, Ghai, Sangeet, Penzkofer, Tobias, Barrett, Tristan, Tammisetti, Varaha S., Løgager, Vibeke B., Černý, Vladimír, Venderink, Wulphert, Law, Yan M., Lee, Young J., Bjartell, Anders, Padhani, Anwar R., Bonekamp, David, Villeirs, Geert, Salomon, Georg, Giannarini, Gianluca, Kalpathy-Cramer, Jayashree, Barentsz, Jelle, Maier-Hein, Klaus H., Rusu, Mirabela, Obuchowski, Nancy A., Rouvière, Olivier, van den Bergh, Roderick, Panebianco, Valeria, Kasivisvanathan, Veeru, Yakar, Derya, Elschot, Mattijs, Veltman, Jeroen, Fütterer, Jurgen J., de Rooij, Maarten, Huisman, Henkjan, Bosma, Joeran S, Twilt, Jasper J, Padhani, Anwar R, Maier-Hein, Klaus H, Obuchowski, Nancy A, and Fütterer, Jurgen J

Published
2024
Full Text
View/download PDF

6. The Medical Segmentation Decathlon

Author

Antonelli, Michela, Reinke, Annika, Bakas, Spyridon, Farahani, Keyvan, AnnetteKopp-Schneider, Landman, Bennett A., Litjens, Geert, Menze, Bjoern, Ronneberger, Olaf, Summers, Ronald M., van Ginneken, Bram, Bilello, Michel, Bilic, Patrick, Christ, Patrick F., Do, Richard K. G., Gollub, Marc J., Heckers, Stephan H., Huisman, Henkjan, Jarnagin, William R., McHugo, Maureen K., Napel, Sandy, Pernicka, Jennifer S. Goli, Rhode, Kawal, Tobon-Gomez, Catalina, Vorontsov, Eugene, Meakin, James A., Ourselin, Sebastien, Wiesenfarth, Manuel, Arbelaez, Pablo, Bae, Byeonguk, Chen, Sihong, Daza, Laura, Feng, Jianjiang, He, Baochun, Isensee, Fabian, Ji, Yuanfeng, Jia, Fucang, Kim, Namkug, Kim, Ildoo, Merhof, Dorit, Pai, Akshay, Park, Beomhee, Perslev, Mathias, Rezaiifar, Ramin, Rippel, Oliver, Sarasua, Ignacio, Shen, Wei, Son, Jaemin, Wachinger, Christian, Wang, Liansheng, Wang, Yan, Xia, Yingda, Xu, Daguang, Xu, Zhanwei, Zheng, Yefeng, Simpson, Amber L., Maier-Hein, Lena, and Cardoso, M. Jorge

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, 68T07
Abstract

International challenges have become the de facto standard for comparative assessment of image analysis algorithms given a specific task. Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem. We hypothesized that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. To investigate the hypothesis, we organized the Medical Segmentation Decathlon (MSD) - a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities. The underlying data set was designed to explore the axis of difficulties typically encountered when dealing with medical images, such as small data sets, unbalanced labels, multi-site data and small objects. The MSD challenge confirmed that algorithms with a consistent good performance on a set of tasks preserved their good average performance on a different set of previously unseen tasks. Moreover, by monitoring the MSD winner for two years, we found that this algorithm continued generalizing well to a wide range of other clinical problems, further confirming our hypothesis. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms are mature, accurate, and generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to non AI experts.

Published
2021
Full Text
View/download PDF

7. The Medical Segmentation Decathlon

Author

Antonelli, Michela, Reinke, Annika, Bakas, Spyridon, Farahani, Keyvan, Kopp-Schneider, Annette, Landman, Bennett A., Litjens, Geert, Menze, Bjoern, Ronneberger, Olaf, Summers, Ronald M., van Ginneken, Bram, Bilello, Michel, Bilic, Patrick, Christ, Patrick F., Do, Richard K. G., Gollub, Marc J., Heckers, Stephan H., Huisman, Henkjan, Jarnagin, William R., McHugo, Maureen K., Napel, Sandy, Pernicka, Jennifer S. Golia, Rhode, Kawal, Tobon-Gomez, Catalina, Vorontsov, Eugene, Meakin, James A., Ourselin, Sebastien, Wiesenfarth, Manuel, Arbeláez, Pablo, Bae, Byeonguk, Chen, Sihong, Daza, Laura, Feng, Jianjiang, He, Baochun, Isensee, Fabian, Ji, Yuanfeng, Jia, Fucang, Kim, Ildoo, Maier-Hein, Klaus, Merhof, Dorit, Pai, Akshay, Park, Beomhee, Perslev, Mathias, Rezaiifar, Ramin, Rippel, Oliver, Sarasua, Ignacio, Shen, Wei, Son, Jaemin, Wachinger, Christian, Wang, Liansheng, Wang, Yan, Xia, Yingda, Xu, Daguang, Xu, Zhanwei, Zheng, Yefeng, Simpson, Amber L., Maier-Hein, Lena, and Cardoso, M. Jorge

Published
2022
Full Text
View/download PDF

8. Erratum to: Velocity‐selective arterial spin labeling perfusion MRI: A review of the state of the art and recommendations for clinical implementation (Magn Reson Med. 2022; 88:1528–1547)

Author

Qin, Qin, primary, Alsop, David C., additional, Bolar, Divya S., additional, Hernandez‐Garcia, Luis, additional, Meakin, James, additional, Liu, Dapeng, additional, Nayak, Krishna S., additional, Schmid, Sophie, additional, van Osch, Matthias J. P., additional, Wong, Eric C., additional, Woods, Joseph G., additional, Zaharchuk, Greg, additional, Zhao, Moss Y., additional, Zun, Zungho, additional, and Guo, Jia, additional

Published
2024
Full Text
View/download PDF

9. Velocity selective preparations in Magnetic Resonance Imaging

Author

Meakin, James A. and Jezzard, Peter

Subjects
616.07, Oncology, Medical Sciences, Physics, Medical Engineering, Arterial Spin Labeling, Magnetic Resonance Imaging
Abstract

Arterial Spin Labeling (ASL) is a Magnetic Resonance Imaging (MRI) technique that is able to non-invasively quantify the rate of delivery of arterial blood to tissue, known as perfusion. In this thesis a method that uses Velocity Selective (VS) preparations to generate contrast between blood and tissue spins is investigated. The systematic errors associated with performing a VSASL experiment on imperfect hardware is first investigated. It is shown through simulations and experiments that some VS preparations will underestimate perfusion due to static and transmit magnetic field errors, and that eddy currents caused by switching of magnetic gradients lead to an overestimation of perfusion with VSASL by up to a factor 2. A novel VS preparation, BIR-8, is presented which is shown to be the most robust to these imperfections. The BIR-8 VSASL technique is then applied in brain tumours where it is found that significant VSASL signal can be detected in less than 5 minutes. However, in a comparison with a spatially selective ASL technique it is found that VSASL overestimates perfusion in these tumours, despite agreeing in Grey Matter. The systematic errors due to physiology are then modelled, and it is shown that both diffusion and bulk motion will systematically bias the VSASL measurement. A diffusion insensitive VSASL technique, VS-TILT, is then developed and it is found that a significant proportion of the VSASL signal originates from diffusion effects. Theoretical models for the shape of the bolus in vascular networks are also derived, and it is shown that an isotropic network of laminar vessels produces the most efficient saturation, but saturation is also achieved with plug flow. The diffusion insensitive VS preparation is then applied in an attempt to isolate the venous compartment in order to measure Oxygen Extraction Fraction. A kinetic model is derived in order to optimise the acquisition. However, it is found that accurate measurements of OEF would not be produced by this sequence in a clinically realistic time.

Published
2014

11. Practical guide to Software Management Plans

Author

Martinez-Ortiz, Carlos, Martinez Lavanchy, Paula, Sesink, Laurents, Olivier, Brett G., Meakin, James, de Jong, Maaike, Cruz, Maria, Akhmerov, Anton, Ancion, Zoé, de Bruin, Jonathan, Culina, Antica, Erdmann, Christopher, Grootveld, Marjan, Psomopoulos, Fotis E., Sarkol, Vera, van Leeuwen, Caspar Martijn, and Vinju, Jurgen J.

Subjects
Software Management Plan, Software Management, Software sustainability, Research Software
Abstract

Research software plays a crucial role in academic research and has become a key output of many research projects. A software management plan helps to implement best practices during software development and ensures that software is accessible and reusable in the short and longer term. It also contributes to the reproducibility of results and stimulates collaborative work on open-source software for research. TheNetherlands eScience CenterandNWO, the Dutch Research Council, tookthe initiative to form a working group anddevelop ed (national) guidelines for software management plans. This working group was composed of five experts in research software, representing different research organizations in the Netherlands, and roles within those organizations. The working group was active between December 2021 and September 2022.

Published
2023
Full Text
View/download PDF

12. Erratum to: Velocity‐selective arterial spin labeling perfusion MRI : A review of the state of the art and recommendations for clinical implementation (Magn Reson Med. 2022; 88:1528–1547)

Author

Qin, Qin, primary, Alsop, David C., additional, Bolar, Divya S., additional, Hernandez‐Garcia, Luis, additional, Meakin, James, additional, Liu, Dapeng, additional, Nayak, Krishna S., additional, Schmid, Sophie, additional, van Osch, Matthias J. P., additional, Wong, Eric C., additional, Woods, Joseph G., additional, Zaharchuk, Greg, additional, Zhao, Moss Y., additional, Zun, Zungho, additional, and Guo, Jia, additional

Published
2022
Full Text
View/download PDF

14. The Medical Segmentation Decathlon

Author

Antonelli, Michela; https://orcid.org/0000-0002-3005-4523, Reinke, Annika; https://orcid.org/0000-0003-4363-1876, Bakas, Spyridon; https://orcid.org/0000-0001-8734-6482, Farahani, Keyvan, Kopp-Schneider, Annette; https://orcid.org/0000-0002-1810-0267, Landman, Bennett A; https://orcid.org/0000-0001-5733-2127, Litjens, Geert; https://orcid.org/0000-0003-1554-1291, Menze, Bjoern; https://orcid.org/0000-0003-4136-5690, Ronneberger, Olaf, Summers, Ronald M, van Ginneken, Bram, Bilello, Michel; https://orcid.org/0000-0001-6313-5437, Bilic, Patrick, Christ, Patrick F, Do, Richard K G; https://orcid.org/0000-0002-6554-0310, Gollub, Marc J; https://orcid.org/0000-0002-6008-0730, Heckers, Stephan H, Huisman, Henkjan; https://orcid.org/0000-0001-6753-3221, Jarnagin, William R, McHugo, Maureen K, Napel, Sandy; https://orcid.org/0000-0002-6876-5507, Pernicka, Jennifer S Golia; https://orcid.org/0000-0002-1076-7948, Rhode, Kawal, Tobon-Gomez, Catalina, Vorontsov, Eugene; https://orcid.org/0000-0002-4530-533X, Meakin, James A, Ourselin, Sébastien; https://orcid.org/0000-0002-5694-5340, Wiesenfarth, Manuel, Arbeláez, Pablo, Bae, Byeonguk; https://orcid.org/0000-0003-2309-8517, et al, Antonelli, Michela; https://orcid.org/0000-0002-3005-4523, Reinke, Annika; https://orcid.org/0000-0003-4363-1876, Bakas, Spyridon; https://orcid.org/0000-0001-8734-6482, Farahani, Keyvan, Kopp-Schneider, Annette; https://orcid.org/0000-0002-1810-0267, Landman, Bennett A; https://orcid.org/0000-0001-5733-2127, Litjens, Geert; https://orcid.org/0000-0003-1554-1291, Menze, Bjoern; https://orcid.org/0000-0003-4136-5690, Ronneberger, Olaf, Summers, Ronald M, van Ginneken, Bram, Bilello, Michel; https://orcid.org/0000-0001-6313-5437, Bilic, Patrick, Christ, Patrick F, Do, Richard K G; https://orcid.org/0000-0002-6554-0310, Gollub, Marc J; https://orcid.org/0000-0002-6008-0730, Heckers, Stephan H, Huisman, Henkjan; https://orcid.org/0000-0001-6753-3221, Jarnagin, William R, McHugo, Maureen K, Napel, Sandy; https://orcid.org/0000-0002-6876-5507, Pernicka, Jennifer S Golia; https://orcid.org/0000-0002-1076-7948, Rhode, Kawal, Tobon-Gomez, Catalina, Vorontsov, Eugene; https://orcid.org/0000-0002-4530-533X, Meakin, James A, Ourselin, Sébastien; https://orcid.org/0000-0002-5694-5340, Wiesenfarth, Manuel, Arbeláez, Pablo, Bae, Byeonguk; https://orcid.org/0000-0003-2309-8517, and et al

Abstract

International challenges have become the de facto standard for comparative assessment of image analysis algorithms. Although segmentation is the most widely investigated medical image processing task, the various challenges have been organized to focus only on specific clinical tasks. We organized the Medical Segmentation Decathlon (MSD)—a biomedical image analysis challenge, in which algorithms compete in a multitude of both tasks and modalities to investigate the hypothesis that a method capable of performing well on multiple tasks will generalize well to a previously unseen task and potentially outperform a custom-designed solution. MSD results confirmed this hypothesis, moreover, MSD winner continued generalizing well to a wide range of other clinical problems for the next two years. Three main conclusions can be drawn from this study: (1) state-of-the-art image segmentation algorithms generalize well when retrained on unseen tasks; (2) consistent algorithmic performance across multiple tasks is a strong surrogate of algorithmic generalizability; (3) the training of accurate AI segmentation models is now commoditized to scientists that are not versed in AI model training.

Published
2022

17. Automated Assessment of CO-RADS and Chest CT Severity Scores in Patients with Suspected COVID-19 Using Artificial Intelligence

Author

Lessmann, Nikolas, Sánchez, Clara I., Beenen, Ludo, Boulogne, Luuk H., Brink, Monique, Calli, Erdi, Charbonnier, Jean-Paul, Dofferhoff, Ton, van Everdingen, Wouter M., Gerke, Paul K., Geurts, Bram, Gietema, Hester A., Groeneveld, Miriam, van Harten, Louis, Hendrix, Nils, Hendrix, Ward, Huisman, Henkjan J., Išgum, Ivana, Jacobs, Colin, Kluge, Ruben, Kok, Michel, Krdzalic, Jasenko, Lassen-Schmidt, Bianca, van Leeuwen, Kicky, Meakin, James, Overkamp, Mike, van Rees Vellinga, Tjalco, van Rikxoort, Eva M., Samperna, Riccardo, Schaefer-Prokop, Cornelia, Schalekamp, Steven, Scholten, Ernst Th., Sital, Cheryl, Stöger, Lauran, Teuwen, Jonas, Vaidhya Venkadesh, Kiran, de Vente, Coen, Vermaat, Marieke, Xie, Weiyi, de Wilde, Bram, Prokop, Mathias, and van Ginneken, Bram

Subjects
Male, COVID-19, Middle Aged, Thorax, Severity of Illness Index, Thoracic Imaging, Artificial Intelligence, Research Design, Data Systems, Humans, Female, Tomography, X-Ray Computed, Original Research, Aged, Retrospective Studies
Abstract

Background The coronavirus disease 2019 (COVID-19) pandemic has spread across the globe with alarming speed, morbidity, and mortality. Immediate triage of patients with chest infections suspected to be caused by COVID-19 using chest CT may be of assistance when results from definitive viral testing are delayed. Purpose To develop and validate an artificial intelligence (AI) system to score the likelihood and extent of pulmonary COVID-19 on chest CT scans using the COVID-19 Reporting and Data System (CO-RADS) and CT severity scoring systems. Materials and Methods The CO-RADS AI system consists of three deep-learning algorithms that automatically segment the five pulmonary lobes, assign a CO-RADS score for the suspicion of COVID-19, and assign a CT severity score for the degree of parenchymal involvement per lobe. This study retrospectively included patients who underwent a nonenhanced chest CT examination because of clinical suspicion of COVID-19 at two medical centers. The system was trained, validated, and tested with data from one of the centers. Data from the second center served as an external test set. Diagnostic performance and agreement with scores assigned by eight independent observers were measured using receiver operating characteristic analysis, linearly weighted κ values, and classification accuracy. Results A total of 105 patients (mean age, 62 years ± 16 [standard deviation]; 61 men) and 262 patients (mean age, 64 years ± 16; 154 men) were evaluated in the internal and external test sets, respectively. The system discriminated between patients with COVID-19 and those without COVID-19, with areas under the receiver operating characteristic curve of 0.95 (95% CI: 0.91, 0.98) and 0.88 (95% CI: 0.84, 0.93), for the internal and external test sets, respectively. Agreement with the eight human observers was moderate to substantial, with mean linearly weighted κ values of 0.60 ± 0.01 for CO-RADS scores and 0.54 ± 0.01 for CT severity scores. Conclusion With high diagnostic performance, the CO-RADS AI system correctly identified patients with COVID-19 using chest CT scans and assigned standardized CO-RADS and CT severity scores that demonstrated good agreement with findings from eight independent observers and generalized well to external data. © RSNA, 2020

Published
2020

18. Automated Assessment of COVID-19 Reporting and Data System and Chest CT Severity Scores in Patients Suspected of Having COVID-19 Using Artificial Intelligence

Author

Lessmann, Nikolas, primary, Sánchez, Clara I., additional, Beenen, Ludo, additional, Boulogne, Luuk H., additional, Brink, Monique, additional, Calli, Erdi, additional, Charbonnier, Jean-Paul, additional, Dofferhoff, Ton, additional, van Everdingen, Wouter M., additional, Gerke, Paul K., additional, Geurts, Bram, additional, Gietema, Hester A., additional, Groeneveld, Miriam, additional, van Harten, Louis, additional, Hendrix, Nils, additional, Hendrix, Ward, additional, Huisman, Henkjan J., additional, Išgum, Ivana, additional, Jacobs, Colin, additional, Kluge, Ruben, additional, Kok, Michel, additional, Krdzalic, Jasenko, additional, Lassen-Schmidt, Bianca, additional, van Leeuwen, Kicky, additional, Meakin, James, additional, Overkamp, Mike, additional, van Rees Vellinga, Tjalco, additional, van Rikxoort, Eva M., additional, Samperna, Riccardo, additional, Schaefer-Prokop, Cornelia, additional, Schalekamp, Steven, additional, Scholten, Ernst Th., additional, Sital, Cheryl, additional, Stöger, J. Lauran, additional, Teuwen, Jonas, additional, Venkadesh, Kiran Vaidhya, additional, de Vente, Coen, additional, Vermaat, Marieke, additional, Xie, Weiyi, additional, de Wilde, Bram, additional, Prokop, Mathias, additional, and van Ginneken, Bram, additional

Published
2021
Full Text
View/download PDF

23. Erratum to: Velocity‐selective arterial spin labeling perfusion MRI: A review of the state of the art and recommendations for clinical implementation (Magn Reson Med. 2022; 88:1528–1547).

Author

Qin, Qin, Alsop, David C., Bolar, Divya S., Hernandez‐Garcia, Luis, Meakin, James, Liu, Dapeng, Nayak, Krishna S., Schmid, Sophie, van Osch, Matthias J. P., Wong, Eric C., Woods, Joseph G., Zaharchuk, Greg, Zhao, Moss Y., Zun, Zungho, and Guo, Jia

Subjects
SPIN labels, MAGNETIC resonance imaging, PERFUSION, BLOOD flow
Abstract

In the above referenced article, we would like to correct the error of the misplaced SI SB B sb term and update the Equation (1) as well as the first sentence of Section 9.5 as below: 9.5 Quantification of VSASL The blood flow (BF, in mL/100 g/min) can be quantified based on the kinetic model as: 1 HT BF=6000- - S-eTIT1,blood2- - -SIPD-SIB$$ \mathrm{BF}=\frac{6000\cdot \uplambda \cdot \Delta \mathrm{S}\cdot {e}^{\frac{\mathrm{T}\mathrm{I}}{{\mathrm{T}} {1,\mathrm{blood}}}}}{2\cdot \upalpha \cdot \uptau \cdot {\mathrm{SI}} {\mathrm{PD}}\cdot {\mathrm{SI}} {\mathrm{B}}} $$ ht Erratum to: Velocity-selective arterial spin labeling perfusion MRI: A review of the state of the art and recommendations for clinical implementation (Magn Reson Med. [Extracted from the article]

Published
2023
Full Text
View/download PDF

24. Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction

Author

Leeuwen, Kicky G. van, Schalekamp, Steven, Rutten, Matthieu J. C. M., Huisman, Merel, Schaefer-Prokop, Cornelia M., Rooij, Maarten de, Ginneken, Bram van, Maresch, Bas, Geurts, Bram H. J., Dijke, Cornelius F. van, Laupman-Koedam, Emmeline, Hulleman, Enzo V., Verhoeff, Eric L., Meys, Evelyne M. J., Mohamed Hoesein, Firdaus A. A., Brugge, Floor M. ter, Hoorn, Francois van, Wel, Frank van der, Berk, Inge A. H. van den, Luyendijk, Jacqueline M., Meakin, James, Habets, Jesse, Verbeke, Jonathan I. M. L., Nederend, Joost, Meys, Karlijn M. E., Deden, Laura N., Langezaal, Lucianne C. M., Nasrollah, Mahtab, Meij, Marleen, Boomsma, Martijn F., Vermeulen, Matthijs, Vestering, Myrthe M., Vijlbrief, Onno, Algra, Paul, Algra, Selma, Bollen, Stijn M., Samson, Tijs, and Fock, Yntor H. G. von Brucken

Abstract

In independent validation, nine artificial intelligence products for detecting lung nodules on chest radiographs or predicting bone age on hand radiographs showed improved or comparable performance to human readers.

Published
2024
Full Text
View/download PDF

29. Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Author

van Leeuwen KG, Schalekamp S, Rutten MJCM, Huisman M, Schaefer-Prokop CM, de Rooij M, van Ginneken B, Maresch B, Geurts BHJ, van Dijke CF, Laupman-Koedam E, Hulleman EV, Verhoeff EL, Meys EMJ, Mohamed Hoesein FAA, Ter Brugge FM, van Hoorn F, van der Wel F, van den Berk IAH, Luyendijk JM, Meakin J, Habets J, Verbeke JIML, Nederend J, Meys KME, Deden LN, Langezaal LCM, Nasrollah M, Meij M, Boomsma MF, Vermeulen M, Vestering MM, Vijlbrief O, Algra P, Algra S, Bollen SM, Samson T, and von Brucken Fock YHG

Subjects
Humans, Female, Male, Child, Middle Aged, Retrospective Studies, Algorithms, Lung, Artificial Intelligence, Software
Abstract

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand ( n = 95) and chest ( n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard ( r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article . See also the editorial by Omoumi and Richiardi in this issue.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results