Search

Your search keyword '"Jannin P"' showing total 588 results
Start Over Author "Jannin P"
588 results on '"Jannin P"'

52. Metrics reloaded: recommendations for image analysis validation

Author

Maier-Hein, L., Reinke, A., Godau, P., Tizabi, M.D., Buettner, F., Christodoulou, E., Glocker, B., Isensee, F., Kleesiek, J., Kozubek, M., Reyes, M., Riegler, M.A., Wiesenfarth, M., Kavur, A.E., Sudre, C.H., Baumgartner, M., Eisenmann, M., Heckmann-Notzel, D., Radsch, T., Acion, L., Antonelli, M., Arbel, T., Bakas, S., Benis, A., Blaschko, M.B., Cardoso, M.J., Cheplygina, V., Cimini, B.A., Collins, G.S., Farahani, K., Ferrer, L., Galdran, A., Ginneken, B. van, Haase, R., Hashimoto, D.A., Hoffman, M.M., Huisman, M., Jannin, P., Kahn, C.E., Kainmueller, D., Kainz, B., Karargyris, A., Karthikesalingam, A., Kofler, F., Kopp-Schneider, A., Kreshuk, A., Kurc, T., Landman, B.A., Litjens, G.J., Madani, A., Maier-Hein, K., Martel, A.L., Mattson, P., Meijering, E., Menze, B., Moons, K.G., Muller, H., Nichyporuk, B., Nickel, F., Petersen, J., Rajpoot, N., Rieke, N., Saez-Rodriguez, J., Sanchez, C.I., Shetty, S., Smeden, M. van, Summers, R.M., Taha, A.A., Tiulpin, A., Tsaftaris, S.A., Calster, B. van, Varoquaux, G., Jager, P.F., Maier-Hein, L., Reinke, A., Godau, P., Tizabi, M.D., Buettner, F., Christodoulou, E., Glocker, B., Isensee, F., Kleesiek, J., Kozubek, M., Reyes, M., Riegler, M.A., Wiesenfarth, M., Kavur, A.E., Sudre, C.H., Baumgartner, M., Eisenmann, M., Heckmann-Notzel, D., Radsch, T., Acion, L., Antonelli, M., Arbel, T., Bakas, S., Benis, A., Blaschko, M.B., Cardoso, M.J., Cheplygina, V., Cimini, B.A., Collins, G.S., Farahani, K., Ferrer, L., Galdran, A., Ginneken, B. van, Haase, R., Hashimoto, D.A., Hoffman, M.M., Huisman, M., Jannin, P., Kahn, C.E., Kainmueller, D., Kainz, B., Karargyris, A., Karthikesalingam, A., Kofler, F., Kopp-Schneider, A., Kreshuk, A., Kurc, T., Landman, B.A., Litjens, G.J., Madani, A., Maier-Hein, K., Martel, A.L., Mattson, P., Meijering, E., Menze, B., Moons, K.G., Muller, H., Nichyporuk, B., Nickel, F., Petersen, J., Rajpoot, N., Rieke, N., Saez-Rodriguez, J., Sanchez, C.I., Shetty, S., Smeden, M. van, Summers, R.M., Taha, A.A., Tiulpin, A., Tsaftaris, S.A., Calster, B. van, Varoquaux, G., and Jager, P.F.

Abstract

Contains fulltext : 305368.pdf (Publisher’s version ) (Closed access), Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint-a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Published
2024

53. Understanding metric-related pitfalls in image analysis validation

Author

Reinke, A., Tizabi, M.D., Baumgartner, M., Eisenmann, M., Heckmann-Notzel, D., Kavur, A.E., Radsch, T., Sudre, C.H., Acion, L., Antonelli, M., Arbel, T., Bakas, S., Benis, A., Buettner, F., Cardoso, M.J., Cheplygina, V., Chen, J., Christodoulou, E., Cimini, B.A., Farahani, K., Ferrer, L., Galdran, A., Ginneken, B. van, Glocker, B., Godau, P., Hashimoto, D.A., Hoffman, M.M., Huisman, M., Isensee, F., Jannin, P., Kahn, C.E., Kainmueller, D., Kainz, B., Karargyris, A., Kleesiek, J., Kofler, F., Kooi, T., Kopp-Schneider, A., Kozubek, M., Kreshuk, A., Kurc, T., Landman, B.A., Litjens, G.J., Madani, A., Maier-Hein, K., Martel, A.L., Meijering, E., Menze, B., Moons, K.G., Muller, H., Nichyporuk, B., Nickel, F., Petersen, J., Rafelski, S.M., Rajpoot, N., Reyes, M., Riegler, M.A., Rieke, N., Saez-Rodriguez, J., Sanchez, C.I., Shetty, S., Summers, R.M., Taha, A.A., Tiulpin, A., Tsaftaris, S.A., Calster, B. van, Varoquaux, G., Yaniv, Z.R., Jager, P.F., Maier-Hein, L., Reinke, A., Tizabi, M.D., Baumgartner, M., Eisenmann, M., Heckmann-Notzel, D., Kavur, A.E., Radsch, T., Sudre, C.H., Acion, L., Antonelli, M., Arbel, T., Bakas, S., Benis, A., Buettner, F., Cardoso, M.J., Cheplygina, V., Chen, J., Christodoulou, E., Cimini, B.A., Farahani, K., Ferrer, L., Galdran, A., Ginneken, B. van, Glocker, B., Godau, P., Hashimoto, D.A., Hoffman, M.M., Huisman, M., Isensee, F., Jannin, P., Kahn, C.E., Kainmueller, D., Kainz, B., Karargyris, A., Kleesiek, J., Kofler, F., Kooi, T., Kopp-Schneider, A., Kozubek, M., Kreshuk, A., Kurc, T., Landman, B.A., Litjens, G.J., Madani, A., Maier-Hein, K., Martel, A.L., Meijering, E., Menze, B., Moons, K.G., Muller, H., Nichyporuk, B., Nickel, F., Petersen, J., Rafelski, S.M., Rajpoot, N., Reyes, M., Riegler, M.A., Rieke, N., Saez-Rodriguez, J., Sanchez, C.I., Shetty, S., Summers, R.M., Taha, A.A., Tiulpin, A., Tsaftaris, S.A., Calster, B. van, Varoquaux, G., Yaniv, Z.R., Jager, P.F., and Maier-Hein, L.

Abstract

Contains fulltext : 305370.pdf (Publisher’s version ) (Closed access), Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

Published
2024

55. Compact atomic gravimeter based on a pulsed and accelerated optical lattice

Author

Andia, Manuel, Jannin, Raphael, Nez, François, Biraben, François, Guellati-Khélifa, Saïda, and Cladé, Pierre

Subjects
Physics - Atomic Physics, Quantum Physics
Abstract

We present a new scheme of compact atomic gravimeter based on atom interferometry. Atoms are maintained against gravity using a sequence of coherent accelerations performed by the Bloch oscillations technique. We demonstrate a sensitivity of 4.8$\times 10^{-8}$ with an integration time of 4 min. Combining this method with an atomic elevator allows to measure the local gravity at different positions in the vacuum chamber. This method can be of relevance to improve the measurement of the Newtonian gravitational constant $G$.

Published
2013
Full Text
View/download PDF

58. Quelles avancées dans la prise en charge du carcinome anaplasique de la thyroïde en 2024 ?

Author

Jannin, Arnaud, Lugat, Alexandre, Escande, Alexandre, Godbert, Yann, Wasserman, Johanna, Cao, Christine Do, and Hadoux, Julien

Abstract

Les carcinomes anaplasiques de la thyroïde correspondent à une forme rare et indifférenciée de cancer thyroïdien. Leur pronostic est sombre avec une survie globale médiane de quatre à dix mois mais tend à s’améliorer ces dernières années grâce au recours plus systématique aux tests moléculaires et aux thérapies ciblées associées à l’immunothérapie ainsi qu’à la mise en place de prises en charge accélérées dédiées dans les centres experts. Cliniquement, le diagnostic sera évoqué devant une masse cervicale rapidement progressive développée aux dépens de la thyroïde, compressive, dure à la palpation et associée à des adénopathies chez des sujets âgés. La confirmation diagnostique nécessite une biopsie urgente relue par un anatomopathologiste expert du réseau TUTHYREF-path avec la recherche systématique d’une altération moléculaire BRAFV600E.Une fois le diagnostic posé, la coordination des intervenants se fait de manière accélérée, au sein d’un centre expert du réseau ENDOCAN-TUTHYREF chaque fois que possible. Une chirurgie est rarement réalisable d’emblée du fait d’un envahissement locorégional cervical fréquent. Le traitement doit être multimodal : inhibiteurs BRAF/MEK (dabrafinib/trametinib) en cas de mutation BRAFV600E,ou chimiothérapie en l’absence de cible moléculaire, associés à la radiothérapie et éventuellement à la chirurgie si la maladie devient résécable lors du traitement d’induction. L’immunothérapie ciblant PD-1/PD-L1 seule ou en association aux thérapies ciblées permet d’allonger la survie de certains patients; les biomarqueurs prédictifs ainsi que leur positionnement optimal dans la séquence thérapeutique (induction et/ou en entretien) restent encore à préciser et est probablement variable en fonction des situations cliniques.

Published
2024
Full Text
View/download PDF

59. Carcinomes neuroendocrines à grandes cellules (CNEGC) : actualités 2024

Author

Gaye, E., Jannin, A., Do Cao, C., and Dansin, E.

Abstract

Les carcinomes neuro-endocrines à grandes cellules (CNEGC) sont des tumeurs rares de haut grade de malignité et de pronostic péjoratif. La prise en charge des CNEGC demeure complexe et certaines situations cliniques (induction, stades métastatïques…) font encore l’objet de nombreuses interrogations. Si l’impact du ciblage moléculaire de ces tumeurs sur le type de traitement systémique optimal à préconiser reste à démontrer, l’évaluation prospective de l’immunothérapie dans les stades métastatiques se met en place et pourrait ouvrir de nouvelles options thérapeutiques.

Published
2024
Full Text
View/download PDF

60. Bullet-DNP Enables NMR Spectroscopy of Pyruvate and Amino Acids at Nanomolar to Low Micromolar Concentrations

Author

Narwal, Pooja, Lorz, Nils, Minaei, Masoud, Jannin, Sami, Kouřil, Karel, Gossert, Alvar, and Meier, Benno

Abstract

Hyperpolarized pyruvate is a widely used marker to track metabolism in vivo and a benchmark molecule for hyperpolarization methods. Here, we show how a combination of improved bullet-DNP instrumentation, an optimized sample preparation and a further sensitivity increase via a 13C–1H polarization transfer after dissolution enable the observation of pyruvate at a concentration of 250 nM immediately after dissolution. At this concentration, the experiment employs a total mass of pyruvate of only 20 ng or 180 pmol. If the concentration is increased to 45 μM, pyruvate may be detected 1 min after dissolution with a signal-to-noise ratio exceeding 50. The procedure can be extended to observe a mixture of amino acids at low micromolar concentrations.

Published
2024
Full Text
View/download PDF

67. Beyond MEN1, When to Think About MEN4? Retrospective Study on 5600 Patients in the French Population and Literature Review

Author

Chevalier, Benjamin, Coppin, Lucie, Romanet, Pauline, Cuny, Thomas, Maïza, Jean-Christophe, Abeillon, Juliette, Forestier, Julien, Walter, Thomas, Gilly, Olivier, Le Bras, Maëlle, Smati, Sarra, Nunes, Marie Laure, Geslot, Aurore, Grunenwald, Solange, Mouly, Céline, Arnault, Gwenaelle, Wagner, Kathy, Koumakis, Eugénie, Cortet-Rudelli, Christine, Merlen, Émilie, Jannin, Arnaud, Espiard, Stéphanie, Morange, Isabelle, Baudin, Éric, Cavaille, Mathias, Tauveron, Igor, Teissier, Marie-Pierre, Borson-Chazot, Françoise, Mirebeau-Prunier, Delphine, Savagner, Frédérique, Pasmant, Éric, Giraud, Sophie, Vantyghem, Marie-Christine, Goudet, Pierre, Barlier, Anne, Cardot-Bauters, Catherine, and Odou, Marie Françoise

Published
2024
Full Text
View/download PDF

68. Lipomatoses

Author

Dupuis, Hippolyte, Lemaitre, Madleen, Jannin, Arnaud, Douillard, Claire, Espiard, Stéphanie, and Vantyghem, Marie-Christine

Abstract

Lipomatoses are benign proliferation of adipose tissue. Lipomas (benign fat tumors) are the most common component of lipomatosis. They may be unique or multiple, encapsulated or not, subcutaneous or sometimes visceral. In some cases, they form large areas of non-encapsulated fat hypertrophy, with a variable degree of fibrosis. They can develop despite the absence of obesity. They may be familial or acquired. At difference with lipodystrophy syndromes, they are not associated with lipoatrophy areas, except in some rare cases such as type 2 familial partial lipodystrophy syndromes (FPLD2). Their metabolic impact is variable in part depending on associated obesity. They may have functional or aesthetic consequences. Lipomatosis may be isolated, be part of a syndrome, or may be visceral. Isolated lipomatoses include multiple symmetrical lipomatosis (Madelung disease or Launois-Bensaude syndrome), familial multiple lipomatosis, the painful Dercum's disease also called Adiposis Dolorosa or Ander syndrome, mesosomatic lipomatosis also called Roch-Leri lipomatosis, familial angiolipomatosis, lipedema and hibernomas. Syndromic lipomatoses include PIK3CA-related disorders, Cowden/PTENhamartomas-tumor syndrome, some lipodystrophy syndromes, and mitochondrial diseases, especially MERRF, multiple endocrine neoplasia type 1, neurofibromatosis type 1, Wilson disease, Pai or Haberland syndromes. Finally, visceral lipomatoses have been reported in numerous organs and sites: pancreatic, adrenal, abdominal, epidural, mediastinal, epicardial… The aim of this review is to present the main types of lipomatosis and their physiopathological component, when it is known.

Published
2024
Full Text
View/download PDF

69. Galectin-3 modulates epithelial cell adaptation to stress at the ER-mitochondria interface

Author

Coppin, Lucie, Jannin, Arnaud, Ait Yahya, Emilie, Thuillier, Caroline, Villenet, Céline, Tardivel, Meryem, Bongiovanni, Antonino, Gaston, Cécile, de Beco, Simon, Barois, Nicolas, van Seuningen, Isabelle, Durand, Emmanuelle, Bonnefond, Amélie, Vienne, Jean-Claude, Vamecq, Joseph, Figeac, Martin, Vincent, Audrey, Delacour, Delphine, Porchet, Nicole, and Pigny, Pascal

Published
2020
Full Text
View/download PDF

73. Toward a standard ontology of surgical process models

Author

Gibaud, Bernard, Forestier, Germain, Feldmann, Carolin, Ferrigno, Giancarlo, Gonçalves, Paulo, Haidegger, Tamás, Julliard, Chantal, Katić, Darko, Kenngott, Hannes, Maier-Hein, Lena, März, Keno, de Momi, Elena, Nagy, Dénes Ákos, Nakawala, Hirenkumar, Neumann, Juliane, Neumuth, Thomas, Rojas Balderrama, Javier, Speidel, Stefanie, Wagner, Martin, and Jannin, Pierre

Published
2018
Full Text
View/download PDF

77. Why is the Winner the Best?

Author

Eisenmann, M., primary, Reinke, A., additional, Weru, V., additional, Tizabi, M. D., additional, Isensee, F., additional, Adler, T. J., additional, Ali, S., additional, Andrearczyk, V., additional, Aubreville, M., additional, Baid, U., additional, Bakas, S., additional, Balu, N., additional, Bano, S., additional, Bernal, J., additional, Bodenstedt, S., additional, Casella, A., additional, Cheplygina, V., additional, Daum, M., additional, De Bruijne, M., additional, Depeursinge, A., additional, Dorent, R., additional, Egger, J., additional, Ellis, D. G., additional, Engelhardt, S., additional, Ganz, M., additional, Ghatwary, N., additional, Girard, G., additional, Godau, P., additional, Gupta, A., additional, Hansen, L., additional, Harada, K., additional, Heinrich, M., additional, Heller, N., additional, Hering, A., additional, Huaulmé, A., additional, Jannin, P., additional, Kavur, A. E., additional, Kodym, O., additional, Kozubek, M., additional, Li, J., additional, Li, H., additional, Ma, J., additional, Martín-Isla, C., additional, Menze, B., additional, Noble, A., additional, Oreiller, V., additional, Padoy, N., additional, Pati, S., additional, Payette, K., additional, Rädsch, T., additional, Rafael-Patiño, J., additional, Bawa, V. Singh, additional, Speidel, S., additional, Sudre, C. H., additional, Van Wijnen, K., additional, Wagner, M., additional, Wei, D., additional, Yamlahi, A., additional, Yap, M. H., additional, Yuan, C., additional, Zenk, M., additional, Zia, A., additional, Zimmerer, D., additional, Aydogan, D., additional, Bhattarai, B., additional, Bloch, L., additional, Brüngel, R., additional, Cho, J., additional, Choi, C., additional, Dou, Q., additional, Ezhov, I., additional, Friedrich, C. M., additional, Fuller, C., additional, Gaire, R. R., additional, Galdran, A., additional, Faura, Á. García, additional, Grammatikopoulou, M., additional, Hong, S., additional, Jahanifar, M., additional, Jang, I., additional, Kadkhodamohammadi, A., additional, Kang, I., additional, Kofler, F., additional, Kondo, S., additional, Kuijf, H., additional, Li, M., additional, Luu, M., additional, Martinčič, T., additional, Morais, P., additional, Naser, M. A., additional, Oliveira, B., additional, Owen, D., additional, Pang, S., additional, Park, J., additional, Park, S., additional, Płotka, S., additional, Puybareau, E., additional, Rajpoot, N., additional, Ryu, K., additional, Saeed, N., additional, Shephard, A., additional, Shi, P., additional, Štepec, D., additional, Subedi, R., additional, Tochon, G., additional, Torres, H. R., additional, Urien, H., additional, Vilaça, J. L., additional, Wahid, K. A., additional, Wang, H., additional, Wang, J., additional, Wang, L., additional, Wang, X., additional, Wiestler, B., additional, Wodzinski, M., additional, Xia, F., additional, Xie, J., additional, Xiong, Z., additional, Yang, S., additional, Yang, Y., additional, Zhao, Z., additional, Maier-Hein, K., additional, Jäger, P. F., additional, Kopp-Schneider, A., additional, and Maier-Hein, L., additional

Published
2023
Full Text
View/download PDF

79. Why is the winner the best?

Author

Eisenmann, M, Reinke, A, Weru, V, Tizabi, MD, Isensee, F, Adler, TJ, Ali, S, Andrearczyk, V, Aubreville, M, Baid, U, Bakas, S, Balu, N, Bano, S, Bernal, J, Bodenstedt, S, Casella, A, Cheplygina, V, Daum, M, De Bruijne, M, Depeursinge, A, Dorent, R, Egger, J, Ellis, DG, Engelhardt, S, Ganz, M, Ghatwary, N, Girard, G, Godau, P, Gupta, A, Hansen, L, Harada, K, Heinrich, M, Heller, N, Hering, A, Huaulmé, A, Jannin, P, Kavur, AE, Kodym, O, Kozubek, M, Li, J, Li, H, Ma, J, Martín-Isla, C, Menze, B, Noble, A, Oreiller, V, Padoy, N, Pati, S, Payette, K, Rädsch, T, Rafael-Patiño, J, Bawa, VS, Speidel, S, Sudre, CH, Van Wijnen, K, Wagner, M, Wei, D, Yamlahi, A, Yap, MH, Yuan, C, Zenk, M, Zia, A, Zimmerer, D, Aydogan, D, Bhattarai, B, Bloch, L, Brüngel, R, Cho, J, Choi, C, Dou, Q, Ezhov, I, Friedrich, CM, Fuller, C, Gaire, RR, Galdran, A, García Faura, A, Grammatikopoulou, M, Hong, S, Jahanifar, M, Jang, I, Kadkhodamohammadi, A, Kang, I, Kofler, F, Kondo, S, Kuijf, H, Li, M, Luu, M, Martinčič, T, Morais, P, Naser, MA, Oliveira, B, Owen, D, Pang, S, Park, J, Park, S, Płotka, S, Puybareau, E, Rajpoot, N, Ryu, K, Saeed, N, Eisenmann, M, Reinke, A, Weru, V, Tizabi, MD, Isensee, F, Adler, TJ, Ali, S, Andrearczyk, V, Aubreville, M, Baid, U, Bakas, S, Balu, N, Bano, S, Bernal, J, Bodenstedt, S, Casella, A, Cheplygina, V, Daum, M, De Bruijne, M, Depeursinge, A, Dorent, R, Egger, J, Ellis, DG, Engelhardt, S, Ganz, M, Ghatwary, N, Girard, G, Godau, P, Gupta, A, Hansen, L, Harada, K, Heinrich, M, Heller, N, Hering, A, Huaulmé, A, Jannin, P, Kavur, AE, Kodym, O, Kozubek, M, Li, J, Li, H, Ma, J, Martín-Isla, C, Menze, B, Noble, A, Oreiller, V, Padoy, N, Pati, S, Payette, K, Rädsch, T, Rafael-Patiño, J, Bawa, VS, Speidel, S, Sudre, CH, Van Wijnen, K, Wagner, M, Wei, D, Yamlahi, A, Yap, MH, Yuan, C, Zenk, M, Zia, A, Zimmerer, D, Aydogan, D, Bhattarai, B, Bloch, L, Brüngel, R, Cho, J, Choi, C, Dou, Q, Ezhov, I, Friedrich, CM, Fuller, C, Gaire, RR, Galdran, A, García Faura, A, Grammatikopoulou, M, Hong, S, Jahanifar, M, Jang, I, Kadkhodamohammadi, A, Kang, I, Kofler, F, Kondo, S, Kuijf, H, Li, M, Luu, M, Martinčič, T, Morais, P, Naser, MA, Oliveira, B, Owen, D, Pang, S, Park, J, Park, S, Płotka, S, Puybareau, E, Rajpoot, N, Ryu, K, and Saeed, N

Abstract

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The 'typical' lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

Published
2023

80. Why is the Winner the Best?

Author

Beeldverwerking ISI, Brain, Cancer, Circulatory Health, Structure and Connections, Eisenmann, M., Reinke, A., Weru, V., Tizabi, M. D., Isensee, F., Adler, T. J., Ali, S., Andrearczyk, V., Aubreville, M., Baid, U., Bakas, S., Balu, N., Bano, S., Bernal, J., Bodenstedt, S., Casella, A., Cheplygina, V., Daum, M., De Bruijne, M., Depeursinge, A., Dorent, R., Egger, J., Ellis, D. G., Engelhardt, S., Ganz, M., Ghatwary, N., Girard, G., Godau, P., Gupta, A., Hansen, L., Harada, K., Heinrich, M., Heller, N., Hering, A., Huaulmé, A., Jannin, P., Kavur, A. E., Kodym, O., Kozubek, M., Li, J., Li, H., Ma, J., Martín-Isla, C., Menze, B., Noble, A., Oreiller, V., Padoy, N., Pati, S., Payette, K., Rädsch, T., Rafael-Patiño, J., Bawa, V. Singh, Speidel, S., Sudre, C. H., Van Wijnen, K., Wagner, M., Wei, D., Yamlahi, A., Yap, M. H., Yuan, C., Zenk, M., Zia, A., Zimmerer, D., Aydogan, D., Bhattarai, B., Bloch, L., Brüngel, R., Cho, J., Choi, C., Dou, Q., Ezhov, I., Friedrich, C. M., Fuller, C., Gaire, R. R., Galdran, A., García Faura, A., Grammatikopoulou, M., Hong, S., Jahanifar, M., Jang, I., Kadkhodamohammadi, A., Kang, I., Kofler, F., Kondo, S., Kuijf, H., Li, M., Luu, M., Martinčič, T., Morais, P., Naser, M. A., Oliveira, B., Owen, D., Pang, S., Park, J., Park, S., Płotka, S., Puybareau, E., Rajpoot, N., Ryu, K., Saeed, N., Shephard, A., Shi, P., Štepec, D., Subedi, R., Tochon, G., Torres, H. R., Urien, H., Vilaça, J. L., Wahid, K. A., Wang, H., Wang, J., Wang, L., Wang, X., Wiestler, B., Wodzinski, M., Xia, F., Xie, J., Xiong, Z., Yang, S., Yang, Y., Zhao, Z., Maier-Hein, K., Jäger, P. F., Kopp-Schneider, A., Maier-Hein, L., Beeldverwerking ISI, Brain, Cancer, Circulatory Health, Structure and Connections, Eisenmann, M., Reinke, A., Weru, V., Tizabi, M. D., Isensee, F., Adler, T. J., Ali, S., Andrearczyk, V., Aubreville, M., Baid, U., Bakas, S., Balu, N., Bano, S., Bernal, J., Bodenstedt, S., Casella, A., Cheplygina, V., Daum, M., De Bruijne, M., Depeursinge, A., Dorent, R., Egger, J., Ellis, D. G., Engelhardt, S., Ganz, M., Ghatwary, N., Girard, G., Godau, P., Gupta, A., Hansen, L., Harada, K., Heinrich, M., Heller, N., Hering, A., Huaulmé, A., Jannin, P., Kavur, A. E., Kodym, O., Kozubek, M., Li, J., Li, H., Ma, J., Martín-Isla, C., Menze, B., Noble, A., Oreiller, V., Padoy, N., Pati, S., Payette, K., Rädsch, T., Rafael-Patiño, J., Bawa, V. Singh, Speidel, S., Sudre, C. H., Van Wijnen, K., Wagner, M., Wei, D., Yamlahi, A., Yap, M. H., Yuan, C., Zenk, M., Zia, A., Zimmerer, D., Aydogan, D., Bhattarai, B., Bloch, L., Brüngel, R., Cho, J., Choi, C., Dou, Q., Ezhov, I., Friedrich, C. M., Fuller, C., Gaire, R. R., Galdran, A., García Faura, A., Grammatikopoulou, M., Hong, S., Jahanifar, M., Jang, I., Kadkhodamohammadi, A., Kang, I., Kofler, F., Kondo, S., Kuijf, H., Li, M., Luu, M., Martinčič, T., Morais, P., Naser, M. A., Oliveira, B., Owen, D., Pang, S., Park, J., Park, S., Płotka, S., Puybareau, E., Rajpoot, N., Ryu, K., Saeed, N., Shephard, A., Shi, P., Štepec, D., Subedi, R., Tochon, G., Torres, H. R., Urien, H., Vilaça, J. L., Wahid, K. A., Wang, H., Wang, J., Wang, L., Wang, X., Wiestler, B., Wodzinski, M., Xia, F., Xie, J., Xiong, Z., Yang, S., Yang, Y., Zhao, Z., Maier-Hein, K., Jäger, P. F., Kopp-Schneider, A., and Maier-Hein, L.

Published
2023

87. Metrics reloaded: recommendations for image analysis validation

Author

Maier-Hein, Lena, Reinke, Annika, Godau, Patrick, Tizabi, Minu D., Buettner, Florian, Christodoulou, Evangelia, Glocker, Ben, Isensee, Fabian, Kleesiek, Jens, Kozubek, Michal, Reyes, Mauricio, Riegler, Michael A., Wiesenfarth, Manuel, Kavur, A. Emre, Sudre, Carole H., Baumgartner, Michael, Eisenmann, Matthias, Heckmann-Nötzel, Doreen, Rädsch, Tim, Acion, Laura, Antonelli, Michela, Arbel, Tal, Bakas, Spyridon, Benis, Arriel, Blaschko, Matthew B., Cardoso, M. Jorge, Cheplygina, Veronika, Cimini, Beth A., Collins, Gary S., Farahani, Keyvan, Ferrer, Luciana, Galdran, Adrian, van Ginneken, Bram, Haase, Robert, Hashimoto, Daniel A., Hoffman, Michael M., Huisman, Merel, Jannin, Pierre, Kahn, Charles E., Kainmueller, Dagmar, Kainz, Bernhard, Karargyris, Alexandros, Karthikesalingam, Alan, Kofler, Florian, Kopp-Schneider, Annette, Kreshuk, Anna, Kurc, Tahsin, Landman, Bennett A., Litjens, Geert, Madani, Amin, Maier-Hein, Klaus, Martel, Anne L., Mattson, Peter, Meijering, Erik, Menze, Bjoern, Moons, Karel G. M., Müller, Henning, Nichyporuk, Brennan, Nickel, Felix, Petersen, Jens, Rajpoot, Nasir, Rieke, Nicola, Saez-Rodriguez, Julio, Sánchez, Clara I., Shetty, Shravya, van Smeden, Maarten, Summers, Ronald M., Taha, Abdel A., Tiulpin, Aleksei, Tsaftaris, Sotirios A., Van Calster, Ben, Varoquaux, Gaël, and Jäger, Paul F.

Abstract

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. In biomedical image analysis, chosen performance metrics often do not reflect the domain interest, and thus fail to adequately measure scientific progress and hinder translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. Developed by a large international consortium in a multistage Delphi process, it is based on the novel concept of a problem fingerprint—a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), dataset and algorithm output. On the basis of the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as classification tasks at image, object or pixel level, namely image-level classification, object detection, semantic segmentation and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

Published
2024
Full Text
View/download PDF

88. Understanding metric-related pitfalls in image analysis validation

Author

Reinke, Annika, Tizabi, Minu D., Baumgartner, Michael, Eisenmann, Matthias, Heckmann-Nötzel, Doreen, Kavur, A. Emre, Rädsch, Tim, Sudre, Carole H., Acion, Laura, Antonelli, Michela, Arbel, Tal, Bakas, Spyridon, Benis, Arriel, Buettner, Florian, Cardoso, M. Jorge, Cheplygina, Veronika, Chen, Jianxu, Christodoulou, Evangelia, Cimini, Beth A., Farahani, Keyvan, Ferrer, Luciana, Galdran, Adrian, van Ginneken, Bram, Glocker, Ben, Godau, Patrick, Hashimoto, Daniel A., Hoffman, Michael M., Huisman, Merel, Isensee, Fabian, Jannin, Pierre, Kahn, Charles E., Kainmueller, Dagmar, Kainz, Bernhard, Karargyris, Alexandros, Kleesiek, Jens, Kofler, Florian, Kooi, Thijs, Kopp-Schneider, Annette, Kozubek, Michal, Kreshuk, Anna, Kurc, Tahsin, Landman, Bennett A., Litjens, Geert, Madani, Amin, Maier-Hein, Klaus, Martel, Anne L., Meijering, Erik, Menze, Bjoern, Moons, Karel G. M., Müller, Henning, Nichyporuk, Brennan, Nickel, Felix, Petersen, Jens, Rafelski, Susanne M., Rajpoot, Nasir, Reyes, Mauricio, Riegler, Michael A., Rieke, Nicola, Saez-Rodriguez, Julio, Sánchez, Clara I., Shetty, Shravya, Summers, Ronald M., Taha, Abdel A., Tiulpin, Aleksei, Tsaftaris, Sotirios A., Van Calster, Ben, Varoquaux, Gaël, Yaniv, Ziv R., Jäger, Paul F., and Maier-Hein, Lena

Abstract

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence research and its translation into practice. However, increasing evidence shows that, particularly in image analysis, metrics are often chosen inadequately. Although taking into account the individual strengths, weaknesses and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multistage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides a reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. Although focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation.

Published
2024
Full Text
View/download PDF

89. Rapid and Simple 13C-Hyperpolarization by 1H Dissolution Dynamic Nuclear Polarization Followed by an Inline Magnetic Field Inversion

Author

Stern, Quentin, Reynard-Feytis, Quentin, Elliott, Stuart J., Ceillier, Morgan, Cala, Olivier, Ivanov, Konstantin, and Jannin, Sami

Abstract

Dissolution dynamic nuclear polarization (dDNP) is a method of choice for preparing hyperpolarized 13C metabolites such as 1-13C-pyruvate used for in vivoapplications, including the real-time monitoring of cancer cell metabolism in human patients. The approach consists of transferring the high polarization of electron spins to nuclear spins via microwave irradiation at low temperatures (1.0–1.5 K) and moderate magnetic fields (3.3–7 T). The solid sample is then dissolved and transferred to an NMR spectrometer or MRI scanner for detection in the liquid state. Common dDNP protocols use direct hyperpolarization of 13C spins reaching polarizations of >50% in ∼1–2 h. Alternatively, 1H spins are polarized before transferring their polarization to 13C spins using cross-polarization, reaching polarization levels similar to those of direct DNP in only ∼20 min. However, it relies on more complex instrumentation, requiring highly skilled personnel. Here, we explore an alternative route using 1H dDNP followed by inline adiabatic magnetic field inversion in the liquid state during the transfer. 1H polarizations of >70% in the solid state are obtained in ∼5–10 min. As the hyperpolarized sample travels from the dDNP polarizer to the NMR spectrometer, it goes through a field inversion chamber, which causes the 1H → 13C polarization transfer. This transfer is made possible by the J-coupling between the heteronuclei, which mixes the Zeeman states at zero-field and causes an antilevel crossing. We report liquid-state 13C polarization up to ∼17% for 3-13C-pyruvate and 13C-formate. The instrumentation needed to perform this experiment in addition to a conventional dDNP polarizer is simple and readily assembled.

Published
2023
Full Text
View/download PDF

92. Abnormal Functional Lateralization and Activity of Language Brain Areas in Typical Specific Language Impairment (Developmental Dysphasia)

Author

de Guibert, Clement, Maumet, Camille, and Jannin, Pierre

Abstract

Atypical functional lateralization and specialization for language have been proposed to account for developmental language disorders, yet results from functional neuroimaging studies are sparse and inconsistent. This functional magnetic resonance imaging study compared children with a specific subtype of specific language impairment affecting structural language (n = 21), to a matched group of typically developing children using a panel of four language tasks neither requiring reading nor metalinguistic skills, including two auditory lexico-semantic tasks (category fluency and responsive naming) and two visual phonological tasks based on picture naming. Data processing involved normalizing the data with respect to a matched pairs paediatric template, groups and between-groups analysis, and laterality indices assessment within regions of interest using single and combined task analysis. Children with specific language impairment exhibited a significant lack of left lateralization in all core language regions (inferior frontal gyrus-opercularis, inferior frontal gyrus-triangularis, supramarginal gyrus and superior temporal gyrus), across single or combined task analysis, but no difference of lateralization for the rest of the brain. Between-group comparisons revealed a left hypoactivation of Wernicke's area at the posterior superior temporal/supramarginal junction during the responsive naming task, and a right hyperactivation encompassing the anterior insula with adjacent inferior frontal gyrus and the head of the caudate nucleus during the first phonological task. This study thus provides evidence that this subtype of specific language impairment is associated with atypical lateralization and functioning of core language areas.

Published
2011
Full Text
View/download PDF

100. Toward the Establishment of Standardized In Vitro Tests for Lipid-Based Formulations. 5. Lipolysis of Representative Formulations by Gastric Lipase

Author

Bakala-N’Goma, Jean-Claude, Williams, Hywel D., Sassene, Philip J., Kleberg, Karen, Calderone, Marilyn, Jannin, Vincent, Igonin, Annabel, Partheil, Anette, Marchaud, Delphine, Jule, Eduardo, Vertommen, Jan, Maio, Mario, Blundell, Ross, Benameur, Hassan, Müllertz, Anette, Pouton, Colin W., Porter, Christopher J. H., and Carrière, Frédéric

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results