Search

Your search keyword '"Oreiller, Valentin"' showing total 10 results
Start Over Author "Oreiller, Valentin" Database OAIster
10 results on '"Oreiller, Valentin"'

1. Why is the winner the best?

Author

Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, Bruijne, Marleen de, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., Wijnen, Kimberlin van, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, Maier-Hein, Lena, Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, Bruijne, Marleen de, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., Wijnen, Kimberlin van, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, and Maier-Hein, Lena

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 multi-center 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 postprocessing (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

2. Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT

Author

Andrearczyk, Vincent, Oreiller, Valentin, Hatt, Mathieu, Depeursinge, Adrien; https://orcid.org/0000-0002-2362-0304, Andrearczyk, V ( Vincent ), Oreiller, V ( Valentin ), Hatt, M ( Mathieu ), Depeursinge, A ( Adrien ), Abobakr, Moamen, Akhavanallaf, Azadeh, Balermpas, Panagiotis; https://orcid.org/0000-0001-5261-6446, Boughdad, Sarah, Capriotti, Leo, Castelli, Joel, Cheze Le Rest, Catherine, Decazes, Pierre, Correia, Ricardo, El-Habashy, Dina, Elhalawani, Hesham; https://orcid.org/0000-0001-9848-2623, Fuller, Clifton D, Jreige, Mario, Khamis, Yornna, La Greca, Agustina; https://orcid.org/0000-0003-4504-611X, Mohamed, Abdallah, Naser, Mohamed, Prior, John O; https://orcid.org/0000-0003-1429-1374, Ruan, Su, Tanadini-Lang, Stephanie; https://orcid.org/0000-0002-4387-1522, Tankyevych, Olena, Salimi, Yazdan, Vallières, Martin; https://orcid.org/0000-0001-7639-8172, Vera, Pierre, Visvikis, Dimitris, Wahid, Kareem, Zaidi, Habib, Andrearczyk, Vincent, Oreiller, Valentin, Hatt, Mathieu, Depeursinge, Adrien; https://orcid.org/0000-0002-2362-0304, Andrearczyk, V ( Vincent ), Oreiller, V ( Valentin ), Hatt, M ( Mathieu ), Depeursinge, A ( Adrien ), Abobakr, Moamen, Akhavanallaf, Azadeh, Balermpas, Panagiotis; https://orcid.org/0000-0001-5261-6446, Boughdad, Sarah, Capriotti, Leo, Castelli, Joel, Cheze Le Rest, Catherine, Decazes, Pierre, Correia, Ricardo, El-Habashy, Dina, Elhalawani, Hesham; https://orcid.org/0000-0001-9848-2623, Fuller, Clifton D, Jreige, Mario, Khamis, Yornna, La Greca, Agustina; https://orcid.org/0000-0003-4504-611X, Mohamed, Abdallah, Naser, Mohamed, Prior, John O; https://orcid.org/0000-0003-1429-1374, Ruan, Su, Tanadini-Lang, Stephanie; https://orcid.org/0000-0002-4387-1522, Tankyevych, Olena, Salimi, Yazdan, Vallières, Martin; https://orcid.org/0000-0001-7639-8172, Vera, Pierre, Visvikis, Dimitris, Wahid, Kareem, and Zaidi, Habib

Abstract

This paper presents an overview of the third edition of the HEad and neCK TumOR segmentation and outcome prediction (HECKTOR) challenge, organized as a satellite event of the 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2022. The challenge comprises two tasks related to the automatic analysis of FDG-PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the fully automatic segmentation of H&N primary Gross Tumor Volume (GTVp) and metastatic lymph nodes (GTVn) from FDG-PET/CT images. Task 2 is the fully automatic prediction of Recurrence-Free Survival (RFS) from the same FDG-PET/CT and clinical data. The data were collected from nine centers for a total of 883 cases consisting of FDG-PET/CT images and clinical information, split into 524 training and 359 test cases. The best methods obtained an aggregated Dice Similarity Coefficient (DSC$_{agg}$) of 0.788 in Task 1, and a Concordance index (C-index) of 0.682 in Task 2.

Published
2023

3. QuantImage v2: a comprehensive and integrated physician-centered cloud platform for radiomics and machine learning research

Author

Abler, Daniel (author), Schaer, Roger (author), Oreiller, Valentin (author), Verma, H. (author), Reichenbach, Julien (author), Aidonopoulos, Orfeas (author), Evéquoz, Florian (author), Jreige, Mario (author), Prior, John (author), Abler, Daniel (author), Schaer, Roger (author), Oreiller, Valentin (author), Verma, H. (author), Reichenbach, Julien (author), Aidonopoulos, Orfeas (author), Evéquoz, Florian (author), Jreige, Mario (author), and Prior, John (author)

Abstract

Background: Radiomics, the field of image-based computational medical biomarker research, has experienced rapid growth over the past decade due to its potential to revolutionize the development of personalized decision support models. However, despite its research momentum and important advances toward methodological standardization, the translation of radiomics prediction models into clinical practice only progresses slowly. The lack of physicians leading the development of radiomics models and insufficient integration of radiomics tools in the clinical workflow contributes to this slow uptake. Methods: We propose a physician-centered vision of radiomics research and derive minimal functional requirements for radiomics research software to support this vision. Free-to-access radiomics tools and frameworks were reviewed to identify best practices and reveal the shortcomings of existing software solutions to optimally support physician-driven radiomics research in a clinical environment. Results: Support for user-friendly development and evaluation of radiomics prediction models via machine learning was found to be missing in most tools. QuantImage v2 (QI2) was designed and implemented to address these shortcomings. QI2 relies on well-established existing tools and open-source libraries to realize and concretely demonstrate the potential of a one-stop tool for physician-driven radiomics research. It provides web-based access to cohort management, feature extraction, and visualization and supports “no-code” development and evaluation of machine learning models against patient-specific outcome data. Conclusions: QI2 fills a gap in the radiomics software landscape by enabling “no-code” radiomics research, including model validation, in a clinical environment. Further information about QI2, a public instance of the system, and its source code is available at https://medgift.github.io/quantimage-v2-info/. Key points As domain experts, physicians play a key role in the, Human-Centred Artificial Intelligence

Published
2023
Full Text
View/download PDF

4. Why is the winner the best?

Author

Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, Bruijne, Marleen de, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., Wijnen, Kimberlin van, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, Maier-Hein, Lena, Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, Bruijne, Marleen de, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., Wijnen, Kimberlin van, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, and Maier-Hein, Lena

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 multi-center 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 postprocessing (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

5. Why is the winner the best?

Author

Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, de Bruijne, Marleen, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., van Wijnen, Kimberlin, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, Maier-Hein, Lena, Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Ali, Sharib, Andrearczyk, Vincent, Aubreville, Marc, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Cheplygina, Veronika, Daum, Marie, de Bruijne, Marleen, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Ellis, David G., Engelhardt, Sandy, Ganz, Melanie, Ghatwary, Noha, Girard, Gabriel, Godau, Patrick, Gupta, Anubha, Hansen, Lasse, Harada, Kanako, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Jannin, Pierre, Kavur, Ali Emre, Kodym, Oldřich, Kozubek, Michal, Li, Jianning, Li, Hongwei, Ma, Jun, Martín-Isla, Carlos, Menze, Bjoern, Noble, Alison, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Rädsch, Tim, Rafael-Patiño, Jonathan, Bawa, Vivek Singh, Speidel, Stefanie, Sudre, Carole H., van Wijnen, Kimberlin, Wagner, Martin, Wei, Donglai, Yamlahi, Amine, Yap, Moi Hoon, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Aydogan, Dogu Baran, Bhattarai, Binod, Bloch, Louise, Brüngel, Raphael, Cho, Jihoon, Choi, Chanyeol, Dou, Qi, Ezhov, Ivan, Friedrich, Christoph M., Fuller, Clifton, Gaire, Rebati Raman, Galdran, Adrian, Faura, Álvaro García, Grammatikopoulou, Maria, Hong, SeulGi, Jahanifar, Mostafa, Jang, Ikbeom, Kadkhodamohammadi, Abdolrahim, Kang, Inha, Kofler, Florian, Kondo, Satoshi, Kuijf, Hugo, Li, Mingxing, Luu, Minh Huan, Martinčič, Tomaž, Morais, Pedro, Naser, Mohamed A., Oliveira, Bruno, Owen, David, Pang, Subeen, Park, Jinah, Park, Sung-Hong, Płotka, Szymon, Puybareau, Elodie, Rajpoot, Nasir, Ryu, Kanghyun, Saeed, Numan, Shephard, Adam, Shi, Pengcheng, Štepec, Dejan, Subedi, Ronast, Tochon, Guillaume, Torres, Helena R., Urien, Helene, Vilaça, João L., Wahid, Kareem Abdul, Wang, Haojie, Wang, Jiacheng, Wang, Liansheng, Wang, Xiyue, Wiestler, Benedikt, Wodzinski, Marek, Xia, Fangfang, Xie, Juanying, Xiong, Zhiwei, Yang, Sen, Yang, Yanwu, Zhao, Zixuan, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, and Maier-Hein, Lena

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 multi-center 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 postprocessing (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., Comment: accepted to CVPR 2023

Published
2023

6. Validating and optimizing the specificity of imaging biomarkers for personalized medicine

Author

Oreiller, Valentin and Oreiller, Valentin

Abstract

In the last decade, biomedical image analysis has advanced significantly, thanks to radiomics and Convolutional Neural Networks (CNNs) being used for constructing predictive models in personalized medicine. These models are built using image features that can be divided into three main categories: intensity, shape, and texture. Although intensity and shape features are essential, texture features have the potential to reveal complex relationships between tumor architecture and patient outcomes. Therefore, the advancement and comprehension of texture features hold potential as effective strategies for clinicians to enhance disease characterization and facilitate personalized medicine. However, common texture features suffer from several limitations. In this thesis, we reviewed the most common texture features, explaining their advantages and disadvantages, and focusing on their robustness to rotations of the images and structures of interest. We proposed a novel method for designing directional image operators that are Locally Rotation Invariant (LRI), which we implemented based on the power spectrum and bispectrum of the circular harmonics expansion for 2D images or the spherical harmonics expansion for 3D images. We further integrated these LRI operators into a convolutional layer and used them in a CNN to obtain various LRI CNNs. We tested several shallow 3D LRI CNNs to classify benign or malignant lung nodules and demonstrated the advantages of bispectral LRI CNNs in terms of accuracy and data efficiency. Additionally, we evaluated our bispectral LRI layer in a 2D U-Net to segment nuclei in histopathological images and obtained comparable performance between the LRI U-Net and a standard U-Net. Furthermore, we showed that the LRI U-Net was more resilient to input rotations than the standard U-Net. The development of machine learning in biomedical imaging requires large datasets and benchmarks to create robust predictive models. Therefore, the second contribution o

Published
2022

7. Biomedical image analysis competitions: The state of current participation practice

Author

Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Godau, Patrick, Cheplygina, Veronika, Kozubek, Michal, Ali, Sharib, Gupta, Anubha, Kybic, Jan, Noble, Alison, de Solórzano, Carlos Ortiz, Pachade, Samiksha, Petitjean, Caroline, Sage, Daniel, Wei, Donglai, Wilden, Elizabeth, Alapatt, Deepak, Andrearczyk, Vincent, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bawa, Vivek Singh, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Choi, Jinwook, Commowick, Olivier, Daum, Marie, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Eichhorn, Hannah, Engelhardt, Sandy, Ganz, Melanie, Girard, Gabriel, Hansen, Lasse, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Kim, Hyunjeong, Landman, Bennett, Li, Hongwei Bran, Li, Jianning, Ma, Jun, Martel, Anne, Martín-Isla, Carlos, Menze, Bjoern, Nwoye, Chinedu Innocent, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Sudre, Carole, van Wijnen, Kimberlin, Vardazaryan, Armine, Vercauteren, Tom, Wagner, Martin, Wang, Chuanbo, Yap, Moi Hoon, Yu, Zeyun, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Bao, Rina, Choi, Chanyeol, Cohen, Andrew, Dzyubachyk, Oleh, Galdran, Adrian, Gan, Tianyuan, Guo, Tianqi, Gupta, Pradyumna, Haithami, Mahmood, Ho, Edward, Jang, Ikbeom, Li, Zhili, Luo, Zhengbo, Lux, Filip, Makrogiannis, Sokratis, Müller, Dominik, Oh, Young-tack, Pang, Subeen, Pape, Constantin, Polat, Gorkem, Reed, Charlotte Rosalie, Ryu, Kanghyun, Scherr, Tim, Thambawita, Vajira, Wang, Haoyu, Wang, Xinliang, Xu, Kele, Yeh, Hung, Yeo, Doyeob, Yuan, Yixuan, Zeng, Yan, Zhao, Xin, Abbing, Julian, Adam, Jannes, Adluru, Nagesh, Agethen, Niklas, Ahmed, Salman, Khalil, Yasmina Al, Alenyà, Mireia, Alhoniemi, Esa, An, Chengyang, Anwar, Talha, Arega, Tewodros Weldebirhan, Avisdris, Netanell, Aydogan, Dogu Baran, Bai, Yingbin, Calisto, Maria Baldeon, Basaran, Berke Doga, Beetz, Marcel, Bian, Cheng, Bian, Hao, Blansit, Kevin, Bloch, Louise, Bohnsack, Robert, Bosticardo, Sara, Breen, Jack, Brudfors, Mikael, Brüngel, Raphael, Cabezas, Mariano, Cacciola, Alberto, Chen, Zhiwei, Chen, Yucong, Chen, Daniel Tianming, Cho, Minjeong, Choi, Min-Kook, Xie, Chuantao Xie Chuantao, Cobzas, Dana, Cohen-Adad, Julien, Acero, Jorge Corral, Das, Sujit Kumar, de Oliveira, Marcela, Deng, Hanqiu, Dong, Guiming, Doorenbos, Lars, Efird, Cory, Escalera, Sergio, Fan, Di, Serj, Mehdi Fatan, Fenneteau, Alexandre, Fidon, Lucas, Filipiak, Patryk, Finzel, René, Freitas, Nuno R., Friedrich, Christoph M., Fulton, Mitchell, Gaida, Finn, Galati, Francesco, Galazis, Christoforos, Gan, Chang Hee, Gao, Zheyao, Gao, Shengbo, Gazda, Matej, Gerats, Beerend, Getty, Neil, Gibicar, Adam, Gifford, Ryan, Gohil, Sajan, Grammatikopoulou, Maria, Grzech, Daniel, Güley, Orhun, Günnemann, Timo, Guo, Chunxu, Guy, Sylvain, Ha, Heonjin, Han, Luyi, Han, Il Song, Hatamizadeh, Ali, He, Tian, Heo, Jimin, Hitziger, Sebastian, Hong, SeulGi, Hong, SeungBum, Huang, Rian, Huang, Ziyan, Huellebrand, Markus, Huschauer, Stephan, Hussain, Mustaffa, Inubushi, Tomoo, Polat, Ece Isik, Jafaritadi, Mojtaba, Jeong, SeongHun, Jian, Bailiang, Jiang, Yuanhong, Jiang, Zhifan, Jin, Yueming, Joshi, Smriti, Kadkhodamohammadi, Abdolrahim, Kamraoui, Reda Abdellah, Kang, Inha, Kang, Junghwa, Karimi, Davood, Khademi, April, Khan, Muhammad Irfan, Khan, Suleiman A., Khantwal, Rishab, Kim, Kwang-Ju, Kline, Timothy, Kondo, Satoshi, Kontio, Elina, Krenzer, Adrian, Kroviakov, Artem, Kuijf, Hugo, Kumar, Satyadwyoom, La Rosa, Francesco, Lad, Abhi, Lee, Doohee, Lee, Minho, Lena, Chiara, Li, Hao, Li, Ling, Li, Xingyu, Liao, Fuyuan, Liao, KuanLun, Oliveira, Arlindo Limede, Lin, Chaonan, Lin, Shan, Linardos, Akis, Linguraru, Marius George, Liu, Han, Liu, Tao, Liu, Di, Liu, Yanling, Lourenço-Silva, João, Lu, Jingpei, Lu, Jiangshan, Luengo, Imanol, Lund, Christina B., Luu, Huan Minh, Lv, Yi, Macar, Uzay, Maechler, Leon, L., Sina Mansour, Marshall, Kenji, Mazher, Moona, McKinley, Richard, Medela, Alfonso, Meissen, Felix, Meng, Mingyuan, Miller, Dylan, Mirjahanmardi, Seyed Hossein, Mishra, Arnab, Mitha, Samir, Mohy-ud-Din, Hassan, Mok, Tony Chi Wing, Murugesan, Gowtham Krishnan, Karthik, Enamundram Naga, Nalawade, Sahil, Nalepa, Jakub, Naser, Mohamed, Nateghi, Ramin, Naveed, Hammad, Nguyen, Quang-Minh, Quoc, Cuong Nguyen, Nichyporuk, Brennan, Oliveira, Bruno, Owen, David, Pal, Jimut Bahan, Pan, Junwen, Pan, Wentao, Pang, Winnie, Park, Bogyu, Pawar, Vivek, Pawar, Kamlesh, Peven, Michael, Philipp, Lena, Pieciak, Tomasz, Plotka, Szymon, Plutat, Marcel, Pourakpour, Fattaneh, Preložnik, Domen, Punithakumar, Kumaradevan, Qayyum, Abdul, Queirós, Sandro, Rahmim, Arman, Razavi, Salar, Ren, Jintao, Rezaei, Mina, Rico, Jonathan Adam, Rieu, ZunHyan, Rink, Markus, Roth, Johannes, Ruiz-Gonzalez, Yusely, Saeed, Numan, Saha, Anindo, Salem, Mostafa, Sanchez-Matilla, Ricardo, Schilling, Kurt, Shao, Wei, Shen, Zhiqiang, Shi, Ruize, Shi, Pengcheng, Sobotka, Daniel, Soulier, Théodore, Fadida, Bella Specktor, Stoyanov, Danail, Mun, Timothy Sum Hon, Sun, Xiaowu, Tao, Rong, Thaler, Franz, Théberge, Antoine, Thielke, Felix, Torres, Helena, Wahid, Kareem A., Wang, Jiacheng, Wang, YiFei, Wang, Wei, Wang, Xiong, Wen, Jianhui, Wen, Ning, Wodzinski, Marek, Wu, Ye, Xia, Fangfang, Xiang, Tianqi, Xiaofei, Chen, Xu, Lizhan, Xue, Tingting, Yang, Yuxuan, Yang, Lin, Yao, Kai, Yao, Huifeng, Yazdani, Amirsaeed, Yip, Michael, Yoo, Hwanseung, Yousefirizi, Fereshteh, Yu, Shunkai, Yu, Lei, Zamora, Jonathan, Zeineldin, Ramy Ashraf, Zeng, Dewen, Zhang, Jianpeng, Zhang, Bokai, Zhang, Jiapeng, Zhang, Fan, Zhang, Huahong, Zhao, Zhongchen, Zhao, Zixuan, Zhao, Jiachen, Zhao, Can, Zheng, Qingshuo, Zhi, Yuheng, Zhou, Ziqi, Zou, Baosheng, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, Maier-Hein, Lena, Eisenmann, Matthias, Reinke, Annika, Weru, Vivienn, Tizabi, Minu Dietlinde, Isensee, Fabian, Adler, Tim J., Godau, Patrick, Cheplygina, Veronika, Kozubek, Michal, Ali, Sharib, Gupta, Anubha, Kybic, Jan, Noble, Alison, de Solórzano, Carlos Ortiz, Pachade, Samiksha, Petitjean, Caroline, Sage, Daniel, Wei, Donglai, Wilden, Elizabeth, Alapatt, Deepak, Andrearczyk, Vincent, Baid, Ujjwal, Bakas, Spyridon, Balu, Niranjan, Bano, Sophia, Bawa, Vivek Singh, Bernal, Jorge, Bodenstedt, Sebastian, Casella, Alessandro, Choi, Jinwook, Commowick, Olivier, Daum, Marie, Depeursinge, Adrien, Dorent, Reuben, Egger, Jan, Eichhorn, Hannah, Engelhardt, Sandy, Ganz, Melanie, Girard, Gabriel, Hansen, Lasse, Heinrich, Mattias, Heller, Nicholas, Hering, Alessa, Huaulmé, Arnaud, Kim, Hyunjeong, Landman, Bennett, Li, Hongwei Bran, Li, Jianning, Ma, Jun, Martel, Anne, Martín-Isla, Carlos, Menze, Bjoern, Nwoye, Chinedu Innocent, Oreiller, Valentin, Padoy, Nicolas, Pati, Sarthak, Payette, Kelly, Sudre, Carole, van Wijnen, Kimberlin, Vardazaryan, Armine, Vercauteren, Tom, Wagner, Martin, Wang, Chuanbo, Yap, Moi Hoon, Yu, Zeyun, Yuan, Chun, Zenk, Maximilian, Zia, Aneeq, Zimmerer, David, Bao, Rina, Choi, Chanyeol, Cohen, Andrew, Dzyubachyk, Oleh, Galdran, Adrian, Gan, Tianyuan, Guo, Tianqi, Gupta, Pradyumna, Haithami, Mahmood, Ho, Edward, Jang, Ikbeom, Li, Zhili, Luo, Zhengbo, Lux, Filip, Makrogiannis, Sokratis, Müller, Dominik, Oh, Young-tack, Pang, Subeen, Pape, Constantin, Polat, Gorkem, Reed, Charlotte Rosalie, Ryu, Kanghyun, Scherr, Tim, Thambawita, Vajira, Wang, Haoyu, Wang, Xinliang, Xu, Kele, Yeh, Hung, Yeo, Doyeob, Yuan, Yixuan, Zeng, Yan, Zhao, Xin, Abbing, Julian, Adam, Jannes, Adluru, Nagesh, Agethen, Niklas, Ahmed, Salman, Khalil, Yasmina Al, Alenyà, Mireia, Alhoniemi, Esa, An, Chengyang, Anwar, Talha, Arega, Tewodros Weldebirhan, Avisdris, Netanell, Aydogan, Dogu Baran, Bai, Yingbin, Calisto, Maria Baldeon, Basaran, Berke Doga, Beetz, Marcel, Bian, Cheng, Bian, Hao, Blansit, Kevin, Bloch, Louise, Bohnsack, Robert, Bosticardo, Sara, Breen, Jack, Brudfors, Mikael, Brüngel, Raphael, Cabezas, Mariano, Cacciola, Alberto, Chen, Zhiwei, Chen, Yucong, Chen, Daniel Tianming, Cho, Minjeong, Choi, Min-Kook, Xie, Chuantao Xie Chuantao, Cobzas, Dana, Cohen-Adad, Julien, Acero, Jorge Corral, Das, Sujit Kumar, de Oliveira, Marcela, Deng, Hanqiu, Dong, Guiming, Doorenbos, Lars, Efird, Cory, Escalera, Sergio, Fan, Di, Serj, Mehdi Fatan, Fenneteau, Alexandre, Fidon, Lucas, Filipiak, Patryk, Finzel, René, Freitas, Nuno R., Friedrich, Christoph M., Fulton, Mitchell, Gaida, Finn, Galati, Francesco, Galazis, Christoforos, Gan, Chang Hee, Gao, Zheyao, Gao, Shengbo, Gazda, Matej, Gerats, Beerend, Getty, Neil, Gibicar, Adam, Gifford, Ryan, Gohil, Sajan, Grammatikopoulou, Maria, Grzech, Daniel, Güley, Orhun, Günnemann, Timo, Guo, Chunxu, Guy, Sylvain, Ha, Heonjin, Han, Luyi, Han, Il Song, Hatamizadeh, Ali, He, Tian, Heo, Jimin, Hitziger, Sebastian, Hong, SeulGi, Hong, SeungBum, Huang, Rian, Huang, Ziyan, Huellebrand, Markus, Huschauer, Stephan, Hussain, Mustaffa, Inubushi, Tomoo, Polat, Ece Isik, Jafaritadi, Mojtaba, Jeong, SeongHun, Jian, Bailiang, Jiang, Yuanhong, Jiang, Zhifan, Jin, Yueming, Joshi, Smriti, Kadkhodamohammadi, Abdolrahim, Kamraoui, Reda Abdellah, Kang, Inha, Kang, Junghwa, Karimi, Davood, Khademi, April, Khan, Muhammad Irfan, Khan, Suleiman A., Khantwal, Rishab, Kim, Kwang-Ju, Kline, Timothy, Kondo, Satoshi, Kontio, Elina, Krenzer, Adrian, Kroviakov, Artem, Kuijf, Hugo, Kumar, Satyadwyoom, La Rosa, Francesco, Lad, Abhi, Lee, Doohee, Lee, Minho, Lena, Chiara, Li, Hao, Li, Ling, Li, Xingyu, Liao, Fuyuan, Liao, KuanLun, Oliveira, Arlindo Limede, Lin, Chaonan, Lin, Shan, Linardos, Akis, Linguraru, Marius George, Liu, Han, Liu, Tao, Liu, Di, Liu, Yanling, Lourenço-Silva, João, Lu, Jingpei, Lu, Jiangshan, Luengo, Imanol, Lund, Christina B., Luu, Huan Minh, Lv, Yi, Macar, Uzay, Maechler, Leon, L., Sina Mansour, Marshall, Kenji, Mazher, Moona, McKinley, Richard, Medela, Alfonso, Meissen, Felix, Meng, Mingyuan, Miller, Dylan, Mirjahanmardi, Seyed Hossein, Mishra, Arnab, Mitha, Samir, Mohy-ud-Din, Hassan, Mok, Tony Chi Wing, Murugesan, Gowtham Krishnan, Karthik, Enamundram Naga, Nalawade, Sahil, Nalepa, Jakub, Naser, Mohamed, Nateghi, Ramin, Naveed, Hammad, Nguyen, Quang-Minh, Quoc, Cuong Nguyen, Nichyporuk, Brennan, Oliveira, Bruno, Owen, David, Pal, Jimut Bahan, Pan, Junwen, Pan, Wentao, Pang, Winnie, Park, Bogyu, Pawar, Vivek, Pawar, Kamlesh, Peven, Michael, Philipp, Lena, Pieciak, Tomasz, Plotka, Szymon, Plutat, Marcel, Pourakpour, Fattaneh, Preložnik, Domen, Punithakumar, Kumaradevan, Qayyum, Abdul, Queirós, Sandro, Rahmim, Arman, Razavi, Salar, Ren, Jintao, Rezaei, Mina, Rico, Jonathan Adam, Rieu, ZunHyan, Rink, Markus, Roth, Johannes, Ruiz-Gonzalez, Yusely, Saeed, Numan, Saha, Anindo, Salem, Mostafa, Sanchez-Matilla, Ricardo, Schilling, Kurt, Shao, Wei, Shen, Zhiqiang, Shi, Ruize, Shi, Pengcheng, Sobotka, Daniel, Soulier, Théodore, Fadida, Bella Specktor, Stoyanov, Danail, Mun, Timothy Sum Hon, Sun, Xiaowu, Tao, Rong, Thaler, Franz, Théberge, Antoine, Thielke, Felix, Torres, Helena, Wahid, Kareem A., Wang, Jiacheng, Wang, YiFei, Wang, Wei, Wang, Xiong, Wen, Jianhui, Wen, Ning, Wodzinski, Marek, Wu, Ye, Xia, Fangfang, Xiang, Tianqi, Xiaofei, Chen, Xu, Lizhan, Xue, Tingting, Yang, Yuxuan, Yang, Lin, Yao, Kai, Yao, Huifeng, Yazdani, Amirsaeed, Yip, Michael, Yoo, Hwanseung, Yousefirizi, Fereshteh, Yu, Shunkai, Yu, Lei, Zamora, Jonathan, Zeineldin, Ramy Ashraf, Zeng, Dewen, Zhang, Jianpeng, Zhang, Bokai, Zhang, Jiapeng, Zhang, Fan, Zhang, Huahong, Zhao, Zhongchen, Zhao, Zixuan, Zhao, Jiachen, Zhao, Can, Zheng, Qingshuo, Zhi, Yuheng, Zhou, Ziqi, Zou, Baosheng, Maier-Hein, Klaus, Jäger, Paul F., Kopp-Schneider, Annette, and Maier-Hein, Lena

Abstract

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

Published
2022

8. Overview of the HECKTOR Challenge at MICCAI 2021: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT Images

Author

Andrearczyk, Vincent, Oreiller, Valentin, Boughdad, Sarah, Rest, Catherine Chez Le, Elhalawani, Hesham, Jreige, Mario, Prior, John O., Vallières, Martin, Visvikis, Dimitris, Hatt, Mathieu, Depeursinge, Adrien, Andrearczyk, Vincent, Oreiller, Valentin, Boughdad, Sarah, Rest, Catherine Chez Le, Elhalawani, Hesham, Jreige, Mario, Prior, John O., Vallières, Martin, Visvikis, Dimitris, Hatt, Mathieu, and Depeursinge, Adrien

Abstract

This paper presents an overview of the second edition of the HEad and neCK TumOR (HECKTOR) challenge, organized as a satellite event of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021. The challenge is composed of three tasks related to the automatic analysis of PET/CT images for patients with Head and Neck cancer (H&N), focusing on the oropharynx region. Task 1 is the automatic segmentation of H&N primary Gross Tumor Volume (GTVt) in FDG-PET/CT images. Task 2 is the automatic prediction of Progression Free Survival (PFS) from the same FDG-PET/CT. Finally, Task 3 is the same as Task 2 with ground truth GTVt annotations provided to the participants. The data were collected from six centers for a total of 325 images, split into 224 training and 101 testing cases. The interest in the challenge was highlighted by the important participation with 103 registered teams and 448 result submissions. The best methods obtained a Dice Similarity Coefficient (DSC) of 0.7591 in the first task, and a Concordance index (C-index) of 0.7196 and 0.6978 in Tasks 2 and 3, respectively. In all tasks, simplicity of the approach was found to be key to ensure generalization performance. The comparison of the PFS prediction performance in Tasks 2 and 3 suggests that providing the GTVt contour was not crucial to achieve best results, which indicates that fully automatic methods can be used. This potentially obviates the need for GTVt contouring, opening avenues for reproducible and large scale radiomics studies including thousands potential subjects.

Published
2022

9. 3D Solid Spherical Bispectrum CNNs for Biomedical Texture Analysis

Author

Oreiller, Valentin, Andrearczyk, Vincent, Fageot, Julien, Prior, John O., Depeursinge, Adrien, Oreiller, Valentin, Andrearczyk, Vincent, Fageot, Julien, Prior, John O., and Depeursinge, Adrien

Abstract

Locally Rotation Invariant (LRI) operators have shown great potential in biomedical texture analysis where patterns appear at random positions and orientations. LRI operators can be obtained by computing the responses to the discrete rotation of local descriptors, such as Local Binary Patterns (LBP) or the Scale Invariant Feature Transform (SIFT). Other strategies achieve this invariance using Laplacian of Gaussian or steerable wavelets for instance, preventing the introduction of sampling errors during the discretization of the rotations. In this work, we obtain LRI operators via the local projection of the image on the spherical harmonics basis, followed by the computation of the bispectrum, which shares and extends the invariance properties of the spectrum. We investigate the benefits of using the bispectrum over the spectrum in the design of a LRI layer embedded in a shallow Convolutional Neural Network (CNN) for 3D image analysis. The performance of each design is evaluated on two datasets and compared against a standard 3D CNN. The first dataset is made of 3D volumes composed of synthetically generated rotated patterns, while the second contains malignant and benign pulmonary nodules in Computed Tomography (CT) images. The results indicate that bispectrum CNNs allows for a significantly better characterization of 3D textures than both the spectral and standard CNN. In addition, it can efficiently learn with fewer training examples and trainable parameters when compared to a standard convolutional layer., Comment: 10 pages

Published
2020

10. Local Rotation Invariance in 3D CNNs

Author

Andrearczyk, Vincent, Fageot, Julien, Oreiller, Valentin, Montet, Xavier, Depeursinge, Adrien, Andrearczyk, Vincent, Fageot, Julien, Oreiller, Valentin, Montet, Xavier, and Depeursinge, Adrien

Abstract

Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and in particular in medical imaging where local structures of tissues occur at arbitrary rotations. LRI constituted the cornerstone of several breakthroughs in texture analysis, including Local Binary Patterns (LBP), Maximum Response 8 (MR8) and steerable filterbanks. Whereas globally rotation invariant Convolutional Neural Networks (CNN) were recently proposed, LRI was very little investigated in the context of deep learning. LRI designs allow learning filters accounting for all orientations, which enables a drastic reduction of trainable parameters and training data when compared to standard 3D CNNs. In this paper, we propose and compare several methods to obtain LRI CNNs with directional sensitivity. Two methods use orientation channels (responses to rotated kernels), either by explicitly rotating the kernels or using steerable filters. These orientation channels constitute a locally rotation equivariant representation of the data. Local pooling across orientations yields LRI image analysis. Steerable filters are used to achieve a fine and efficient sampling of 3D rotations as well as a reduction of trainable parameters and operations, thanks to a parametric representations involving solid Spherical Harmonics (SH), which are products of SH with associated learned radial profiles.Finally, we investigate a third strategy to obtain LRI based on rotational invariants calculated from responses to a learned set of solid SHs. The proposed methods are evaluated and compared to standard CNNs on 3D datasets including synthetic textured volumes composed of rotated patterns, and pulmonary nodule classification in CT. The results show the importance of LRI image analysis while resulting in a drastic reduction of trainable parameters, outperforming standard 3D CNNs trained with data augmentation.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results