Passer à la navigation principale Passer à la recherche Passer au contenu principal

The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification

  • Vasileios Baltatzis
  • , Kyriaki Margarita Bintsi
  • , Loïc Le Folgoc
  • , Octavio E. Martinez Manzanera
  • , Sam Ellis
  • , Arjun Nair
  • , Sujal Desai
  • , Ben Glocker
  • , Julia A. Schnabel
  • King's College London
  • Imperial College London
  • University College London
  • The Royal Brompton and Harefield NHS Foundation Trust
  • Technical University of Munich
  • German Research Center for Environmental Health

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

6 Citations (Scopus)

Résumé

Using publicly available data to determine the performance of methodological contributions is important as it facilitates reproducibility and allows scrutiny of the published results. In lung nodule classification, for example, many works report results on the publicly available LIDC dataset. In theory, this should allow a direct comparison of the performance of proposed methods and assess the impact of individual contributions. When analyzing seven recent works, however, we find that each employs a different data selection process, leading to largely varying total number of samples and ratios between benign and malignant cases. As each subset will have different characteristics with varying difficulty for classification, a direct comparison between the proposed methods is thus not always possible, nor fair. We study the particular effect of truthing when aggregating labels from multiple experts. We show that specific choices can have severe impact on the data distribution where it may be possible to achieve superior performance on one sample distribution but not on another. While we show that we can further improve on the state-of-the-art on one sample selection, we also find that on a more challenging sample selection, on the same database, the more advanced models underperform with respect to very simple baseline methods, highlighting that the selected data distribution may play an even more important role than the model architecture. This raises concerns about the validity of claimed methodological contributions. We believe the community should be aware of these pitfalls and make recommendations on how these can be avoided in future work.

langue originaleAnglais
titrePredictive Intelligence in Medicine - 4th International Workshop, PRIME 2021, Held in Conjunction with MICCAI 2021, Proceedings
rédacteurs en chefIslem Rekik, Ehsan Adeli, Sang Hyun Park, Julia Schnabel
EditeurSpringer Science and Business Media Deutschland GmbH
Pages201-211
Nombre de pages11
ISBN (imprimé)9783030876012
Les DOIs
étatPublié - 1 janv. 2021
Modification externeOui
Evénement4th International Workshop on Predictive Intelligence in Medicine, PRIME 2021, held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021 - Virtual, Online, France
Durée: 1 oct. 20211 oct. 2021

Série de publications

NomLecture Notes in Computer Science
Volume12928 LNCS
ISSN (imprimé)0302-9743
ISSN (Electronique)1611-3349

Une conférence

Une conférence4th International Workshop on Predictive Intelligence in Medicine, PRIME 2021, held in conjunction with 24th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2021
Pays/TerritoireFrance
La villeVirtual, Online
période1/10/211/10/21

Empreinte digitale

Examiner les sujets de recherche de « The Pitfalls of Sample Selection: A Case Study on Lung Nodule Classification ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation