Predicting breast tumor proliferation from whole‐slide images: The TUPAC16 challenge

By M. Veta, Y. Heng, N. Stathonikos, Babak Ehteshami Bejnordi, F. Beca, Thomas Wollmann, Karl Rohr, Manan A. Shah, Dayong Wang, Mikaël Rousson and 23 more. Medical Image Anal., 2018

307 citations recorded by the source corpus.

&NA; Tumor proliferation is an important biomarker indicative of the prognosis of breast cancer patients. Assessment of tumor proliferation in a clinical setting is a highly subjective and labor‐intensive task. Previous efforts to automate tumor proliferation assessment by image analysis only focused on mitosis detection in predefined tumor regions. However, in a real‐world scenario, automatic mitosis detection should be performed in whole‐slide images (WSIs) and an automatic method should be able to produce a tumor proliferation score given a WSI as input. To address this, we organized the TUmor Proliferation Assessment Challenge 2016 (TUPAC16) on prediction of tumor proliferation scores from WSIs. The challenge dataset consisted of 500 training and 321 testing breast cancer histopathology WSIs. In order to ensure fair and independent evaluation, only the ground truth for the training dataset was provided to the challenge participants. The first task of the challenge was to predict mitotic scores, i.e., to reproduce the manual method of assessing tumor proliferation by a pathologist. The second task was to predict the gene expression based PAM50 proliferation scores from the WSI. The best performing automatic method for the first task achieved a quadratic‐weighted Cohen's kappa score of &kgr; = 0.567, 95% CI [0.464, 0.671] between the predicted scores and the ground truth. For the second task, the predictions of the top method had a Spearman's correlation coefficient of r = 0.617, 95% CI [0.581 0.651] with the ground truth. This was the first comparison study that investigated tumor proliferation assessment from WSIs. The achieved results are promising given the difficulty of the tasks and weakly‐labeled nature of the ground truth. However, further research is needed to improve the practical utility of image analysis methods for this task.

Subfields: Artificial Intelligence, Cancer Research, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/c377304af802f1ea67c6d696806a69f516a4472f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Self supervised contrastive learning for digital histopathology (2020, unknown): “For instance, TUPAC 2016 Veta et al. (2019) contains 500 WSIs and only extracting patches of size 224 × 224 pixels at 0.”
Emerging role of deep learning‐based artificial intelligence in tumor pathology (2020, methodology): “…[46]-[48] Evaluation of pathological features Mitotic count F-score: 0.611 [57] Ki-67 index F-score: 0.91 [64] Proliferation score Kappa: 0.613 [58] Immune cell-rich/Immune cell-poor regions AUC: 0.99 [62] Evaluation of biomarkers HER2 status: Negative (0 and 1 + )/ Equivocal (2 + )/Positive…”
Artificial intelligence for digital and computational pathology (2023, unknown): “Patches, nuclei, pixels, etc.”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, unknown): “However, this practice has not been ubiquitous due to the difficulty of obtaining data spanning multiple hospitals (Esteva et al., 2017; Bejnordi et al., 2017; Codella et al., 2019; Veta et al., 2019).”
Deep Learning for Whole Slide Image Analysis: An Overview (2019, methodology): “Automating this process through the use of convolutional neural networks (CNNs) has been shown to result in more discriminative features tailored for the problem at hand (13, 23, 25, 26).”