ArXiv Preprint
Since the introduction of digital and computational pathology as a field, one
of the major problems in the clinical application of algorithms has been the
struggle to generalize well to examples outside the distribution of the
training data. Existing work to address this in both pathology and natural
images has focused almost exclusively on classification tasks. We explore and
evaluate the robustness of the 7 best performing nuclear segmentation and
classification models from the largest computational pathology challenge for
this problem to date, the CoNIC challenge. We demonstrate that existing
state-of-the-art (SoTA) models are robust towards compression artifacts but
suffer substantial performance reduction when subjected to shifts in the color
domain. We find that using stain normalization to address the domain shift
problem can be detrimental to the model performance. On the other hand, neural
style transfer is more consistent in improving test performance when presented
with large color variations in the wild.
Quoc Dang Vu, Robert Jewsbury, Simon Graham, Mostafa Jahanifar, Shan E Ahmed Raza, Fayyaz Minhas, Abhir Bhalerao, Nasir Rajpoot
2023-01-09
