Structured crowdsourcing enables convolutional segmentation of histology images

By M. Amgad, H. Elfandy, Hagar Hussein, Lamees A. Atteya, Mai A T. Elsebaie, Lamia S. Abo Elnasr, R. Sakr, Hazem S. E. Salem, Ahmed F. Ismail, A. M. Saad and 21 more. Bioinform., 2019

317 citations recorded by the source corpus.

Abstract Motivation While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. Results We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. Availability and Implementation Dataset is freely available at: https://goo.gl/cNM4EL. Supplementary information Supplementary data are available at Bioinformatics online.

Subfields: Artificial Intelligence, Biophysics, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/a2efa44d01171057223a67db9bff5a78d1035b17

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 Biophysics

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Deep neural network models for computational histopathology: A survey (2019, background): “tionalcrowdsourcing layer for improving model performance. An alternativeapproachistomakeuseofexpertadvice(suchas anexperiencedpathologist)byprovidingfeedbackforannotating rare and challenging cases (Amgad et al., 2019). It is evident from the above studies that it is possible to train models using ”
Computational pathology definitions, best practices, and recommendations for regulatory guidance: a white paper from the Digital Pathology Association (2019, methodology): “Web-based tools may be ideal in sharing annotations between different research groups, as they avoid the need to install specific software on multiple systems [40].”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, unknown): “A 3 rd study employed a structured crowd sourcing method to generate tumor inﬁltrating lymphocyte maps [152], [181].”