
Proceedings Paper
Tumor proliferation assessment of whole slide imagesFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
Grading whole slide images (WSIs) from patient tissue samples is an important task in digital pathology, particularly for diagnosis and treatment planning. However, this visual inspection task, performed by pathologists, is inherently subjective and has limited reproducibility. Moreover, grading of WSIs is time consuming and expensive. Designing a robust and automatic solution for quantitative decision support can improve the objectivity and reproducibility of this task. This paper presents a fully automatic pipeline for tumor proliferation assessment based on mitosis counting. The approach consists of three steps: i) region of interest selection based on tumor color characteristics, ii) mitosis counting using a deep network based detector, and iii) grade prediction from ROI mitosis counts. The full strategy was submitted and evaluated during the Tumor Proliferation Assessment Challenge (TUPAC) 2016. TUPAC is the first digital pathology challenge grading whole slide images, thus mimicking more closely a real case scenario. The pipeline is extremely fast and obtained the 2nd place for the tumor proliferation assessment task and the 3rd place in the mitosis counting task, among 17 participants. The performance of this fully automatic method is similar to the performance of pathologists and this shows the high quality of automatic solutions for decision support.
Paper Details
Date Published: 6 March 2018
PDF: 9 pages
Proc. SPIE 10581, Medical Imaging 2018: Digital Pathology, 105810Y (6 March 2018); doi: 10.1117/12.2293634
Published in SPIE Proceedings Vol. 10581:
Medical Imaging 2018: Digital Pathology
John E. Tomaszewski; Metin N. Gurcan, Editor(s)
PDF: 9 pages
Proc. SPIE 10581, Medical Imaging 2018: Digital Pathology, 105810Y (6 March 2018); doi: 10.1117/12.2293634
Show Author Affiliations
Mikael Rousson, ContextVision AB (Sweden)
Martin Hedlund, ContextVision AB (Sweden)
Mats Andersson, ContextVision AB (Sweden)
Ludwig Jacobsson, ContextVision AB (Sweden)
Gunnar Lathen, ContextVision AB (Sweden)
Martin Hedlund, ContextVision AB (Sweden)
Mats Andersson, ContextVision AB (Sweden)
Ludwig Jacobsson, ContextVision AB (Sweden)
Gunnar Lathen, ContextVision AB (Sweden)
Bjorn Norell, ContextVision AB (Sweden)
Oscar Jimenez-del-Toro, Univ. of Applied Sciences Western Switzerland (Switzerland)
Henning Mueller, Univ. of Applied Sciences Western Switzerland (Switzerland)
Manfredo Atzori, Univ. of Applied Sciences Western Switzerland (Switzerland)
Oscar Jimenez-del-Toro, Univ. of Applied Sciences Western Switzerland (Switzerland)
Henning Mueller, Univ. of Applied Sciences Western Switzerland (Switzerland)
Manfredo Atzori, Univ. of Applied Sciences Western Switzerland (Switzerland)
Published in SPIE Proceedings Vol. 10581:
Medical Imaging 2018: Digital Pathology
John E. Tomaszewski; Metin N. Gurcan, Editor(s)
© SPIE. Terms of Use
