ReCasNet: Improving consistency within the two-stage mitosis detection framework

02/28/2022
by   Chawan Piansaddhayanon, et al.
0

Mitotic count (MC) is an important histological parameter for cancer diagnosis and grading, but the manual process for obtaining MC from whole-slide histopathological images is very time-consuming and prone to error. Therefore, deep learning models have been proposed to facilitate this process. Existing approaches utilize a two-stage pipeline: the detection stage for identifying the locations of potential mitotic cells and the classification stage for refining prediction confidences. However, this pipeline formulation can lead to inconsistencies in the classification stage due to the poor prediction quality of the detection stage and the mismatches in training data distributions between the two stages. In this study, we propose a Refine Cascade Network (ReCasNet), an enhanced deep learning pipeline that mitigates the aforementioned problems with three improvements. First, window relocation was used to reduce the number of poor quality false positives generated during the detection stage. Second, object re-cropping was performed with another deep learning model to adjust poorly centered objects. Third, improved data selection strategies were introduced during the classification stage to reduce the mismatches in training data distributions. ReCasNet was evaluated on two large-scale mitotic figure recognition datasets, canine cutaneous mast cell tumor (CCMCT) and canine mammary carcinoma (CMC), which resulted in up to 4.8 percentage point improvements in the F1 scores for mitotic cell detection and 44.1 Techniques that underlie ReCasNet can be generalized to other two-stage object detection networks and should contribute to improving the performances of deep learning models in broad digital pathology applications.

READ FULL TEXT

page 4

page 6

page 11

research
09/26/2021

Automated Multi-Process CTC Detection using Deep Learning

Circulating Tumor Cells (CTCs) bear great promise as biomarkers in tumor...
research
03/29/2022

SHOP: A Deep Learning Based Pipeline for near Real-Time Detection of Small Handheld Objects Present in Blurry Video

While prior works have investigated and developed computational models c...
research
03/01/2022

Colon Nuclei Instance Segmentation using a Probabilistic Two-Stage Detector

Cancer is one of the leading causes of death in the developed world. Can...
research
06/30/2022

End-to-end Learning for Image-based Detection of Molecular Alterations in Digital Pathology

Current approaches for classification of whole slide images (WSI) in dig...
research
06/21/2021

Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules

In the operation maintenance (O M) of photovoltaic (PV) plants, th...
research
12/01/2017

Propagating Uncertainty in Multi-Stage Bayesian Convolutional Neural Networks with Application to Pulmonary Nodule Detection

Motivated by the problem of computer-aided detection (CAD) of pulmonary ...
research
02/12/2019

Field of Interest Prediction for Computer-Aided Mitotic Count

Manual counts of mitotic figures, which are determined in the tumor regi...

Please sign up or login with your details

Forgot password? Click here to reset