Detecting mitotic figures in breast cancer histopathology images

2013 ◽  
Author(s):  
M. Veta ◽  
P. J. van Diest ◽  
J. P. W. Pluim
Keyword(s):  
Breast Cancer ◽  
Histopathology Images ◽  
Mitotic Figures

scholarly journals Recurrent uterine tumors resembling ovarian sex-cord tumors with the growth regulation by estrogen in breast cancer 1-nuclear receptor coactivator 2 fusion gene: a case report and literature review

2020 ◽  
Vol 15 (1) ◽  
Author(s):  
Bin Chang ◽  
Qianming Bai ◽  
Lin Liang ◽  
Huijuan Ge ◽  
Qianlan Yao
Keyword(s):  
Breast Cancer ◽  
Nuclear Receptor ◽  
Growth Regulation ◽  
Fusion Gene ◽  
Nuclear Receptor Coactivator ◽  
Mesenchymal Neoplasms ◽  
Uterine Tumors ◽  
Molecular Events ◽  
Pathologic Features ◽  
Mitotic Figures

Abstract Background Uterine tumors resembling ovarian sex-cord tumors (UTROSCTs) are rare mesenchymal neoplasms predominantly arising in perimenopausal and postmenopausal women. UTROSCTs with growth regulation by estrogen in breast cancer 1 (GREB1)-rearrangement or GREB1-rearranged uterine tumors are exceptionally rare, with only 12 previously reported cases. Here, we report a case of UTROSCT with the GREB1-nuclear receptor coactivator 2 (NCOA2) fusion gene. Case presentation A 57-year-old woman presented with a 10.0 cm uterine mass. The tumor was composed of short spindle or epithelioid cells, arranged in diffused sheets, nested, and trabecular/cordlike. The tumor harbored the GREB1-NCOA2 fusion gene, as confirmed by RNA sequencing. The tumor recurred in the pelvis at 30 months after the initial diagnosis. We also compared the clinical and pathologic features of this case with those of the 12 previously published uterine GREB1-rearranged tumors. Of the combined 13 cases (present case and 12 previous cases), the mean age of patients was 64.8 years (range, 51–74 years). Of the nine reported cases of GREB1-rearranged tumor with follow up, four cases recurred or metastasized (44.4%). Microscopically, most tumors (10/12, 83.3%) showed infiltrative growth, and two were well demarcated. Mitotic figures ranged from 0 to 14 per 10 high-power fields (2 mm2; mean: 3.6). Lymphovascular invasion and necrosis were each present in two cases (2/12, 16.7% and 2/7, 28.6%, respectively). Conclusions This case provided further evidence that UTROSCTs with GREB1-rearrangement may have a high risk of recurrence/metastasis. Further studies are necessary to clarify the clinical features of this type of tumor, particularly the prognosis, potential treatment, and range of possible molecular events.

scholarly journals Artificial Intelligence-Based Mitosis Detection in Breast Cancer Histopathology Images Using Faster R-CNN and Deep CNNs

2020 ◽  
Vol 9 (3) ◽  
pp. 749 ◽  
Author(s):  
Tahir Mahmood ◽  
Muhammad Arsalan ◽  
Muhammad Owais ◽  
Min Beom Lee ◽  
Kang Ryoung Park
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
Computational Cost ◽  
Mitotic Cell ◽  
Medical Doctor ◽  
Cell Detection ◽  
Generalization Capability ◽  
Mitosis Detection ◽  
Histopathology Images ◽  
Mitotic Cells

Breast cancer is the leading cause of mortality in women. Early diagnosis of breast cancer can reduce the mortality rate. In the diagnosis, the mitotic cell count is an important biomarker for predicting the aggressiveness, prognosis, and grade of breast cancer. In general, pathologists manually examine histopathology images under high-resolution microscopes for the detection of mitotic cells. However, because of the minute differences between the mitotic and normal cells, this process is tiresome, time-consuming, and subjective. To overcome these challenges, artificial-intelligence-based (AI-based) techniques have been developed which automatically detect mitotic cells in the histopathology images. Such AI techniques accelerate the diagnosis and can be used as a second-opinion system for a medical doctor. Previously, conventional image-processing techniques were used for the detection of mitotic cells, which have low accuracy and high computational cost. Therefore, a number of deep-learning techniques that demonstrate outstanding performance and low computational cost were recently developed; however, they still require improvement in terms of accuracy and reliability. Therefore, we present a multistage mitotic-cell-detection method based on Faster region convolutional neural network (Faster R-CNN) and deep CNNs. Two open datasets (international conference on pattern recognition (ICPR) 2012 and ICPR 2014 (MITOS-ATYPIA-14)) of breast cancer histopathology were used in our experiments. The experimental results showed that our method achieves the state-of-the-art results of 0.876 precision, 0.841 recall, and 0.858 F1-measure for the ICPR 2012 dataset, and 0.848 precision, 0.583 recall, and 0.691 F1-measure for the ICPR 2014 dataset, which were higher than those obtained using previous methods. Moreover, we tested the generalization capability of our technique by testing on the tumor proliferation assessment challenge 2016 (TUPAC16) dataset and found that our technique also performs well in a cross-dataset experiment which proved the generalization capability of our proposed technique.

Sign in / Sign up

Export Citation Format

Share Document