A review and comparison of breast tumor cell nuclei segmentation performances using deep convolutional neural networks

Lagree, Andrew; Mohebpour, Majidreza; Meti, Nicholas; Saednia, Khadijeh; Lu, Fang-I; Slodkowska, Elzbieta; Gandhi, Sonal; Rakovitch, Eileen; Shenfield, Alex; Sadeghi‐Naini, Ali; Tran, William T.

doi:10.1038/s41598-021-87496-1

Cited by 59 publications

(39 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several methods for generating synthetic samples using generative adversarial networks have recently been proposed Zhou F. et al [ 110 ]. The generative adversarial network can generate samples in data augmentation tasks rapidly, especially in image-to-image translation [ 20 ].…”

Section: Resultsmentioning

confidence: 99%

“…The tissue will be immersed in the formalin solution and planted in paraffin wax before being cut carefully, resulting in histopathology slides which then converted to images [ 18 , 19 ]. However, the manual procedure of biopsy analysis is tedious, time-consuming, and restricted by the quality of the histopathology image and the histopathologists’ skill [ 20 , 21 ]. The histopathology images are stored and analyzed using the Computer-Aided Diagnosis (CAD) system [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Khairi

Bakar

et al. 2021

Healthcare

View full text Add to dashboard Cite

Medical imaging is gaining significant attention in healthcare, including breast cancer. Breast cancer is the most common cancer-related death among women worldwide. Currently, histopathology image analysis is the clinical gold standard in cancer diagnosis. However, the manual process of microscopic examination involves laborious work and can be misleading due to human error. Therefore, this study explored the research status and development trends of deep learning on breast cancer image classification using bibliometric analysis. Relevant works of literature were obtained from the Scopus database between 2014 and 2021. The VOSviewer and Bibliometrix tools were used for analysis through various visualization forms. This study is concerned with the annual publication trends, co-authorship networks among countries, authors, and scientific journals. The co-occurrence network of the authors’ keywords was analyzed for potential future directions of the field. Authors started to contribute to publications in 2016, and the research domain has maintained its growth rate since. The United States and China have strong research collaboration strengths. Only a few studies use bibliometric analysis in this research area. This study provides a recent review on this fast-growing field to highlight status and trends using scientific visualization. It is hoped that the findings will assist researchers in identifying and exploring the potential emerging areas in the related field.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Khairi

Bakar

et al. 2021

Healthcare

View full text Add to dashboard Cite

show abstract

“…To our knowledge, the current publicly available data sets with nuclei fully annotated [ 17 ] are Multi-Organ Nucleus Segmentation (MoNuSeg) challenge [ 18 ] and Triple Negative Breast Cancer (TNBC) dataset [ 19 ]. The MoNuSeg dataset contained 44 sub-images with a size of 1000 × 1000 pixels cropped from hematoxylin and eosin (H&E) stained WSDP images at 40× magnification.…”

Section: Introductionmentioning

confidence: 99%

Recursive Training Strategy for a Deep Learning Network for Segmentation of Pathology Nuclei With Incomplete Annotation

et al. 2022

View full text Add to dashboard Cite

This study developed a recursive training strategy to train a deep learning model for nuclei detection and segmentation using incomplete annotation. A dataset of 141 H&E stained breast cancer pathologic images with incomplete annotation was randomly split into training/validation set and test set of 89 and 52 images, respectively. The positive training samples were extracted at each annotated cell and augmented with affine translation. The negative training samples were selected from the non-cellular regions free of nuclei using a histogram-based semi-automatic method. A U-Net model was initially trained by minimizing a custom loss function. After the first stage of training, the trained U-Net model was applied to the images in the training set in an inference mode. The U-Net segmented objects with high quality were selected by a semi-automated method. Combining the newly selected high quality objects with the annotated nuclei and the previously generated negative samples, the U-Net model was retrained recursively until the stopping criteria were satisfied. For the 52 test images, the U-Net trained with and without using our recursive training method achieved a sensitivity of 90.3% and 85.3% for nuclei detection, respectively. For nuclei segmentation, the average Dice coefficient and average Jaccard index were 0.831±0.213 and 0.750±0.217, 0.780±0.270 and 0.697±0.264, for U-Net with and without recursive training, respectively. The improvement achieved by our proposed method was statistically significant ( P < 0.05). In conclusion, our recursive training method effectively enlarged the set of annotated objects for training the deep learning model and further improved the detection and segmentation performance.

show abstract

“…Overall, these studies demonstrate the ongoing interest to enhance automation for breast cancer diagnosis. In this present study, we build on our previous work [ 31 , 32 , 33 ] to develop CADs for pathology and propose a computational pipeline for histologic grading.…”

Section: Introductionmentioning

confidence: 99%

Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background: Evaluating histologic grade for breast cancer diagnosis is standard and associated with prognostic outcomes. Current challenges include the time required for manual microscopic evaluation and interobserver variability. This study proposes a computer-aided diagnostic (CAD) pipeline for grading tumors using artificial intelligence. Methods: There were 138 patients included in this retrospective study. Breast core biopsy slides were prepared using standard laboratory techniques, digitized, and pre-processed for analysis. Deep convolutional neural networks (CNNs) were developed to identify the regions of interest containing malignant cells and to segment tumor nuclei. Imaging-based features associated with spatial parameters were extracted from the segmented regions of interest (ROIs). Clinical datasets and pathologic biomarkers (estrogen receptor, progesterone receptor, and human epidermal growth factor 2) were collected from all study subjects. Pathologic, clinical, and imaging-based features were input into machine learning (ML) models to classify histologic grade, and model performances were tested against ground-truth labels at the patient-level. Classification performances were evaluated using receiver-operating characteristic (ROC) analysis. Results: Multiparametric feature sets, containing both clinical and imaging-based features, demonstrated high classification performance. Using imaging-derived markers alone, the classification performance demonstrated an area under the curve (AUC) of 0.745, while modeling these features with other pathologic biomarkers yielded an AUC of 0.836. Conclusion: These results demonstrate an association between tumor nuclear spatial features and tumor grade. If further validated, these systems may be implemented into pathology CADs and can assist pathologists to expeditiously grade tumors at the time of diagnosis and to help guide clinical decisions.

show abstract

A review and comparison of breast tumor cell nuclei segmentation performances using deep convolutional neural networks

Cited by 59 publications

References 74 publications

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Recursive Training Strategy for a Deep Learning Network for Segmentation of Pathology Nuclei With Incomplete Annotation

Assessment of Digital Pathology Imaging Biomarkers Associated with Breast Cancer Histologic Grade

Contact Info

Product

Resources

About