Automated Tubule Nuclei Quantification and Correlation with Oncotype DX risk categories in ER+ Breast Cancer Whole Slide Images

Romo-Bucheli, David; Janowczyk, Andrew; Gilmore, Hannah; Romero, Eduardo; Madabhushi, Anant

doi:10.1038/srep32706

Cited by 74 publications

(41 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this processing pipeline, a total of 299 features can be obtained. We note that this is significantly higher than in studies such as Wang et al 29 and Romo et al 30 . As briefly mentioned above, some imaging studies, especially the early ones, utilize low dimensional imaging features.…”

Section: Methodscontrasting

confidence: 67%

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Zhang

Fan

Zhong

et al. 2020

Sci Rep

View full text Add to dashboard Cite

For lung and many other cancers, prognosis is essentially important, and extensive modeling has been carried out. Cancer is a genetic disease. In the past 2 decades, diverse molecular data (such as gene expressions and DNA mutations) have been analyzed in prognosis modeling. More recently, histopathological imaging data, which is a “byproduct” of biopsy, has been suggested as informative for prognosis. In this article, with the TCGA LUAD and LUSC data, we examine and directly compare modeling lung cancer overall survival using gene expressions versus histopathological imaging features. High-dimensional penalization methods are adopted for estimation and variable selection. Our findings include that gene expressions have slightly better prognostic performance, and that most of the gene expressions are weakly correlated imaging features. This study may provide additional insight into utilizing the two types of important data in cancer prognosis modeling and into lung cancer overall survival.

show abstract

Section: Methodscontrasting

confidence: 67%

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Zhang

Fan

Zhong

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Yuan and colleagues [12] showed that quantitative measurements of the extent and density of lymphocytic infiltration was predictive of risk of recurrence following endocrine therapy in ER+ breast cancers. More recently, Romo-Bucheli et al [13, 14] showed that quantitative estimation of mitotic activity and tubular formation in ER+ breast cancer histology images via machine learning and image analysis approaches was strongly correlated with the corresponding Oncotype DX risk categories.…”

Section: Introductionmentioning

confidence: 99%

Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers

Romo-Bucheli

Wang

et al. 2018

Laboratory Investigation

Self Cite

116

View full text Add to dashboard Cite

Early-stage estrogen receptor-positive (ER+) breast cancer (BCa) is the most common type of BCa in the United States. One critical question with these tumors is identifying which patients will receive added benefit from adjuvant chemotherapy. Nuclear pleomorphism (variance in nuclear shape and morphology) is an important constituent of breast grading schemes, and in ER+ cases, the grade is highly correlated with disease outcome. This study aimed to investigate whether quantitative computer-extracted image features of nuclear shape and orientation on digitized images of hematoxylin-stained and eosinstained tissue of lymph node-negative (LN−), ER+ BCa could help stratify patients into discrete (<10 years short-term vs. >10 years long-term survival) outcome groups independent of standard clinical and pathological parameters. We considered a tissue microarray (TMA) cohort of 276 ER+, LN− patients comprising 150 patients with long-term and 126 patients with short-term overall survival, wherein 177 randomly chosen cases formed the modeling set, and 99 remaining cases the test set. Segmentation of individual nuclei was performed using multiresolution watershed; subsequently, 615 features relating to nuclear shape/texture and orientation disorder were extracted from each TMA spot. The Wilcoxon’s rank-sum test identified the 15 most prognostic quantitative histomorphometric features within the modeling set. These features were then subsequently combined via a linear discriminant analysis classifier and evaluated on the test set to assign a probability of long-term vs. short-term disease-specific survival. In univariate survival analysis, patients identified by the image classifier as high risk had significantly poorer survival outcome: hazard ratio (95% confident interval) = 2.91(1.23–6.92), p = 0.02786. Multivariate analysis controlling for T-stage, histology grade, and nuclear grade showed the classifier to be independently predictive of poorer survival: hazard ratio (95% confident interval) = 3.17(0.33–30.46), p = 0.01039. Our results suggest that quantitative histomorphometric features of nuclear shape and orientation are strongly and independently predictive of patient survival in ER+, LN− BCa.

show abstract

“…Most previous studies have been based on supervised learning (e.g. tumor, mitosis and tubule nuclei detection [ 13 – 16 , 20 , 51 ]), with relatively few approaches being geared towards unsupervised learning [ 16 , 49 , 50 , 52 ]. In fact, the most successful representation learning approaches in histopathology image analysis have been supervised approaches involving CNNs, outperforming hand-crafted features in several problems [ 53 ].…”

Section: Previous Related Workmentioning

confidence: 99%

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection

et al. 2018

Self Cite

View full text Add to dashboard Cite

Precise detection of invasive cancer on whole-slide images (WSI) is a critical first step in digital pathology tasks of diagnosis and grading. Convolutional neural network (CNN) is the most popular representation learning method for computer vision tasks, which have been successfully applied in digital pathology, including tumor and mitosis detection. However, CNNs are typically only tenable with relatively small image sizes (200 × 200 pixels). Only recently, Fully convolutional networks (FCN) are able to deal with larger image sizes (500 × 500 pixels) for semantic segmentation. Hence, the direct application of CNNs to WSI is not computationally feasible because for a WSI, a CNN would require billions or trillions of parameters. To alleviate this issue, this paper presents a novel method, High-throughput Adaptive Sampling for whole-slide Histopathology Image analysis (HASHI), which involves: i) a new efficient adaptive sampling method based on probability gradient and quasi-Monte Carlo sampling, and, ii) a powerful representation learning classifier based on CNNs. We applied HASHI to automated detection of invasive breast cancer on WSI. HASHI was trained and validated using three different data cohorts involving near 500 cases and then independently tested on 195 studies from The Cancer Genome Atlas. The results show that (1) the adaptive sampling method is an effective strategy to deal with WSI without compromising prediction accuracy by obtaining comparative results of a dense sampling (∼6 million of samples in 24 hours) with far fewer samples (∼2,000 samples in 1 minute), and (2) on an independent test dataset, HASHI is effective and robust to data from multiple sites, scanners, and platforms, achieving an average Dice coefficient of 76%.

show abstract

Automated Tubule Nuclei Quantification and Correlation with Oncotype DX risk categories in ER+ Breast Cancer Whole Slide Images

Cited by 74 publications

References 33 publications

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Histopathological imaging features- versus molecular measurements-based cancer prognosis modeling

Nuclear shape and orientation features from H&E images predict survival in early-stage estrogen receptor-positive breast cancers

High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection

Contact Info

Product

Resources

About