Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX

Abstract

In this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV) framework for integrating image-based information from differently stained histopathology slides. The multi-FOV approach involves a fixed image resolution while simultaneously integrating image descriptors from many FOVs corresponding to different sizes. For each study, the corresponding risk score (high scores reflecting aggressive disease and vice versa), predicted by a molecular assay (Oncotype DX), is available and serves as the surrogate ground truth for long-term patient outcome. Using the risk scores, a trained classifier is used to identify disease aggressiveness for each FOV size. The predictions for each FOV are then combined to yield the final prediction of disease aggressiveness (good, intermediate, or poor outcome). Independent multi-FOV classifiers are constructed for (1) 50 image features describing the spatial arrangement of cancer nuclei (via Voronoi diagram, Delaunay triangulation, and minimum spanning tree graphs) in H and E stained histopathology and (2) one image feature describing the vascular density in CD34 IHC stained histopathology. In a cohort of 29 patients, the multi-FOV classifiers obtained by combining information from the H and E and CD34 IHC stained channels were able to distinguish low- and high-risk patients with an accuracy of 0.91 ± 0.02 and a positive predictive value of 0.94 ± 0.10, suggesting that a purely image-based assay could potentially replace more expensive molecular assays for making disease prognostic predictions.

A Quantitative Histomorphometric Classifier (QuHbIC) Identifies Aggressive Versus Indolent p16-Positive Oropharyngeal Squamous Cell Carcinoma

“…Quantitative histomorphometry has already been successful in predicting recurrence in breast cancer 15,30 and biochemical recurrence in prostate cancer. In men with prostate cancer, quantitative histomorphometrics was able to predict biochemical recurrence in patients with long-term follow-up after prostatectomy.…”

“…13 Many quantitative features can be assessed, such as precise numeric measurements pertaining to the spatial arrangement and architecture of nuclei, shapes of nests and nuclei, and nuclear texture. This technology has already been shown to be useful for the detection of prostate adenocarcinomas in tissue sections 14 and also for predicting tumor biology and clinical behavior in breast 15 carcinomas. It has significant potential to transform the practice of pathology.…”

Automated grading of breast cancer histopathology using cascaded ensemble with combination of multi-level image features

“…For instance, a number of techniques have been developed on automated nuclei segmentation in routinely stained breast histopathological images using methodologies, such as adaptive thresholding [14], region growing [15], watershed [16], graph cuts [17], active contour [18], statistical model [19], and deep learning [20,21]. Further, various intensity, morphology, and textural features, e.g., vascular density [22], Voronoi and Delaunay graphs [15], co-occurring gland angularity [23], and combinations of different feature subtypes [24,25,26], have been implemented for malignancy detection in breast cancer histopathology. Such CAD systems on the breast histopathology could be used for increased diagnosis accuracy and reduced subjective variability of breast cancer grading as well the workload of the pathologists [27].…”

Improving Accuracy of Nuclei Segmentation by Reducing Histological Image Variability BMI 260 - Spring 2017

“…Nuclear morphology is an important indicator of the grade of cancer and the stage of its progression [3]. It has also been shown to be a predictor of cancer outcome [4] and counting mitosis events in nuclei is a useful marker of cancerous growth. [2] Currently, histological analysis such as these are done manually, with pathologists counting and evaluating cells by inspection.…”