Heterogeneity assessment of histological tissue sections in whole slide images

Belhomme, Philippe; Toralba, Simon; Plancoulaine, Benoît; Oger, Myriam; Gürcan, Metin N.; Bor-Angelier, Catherine

doi:10.1016/j.compmedimag.2014.11.006

Cited by 15 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The annotations were edited to exclude slide background for higher quality ground truth. Each annotation was sampled for 64x64 pixel tiles at 20x magnification using a method inspired by point counting stereology [ 29 ]–a grid of points arranged in squares is laid across the image, and squares that fall within the boundary of the annotation are extracted as patches. The Euclidean distance between every tile of a class across all slides was computed and subjected to multidimensional scaling to eliminate outliers [ 30 ].…”

Section: Methodsmentioning

confidence: 99%

Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning

et al. 2018

Self Cite

View full text Add to dashboard Cite

The World Health Organization (WHO) has clear guidelines regarding the use of Ki67 index in defining the proliferative rate and assigning grade for pancreatic neuroendocrine tumor (NET). WHO mandates the quantification of Ki67 index by counting at least 500 positive tumor cells in a hotspot. Unfortunately, Ki67 antibody may stain both tumor and non-tumor cells as positive depending on the phase of the cell cycle. Likewise, the counter stain labels both tumor and non-tumor as negative. This non-specific nature of Ki67 stain and counter stain therefore hinders the exact quantification of Ki67 index. To address this problem, we present a deep learning method to automatically differentiate between NET and non-tumor regions based on images of Ki67 stained biopsies. Transfer learning was employed to recognize and apply relevant knowledge from previous learning experiences to differentiate between tumor and non-tumor regions. Transfer learning exploits a rich set of features previously used to successfully categorize non-pathology data into 1,000 classes. The method was trained and validated on a set of whole-slide images including 33 NETs subject to Ki67 immunohistochemical staining using a leave-one-out cross-validation. When applied to 30 high power fields (HPF) and assessed against a gold standard (evaluation by two expert pathologists), the method resulted in a high sensitivity of 97.8% and specificity of 88.8%. The deep learning method developed has the potential to reduce pathologists’ workload by directly identifying tumor boundaries on images of Ki67 stained slides. Moreover, it has the potential to replace sophisticated and expensive imaging methods which are recently developed for identification of tumor boundaries in images of Ki67-stained NETs.

show abstract

Section: Methodsmentioning

confidence: 99%

Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The histogram analysis completed on the whole slice of the HE staining image with ImageJ software to obtain the parameters that reflect tumor heterogeneity: standard deviation (SD) and kurtosis. An ROI was manually drawn along the tumor border on this HE slice after conversion from color to grayscale (Figure 3) (19)(20)(21)(22)(23).…”

Section: Histopathological Analysismentioning

confidence: 99%

Evaluation of intratumoral heterogeneity by using diffusion kurtosis imaging and stretched exponential diffusion-weighted imaging in an orthotopic hepatocellular carcinoma xenograft model

Guo¹,

Yang²,

Lu³

et al. 2019

Quant. Imaging Med. Surg.

View full text Add to dashboard Cite

Background: To investigate the value of diffusion kurtosis imaging (DKI) and diffusion-weighted imaging (DWI) with a stretched exponential model (SEM) in the evaluation of tumor heterogeneity in an orthotopic hepatocellular carcinoma (HCC) xenograft model. Methods: Thirty orthotopic HCC xenograft nude mice models were established and randomly divided into two groups, the sorafenib induction group (n=15) and control group (n=15). Every mouse in each group underwent MRI with DKI and SEM on a 1.5T MR scanner at 7, 14, and 21 days after sorafenib intervention. DKI and SEM parameters including mean kurtosis (MK), mean diffusivity (MD), α, and distributed diffusion coefficient (DDC) were measured, calculated, and compared between the two groups and among different time points. Sequential correlations between histopathological results including necrotic fraction (NF), micro-vessel density (MVD), Ki-67 index, standard deviation (SD), and kurtosis from hematoxylin-eosin staining, and DKI and SEM parameters were analyzed.Results: MK, MD, and DDC of HCC in the sorafenib induction group were significantly higher than those in the control group at each time point (P<0.05), while α was significantly lower (P<0.05). Significantly positive correlations were found between MK and NF (r=0.

show abstract

“…These annotations were then manually transferred over to adjacent H&E slides and verified by the pathologist. Each annotation within H&E was then sampled for 256 × 256 tiles at 40x magnification using stereology 32 – a square grid of points is laid across an image, and squares strictly inside the annotation are extracted as tiles – shown in Supplementary Fig. S2.…”

Section: Methodsmentioning

confidence: 99%

A modular cGAN classification framework: Application to colorectal tumor detection

Tavolara

Niazi

Arole

et al. 2019

Sci Rep

Self Cite

View full text Add to dashboard Cite

Automatic identification of tissue structures in the analysis of digital tissue biopsies remains an ongoing problem in digital pathology. Common barriers include lack of reliable ground truth due to inter- and intra- reader variability, class imbalances, and inflexibility of discriminative models. To overcome these barriers, we are developing a framework that benefits from a reliable immunohistochemistry ground truth during labeling, overcomes class imbalances through single task learning, and accommodates any number of classes through a minimally supervised, modular model-per-class paradigm. This study explores an initial application of this framework, based on conditional generative adversarial networks, to automatically identify tumor from non-tumor regions in colorectal H&E slides. The average precision, sensitivity, and F1 score during validation was 95.13 ± 4.44%, 93.05 ± 3.46%, and 94.02 ± 3.23% and for an external test dataset was 98.75 ± 2.43%, 88.53 ± 5.39%, and 93.31 ± 3.07%, respectively. With accurate identification of tumor regions, we plan to further develop our framework to establish a tumor front, from which tumor buds can be detected in a restricted region. This model will be integrated into a larger system which will quantitatively determine the prognostic significance of tumor budding.

show abstract

Heterogeneity assessment of histological tissue sections in whole slide images

Cited by 15 publications

References 11 publications

Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning

Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning

Evaluation of intratumoral heterogeneity by using diffusion kurtosis imaging and stretched exponential diffusion-weighted imaging in an orthotopic hepatocellular carcinoma xenograft model

A modular cGAN classification framework: Application to colorectal tumor detection

Contact Info

Product

Resources

About