Slide-specific models for segmentation of differently stained digital histopathology whole slide images

Brieu, Nicolas; Pauly, Olivier; Zimmermann, Johannes; Binnig, G.; Schmidt, Günter

doi:10.1117/12.2208620

Cited by 25 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Marker Area detection algorithm was applied to detect cav1-positive stained component. We applied an image processing workflow by the following steps: preprocessing (Tissue background separation & annotation of pancreatic tumor), tissue segmentation (into cellular and stromal components) then marker area detection to quantify cav-1 expression levels (35). The marker area was calculated as the percent of positive IHC stained area to the whole tissue.…”

Section: Methodsmentioning

confidence: 99%

Gemcitabine enhances the transport of nanovector-albumin-bound paclitaxel in gemcitabine-resistant pancreatic ductal adenocarcinoma

et al. 2017

View full text Add to dashboard Cite

The mechanism for improved therapeutic efficacy of the combination therapy with albumin-bound paclitaxel (nAb-PTX) and gemcitabine (gem) for pancreatic ductal adenocarcinoma (PDAC) has been ascribed to enhanced gem transport by nAb-PTX. Here, we used an orthotopic mouse model of gem-resistant human PDAC in which increasing gem transport would not improve the efficacy, thus revealing the importance of nAb-PTX transport. We aimed to evaluate therapeutic outcomes and transport of nAb-PTX to PDAC as a result of: (1)encapsulating nAb-PTX in multistage nanovectors (MSV); (2)effect of gem on caveolin-1 expression. Treatment with MSV/nAb-PTX+gem was highly efficient in prolonging animal survival in comparison to other therapeutic regimens. MSV/nAb-PTX+gem also caused a substantial increase in tumor PTX accumulation and significantly reduced tumor growth and tumor cell proliferation, and increased apoptosis. Moreover, gem enhanced caveolin-1 expression in vitro and in vivo, thereby improving transport of nAb-PTX to PDAC. This data was confirmed by analysis of PDACs from patients who received gem-based neo-adjuvant chemotherapy. In conclusion, we found that nAb-PTX treatment of gem-resistant PDAC can be enhanced by: (1)gem through up-regulation of caveolin-1; (2)MSV through increasing accumulation of nAb-PTX in the tumor.

show abstract

Section: Methodsmentioning

confidence: 99%

Gemcitabine enhances the transport of nanovector-albumin-bound paclitaxel in gemcitabine-resistant pancreatic ductal adenocarcinoma

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The methodology is comprised of four distinct stages: (a) A classification RF was trained with long-range spatial context features [69] extracted from manually annotated epithelial and non-epithelial regions (n = 4, resolution=1200 × 1200 pixels). Subsequently, the RF generated an epithelial mask for all IF images [70]. (b) A regression RF was trained to generate proximity maps using coordinates from manual annotations of cell nuclei (n = 750 from 19 fields of view, resolution=1485 × 1485).…”

Section: Methodsmentioning

confidence: 99%

Identification of Immunological Features Enables Survival Prediction of Muscle-Invasive Bladder Cancer Patients Using Machine Learning

Gavriel

Dimitriou

Brieu³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Clinical staging and prognosis of muscle-invasive bladder cancer (MIBC) routinely includes assessment of patient tissue samples by a pathologist. Recent studies corroborate the importance of image analysis in identifying and quantifying immunological markers from tissue samples that can provide further insights into patient prognosis. In this paper, we apply multiplex immunofluorescence on MIBC tissue sections to capture whole slide images and quantify potential prognostic markers related to lymphocytes, macrophages, tumour buds, and PD-L1. We propose a machine learning based approach for the prediction of 5 year prognosis with different combinations of image, clinical, and spatial features. An ensemble model comprising several functionally different models successfully stratifies MIBC patients into two risk groups with high statistical significance (p value < 1e − 05). Critical to improving MIBC survival rates, our method classifies correctly 71.4% of the patients who succumb to MIBC within 5 years, significantly higher than the 28.6% of the current clinical gold standard, the TNM staging system.

show abstract

“…However, instead of using directly the red, green, blue (RGB) colour components of the image pixels, the training is performed on cell density heatmaps. Such heatmaps are generated after segmentation and classification of all cell nuclei contained in the images . In particular, detected nuclei are categorized into homogeneous nuclei (mostly corresponding to immune cells), and textured nuclei (various types of cells, including melanoma cells).…”

Section: Methodsmentioning

confidence: 99%

“…Such heatmaps are generated after segmentation and classification of all cell nuclei contained in the images. 21 In particular, detected nuclei are categorized into homogeneous nuclei (mostly corresponding to immune cells), and textured nuclei (various types of cells, including melanoma cells). Figure 3 shows…”

Section: Tumour Region Detectionmentioning

confidence: 99%

iDermatoPath – a novel software tool for mitosis detection in H&E‐stained tissue sections of malignant melanoma

Andrés

Andres-Belloni

Hein

et al. 2017

Acad Dermatol Venereol

View full text Add to dashboard Cite

On the technical side, the developed iDermatoPath software tool provides a novel approach for mitosis detection in MM, which can be further improved using more training data such as dermatopathologist annotations. On the practical side, a first evaluation of the clinical utility was positive, albeit this approach provides most benefit for difficult cases in a research setting. Assuming all slides to be digitally processed and reported in the near future, this method could become a helpful additional tool for the pathologist.

show abstract

Slide-specific models for segmentation of differently stained digital histopathology whole slide images

Cited by 25 publications

References 6 publications

Gemcitabine enhances the transport of nanovector-albumin-bound paclitaxel in gemcitabine-resistant pancreatic ductal adenocarcinoma

Gemcitabine enhances the transport of nanovector-albumin-bound paclitaxel in gemcitabine-resistant pancreatic ductal adenocarcinoma

Identification of Immunological Features Enables Survival Prediction of Muscle-Invasive Bladder Cancer Patients Using Machine Learning

iDermatoPath – a novel software tool for mitosis detection in H&E‐stained tissue sections of malignant melanoma

Contact Info

Product

Resources

About