1 January 2016 in Russian Journal of Archive of Pathology
Angiogenesis is a process of new blood vessels formation. The role of angiogenesis in growth, invasion and metastasis of malignant tumours is nowdays universally recognized. Though, investigation of mechanisms of blood vessels formation and elaboration methods for assessment of tumour angiogenesis are still up-dated. Another important concern are different aspects of usage of immunohistochemical markers of blood vessels endothelium (CD31 and CD34) for assessment of tumour aggressiveness and prognosis. The problems of malignant lymphangiogenesis are also up-to-date. The focus is on methods of immunohistochemical visualization of forming lymphatic vessels, role of podoplanin, the most reliable marker of lymphatic vessels, in their identification, and formulization of the main criteria for lymphangiogenesis estimation, its correlation with metastatic activity and prognostic potential. Studying of angiogenesis and lymph angiogenesis in malignant tumors is important and challenging direction for researching tumour progression and invention of antiangiogenic therapy.
9 May 2019 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Mucous glands is an important diagnostic element in digestive pathology. The first step of differential diagnosis of colon polyps in order to assess their malignant potential is gland segmentation. The process of mucous glands segmentation is challenging as the glands not only needed to be separated from a background but also individually identified to obtain reliable morphometric criteria for quantitative diagnostic methods. We propose a new convolutional neural network for mucous gland segmentation that takes into account glands’ contours and can be used for gland instance segmentation. Training and evaluation of the network was performed on a standard Warwick-QU dataset as well as on the collected PATH-DT-MSU dataset of histological images obtained from hematoxylin and eosin staining of paraffin sections of colon biopsy material collected by our Pathology department. The collected PATH-DT-MSU dataset will be available at http://imaging.cs.msu.ru/en/research/histology.
18 March 2019 in Endoscopy
Aims: Artificial intelligence is rapidly gaining ground in online detection, endoscopic and morphological characterization of colon epithelial neoplasms. Even for pathologists identification of metaplasia and dysplasia in the epithelium of the mucous glands could be an extremely difficult task. The same task in vivo, directly during the endoscopic examination is no less difficult, therefore the development of auxiliary mathematical models for image recognition is requested. Methods: We propose a new design of a convolutional neural network (CNN) based on U-Net model and use it for mucous glands segmentation. The main distinctive ideas of the proposed CNN lay in the multiscale architecture, using non-local blocks to capture long-range dependencies in the image and using a contour-aware loss function. The network was first trained on the public Warwick-QU dataset with non-linear augmentation process and was afterthat fine-tuned on the manually labeled histological images obtained from paraffin sections of endoscopic biopsy material of the colon. Results: The multiscale architecture of the proposed segmentational CNN makes it less sensitive to the scale of the input image. Due to the specific loss function it is able to detect and separate “stuck” glands. The used non-linear blocks have a positive effect on the time needed for model to converge. Altogether this leads to the accurate segmentation of glands on histology images (Dice coefficient = 0.87 for Warwick-QU dataset, Dice coefficient = 0.83 for the obtained dataset). Conclusions: The generalization ability of the proposed algorithm enables it to effectively segment individual glands as well as to perform inner-gland segmentation (detect nuclei, lumen and cytoplasm) in histological images. The subsequent development of this gland segmentation technology can allow to detect changes in the lumen shape (serration) of glands, in the nuclear-cytoplasmic ratio inside mucus-forming cells, and in the character of the expression of immunohistochemical markers.
1 January 2017 in Russian Journal of Archive of Pathology
Medical article медицинская статья
1 January 2022 in Russian Journal of Archive of Pathology
Cancer-associated fibroblasts (CAFs) are a heterogeneous cell population in the tumor stroma and have important prognostic and clinical significance for solid tumors, including colorectal cancer. The identification of CAF presents difficulties due to the lack of a unique diagnostic marker. Detection of CAF by multiplex immunohistochemical staining and assessment of their colocalization. For multiplex IHC staining specimens of 10 colon adenocarcinomas without neoadjuvant treatment were selected. We used «OPAL 7-COLOR MANUAL IHC KIT» (Akoya Biosciences, USA) with five antibodies (FAP, PDGFRβ, CD31, POD, PCK) for staining and Mantra 2 Quantitative Pathology Imaging System (Akoya Biosciences, USA) for evaluation of results. CD31 and CAF markers (FAP, PDGFRβ, POD) are expressed fundamentally in different cells (p<0.0001) in all areas of the tumor (apical, central, invasive margin). Pairs FAP+PDGFRβ in all zones demonstrated significantly higher (p<0.0001) square of tandem staining. It shows that these markers are expressed in the same stromal cells (probably CAF). In pair FAP+POD significant colocalization (p=0.011) was detected only in apical zone. We connect this finding rather with active proliferation of population of young fibroblasts in zones of ulceration and granulations than with CAF. We evaluated co-localization of CAF markers (FAP, PDGFRβ, POD) and endothelial cells (CD31) in different zones of colorectal carcinomas. We showed colocalization of CAF markers for pairs FAP+PDGFRβ in all tumor zones and for pair FAP+POD in apical zone.
1 January 2020 in Russian Journal of Archive of Pathology