Search

Your search keyword '"Kakkar, Aanchal"' showing total 817 results
Start Over Author "Kakkar, Aanchal"
817 results on '"Kakkar, Aanchal"'

5. GenSelfDiff-HIS: Generative Self-Supervision Using Diffusion for Histopathological Image Segmentation

Author

Purma, Vishnuvardhan, Srinath, Suhas, Srirangarajan, Seshan, Kakkar, Aanchal, and P, Prathosh A.

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Histopathological image segmentation is a laborious and time-intensive task, often requiring analysis from experienced pathologists for accurate examinations. To reduce this burden, supervised machine-learning approaches have been adopted using large-scale annotated datasets for histopathological image analysis. However, in several scenarios, the availability of large-scale annotated data is a bottleneck while training such models. Self-supervised learning (SSL) is an alternative paradigm that provides some respite by constructing models utilizing only the unannotated data which is often abundant. The basic idea of SSL is to train a network to perform one or many pseudo or pretext tasks on unannotated data and use it subsequently as the basis for a variety of downstream tasks. It is seen that the success of SSL depends critically on the considered pretext task. While there have been many efforts in designing pretext tasks for classification problems, there haven't been many attempts on SSL for histopathological segmentation. Motivated by this, we propose an SSL approach for segmenting histopathological images via generative diffusion models in this paper. Our method is based on the observation that diffusion models effectively solve an image-to-image translation task akin to a segmentation task. Hence, we propose generative diffusion as the pretext task for histopathological image segmentation. We also propose a multi-loss function-based fine-tuning for the downstream task. We validate our method using several metrics on two publically available datasets along with a newly proposed head and neck (HN) cancer dataset containing hematoxylin and eosin (H\&E) stained images along with annotations. Codes will be made public at https://github.com/PurmaVishnuVardhanReddy/GenSelfDiff-HIS.git.

Published
2023

26. SMARCA4/BRG1-Deficient Sinonasal Carcinoma: Morphologic Spectrum of an Evolving Entity

Author

Kakkar, Aanchal, Ashraf, Subiyathul Farah, Rathor, Amber, Adhya, Amit Kumar, Mani, Suresh, Sikka, Kapil, and Jain, Deepali

Subjects
Immunohistochemistry -- Analysis, Nose cancer -- Care and treatment -- Genetic aspects, Keratin -- Analysis, Health
Abstract

* Context.--Molecular analysis of poorly differentiated/ undifferentiated sinonasal neoplasms has resulted in identification of a growing number of genetically defined tumors. SMARCA4-deficient sinonasal carcinoma is one such recently described entity that emerged from within sinonasal undifferentiated carcinoma (SNUC), neuroendocrine carcinoma (NEC), and teratocarcinosarcoma (TCS). Objective.--To identify SMARCA4-deficient sinonasal carcinomas from a large institutional cohort of poorly differentiated/undifferentiated carcinomas and evaluate their clinicopathologic features. Design.--SMARCA4/BRG1 immunohistochemistry was performed on all tumors diagnosed as SNUC, poorly differentiated carcinoma, NEC, and TCS during a 12-year period. SMARCA2/BRM and INSM1 immunostaining was performed in SMARCA4-deficient cases. Results.--Twelve SMARCA4-deficient sinonasal carcinomas were identified among 299 cases. Morphologically, 5 cases were large cell NEC, 2 cases were small cell NEC, and 5 were TCS. SMARCA4 loss was diffuse and complete in 10 cases, while 2 cases showed focal retention. Most cases showed diffuse cytokeratin staining accompanied by weak, usually focal staining for chromogranin and synaptophysin. INSM-1 showed negativity in most cases. All cases showed retained SMARCA2 expression. IDH1/2 mutation was absent in all cases analyzed. Four of 7 patients died of disease, and aggressive multimodality treatment provided better outcome. Conclusions.--SMARCA4-deficient sinonasal carcinomas are morphologically akin to sinonasal poorly differentiated NECs and TCS, display cytokeratin positivity and only focal staining for neuroendocrine markers, and have aggressive biological behavior. Inclusion of SMARCA4 in the immunohistochemical panel for diagnostic workup of all sinonasal NEC and TCS phenotypes will facilitate their early recognition. Comprehensive germline and somatic mutational analyses of these tumors are necessary for further insights into their molecular pathogenesis. (Arch Pathol Lab Med. 2022;146:1122-1130; doi: 10.5858/arpa.2021-0001-OA), The sinonasal tract harbors a diverse spectrum of high-grade neoplasms, many of which have considerable overlapping morphologic features owing to their poorly differentiated or undifferentiated appearance. (1,2) Some of these [...]

Published
2022
Full Text
View/download PDF

42. Virological and cytological changes in tears and conjunctiva of patients with COVID-19

Author

Angmo, Dewang, Mahalingam, Karthikeyan, Kakkar, Aanchal, Rathod, Aishwarya, Meena, Suman, Kaur, Avneet, Choudhary, Aashish, Sharma, Puneet, Dar, Lalit, Samaddar, Arpan, Trikha, Anjan, Saxena, Rohit, Titiyal, Jeewan, and Sharma, Namrata

Subjects
Virulence (Microbiology) -- Analysis, Eye diseases -- Risk factors -- Prevention, Tearing -- Composition, Conjunctiva -- Analysis, Health
Abstract

Byline: Dewang. Angmo, Karthikeyan. Mahalingam, Aanchal. Kakkar, Aishwarya. Rathod, Suman. Meena, Avneet. Kaur, Aashish. Choudhary, Puneet. Sharma, Lalit. Dar, Arpan. Samaddar, Anjan. Trikha, Rohit. Saxena, Jeewan. Titiyal, Namrata. Sharma Purpose: [...]

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results