AKAmeya Madhav Kulkarni

Ameya Madhav Kulkarni

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ameya Madhav Kulkarni has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    MMDC-CLIP-F: Vision-language multi-view mammogram density classification with uncertainty assessment

    by Jacob Schaffer, Wandong Zhang, Tianqi Ni, Yimin Yang, Ameya Madhav Kulkarni, Ashirbani Saha

  • Open Access

    High-Risk Benign Breast Lesions: An Ontario Health (Cancer Care Ontario) Recommendations Report

    by Andrea Eisen, Anita Bane, Petrina Causer, Erin Cordeiro, Samantha Fienberg, Anat Kornecki, Ameya Kulkarni, Nicole Look Hong, Talia Mancuso, Derek Muradali, et al.

    High-risk benign breast lesions are histological abnormalities that present in breast tissue, typically identified by screening or diagnostic imaging. The presence of invasive or in situ breast cancer can be confirmed or ruled out within these lesions, and the risk of developing breast cancer can be reduced by their appropriate management. These potential high-risk lesions reviewed include atypical ductal hyperplasia, mucocele-like lesions, papillary lesions with or without atypia, radial scar/complex sclerosing lesion with or without atypia, atypical lobular hyperplasia, classical lobular carcinoma in situ, pleomorphic/florid lobular carcinoma in situ, flat epithelial atypia, columnar cell change, fibroepithelial lesions with stromal cellularity, spindle cell lesions/mesenchymal lesions, and microglandular adenosis. The lack of a clear consensus on the management of many of these lesions led the Ontario Health (Cancer Care Ontario) (OH-CCO) Breast Cancer Pathway Map Working Group and Breast Cancer Advisory Committee to identify the need for a recommendation document. A multidisciplinary working group was formed, with members representing surgical oncology, radiology, pathology, medical oncology, and genetic counselling. The working group developed a list of high-risk benign lesions to be included in this recommendation report. An updated literature review was completed, and these publications were reviewed by the working group, and recommendations were drafted. When evidence was lacking, the expert opinion was included. These draft recommendations were subjected to an extensive review by experts both within Cancer Care Ontario and across Canada. The recommendations included in this report are relevant to clinicians, primary care physicians, oncologists, radiologists, and pathologists who treat breast cancer and manage breast conditions.


  • IOTA Simple Rules: Review of 10 Points for Evaluation of Adnexal Masses

    by Ameya M. Kulkarni, Sepideh Mehravaran, Stefanie Y. Lee

    The International Ovarian Tumor Analysis (IOTA) group's 10 Simple Rules for evaluation of adnexal lesions at US help classify benign and malignant lesions to increase accuracy of categorization and...


  • Pancreas adenocarcinoma CT texture analysis: comparison of 3D and 2D tumor segmentation techniques

    by Ameya Kulkarni, Ivan Carrion-Martinez, Kiret Dhindsa, Amer A. Alaref, Radu Rozenberg, Christian B. van der Pol

    Purpose To determine equivalency of multi-slice 3D CTTA and single slice 2D CTTA of pancreas adenocarcinoma. Methods This retrospective study was research ethics board approved. Untreated pancreas adenocarcinomas were segmented on CT in 128 consecutive patients. Tumor segmentation was compared using two techniques: 3D segmentation by contouring all visible tumor in a 3D volume, and 2D segmentation using only a single axial image. First-order CTTA features including mean, minimum, maximum Hounsfield units (HU), standard deviation, skewness, kurtosis, entropy, and second-order gray-level co-occurrence matrix (GLCM) features homogeneity, contrast, correlation, entropy and dissimilarity were extracted. Median values were compared using the Mann–Whitney U test with Holm–Bonferroni correction. Kendall’s Rank Correlation Tau assessed for correlation, and agreement was calculated using intraclass correlation coefficients (ICC) using a two-way model with single rating and absolute agreement. Statistical significance defined as P < 0.05. Results The median values of CTTA features differed significantly between 3 and 2D segmentations for all of the evaluated features except for mean attenuation, standard deviation and skewness (P = 0.2979 each). 3D and 2D segmentations had moderate correlation for mean attenuation (R = 0.69, P < 0.01), while all other features demonstrated poor to fair correlation. Agreement between 3 and 2D segmentations was good for mean attenuation (ICC: 0.87, P < 0.01), moderate for minimum (ICC: 0.65, P < 0.01) and standard deviation (ICC: 0.56, P < 0.01), and poor for all other features. Conclusion While pancreas adenocarcinoma CTTA features obtained using 3D and 2D segmentation have multiple associations with clinically relevant outcomes, these segmentation techniques are likely not interchangeable other than for mean HU.