Prof. Selim Aksoy Profile

Prof. Selim Aksoy

Professor at Bilkent Univ

SPIE Involvement:

Conference Program Committee | Author

Publications (9)

Proceedings Article | 2 April 2024 Poster + Paper

Deep convolutional neural networks for PET super-resolution

Kaan Özaltan, Emir Türkölmez, I. Jacques Namer, A. Ercüment Çiçek, Selim Aksoy

Proceedings Volume 12926, 1292636 (2024) https://doi.org/10.1117/12.3007549

KEYWORDS: Positron emission tomography, Super resolution, Image quality, Image processing, Interpolation, Brain, Deep convolutional neural networks

Read Abstract +

Proceedings Article | 7 April 2023 Presentation + Paper

On the benefits of region of interest detection for whole slide image classification

Sena Korkut, Cihan Erkan, Selim Aksoy

Proceedings Volume 12471, 124710N (2023) https://doi.org/10.1117/12.2654193

KEYWORDS: Education and training, Image classification, Cancer detection, Image segmentation, Image processing, Tumor growth modeling, Binary data, Breast, Histopathology, Statistical modeling

Read Abstract +

Proceedings Article | 7 April 2023 Poster + Paper

Space-filling curves for modeling spatial context in transformer-based whole slide image classification

Cihan Erkan, Selim Aksoy

Proceedings Volume 12471, 124711L (2023) https://doi.org/10.1117/12.2654191

KEYWORDS: Transformers, Image classification, Tumor growth modeling, Feature extraction, Education and training, Cross validation, Raster graphics, Data modeling, Modeling, Lung cancer

Read Abstract +

Proceedings Article | 16 March 2020 Presentation + Paper

Graph convolutional networks for region of interest classification in breast histopathology

Bulut Aygüneş, Selim Aksoy, Ramazan Gökberk Cinbiş, Kemal Kösemehmetoğlu, Sevgen Önder, Ayşegül Üner

Proceedings Volume 11320, 113200K (2020) https://doi.org/10.1117/12.2550636

KEYWORDS: Diagnostics, Image classification, Breast, Data modeling, Pathology, Feature extraction, Tissues, Machine learning

Read Abstract +

Proceedings Article | 18 March 2019 Presentation + Paper

From patch-level to ROI-level deep feature representations for breast histopathology classification

Caner Mercan, Selim Aksoy, Ezgi Mercan, Linda Shapiro, Donald Weaver, Joann Elmore

Proceedings Volume 10956, 109560H (2019) https://doi.org/10.1117/12.2510665

KEYWORDS: Breast, Feature extraction, Diagnostics, Cancer, Pathology, Convolutional neural networks, Image classification, Image analysis

Read Abstract +

Proceedings Article | 23 March 2016 Paper

Multi-instance multi-label learning for whole slide breast histopathology

Caner Mercan, Ezgi Mercan, Selim Aksoy, Linda Shapiro, Donald Weaver, Joann Elmore

Proceedings Volume 9791, 979108 (2016) https://doi.org/10.1117/12.2216458

KEYWORDS: Breast, Computer aided diagnosis and therapy, Image classification, Diagnostics, Pathology, Image analysis, Biopsy, Imaging technologies, Imaging systems, Computing systems, Zoom lenses, Cancer, Machine learning, Binary data, Feature extraction

Read Abstract +

Digitization of full biopsy slides using the whole slide imaging technology has provided new opportunities for understanding the diagnostic process of pathologists and developing more accurate computer aided diagnosis systems. However, the whole slide images also provide two new challenges to image analysis algorithms. The first one is the need for simultaneous localization and classification of malignant areas in these large images, as different parts of the image may have different levels of diagnostic relevance. The second challenge is the uncertainty regarding the correspondence between the particular image areas and the diagnostic labels typically provided by the pathologists at the slide level. In this paper, we exploit a data set that consists of recorded actions of pathologists while they were interpreting whole slide images of breast biopsies to find solutions to these challenges. First, we extract candidate regions of interest (ROI) from the logs of pathologists' image screenings based on different actions corresponding to zoom events, panning motions, and fixations. Then, we model these ROIs using color and texture features. Next, we represent each slide as a bag of instances corresponding to the collection of candidate ROIs and a set of slide-level labels extracted from the forms that the pathologists filled out according to what they saw during their screenings. Finally, we build classifiers using five different multi-instance multi-label learning algorithms, and evaluate their performances under different learning and validation scenarios involving various combinations of data from three expert pathologists. Experiments that compared the slide-level predictions of the classifiers with the reference data showed average precision values up to 62% when the training and validation data came from the same individual pathologist's viewing logs, and an average precision of 64% was obtained when the candidate ROIs and the labels from all pathologists were combined for each slide.

Proceedings Article | 24 May 2012 Paper

Detection of compound structures using a Gaussian mixture model with spectral and spatial constraints

Çağlar Arı, Selim Aksoy

Proceedings Volume 8390, 83901Y (2012) https://doi.org/10.1117/12.919827

KEYWORDS: Expectation maximization algorithms, Data modeling, Detection and tracking algorithms, Image segmentation, RGB color model, Buildings, Spectral models, Roads, Image processing algorithms and systems, Matrices

Read Abstract +

Proceedings Article | 21 November 2002 Paper

Interactive classification and content-based retrieval of tissue images

Selim Aksoy, Giovanni Marchisio, Carsten Tusk, Krzysztof Koperski

Proceedings Volume 4790, (2002) https://doi.org/10.1117/12.453862

KEYWORDS: Tissues, Prototyping, Image classification, Image retrieval, Fuzzy logic, Data modeling, Image segmentation, Databases, Blood, Classification systems

Read Abstract +

Proceedings Article | 24 September 2002 Paper

Interactive models for semantic labeling of satellite images

Krzysztof Koperski, Giovanni Marchisio, Carsten Tusk, Selim Aksoy

Proceedings Volume 4814, (2002) https://doi.org/10.1117/12.452068

KEYWORDS: Feature extraction, Databases, Data modeling, Data mining, Image processing, Image segmentation, Data analysis, Satellites, Visualization, Earth observing sensors

Read Abstract +

Showing 5 of 9 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years