TY - GEN
T1 - Enhancing Histopathological Image Analysis
T2 - 1st International Conference on Computation of Artificial Intelligence and Machine Learning, ICCAIML 2024
AU - Sudhamsh, G. V.S.
AU - Rashmi, R.
AU - Girisha, S.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Histopathological images have significant potential for disease diagnosis and prognosis, but their inherent color variations can impede accurate analysis and reliable model performance. Color variations in histopathological images can indeed be a major challenge for accurate diagnosis and reliable model performance. This study investigates the critical role of color normalization in mitigating these inconsistencies, improving feature extraction, the model’s generalizability, and reducing staining bias. More this study examines the impact of activation functions, essential components in deep learning architectures for histopathological image analysis. Selecting the optimal function is crucial for optimizing the model performance. By emphasizing the importance of color normalization and careful activation function selection, this study lays the groundwork for more robust and reliable analysis of histopathological images, ultimately leading to improved disease diagnosis. In the present work, different segmentation architectures are analyzed with and without color normalization and with different activation functions.
AB - Histopathological images have significant potential for disease diagnosis and prognosis, but their inherent color variations can impede accurate analysis and reliable model performance. Color variations in histopathological images can indeed be a major challenge for accurate diagnosis and reliable model performance. This study investigates the critical role of color normalization in mitigating these inconsistencies, improving feature extraction, the model’s generalizability, and reducing staining bias. More this study examines the impact of activation functions, essential components in deep learning architectures for histopathological image analysis. Selecting the optimal function is crucial for optimizing the model performance. By emphasizing the importance of color normalization and careful activation function selection, this study lays the groundwork for more robust and reliable analysis of histopathological images, ultimately leading to improved disease diagnosis. In the present work, different segmentation architectures are analyzed with and without color normalization and with different activation functions.
UR - https://www.scopus.com/pages/publications/85208440599
UR - https://www.scopus.com/pages/publications/85208440599#tab=citedBy
U2 - 10.1007/978-3-031-71484-9_20
DO - 10.1007/978-3-031-71484-9_20
M3 - Conference contribution
AN - SCOPUS:85208440599
SN - 9783031714832
T3 - Communications in Computer and Information Science
SP - 220
EP - 232
BT - Computation of Artificial Intelligence and Machine Learning - 1st International Conference, ICCAIML 2024, Proceedings
A2 - Bairwa, Amit Kumar
A2 - Tiwari, Varun
A2 - Vishwakarma, Santosh Kumar
A2 - Tuba, Milan
A2 - Ganokratanaa, Thittaporn
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 18 January 2024 through 19 January 2024
ER -