A review and benchmark of feature importance methods for neural networks

H Mandler, B Weigand - ACM Computing Surveys, 2024 - dl.acm.org
Feature attribution methods (AMs) are a simple means to provide explanations for the
predictions of black-box models such as neural networks. Due to their conceptual …

Analysis of WSI images by hybrid systems with fusion features for early diagnosis of cervical cancer

M Hamdi, EM Senan, B Awaji, F Olayah, ME Jadhav… - Diagnostics, 2023 - mdpi.com
Cervical cancer is one of the most common types of malignant tumors in women. In addition,
it causes death in the latter stages. Squamous cell carcinoma is the most common and …

A deep attention model for wide-genome protein-peptide binding affinity prediction at a sequence level

X Sun, Z Wu, J Su, C Li - International Journal of Biological Macromolecules, 2024 - Elsevier
Peptides are pivotal in numerous biological activities by engaging in up to 40% of protein-
protein interactions in many cellular processes. Due to their exceptional specificity and …

XAI Unveiled: Revealing the Potential of Explainable AI in Medicine-A Systematic Review

N Scarpato, P Ferroni, F Guadagni - IEEE Access, 2024 - ieeexplore.ieee.org
Nowadays, artificial intelligence in medicine plays a leading role. This necessitates the need
to ensure that artificial intelligence systems are not only high-performing but also …

Response surface methodology and artificial neural network based media optimization for pullulan production in Aureobasidium pullulans

N Sahu, B Mahanty, D Haldar - International Journal of Biological …, 2025 - Elsevier
The selection and optimization of carbon and nitrogen sources are essential for enhancing
pullulan production in Aureobasidium pullulans. In this study, combinations of carbon …

Partial least squares regression based rapid quantification of intracellular biopolymers from a Sudan black absorption assay

N Sahu, AR Katharin, B Mahanty - Microchemical Journal, 2024 - Elsevier
Rapid quantitation of intracellular polyhydroxyalkanoate (PHA) is essential for monitoring
and possibly intervening in ongoing bioprocesses. The traditional multistep protocol …

Allergic Contact Dermatitis Detection with Machine Learning

KS Panagiotidis, IA Vezakis, A Kyritsi… - 2023 International …, 2023 - ieeexplore.ieee.org
Allergic contact dermatitis (ACD) is a prevalent immune-mediated skin condition, affecting
millions of people worldwide. Significant diagnostic challenges occur due to the subjectivity …

[PDF][PDF] Challenges and Advances on Explainable Artificial Intelligence (AI): Diagnosing and Treating Tumors of the Female Reproductive Systems

X Gao, H Li, C You, L Zhou, Q Shi, Z Yang, S Shao… - 2024 - preprints.org
Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for
women's mental and physical health, especially affecting female reproductive systems …

[PDF][PDF] Explainable Artificial Intelligence (XAI) for Diagnosing and Treating Tumors of the Female Reproductive Systems: Challenges and Advances

X Gao, H Li, C You, L Zhou, Q Shi, Z Yang, S Shao… - 2024 - preprints.org
Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for
women's mental and physical health, especially affecting female reproductive systems …

[PDF][PDF] Analysis of WSI Images by Hybrid Systems with Fusion Features for Early Diagnosis of Cervical Cancer. Diagnostics 2023, 13, 2538

M Hamdi, EM Senan, B Awaji, F Olayah, ME Jadhav… - 2023 - academia.edu
Cervical cancer is one of the most common types of malignant tumors in women. In addition,
it causes death in the latter stages. Squamous cell carcinoma is the most common and …