Version 1
: Received: 26 October 2023 / Approved: 26 October 2023 / Online: 27 October 2023 (07:20:56 CEST)
How to cite:
Mustapha, M. T.; Uzun, B.; Ozsahin, D. U. Leveraging the Novel MSHA Model: A Focus on Adrenocortical Carcinoma. Preprints2023, 2023101738. https://doi.org/10.20944/preprints202310.1738.v1
Mustapha, M. T.; Uzun, B.; Ozsahin, D. U. Leveraging the Novel MSHA Model: A Focus on Adrenocortical Carcinoma. Preprints 2023, 2023101738. https://doi.org/10.20944/preprints202310.1738.v1
Mustapha, M. T.; Uzun, B.; Ozsahin, D. U. Leveraging the Novel MSHA Model: A Focus on Adrenocortical Carcinoma. Preprints2023, 2023101738. https://doi.org/10.20944/preprints202310.1738.v1
APA Style
Mustapha, M. T., Uzun, B., & Ozsahin, D. U. (2023). Leveraging the Novel MSHA Model: A Focus on Adrenocortical Carcinoma. Preprints. https://doi.org/10.20944/preprints202310.1738.v1
Chicago/Turabian Style
Mustapha, M. T., Berna Uzun and Dilber Uzun Ozsahin. 2023 "Leveraging the Novel MSHA Model: A Focus on Adrenocortical Carcinoma" Preprints. https://doi.org/10.20944/preprints202310.1738.v1
Abstract
This study aims to explore the utilization of deep learning models, specifically the innovative Multi-Modal Contextual Fusion Convolutional Neural Network (MSHA), for the detection and diagnosis of Adrenocortical Carcinoma (ACC) using computed tomography (CT) images. The objective is to develop an accurate and reliable model that can assist in the effective detection and classification of ACC. The study utilizes a dataset comprising contrast-enhanced CT images from 53 confirmed ACC patients. The MSHA model is employed, which incorporates a combination of mixed-scale dense convolution, self-attention mechanism, hierarchical feature fusion, and attention-based contextual information techniques. Evaluation metrics are used to assess the performance of the MSHA model, and a comparison is made with other established models, including ResNet50, VGG16, VGG19, and InceptionV3. The evaluation of the MSHA model demonstrates high performance, with an accuracy of 96.65% and precision, sensitivity, specificity, and F1 score of 96.0%. These results highlight the MSHA model's capability in accurately detecting and classifying ACC. Furthermore, compared to other models, the MSHA model outperforms ResNet50, VGG16, VGG19, and InceptionV3, indicating its superior performance in ACC detection and diagnosis. The findings of this study suggest that the MSHA model holds significant potential in assisting healthcare professionals with the detection and diagnosis of ACC. With its advanced features and contextual fusion techniques, the MSHA model achieves high accuracy and performance. The results highlight the clinical significance of this novel model and its potential to improve patient management and outcomes in the detection and diagnosis of ACC using CT images.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
