2690-6791ISSN (Online)
2769-786XISSN (Print)
Volume 17 , Issue 2 , PP: 238-249, 2025 | Cite this article as | XML | Html | PDF | Full Length Article
Karthick Natarajan 1 * , Nithya Palanisamy 2
Doi: https://doi.org/10.54216/JISIoT.170215
An accurate diagnosis of Endometrial Cancer (EC) is crucial for gynecologists, as different types may require specific treatments. Radiomics, a quantitative method, can help analyze and quantify image heterogeneity, aiding in lesion diagnosis. Previous research introduced a Transformer-based Semantic-Aware U-Net with Deep Endometrial Cancer Prediction (TSA-UNet-DeepECP) to segment and classify EC stages in Magnetic Resonance Imaging MRI scans. However, the heterogeneous properties of input scans can affect the DeepECP model's performance. Hence, this study presents the TSA-UNet with an Improved DeepECP model (TSA-UNet-IDeepECP) for EC stage classification. This IDeepECP model incorporates a multi-view learning approach, combining local 2D MRI image information with global 3D MRI image information. First, the endometrium MRI scans are collected, augmented, and segmented using the TSA-UNet model. Various Deep Learning (DL) models, one for 2D and one for 3D, are fed the segmented images. In contrast to the 3D view model, which collects global information from 3D MRI images, the 2D view model primarily recovers local features from 2D MRI data. The multi-view DeepECP model is trained using these combined characteristics. A Fully Connected (FC) layer and the softmax classifier are used for classifying EC stages using the combined features. When compared to traditional models, a TSA-UNet-IDeepECP model achieves better performance in EC detection from MRI images.
Endometrial cancer , MRI , TSA-UNet , DeepECP , Heterogeneity , Multi-view learning
[1] Markowska, A. Chudecka-Głaz, K. Pityński, W. Baranowski, J. Markowska, and W. Sawicki, “Endometrial cancer management in young women,” Cancers, vol. 14, no. 8, pp. 1–13, 2022.
[2] T. M. Kuhn, S. Dhanani, and S. Ahmad, “An overview of endometrial cancer with novel therapeutic strategies,” Curr. Oncol., vol. 30, no. 9, pp. 7904–7919, 2023.
[3] R. L. Siegel, A. N. Giaquinto, and A. Jemal, “Cancer statistics, 2024,” CA: A Cancer J. Clin., vol. 74, no. 1, pp. 12–49, 2024.
[4] Cancer of the Endometrium - Cancer Stat Facts. SEER. [Online]. Available: https://seer.cancer.gov/statfacts/html/corp.html
[5] Endometrial cancer statistics. World Cancer Research Fund International. [Online]. Available: https://www.wcrf.org/cancer-trends/endometrial-cancer-statistics/, Jun. 26, 2024.
[6] M. Menendez-Santos, C. Gonzalez-Baerga, D. Taher, R. Waters, M. Virarkar, and P. Bhosale, “Endometrial Cancer: 2023 Revised FIGO Staging System and the Role of Imaging,” Cancers, vol. 16, no. 10, pp. 1–24, 2024.
[7] J. C. Kasius, J. M. Pijnenborg, K. Lindemann, D. Forsse, J. van Zwol, G. B. Kristensen, and F. Amant, “Risk stratification of endometrial cancer patients: FIGO stage, biomarkers and molecular classification,” Cancers, vol. 13, no. 22, pp. 1–19, 2021.
[8] G. F. Ma, G. L. Lin, S. T. Wang, Y. Y. Huang, C. L. Xiao, J. Sun, and L. B. Xiang, “Prediction of recurrence-related factors for patients with early-stage cervical cancer following radical hysterectomy and adjuvant radiotherapy,” BMC Women's Health, vol. 24, no. 1, p. 81, 2024.
[9] R. Johnson, C. I. Liao, C. Tian, M. T. Richardson, K. Duong, N. Tran, and J. K. Chan, “Uterine cancer among Asian Americans–disparities & clinical characteristics,” Gynecol. Oncol., vol. 182, pp. 24–31, 2024.
[10] M. Palmér, Å. Åkesson, J. Marcickiewicz, E. Blank, L. Hogström, M. Torle, and H. Leonhardt, “Accuracy of transvaginal ultrasound versus MRI in the PreOperative Diagnostics of low-grade Endometrial Cancer (PODEC) study: a prospective multicentre study,” Clin. Radiol., vol. 78, no. 1, pp. 70–79, 2023.
[11] M. N. Yeasmin, M. Al Amin, T. J. Joti, Z. Aung, and M. A. Azim, “Advances of AI in image-based computer-aided diagnosis: A review,” Array, vol. 23, pp. 1–23, 2024.
[12] Y. A. Kadhim, M. U. Khan, and A. Mishra, “Deep learning-based computer-aided diagnosis (cad): applications for medical image datasets,” Sensors, vol. 22, no. 22, pp. 1–21, 2022.
[13] Urushibara, T. Saida, K. Mori, T. Ishiguro, K. Inoue, T. Masumoto, and T. Nakajima, “The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: a comparison with radiologists,” BMC Med. Imag., vol. 22, no. 1, pp. 1–14, 2022.
[14] W. Mao, C. Chen, H. Gao, L. Xiong, and Y. Lin, “A deep learning-based automatic staging method for early endometrial cancer on MRI images,” Front. Physiol., vol. 13, pp. 1–12, 2022.
[15] J. Tao, Y. Wang, Y. Liang, and A. Zhang, “Evaluation and monitoring of endometrial cancer based on magnetic resonance imaging features of deep learning,” Contrast Media Mol. Imag., vol. 2022, no. 1, pp. 1–9, 2022.
[16] J. Yang, Y. Cao, F. Zhou, C. Li, J. Lv, and P. Li, “Combined deep-learning MRI-based radiomic models for preoperative risk classification of endometrial endometrioid adenocarcinoma,” Front. Oncol., vol. 13, pp. 1–10, 2023.
[17] J. Liu, S. Li, H. Lin, P. Pang, P. Luo, B. Fan, and J. Yu, “Development of MRI-based radiomics predictive model for classifying endometrial lesions,” Sci. Rep., vol. 13, no. 1, pp. 1–10, 2023.
[18] L. Xiong, C. Chen, Y. Lin, W. Mao, and Z. Song, “A computer-aided determining method for the myometrial infiltration depth of early endometrial cancer on MRI images,” Biomed. Eng. Online, vol. 22, no. 1, pp. 1–17, 2023.
[19] H. Meng, Y. F. Sun, Y. Zhang, Y. N. Yu, J. Wang, J. N. Wang, and X. P. Yin, “Predicting risk stratification in early-stage endometrial carcinoma: significance of multiparametric MRI radiomics Model,” J. Imag. Inform. Med., vol. 37, no. 1, pp. 1–11, 2024.
[20] Y. M. Cui, H. L. Wang, R. Cao, H. Bai, D. Sun, J. X. Feng, and X. F. Lu, “The Segmentation of multiple types of uterine lesions in magnetic resonance images using a sequential deep learning method with image-level annotations,” J. Imag. Inform. Med., vol. 37, no. 1, pp. 1–12, 2024.
[21] H. Bae, S. E. Rha, H. Kim, J. Kang, and Y. R. Shin, “Predictive value of magnetic resonance imaging in risk stratification and molecular classification of endometrial cancer,” Cancers, vol. 16, no. 5, pp. 1–17, 2024.
[22] TCGA-UCEC. The Cancer Imaging Archive (TCIA). [Online]. Available: https://www.cancerimagingarchive.net/collection/tcga-ucec/, 2024.
[23] CPTAC-UCEC. The Cancer Imaging Archive (TCIA). [Online]. Available: https://www.cancerimagingarchive.net/collection/cptac-ucec/, 2024.
