Ovarian Cancer Diagnosis Using Advanced Deep Learning Models with Histopathology Images

Abstract

The classification of ovarian cancer through advanced deep learning models presents a noteworthy challenge in the field of medical diagnosis, given potential implications for patient health and wellbeing. In this study, our focus is on automating the classification of ovarian cancer using cutting-edge deep-learning models such as VGG-19, ResNet-50, InceptionV3, and EfficientNetV2. Each model employs transfer learning, drawing insights from an extensive dataset consisting of various imaging modalities, eventually categorizing them into five clearly defined ovarian cancer conditions: (1) HGSC - High-Grade Serous Carcinoma, (2) CC - Clear-Cell Ovarian Carcinoma, (3) EC - Endometrioid, (4) LGSC - Low-Grade Serous, and (5) MC - Mucinous Carcinoma. The training dataset contains samples that are all characterized by distinct cellular morphologies, etiologies, molecular and genetic profiles, and clinical attributes, encompassing all five cancer subtypes. Our analysis demonstrates that among the models assessed, EfficientNetV2 showcases exceptional performance, achieving an impressive classification accuracy of 98.11%, precision of 99.3%, and a recall of 99.1%, outperforming the other models. 

References

[1] Kamali D, Romain J, Liu H, Peng W, Meng J, Kordjamshidi P. Using Persuasive Writing Strategies to Explain and Detect Health Misinformation. arXiv preprint arXiv:2211.05985. 2022 Nov 11.

[2] Saeidi N, Ansarikojouri M, Mardani M, Rezazadeh R, Goodarzi MK, Amiri F. Enhancing the Cytotoxic Effects of Carboplatin and Cisplatin on Liposomes in Oral Cancer Cells with Curcumin. Asian Pacific Journal of Cancer Biology. 2024 Nov 26;9(4):579-87.

[3] Vahedi MM, Shahini A, Mottahedi M, Garousi S, Shariat Razavi SA, Pouyamanesh G, Afshari AR, Ferns GA, Bahrami A. Harmaline exerts potentially anti-cancer effects on U-87 human malignant glioblastoma cells in vitro. Molecular Biology Reports. 2023 May;50(5):4357-66.

[4] Rahimi N, Feizi I, Mashayekhi F, Salehi O, Norouzi F, Iranparvar-Alamdari M, Kani AA, Zandian H, Khalaji A. Evaluation of the thyroid and hypothyroid function after postoperative radiation therapy among breast cancer patients. Canadian OnCOlOgy nursing JOurnal. 2024 Nov 1;34(4):477.

[5] Rahimi N, Feizi I, Mashayekhi F, Salehi O, Norouzi F, Iranparvar-Alamdari M, Kani AA, Zandian H, Khalaji A. Evaluation of the thyroid and hypothyroid function after postoperative radiation therapy among breast cancer patients. Canadian OnCOlOgy nursing JOurnal. 2024 Nov 1;34(4):477.

[6] Shakiba D, Shabestari AM, Mokhtari T, Goodarzi MK, Saeed S, Zinatbakhsh Z, Akaberi K, Allahyartorkaman M. Nanoliposomes Meet Folic Acid: A Precision Delivery System for Bleomycin in Cancer Treatment. Asian Pacific Journal of Cancer Biology. 2024 Nov 26;9(4):561-8.

[7] Shoarishoar SS, Milani F, Adineh S, Sorouri ZR, Attari SM. Comparison of pregnancy outcomes in amniocentesis recipients with normal and abnormal maternal serum analytes. Cellular and Molecular Biology. 2024 Nov 27;70(11).

[8] Lheureux, S., Braunstein, M., and Oza, A.M. (2019). Epithelial ovarian cancer: evolution of management in the era of precision medicine. CA A Cancer J. Clin. 69, 280–304. https://doi.org/10.3322/caac. 21559.

[9] Kargar Gaz Kooh Y, Huebsch N. Bridging high resolution sub-cellular imaging with physiologically relevant engineered tissues. Frontiers in Mechanical Engineering. 2024 Nov 26;10:1481933.

[10] Wang, R., Cai, Y., Lee, I.K., Hu, R., Purkayastha, S., Pan, I., Yi, T., Tran, T.M.L., Lu, S., Liu, T., et al. (2021). Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging. Eur. Radiol. 31, 4960– 4971. https://doi.org/10.1007/s00330-020- 07266-x

[11] Armstrong, D.K., Alvarez, R.D., BakkumGamez, J.N., Barroilhet, L., Behbakht, K., Berchuck, A., Chen, L.M., Cristea, M., DeRosa, M., Eisenhauer, E.L., et al. (2021). Ovarian Cancer. version 2.2020, NCCN Clinical Practice Guidelines in Oncology. J. Natl. Compr. Cancer Netw. 19, 191–226.

[12] Davari M, Harooni A, Nasr A, Savoji K, Soleimani M. Improving recognition accuracy for facial expressions using scattering wavelet. EAI Endorsed Transactions on AI and Robotics. 2024 Mar 13;3.

[13] Price I, Sanchez-Gonzalez A, Alet F, Andersson TR, El-Kadi A, Masters D, Ewalds T, Stott J, Mohamed S, Battaglia P, Lam R. Probabilistic weather forecasting with machine learning. Nature. 2025 Jan;637(8044):84-90.

[14] Alam T, Shia WC, Hsu FR, Liao LD, Hussain T, Kuo YH. A Comprehensive Review: Efficacy of Segmentation and Machine Learning, Deep Learning Techniques in Breast Tumor Detection. Authorea Preprints. 2025 Jan 5.

[15] Schwehr Z, Achanta S. Brain tumor segmentation based on deep learning, attention mechanisms, and energy-based uncertainty predictions. Multimedia Tools and Applications. 2025 Jan 20:1-20.

[16] Muetunda F, Sabry S, Jamil ML, Pais S, Dias G, Cordeiro J. AI-Assisted Diagnosing, Monitoring and Treatment of Mental Disorders: A Survey. ACM Transactions on Computing for Healthcare. 2024 Oct 23;5(4):1-24.

[17] Mohammadigilani A, Attar H, Chimeh HE, Karami M. Enhanced LSTM by Attention Mechanism for Early Detection of Parkinson's Disease Through Voice Signals. In2023 2nd International Engineering Conference on Electrical, Energy, and Artificial Intelligence (EICEEAI) 2023 Dec 27 (pp. 1-5). IEEE.

[18] Kale MB, Wankhede NL, Pawar RS, Ballal S, Kumawat R, Goswami M, Khalid M, Taksande BG, Upaganlawar AB, Umekar MJ, Kopalli SR. AI-driven innovations in Alzheimer's disease: Integrating early diagnosis, personalized treatment, and prognostic modelling. Ageing Research Reviews. 2024 Sep 16:102497.

[19] Sharifi S, Donyadadi A. Detection and Diagnosis of Congenital Heart Disease from Chest X-Rays with Deep Learning Models. International Journal of Applied Data Science in Engineering and Health. 2025 Jan 2;1(1):1-9.

[20] Bozorgi E, Soleimani S, Alqaiidi SK, Arabnia HR, Kochut K. Subgraph2vec: A random walk-based algorithm for embedding knowledge graphs. arXiv preprint arXiv:2405.02240. 2024 May 3.

[21] Ke S, Montiel Olea JL, Nesbit J. Robust machine learning algorithms for text analysis. Quantitative Economics. 2024 Nov;15(4):939-70.

[22] Shoarishoar SS, Milani F, Adineh S, Sorouri ZR, Attari SM. Comparison of pregnancy outcomes in amniocentesis recipients with normal and abnormal maternal serum analytes. Cellular and Molecular Biology. 2024 Nov 27;70(11).

[23] Panigrahi S, Swarnkar T. Machine learning techniques used for the histopathological image analysis of oral cancer-a review Open Bioinform.

[24] Wu M, Yan C, Liu H, Liu Q. Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks. Bioscience reports. 2018 May 8;38(3):BSR20180289.

[25] Nobel SN, Swapno SM, Hossain MA, Safran M, Alfarhood S, Kabir MM, Mridha MF. RETRACTED: Modern Subtype Classification and Outlier Detection Using the Attention Embedder to Transform Ovarian Cancer Diagnosis. Tomography. 2024 Jan 15;10(1):105-32.

[26] Ovarian Cancer Subtype Classification. Available online: https://www.kaggle.com/datasets/sunilthite/ovarian-cancer-classification-dataset/data

[27] Karen S. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv: 1409.1556. 2014.

[28] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).

[29] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 2818-2826).