Abstract
Ovarian tumors affect women of all ages and the main challenge for optimal therapeutic management is to determine whether there is a benign or malignant tumor. The main imagistic tool for the evaluation of ovarian tumors is pelvic ultrasonography. To support the diagnosis of clinicians several artificial intelligence applications and ultrasound computer-aided diagnosis systems are emerging in recent years. This paper covers a comparative study between different convolutional neural networks based on semantic segmentation, implemented, and proposed for the identification of four benign ovarian tumor masses (chocolate cyst, mucinous cystadenoma, teratoma, and simple cyst). The semantic segmentation networks used in our comparative study are based on DeepLab-V3+ networks with 5 different encoders and a fully convolutional network. The scope of this study is to present the performances of each network for each of the covered benign classes and to illustrate the ones with the best performances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Siegel, R.L., Miller, K.D., Fuchs, H.E., Jemal, A.: Cancer statistics. CA Cancer J. Clin. 72(1), 7–33 (2022)
Zeppernick, F., Meinhold-Heerlein, I., Meinhold-Heerlein, Á.I.: The new FIGO staging system for ovarian, fallopian tube, and primary peritoneal cancer. Arch. Gynecol Obs. 290(5), 839–842 (2014)
Basha, M.A.A., Metwally, M.I., Gamil, S.A., et al.: Comparison of O-RADS, GI-RADS, and IOTA simple rules regarding malignancy rate, validity, and reliability for diagnosis of adnexal masses. Eur. Radiol. 31(2), 674–684 (2021)
Sokalska, A., et al.: Diagnostic accuracy of transvaginal ultrasound examination for assigning a specific diagnosis to adnexal masses. Ultrasound Obstet Gynecol. 34(4), 462–470 (2009)
Wu, C., Wang, Y., Wang, F.: Deep learning for ovarian tumor classification with ultrasound images. In: Hong, R., Cheng, W.-H., Yamasaki, T., Wang, M., Ngo, C.-W. (eds.) PCM 2018. LNCS, vol. 11166, pp. 395–406. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00764-5_36
Wang, H., et al.: Application of deep convolutional neural networks for discriminating benign, borderline, and malignant serous ovarian tumors from ultrasound images. Front Oncol. 11, 770683 (2021)
Hsu, S.T., Su, Y.J., Hung, C.H., Chen, M.J., Lu, C.H., Kuo, C.E.: Automatic ovarian tumors recognition system based on ensemble convolutional neural network with ultrasound imaging. BMC Med. Inform. Decis. Mak. 22(1), 298 (2022)
Christiansen, F., Epstein, E.L., Smedberg, E., Åkerlund, M., Smith, K., Epstein, E.: Ultrasound image analysis using deep neural networks for discriminating between benign and malignant ovarian tumors: comparison with expert subjective assessment. Ultrasound Obstet Gynecol. 57(1), 155–163 (2021)
Saida, T., et al.: Diagnosing ovarian cancer on MRI: a preliminary study comparing deep learning and radiologist assessments. Cancers (Basel). 14(4), 987 (2022)
Jung, Y., et al.: Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder. Sci. Rep. 12, 17024 (2022)
Pavlik, E.J., et al.: Frequency and disposition of ovarian abnormalities followed with serial transvaginal ultrasonography. Obstet Gynecol. 122(2 Pt 1), 210–217 (2013)
Stany, M.P., Hamilton, C.A.: Benign disorders of the ovary. Obstet. Gynecol. Clin. North Am. 35(2), 271–284 (2008)
Louis, M.S., Mangal, R., Stead, T.S., Sosa, M., Ganti, L.: Ovarian dermoid tumor. Cureus, 14(7), e27233 (2022)
Moyon, M.A., et al.: Giant ovarian mucinous cystadenoma, a challenging situation in resource-limited countries. J. Surg. Case Rep. (12), rjz366 (2019)
Vercellini, P., Viganò, P., Somigliana, E., Fedele, L.: Endometriosis: pathogenesis and treatment. Nat. Rev. Endocrinol. 10(5), 261–275 (2014)
Van Holsbeke, C., Van Calster, B., Guerriero, S., et al.: Endometriomas: their ultrasound characteristics. Ultrasound Obstet. Gynecol. 35(6), 730–740 (2010)
https://github.com/cv516buaa/mmotu_ds2net. Accessed 21 Jan 2023
Zhao, Q., et al.: A multi-modality ovarian tumor ultrasound image dataset for unsupervised cross-domain semantic segmentation. arXiv: 2207.06799 (2022)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440. June 7–12, Boston, MA, USA (2015)
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds.) Computer Vision – ECCV 2018. ECCV 2018. LNCS, vol. 11211 (2018)
El-Khatib, M., Teodor, O., Popescu, D., Ichim, L.: Using combined CNNs for ROI segmentation in early investigation of pregnancy. In: 8th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 897–902. May 17–20, Istanbul, Turkey (2022)
Howard, A.G., et al.: MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv: 1704.04861 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
El-Khatib, M., Teodor, O.M., Popescu, D., Ichim, L. (2023). Identification of Benign Tumor Masses Using Deep Learning Techniques Based on Semantic Segmentation. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2023. Lecture Notes in Computer Science, vol 14134. Springer, Cham. https://doi.org/10.1007/978-3-031-43085-5_42
Download citation
DOI: https://doi.org/10.1007/978-3-031-43085-5_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43084-8
Online ISBN: 978-3-031-43085-5
eBook Packages: Computer ScienceComputer Science (R0)