Empirical Study of Ovarian Tumors Detection and Classification in Ultrasound Images
Abstract
Ovarian cancer is one of the leading causes
of death in women. Ultrasound images often provide initial
findings and diagnosis before further tests are performed.
Despite some progress in medical image analysis, the detection
and recognition of ovarian cancers remains still quite limited.
Most existing works focused on detecting or classifying two
tumor categories, namely benign and malignant lesions. This
paper presents an initial comprehensive study of ovarian
tumor detection, and at the same time classifies eight classes
of ovarian tumors in ultrasound images using deep-learning
models. Due to the lack of training data, we implemented a
data augmentation process and examined the improvement
of performance with and without data augmentation. Experiments
carried out on the OTU-2D set of MMOTU dataset with
YOLOv5, YOLOv7, and YOLOv7 variants show promising
detection and classification results.
References
N. C. Institute, “Cancer Stat Facts: Ovarian Cancer,” https://seer.cancer.gov/statfacts/html/ovary.html, 2023, [Online; accessed 14-July-2023].
Vietnam, “Overcrowding strains HCM City hospitals, doctors,” https://en.vietnamplus.vn/vietnam-to-publicly-rank-quality-of-hospitals/87505.vnp, 2023, [Online; accessed 14-July-2023].
J. R. Astley, J. M. Wild, and B. A. Tahir, “FUNCTIONAL IMAGING OF THE LUNG SPECIAL FEATURE : Artificial
intelligence in functional imaging of the lung,” Br J Radiol. 2022 Apr 1; 95(1132): 20201107, no. April 2021, 2022.
Z. Jin, T. Gan, P. Wang, Z. Fu, C. Zhang, Q. Yan, X. Zheng, X. Liang, and X. Ye, “Deep learning for gastroscopic images: computer-aided techniques for clinicians,” BioMedical Engineering Online, vol. 21, no. 1, pp. 1–41, 2022. [Online]. Available: https://doi.org/10.1186/s12938-022-00979-8
P.-T. Nguyen, M.-Q. Le, Q.-T. Dao, V. A. Tran, V.-H. Dao, and T.-H. Tran, “Automatic classification of upper
gastrointestinal tract diseases from endoscopic images,” in 2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS). IEEE, 2022, pp. 442–447.
T.-H. Tran, D. H. Vu, D. H. Tran, K. L. Do, P. T. Nguyen, V. T. Nguyen, L. T. Nguyen, N. K. Ho, H. Vu, and V. H.
Dao, “Dcs-unet: Dual-path framework for segmentation of reflux esophagitis lesions from endoscopic images with unet-based segmentation and color/texture analysis,” Vietnam Journal of Computer Science, vol. 10, no. 02, pp. 217–242, 2023.
P. Xue, J. Wang, D. Qin, H. Yan, Y. Qu, S. Seery, Y. Jiang, and Y. Qiao, “Deep learning in image-based breast and
cervical cancer detection: a systematic review and metaanalysis,” npj Digital Medicine, vol. 5, no. 1, 2022.
E. Mahoro and M. A. Akhloufi, “Applying Deep Learning for Breast Cancer Detection in Radiology,” Current Oncology, vol. 29, no. 11, pp. 8767–8793, 2022.
A. S. Lundervold and A. Lundervold, “An overview of deep learning in medical imaging focusing on MRI,” Zeitschrift fur Medizinische Physik, vol. 29, no. 2, pp. 102–127, 2019.
B. Usha and S. Sandya, “Abnormality Detection in Ovarian Ultrasound Images using Active Contours,” Journal of Biomedical Engineering and Medical Imaging, vol. 1, no. 4, pp. 14–23, 2014.
T.-l. Pham, V.-h. Le, T.-h. Tran, and D. H. Vu, “Comprehensive study on Semantic Segmentation of Ovarian Tumors from Ultrasound Images,” in Conference on Information Technology and its Applications, 2023.
J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” https://arxiv.org/pdf/1804.02767.pdf, 2018. [Online]. Available: http://arxiv.org/abs/1804.02767
X. Zhu, S. Lyu, X. Wang, and Q. Zhao, “TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios,” Proceedings of the IEEE International Conference on Computer Vision, vol. 2021-October, pp. 2778–2788, 2021.
G. Weng, D. Liu, L. Liu, Q. Wan, and S. Wu, “Research on an improved yolov7 algorithm for road surface crack
detection,” 2023.
S. Srivastava, P. Kumar, V. Chaudhry, and A. Singh, “Detection of ovarian cyst in ultrasound images using finetuned vgg-16 deep learning network,” SN Computer Science, vol. 1, pp. 1–8, 2020.
M. Akazawa and K. Hashimoto, “Artificial intelligence in ovarian cancer diagnosis,” Anticancer research, vol. 40, no. 8, pp. 4795–4800, 2020.
Q. Zhao, S. Lyu, W. Bai, L. Cai, B. Liu, M. Wu, X. Sang, M. Yang, and L. Chen, “A multi-modality ovarian tumor
ultrasound image dataset for unsupervised cross-domain semantic segmentation,” CoRR, vol. abs/2207.06799, 2022.
P. Chlap, H. Min, N. Vandenberg, J. Dowling, L. Holloway, and A. Haworth, “A review of medical image data augmentation techniques for deep learning applications,” Journal of Medical Imaging and Radiation Oncology, vol. 65, no. 5, pp. 545–563, 2021.
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in
Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779–788.
Y. Zhu, S. Li, W. Du, and Y. Du, “Identification of table grapes in the natural environment based on an improved yolov5 and localization of picking points,” Precision Agriculture, vol. 24, no. (4), pp. 1–22, 2023.
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv, 2020.
C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, “YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for realtime object detectors,” https://arxiv.org/pdf/2207.02696.pdf, pp. 7464–7475, 2022. [Online]. Available: http://arxiv.org/abs/2207.02696
N. Sathiadhas Puvaneswari, “Detection of polycystic ovarian syndrome using convolutional neural network in conjunction with transfer learning models,” Ph.D. dissertation, Dublin, National College of Ireland, 2022.
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Doll´ar, and C. L. Zitnick, “Microsoft coco:
Common objects in context,” in European conference on computer vision. Springer, 2014, pp. 740–755.
