Differential Diagnosis of Benign and Malignant Ovarian Tumors Based on Convolutional Neural Network

Zhixin YANG; Lizhu ZHAO; Yue DENG; Lihua YANG

doi:10.12259/j.issn.2095-610X.S20231027

Volume 44 Issue 10

Oct. 2023

Turn off MathJax

Article Contents

Abstract

References

Relative Articles

Article Navigation > Journal of Kunming Medical University > 2023 > 44(10): 134-139

Zhixin YANG, Lizhu ZHAO, Yue DENG, Lihua YANG. Differential Diagnosis of Benign and Malignant Ovarian Tumors Based on Convolutional Neural Network[J]. Journal of Kunming Medical University, 2023, 44(10): 134-139. doi: 10.12259/j.issn.2095-610X.S20231027

Citation:

Zhixin YANG, Lizhu ZHAO, Yue DENG, Lihua YANG. Differential Diagnosis of Benign and Malignant Ovarian Tumors Based on Convolutional Neural Network[J]. Journal of Kunming Medical University, 2023, 44(10): 134-139. doi: 10.12259/j.issn.2095-610X.S20231027

Citation:

PDF( 1710 KB)

Differential Diagnosis of Benign and Malignant Ovarian Tumors Based on Convolutional Neural Network

doi: 10.12259/j.issn.2095-610X.S20231027

Dept. of Gynecology，The 2nd Affiliated Hospital of Kunming Medical University，Kunming Yunnan 650101，China

Received Date: 2023-08-08
Available Online: 2023-09-12
Publish Date: 2023-10-25

Abstract

Abstract

Objective To establish a convolutional neural network model for ultrasound diagnosis of ovarian tumors and explore its value in distinguishing between benign and malignant ovarian tumors. Methods A total of 400 ovarian tumor ultrasound images, including 200 benign and 200 malignant tumors, were collected from June 2015 to September 2022 at the Second Affiliated Hospital of Kunming Medical University. These images were confirmed by cytology or histopathology. The images were divided into a training set and a validation set in a 1∶3 ratio. Two diagnostic models, VGG16 and MobileNet-V2 were constructed based on convolutional neural networks for training and validation. A senior and a junior sonographers were selected to diagnose the ultrasound images in the training set. The performance of the two diagnostic models and the ultrasound doctors in distinguishing between benign and malignant ovarian tumors was evaluated using the pathological results as the gold standard. Results The sensitivity, specificity and accuracy of VGG16 model in diagnosing the benign and malignant nature of ovarian tumors were 80.67%, 79.33% and 80.00% respectively. The sensitivity, specificity and accuracy of MobileNet-V2 were 89.33%, 93.33% and 91.33% respectively. The MobileNet-V2 model had the best diagnostic performance, and both the MobileNet-V2 and VGG16 models had better diagnostic performance than ultrasound doctors （P < 0.05）. Conclusion The convolutional neural network ovarian tumor diagnostic model has good diagnostic value, with the MobileNet-V2 model accurately determining the benign or malignant nature of ovarian tumor ultrasound images.
- Convolutional neural network,
- Ovarian tumors,
- Ultrasonic diagnosis

FullText(HTML)

References(20)

References

[1]	狄文,胡媛. 卵巢癌的大数据研究[J]. 中国实用妇科与产科杂志,2018,34(1):18-22. doi: 10.19538/j.fk2018010105
[2]	Reid F,Bhatla N,Oza A M,et al. The World Ovarian Cancer Coalition Every Woman Study: Identifying challenges and opportunities to improve survival and quality of life[J]. Int J Gynecol Cancer,2021,31(2):238-244. doi: 10.1136/ijgc-2019-000983
[3]	La Vecchia C. Ovarian cancer: Epidemiology and risk factors[J]. Eur J Cancer Prev,2017,26(1):55-62. doi: 10.1097/CEJ.0000000000000217
[4]	张家雨,何昕晖,宫婷婷,等. 肉类摄入与卵巢癌发病及预后关系的研究进展[J]. 肿瘤防治研究,2019,46(5):490-496.
[5]	Trinidad C V,Tetlow A L,Bantis L E,et al. Reducing ovarian cancer mortality through early detection: Approaches using circulating biomarkers[J]. Cancer Prev Res (Phila),2020,13(3):241-252. doi: 10.1158/1940-6207.CAPR-19-0184
[6]	Kim G R,Lee E,Kim H R,et al. Convolutional neural network to stratify the malignancy risk of thyroid nodules: Diagnostic performance compared with the American college of radiology thyroid imaging reporting and data system implemented by experienced radiologists[J]. AJNR Am J Neuroradiol,2021,42(8):1513-1519. doi: 10.3174/ajnr.A7149
[7]	Hejduk P,Marcon M,Unkelbach J,et al. Fully automatic classification of automated breast ultrasound (ABUS) imaging according to BI-RADS using a deep convolutional neural network[J]. Eur Radiol,2022,32(7):4868-4878. doi: 10.1007/s00330-022-08558-0
[8]	Mitrea D,Badea R,Mitrea P,et al. Hepatocellular carcinoma automatic diagnosis within CEUS and B-Mode ultrasound images using advanced machine learning methods[J]. Sensors (Basel),2021,21(6):1-31. doi: 10.1109/JSEN.2021.3057283
[9]	李睿,许祥丛,林静怡,等. 基于卷积神经网络的超声影像肝癌自动分类[J]. 生物化学与生物物理进展,2023,50(3):668-675. doi: 10.16476/j.pibb.2022.0101
[10]	曹宇,邢素霞,逄键梁,等. 基于改进的VGG-16卷积神经网络的肺结节检测[J]. 中国医学物理学杂志,2020,37(7):940-944. doi: 10.3969/j.issn.1005-202X.2020.07.026
[11]	高慧明. 基于卷积神经网络的肺结节检测及良恶性分类方法研究[D]. 太原: 太原理工大学, 2019.
[12]	Han Y,Ma Y,Wu Z,et al. Histologic subtype classification of non-small cell lung cancer using PET/CT images[J]. Eur J Nucl Med Mol Imaging,2021,48(2):350-360. doi: 10.1007/s00259-020-04771-5
[13]	Alshammari A. Construction of VGG16 convolution neural network (VGG16_CNN) classifier with NestNet-Based segmentation paradigm for brain metastasis classification[J]. Sensors (Basel),2022,22(20):1-19. doi: 10.1109/JSEN.2022.3211123
[14]	Altun S,Alkan A,Altun I. LSS-VGG16: Diagnosis of lumbar spinal stenosis with deep learning[J]. Clin Spine Surg,2023,36(5):E180-E190. doi: 10.1097/BSD.0000000000001418
[15]	刘雪纯,刘大铭,常佳鑫,等. 基于MobileNet V2迁移学习的中药材图像识别[J]. 长江信息通信,2022,35(7):33-37. doi: 10.3969/j.issn.1673-1131.2022.07.009
[16]	易振通,吴瑰,官端正,等. 轻量化卷积神经网络的研究综述[J]. 工业控制计算机,2022,35(10):109-111.
[17]	Palczynski K,Smigiel S,Gackowska M,et al. IoT application of transfer learning in hybrid artificial intelligence systems for acute lymphoblastic leukemia classification[J]. Sensors (Basel),2021,21(23):1-12. doi: 10.1109/JSEN.2021.3128120
[18]	Srinivasu P N,SivaSai J G,Ijaz M F,et al. Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM[J]. Sensors (Basel),2021,21(8):1-27. doi: 10.1109/JSEN.2021.3063942
[19]	Yu C J,Yeh H J,Chang C C,et al. Lightweight deep neural networks for cholelithiasis and cholecystitis detection by point-of-care ultrasound[J]. Comput Methods Programs Biomed,2021,211:106382. doi: 10.1016/j.cmpb.2021.106382
[20]	Martinez-Mas J,Bueno-Crespo A,Khazendar S,et al. Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images[J]. PLoS One,2019,14(7):e219388.

Relative Articles(20)

Relative Articles

[1]	Ruicheng LI, Hongwei QIAN, Yanni FAN, Peipei ZHAO, Shan WEI, Huarong JING. Application of Logistic Regression and Artificial Neural Networks in the Differential Diagnosis of LC-MPE. Journal of Kunming Medical University, 2024, 45(10): 55-60. doi: 10.12259/j.issn.2095-610X.S20241009
[2]	Li Fei Fei , Han Chang Nian , Liu Zhi Qin , Hao Jin Gang . . Journal of Kunming Medical University, 2019, 40(11): 87-91.
[3]	Wang Ya Mei . Quantitative Analysis of Malignant and Benign Ovarian Masses with Transvaginal Three-dimensional Power Doppler Ultrasound. Journal of Kunming Medical University,
[4]	Qiu Mei . Unnecessity of Integrating Metabolic Indices into the Diagnosis of Polycystic Ovary Syndrome. Journal of Kunming Medical University,
[5]	Lin Ken . Diagnosis and Treatment of 98 Children with Thyroglossal Duct Cyst. Journal of Kunming Medical University,
[6]	Ning Rong Ping . Prenatal Ultrasound Diagnosis and Misdiagnosis Analysis of Fetal Persistent Right Umbilical Vein. Journal of Kunming Medical University,
[7]	Ma Ju Xiang . . Journal of Kunming Medical University,
[8]	Zhu Ying Jie . . Journal of Kunming Medical University,
[9]	Liu Xi . . Journal of Kunming Medical University,
[10]	Gao Hong . . Journal of Kunming Medical University,
[11]	Lu Jian Fei . . Journal of Kunming Medical University,
[12]	Zhao Xing Yuan . . Journal of Kunming Medical University,
[13]	Zhang Li . . Journal of Kunming Medical University,
[14]	Yang Li Hua . . Journal of Kunming Medical University,
[15]	Wu Li Zhen . Value of High Frequency Ultrasound Parameters in Differential Diagnosis of Breast Phyllodes Tumor and Breast Fibroadenoma. Journal of Kunming Medical University,
[16]	Ma Kai Yu . . Journal of Kunming Medical University,
[17]	Chen Hai Tao . . Journal of Kunming Medical University,
[18]	Ma Jin Xia . . Journal of Kunming Medical University,
[19]	. Ultrasonographic Diagnosis and Misdiagnosis Analysis on Peripheral Neurilemmoma. Journal of Kunming Medical University,
[20]	Ma Yong Hong . . Journal of Kunming Medical University,

Supplements(0)

Cited By

Cited by

Periodical cited type(2)

1.	梁玉清，陈成彩. 超声成像技术评估卵巢肿瘤的研究进展. 影像研究与医学应用. 2024(10): 4-6 .
2.	管锡琴，刘斌，侯丽芳，吴小川. 语义分割用于分割弥散加权成像中脑梗死病灶. 中国医学影像技术. 2024(12): 1818-1821 .