Department of Ultrasound, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, 758 Hefei Road, Qingdao, Shandong 266035, China.
Department of Obstetrics and Gynecology, Qilu Hospital (Qingdao), Cheeloo College of Medicine, Shandong University, 758 Hefei Road, Qingdao, Shandong 266035, China.
Comput Math Methods Med. 2022 Feb 15;2022:7531371. doi: 10.1155/2022/7531371. eCollection 2022.
To explore the establishment and verification of logistic regression model for qualitative diagnosis of ovarian cancer based on MRI and ultrasonic signs.
207 patients with ovarian tumors in our hospital from April 2018 to April 2021 were selected, of which 138 were used as the training group for model creation and 69 as the validation group for model evaluation. The differences of MRI and ultrasound signs in patients with ovarian cancer and benign ovarian tumor in the training group were analyzed. The risk factors were screened by multifactor unconditional logistic regression analysis, and the regression equation was established. The self-verification was carried out by subject working characteristics (ROC), and the external verification was carried out by K-fold cross verification.
There was no significant difference in age, body mass index, menstruation, dysmenorrhea, times of pregnancy, cumulative menstrual years, and marital status between the two groups ( > 0.05). After logistic regression analysis, the diagnostic model of ovarian cancer was established: logit () = -1.153 + [MRI signs : morphology × 1.459 + boundary × 1.549 + reinforcement × 1.492 + tumor components × 1.553] + [ultrasonic signs : morphology × 1.594 + mainly real × 1.417 + separated form × 1.294 + large nipple × 1.271 + blood supply × 1.364]; self-verification: AUC of the model is 0.883, diagnostic sensitivity is 93.94%, and specificity is 80.95%; K-fold cross validation: the training accuracy was 0.904 ± 0.009 and the prediction accuracy was 0.881 ± 0.049.
Irregular shape, unclear boundary, obvious enhancement in MRI signs, cystic or solid tumor components and irregular shape, solid-dominated shape, thick septate shape, large nipple, and abundant blood supply in ultrasound signs are independent risk factors for ovarian cancer. After verification, the diagnostic model has good accuracy and stability, which provides basis for clinical decision-making.
探讨基于 MRI 和超声征象的卵巢癌定性诊断的逻辑回归模型的建立与验证。
选取我院 2018 年 4 月至 2021 年 4 月收治的卵巢肿瘤患者 207 例，其中 138 例用于模型建立的训练组，69 例用于模型评价的验证组。分析训练组中卵巢癌和良性卵巢肿瘤患者的 MRI 和超声征象差异，多因素非条件逻辑回归分析筛选风险因素，建立回归方程。采用受试者工作特征曲线（ROC）进行自我验证，K 折交叉验证进行外部验证。
两组患者的年龄、体质量指数、月经情况、痛经、妊娠次数、累计月经年数、婚姻状况比较，差异无统计学意义（>0.05）。逻辑回归分析后，建立卵巢癌诊断模型：logit（）=-1.153+[MRI 征象：形态×1.459+边界×1.549+强化×1.492+肿瘤成分×1.553]+[超声征象：形态×1.594+主要实性×1.417+分隔形式×1.294+大乳头×1.271+血流供应×1.364]；自我验证：模型的 AUC 为 0.883，诊断敏感度为 93.94%，特异度为 80.95%；K 折交叉验证：训练集准确率为 0.904±0.009，预测准确率为 0.881±0.049。
MRI 征象中不规则形态、边界不清、明显强化、囊实性或实性肿瘤成分和超声征象中不规则形态、实性为主形态、厚分隔形态、大乳头、丰富血流供应是卵巢癌的独立危险因素。经验证，该诊断模型具有良好的准确性和稳定性，为临床决策提供了依据。
