Machine learning based on radiomics features combing B-mode transrectal ultrasound and contrast-enhanced ultrasound to improve peripheral zone prostate cancer detection,Abdominal Radiology

当前位置： X-MOL 学术 › Abdom. Radiol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Machine learning based on radiomics features combing B-mode transrectal ultrasound and contrast-enhanced ultrasound to improve peripheral zone prostate cancer detection
Abdominal Radiology ( IF 2.3 ) Pub Date : 2023-10-05 , DOI: 10.1007/s00261-023-04050-5
Ya Sun ₁ , Jingyang Fang ₁ , Yanping Shi ₁ , Huarong Li ₁ , Jiajun Wang ₁ , Jingxu Xu ₂ , Bao Zhang ₃ , Lei Liang ₁

Affiliation

Purpose

To construct machine learning models based on radiomics features combing conventional transrectal ultrasound (B-mode) and contrast-enhanced ultrasound (CEUS) to improve prostate cancer (PCa) detection in peripheral zone (PZ).

Methods

A prospective study of 166 men (72 benign, 94 malignant lesions) with targeted biopsy-confirmed pathology who underwent B-mode and CEUS examinations was performed. Risk factors, including age, serum total prostate-specific antigen (tPSA), free PSA (fPSA), f/t PSA, prostate volume and prostate-specific antigen density (PSAD), were collected. Time-intensity curves were obtained using SonoLiver software for all lesions in regions of interest. Four parameters were collected as risk factors: the maximum intensity (IMAX), rise time (RT), time to peak (TTP), and mean transit time (MTT). Radiomics features were extracted from the target lesions from B-mode and CEUS imaging. Multivariable logistic regression analysis was used to construct the model.

Results

A total of 3306 features were extracted from seven categories. Finally, 32 features were screened out from radiomics models. Five models were developed to predict PCa: the B-mode radiomics model (B model), CEUS radiomics model (CEUS model), B-CEUS combined radiomics model (B-CEUS model), risk factors model, and risk factors-radiomics combined model (combined model). Age, PSAD, tPSA, and RT were significant independent predictors in discriminating benign and malignant PZ lesions (P < 0.05). The risk factors model combing these four predictors showed better discrimination in the validation cohort (area under the curve [AUC], 0.84) than the radiomics images (AUC, 0.79 on B model; AUC, 0.78 on CEUS model; AUC, 0.83 on B-CEUS model), and the combined model (AUC: 0.89) achieved the greatest predictive efficacy.

Conclusion

The prediction model including B-mode and CEUS radiomics signatures and risk factors represents a promising diagnostic tool for PCa detection in PZ, which may contribute to clinical decision-making.

中文翻译：

基于放射组学特征的机器学习，结合 B 型经直肠超声和对比增强超声，以改善周围区前列腺癌的检测

目的

构建基于放射组学特征的机器学习模型，结合传统经直肠超声（B 型）和对比增强超声（CEUS），以改善周围区（PZ）前列腺癌（PCa）的检测。

方法

对 166 名男性（72 名良性病变，94 名恶性病变）进行了一项前瞻性研究，这些男性接受了 B 型和 CEUS 检查，并进行了靶向活检证实的病理学检查。收集的危险因素包括年龄、血清总前列腺特异性抗原（tPSA）、游离PSA（fPSA）、f/t PSA、前列腺体积和前列腺特异性抗原密度（PSAD）。使用 SonoLiver 软件获得感兴趣区域中所有病变的时间-强度曲线。收集四个参数作为危险因素：最大强度 (IMAX)、上升时间 (RT)、到达峰值时间 (TTP) 和平均通过时间 (MTT)。通过 B 模式和 CEUS 成像从目标病变中提取放射组学特征。使用多变量逻辑回归分析来构建模型。

结果

从七个类别中总共提取了 3306 个特征。最终从放射组学模型中筛选出32个特征。开发了五种预测 PCa 的模型：B 模式放射组学模型（B 模型）、CEUS 放射组学模型（CEUS 模型）、B-CEUS 组合放射组学模型（B-CEUS 模型）、危险因素模型和危险因素-放射组学组合模型（组合模型）。年龄、PSAD、tPSA 和 RT 是区分良恶性 PZ 病变的显着独立预测因子（ P < 0.05）。结合这四个预测因子的风险因素模型在验证队列中显示出比放射组学图像（B 模型上的 AUC，0.79；CEUS 模型上的 AUC，0.78；B 上的 AUC，0.83）更好的区分度（曲线下面积 [AUC]，0.84） -CEUS模型），联合模型（AUC：0.89）取得了最大的预测功效。