Yang Yuan, Long Huiling, Feng Yong, Tian Shuangming, Chen Haibin, Zhou Ping
Department of Ultrasound, The Third Xiangya Hospital, Central South University, Changsha, 410013, China.
Hunan Drug Evaluation and Adverse Reaction Monitoring Center.
Heliyon. 2024 May 28;10(11):e32115. doi: 10.1016/j.heliyon.2024.e32115. eCollection 2024 Jun 15.
Through a nested cohort study, we evaluated the diagnostic performance of breath-omics in differentiating between benign and malignant breast lesions, and assessed the diagnostic performance of a multi-omics approach that combines breath-omics, ultrasound radiomics, and clinic-omics in distinguishing between benign and malignant breast lesions.
We recruited 1,723 consecutive patients who underwent an automated breast volume scanner (ABVS) examination. Breath samples were collected and analyzed by high-pressure photon ionization time-of-flight mass spectrometry (HPPI-TOF-MS) to obtain breath-omics features. 238 of 1,723 enrolled participants have received pathological confirmation of breast nodules finally. The breast lesions of the 238 participants were contoured manually based on ABVS images for ultrasound radiomics feature calculation. Then, single- and multi-omics models were constructed and evaluated for breast nodules diagnosis via five-fold cross-validation.
The area under the curve (AUC) of the breath-omics model was 0.855. In comparison, the multi-omics model demonstrated superior diagnostic performance for breast cancer, with sensitivity, specificity, and AUC of 84.1 %, 89.9 %, and 0.946, respectively. The multi-omics performance was comparable to that of the Breast Imaging Reporting and Data System (BI-RADS) classification via senior ultrasound physician evaluation.
The multi-omics approach combining metabolites in exhaled breath, ultrasound imaging, and basic clinical information exhibits superior diagnostic performance and promises to be a non-invasive and reliable tool for breast cancer diagnosis.
通过一项巢式队列研究，我们评估了呼吸组学在鉴别乳腺良性和恶性病变中的诊断性能，并评估了一种结合呼吸组学、超声影像组学和临床组学的多组学方法在区分乳腺良性和恶性病变中的诊断性能。
我们招募了1723例连续接受自动乳腺容积扫描仪（ABVS）检查的患者。收集呼吸样本并通过高压光子电离飞行时间质谱（HPPI-TOF-MS）进行分析，以获得呼吸组学特征。1723名登记参与者中的238例最终获得了乳腺结节的病理证实。基于ABVS图像手动勾勒出这238名参与者的乳腺病变轮廓，以计算超声影像组学特征。然后，构建单组学和多组学模型，并通过五折交叉验证对乳腺结节诊断进行评估。
呼吸组学模型的曲线下面积（AUC）为0.855。相比之下，多组学模型对乳腺癌表现出更好的诊断性能，敏感性、特异性和AUC分别为84.1%、89.9%和0.946。通过资深超声医师评估，多组学性能与乳腺影像报告和数据系统（BI-RADS）分类相当。
结合呼出气体中的代谢物、超声成像和基本临床信息的多组学方法表现出卓越的诊断性能，有望成为一种用于乳腺癌诊断的非侵入性可靠工具。
