Photon-counting Detector CT with Deep Learning Noise Reduction to Detect Multiple Myeloma,Radiology

当前位置： X-MOL 学术 › Radiology › 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.)

Photon-counting Detector CT with Deep Learning Noise Reduction to Detect Multiple Myeloma
Radiology ( IF 19.7 ) Pub Date : 2022-09-06 , DOI: 10.1148/radiol.220311
Francis I Baffour ₁ , Nathan R Huber ₁ , Andrea Ferrero ₁ , Kishore Rajendran ₁ , Katrina N Glazebrook ₁ , Nicholas B Larson ₁ , Shaji Kumar ₁ , Joselle M Cook ₁ , Shuai Leng ₁ , Elisabeth R Shanblatt ₁ , Cynthia H McCollough ₁ , Joel G Fletcher ₁

Affiliation

Background

Photon-counting detector (PCD) CT and deep learning noise reduction may improve spatial resolution at lower radiation doses compared with energy-integrating detector (EID) CT.

Purpose

To demonstrate the diagnostic impact of improved spatial resolution in whole-body low-dose CT scans for viewing multiple myeloma by using PCD CT with deep learning denoising compared with conventional EID CT.

Materials and Methods

Between April and July 2021, adult participants who underwent a whole-body EID CT scan were prospectively enrolled and scanned with a PCD CT system in ultra-high-resolution mode at matched radiation dose (8 mSv for an average adult) at an academic medical center. EID CT and PCD CT images were reconstructed with Br44 and Br64 kernels at 2-mm section thickness. PCD CT images were also reconstructed with Br44 and Br76 kernels at 0.6-mm section thickness. The thinner PCD CT images were denoised by using a convolutional neural network. Image quality was objectively quantified in two phantoms and a randomly selected subset of participants (10 participants; median age, 63.5 years; five men). Two radiologists scored PCD CT images relative to EID CT by using a five-point Likert scale to detect findings reflecting multiple myeloma. The scoring for the matched reconstruction series was blinded to scanner type. Reader-averaged scores were tested with the null hypothesis of equivalent visualization between EID and PCD.

Results

Twenty-seven participants (median age, 68 years; IQR, 61–72 years; 16 men) were included. The blinded assessment of 2-mm images demonstrated improvement in viewing lytic lesions, intramedullary lesions, fatty metamorphosis, and pathologic fractures for PCD CT versus EID CT (P < .05 for all comparisons). The 0.6-mm PCD CT images with convolutional neural network denoising also demonstrated improvement in viewing all four pathologic abnormalities and detected one or more lytic lesions in 21 of 27 participants compared with the 2-mm EID CT images (P < .001).

Conclusion

Ultra-high-resolution photon-counting detector CT improved the visibility of multiple myeloma lesions relative to energy-integrating detector CT.

Online supplemental material is available for this article.

中文翻译：

具有深度学习降噪功能的光子计数检测器 CT 可检测多发性骨髓瘤

背景

与能量积分探测器 (EID) CT 相比，光子计数探测器 (PCD) CT 和深度学习降噪可以在较低辐射剂量下提高空间分辨率。

目的

与传统的 EID CT 相比，通过使用具有深度学习去噪的 PCD CT 来证明在全身低剂量 CT 扫描中提高空间分辨率以查看多发性骨髓瘤的诊断影响。

材料和方法

在 2021 年 4 月至 2021 年 7 月期间，接受过全身 EID CT 扫描的成年参与者被前瞻性地纳入并使用 PCD CT 系统在超高分辨率模式下以匹配的辐射剂量（普通成年人为 8 mSv）在学术医疗机构进行扫描中心。EID CT 和 PCD CT 图像是用 2 毫米切片厚度的 Br44 和 Br64 内核重建的。还使用 0.6 毫米切片厚度的 Br44 和 Br76 内核重建 PCD CT 图像。使用卷积神经网络对较薄的 PCD CT 图像进行去噪。图像质量在两个模型和随机选择的参与者子集（10 名参与者；中位年龄 63.5 岁；5 名男性）中进行了客观量化。两名放射科医师使用五点李克特量表对 PCD CT 图像相对于 EID CT 进行评分，以检测反映多发性骨髓瘤的发现。匹配重建系列的评分对扫描仪类型不知情。使用 EID 和 PCD 之间等效可视化的零假设测试读者平均分数。

结果

包括 27 名参与者（中位年龄 68 岁；IQR，61-72 岁；16 名男性）。2 毫米图像的盲法评估表明，PCD CT 与 EID CT 相比，在观察溶解性病变、髓内病变、脂肪变态和病理性骨折方面有所改善（所有比较P < .05）。与 2 毫米 EID CT 图像相比，具有卷积神经网络去噪功能的 0.6 毫米 PCD CT 图像也显示出在观察所有四种病理异常方面有所改善，并在 27 名参与者中的 21 名中检测到一处或多处溶骨性病变 (P < .001 )。