当前位置: X-MOL 学术Comput. Methods Programs Biomed. › 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.)
Deep learning-based pulmonary nodule detection: Effect of slab thickness in maximum intensity projections at the nodule candidate detection stage.
Computer Methods and Programs in Biomedicine ( IF 6.1 ) Pub Date : 2020-06-20 , DOI: 10.1016/j.cmpb.2020.105620
Sunyi Zheng 1 , Xiaonan Cui 2 , Marleen Vonder 3 , Raymond N J Veldhuis 4 , Zhaoxiang Ye 5 , Rozemarijn Vliegenthart 6 , Matthijs Oudkerk 7 , Peter M A van Ooijen 1
Affiliation  

Background and Objective

To investigate the effect of the slab thickness in maximum intensity projections (MIPs) on the candidate detection performance of a deep learning-based computer-aided detection (DL-CAD) system for pulmonary nodule detection in CT scans.

Methods

The public LUNA16 dataset includes 888 CT scans with 1186 nodules annotated by four radiologists. From those scans, MIP images were reconstructed with slab thicknesses of 5 to 50 mm (at 5 mm intervals) and 3 to 13 mm (at 2 mm intervals). The architecture in the nodule candidate detection part of the DL-CAD system was trained separately using MIP images with various slab thicknesses. Based on ten-fold cross-validation, the sensitivity and the F2 score were determined to evaluate the performance of using each slab thickness at the nodule candidate detection stage. The free-response receiver operating characteristic (FROC) curve was used to assess the performance of the whole DL-CAD system that took the results combined from 16 MIP slab thickness settings.

Results

At the nodule candidate detection stage, the combination of results from 16 MIP slab thickness settings showed a high sensitivity of 98.0% with 46 false positives (FPs) per scan. Regarding a single MIP slab thickness of 10 mm, the highest sensitivity of 90.0% with 8 FPs/scan was reached before false positive reduction. The sensitivity increased (82.8% to 90.0%) for slab thickness of 1 to 10 mm and decreased (88.7% to 76.6%) for slab thickness of 15–50 mm. The number of FPs was decreasing with increasing slab thickness, but was stable at 5 FPs/scan at a slab thickness of 30 mm or more. After false positive reduction, the DL-CAD system, utilizing 16 MIP slab thickness settings, had the sensitivity of 94.4% with 1 FP/scan.

Conclusions

The utilization of multi-MIP images could improve the performance at the nodule candidate detection stage, even for the whole DL-CAD system. For a single slab thickness of 10 mm, the highest sensitivity for pulmonary nodule detection was reached at the nodule candidate detection stage, similar to the slab thickness usually applied by radiologists.



中文翻译:

基于深度学习的肺结节检测:在结节候选检测阶段,平板厚度对最大强度投影的影响。

背景与目的

要研究最大强度投影(MIP)中平板厚度对基于深度学习的计算机辅助检测(DL-CAD)系统在CT扫描中进行肺结节检测的候选检测性能的影响。

方法

公开的LUNA16数据集包括888个CT扫描,其中有4个放射科医生注释了1186个结节。从这些扫描中,以5至50毫米(以5毫米的间隔)和3至13毫米(以2毫米的间隔)的板厚重建MIP图像。使用具有各种平板厚度的MIP图像分别训练了DL-CAD系统的结核候选检测部分中的体系结构。基于十倍交叉验证,确定敏感性和F 2分数,以评估在候选结节检测阶段使用每个平板厚度的性能。使用自由响应的接收器工作特性(FROC)曲线来评估整个DL-CAD系统的性能,该系统结合了16个MIP板坯厚度设置的结果。

结果

在结节候选检测阶段,来自16个MIP平板厚度设置的结果组合显示出98.0%的高灵敏度,每次扫描有46个假阳性(FP)。关于10 mm的单个MIP平板厚度,在假阳性减少之前,使用8个FP /扫描可达到90.0%的最高灵敏度。平板厚度为1至10 mm时,灵敏度增加(82.8%至90.0%),而平板厚度为15–50 mm时,灵敏度则降低(88.7%至76.6%)。FP的数量随着板坯厚度的增加而减少,但在板坯厚度为30 mm或更大的情况下,每次扫描5 FPs时稳定。假阳性减少后,利用16个MIP平板厚度设置的DL-CAD系统在1 FP /扫描下灵敏度为94.4%。

结论

即使在整个DL-CAD系统中,多MIP图像的利用也可以提高结节候选检测阶段的性能。对于10 mm的单个平板厚度,在结节候选检测阶段达到了肺结节检测的最高灵敏度,这与放射科医生通常采用的平板厚度相似。

更新日期:2020-06-20
down
wechat
bug