Purpose: Identification of abdominal Lymph Nodes (LN) that are suspicious for
metastasis in T2 Magnetic Resonance Imaging (MRI) scans is critical for staging
of lymphoproliferative diseases. Prior work on LN detection has been limited to
specific anatomical regions of the body (pelvis, rectum) in single MR slices.
Therefore, the development of a universal approach to detect LN in full T2 MRI
volumes is highly desirable.
Methods: In this study, a Computer Aided Detection (CAD) pipeline to
universally identify abdominal LN in volumetric T2 MRI using neural networks is
proposed. First, we trained various neural network models for detecting LN:
Faster RCNN with and without Hard Negative Example Mining (HNEM), FCOS,
FoveaBox, VFNet, and Detection Transformer (DETR). Next, we show that the
state-of-the-art (SOTA) VFNet model with Adaptive Training Sample Selection
(ATSS) outperforms Faster RCNN with HNEM. Finally, we ensembled models that
surpassed a 45% mAP threshold. We found that the VFNet model and one-stage
model ensemble can be interchangeably used in the CAD pipeline.
Results: Experiments on 122 test T2 MRI volumes revealed that VFNet achieved
a 51.1% mAP and 78.7% recall at 4 false positives (FP) per volume, while the
one-stage model ensemble achieved a mAP of 52.3% and sensitivity of 78.7% at
4FP.
Conclusion: Our contribution is a CAD pipeline that detects LN in T2 MRI
volumes, resulting in a sensitivity improvement of $\sim$14 points over the
current SOTA method for LN detection (sensitivity of 78.7% at 4 FP vs. 64.6% at
5 FP per volume).

本文提出了一种计算机辅助检测（CAD）管道，使用神经网络普适性地在容积 T2 MRI 中识别腹部淋巴结（LN），其灵敏度比目前 SOTA 方法高 14 个百分点（4FP 时的 78.7％对比每卷 5 FP 的 64.6％）；VFNet 模型表现优异，能够在 CAD 管道中与单阶段模型集成使用。

使用神经网络在 T2 MRI 中进行通用淋巴结检测

Universal Lymph Node Detection in T2 MRI using Neural Networks

Breast cancer is the most common cancer in women worldwide. The most common
screening technology is mammography. To reduce the cost and workload of
radiologists, we propose a computer aided detection approach for classifying
and localizing calcifications and masses in mammogram images. To improve on
conventional approaches, we apply deep convolutional neural networks (CNN) for
automatic feature learning and classifier building. In computer-aided
mammography, deep CNN classifiers cannot be trained directly on full mammogram
images because of the loss of image details from resizing at input layers.
Instead, our classifiers are trained on labelled image patches and then adapted
to work on full mammogram images for localizing the abnormalities.
State-of-the-art deep convolutional neural networks are compared on their
performance of classifying the abnormalities. Experimental results indicate
that VGGNet receives the best overall accuracy at 92.53\% in classifications.
For localizing abnormalities, ResNet is selected for computing class activation
maps because it is ready to be deployed without structural change or further
training. Our approach demonstrates that deep convolutional neural network
classifiers have remarkable localization capabilities despite no supervision on
the location of abnormalities is provided.

针对乳腺癌的计算机辅助检测方法，通过对乳腺 X 线照片图像的卷积神经网络 (CNN) 自动建模和分类，实现对钙化和肿块的分类和定位，以降低放射科医师的成本和工作量。