A net for everyone fully personalized and unsupervised neural networks trained with longitudinal data from a single patient

2025-04-30 0 0 536.54KB 15 页 10玖币

侵权投诉

“A net for everyone”: fully personalized and unsupervised

neural networks trained with longitudinal data from a single

patient

Christian Strack1,2*, Kelsey L. Pomykala3, Heinz-Peter Schlemmer1,5, Jan Egger3,4

Jens Kleesiek3,4,5

1 Division of Radiology, German Cancer Research Center (DKFZ), 69120 Heidelberg, Germany

2 Medical Faculty Heidelberg, Heidelberg University, 69120 Heidelberg, Germany

3 Institute for AI in Medicine (IKIM), University Hospital Essen (AöR), Girardetstraße 2, 45131

Essen, Germany

4 Cancer Research Center Cologne Essen (CCCE), University Medicine Essen, Hufelandstraße

55, 45147 Essen, Germany

5 German Cancer Consortium (DKTK), Partner Site Essen, Hufelandstraße 55, 45147 Essen,

Germany

*corresponding author: c.strack@dkfz-heidelberg.de

Abstract

With the rise in importance of personalized medicine, we trained personalized neural networks to

detect tumor progression in longitudinal datasets. The model was evaluated on two datasets with

a total of 64 scans from 32 patients diagnosed with glioblastoma multiforme (GBM). Contrast-

enhanced T1w sequences of brain magnetic resonance imaging (MRI) images were used in this

study. For each patient, we trained their own neural network using just two images from different

timepoints. Our approach uses a Wasserstein-GAN (generative adversarial network), an

unsupervised network architecture, to map the differences between the two images. Using this

map, the change in tumor volume can be evaluated. Due to the combination of data augmentation

and the network architecture, co-registration of the two images is not needed. Furthermore, we

do not rely on any additional training data, (manual) annotations or pre-training neural networks.

The model received an AUC-score of 0.87 for tumor change. We also introduced a modified

RANO criteria, for which an accuracy of 66% can be achieved. We show that using data from just

one patient can be used to train deep neural networks to monitor tumor change.

Keywords: Neural networks, personalized, Wasserstein-GAN, unsupervised, machine learning,

privacy-safe, zero-training data, longitudinal, brain tumor, MRI.

1  Introduction 
One key difference between human and artificial intelligence is the number of training examples 
needed to generate knowledge. While children can learn to recognize new objects with only a few 
examples, most machine learning tasks require hundreds of examples for the same task. In fact, 
increasing the dataset size is often a key step in improving the performance of a machine learning 
model. ImageNet [1], the most famous dataset in computer vision, now consists of over 14 million 
training examples.  The state of the art models in computer vision are often trained on  large 
datasets such as ImageNet and may not transfer well to smaller datasets. Getting large datasets 
may not always be a feasible approach though, especially in the medical domain. 
Gathering large datasets is one of the key challenges of medical deep learning applications.  
Keeping a patient’s medical information safe is critical and there are laws protecting it in most 
countries. This makes it more difficult to get the data and leads to the medical datasets being 
much  smaller  compared  to  traditional  computer  vision  datasets.  Additionally,  deep  neural 
networks themselves offer another privacy threat. It has been shown that training examples of 
fully trained networks can be recovered with a model inversion attack [2]. This makes it more 
difficult  to  publish  medical  deep  learning  applications  as  the  patient’s  privacy  can  not  be 
guaranteed. These two reasons give a big incentive to find ways to train neural networks with 
smaller datasets or even just one patient’s data. 
There  have  been  several models  proposed to challenge the  task  of  reducing  the number of 
training examples. One shot  learning is a method of  learning  a  class from  only  one  labeled 
example [3]. Siamese neural networks are able to determine if two images show the same person, 
even if they have never seen images of that person before [4]. They have also been used in 
medicine to distinguish between COPD and asthma [5]. While new classes can be learned from 
as little as one example, one shot learning still requires thousands of training examples of other 
classes  beforehand.  Another  method  to  handle  small  datasets  is  transfer  learning,  where 
networks trained on large datasets are used as a starting point to train on training examples of 
new classes. Transfer learning makes use of the fact that features learned on the large dataset 
can be reapplied to new data. 
In this paper, we introduce personalized neural networks, which use only one patient’s data for 
training. Our proposed method only needs two MRIs from the same patient and no additional 
pretraining. This also results in a privacy-safe processing of the data, because the data “stays” 
within the same patient. Our model is based on Generative Adversarial Networks (GANs) [6]. 
GANs have gained in popularity in recent years in the medical AI community. Originally used for 
image synthesis, there have been applications to generate medical images [7, 8]. Other studies 
focus on classification or segmentation tasks [9, 10]. We apply the personalized neural networks 
on subjects with brain tumors. 
Brain tumors belong to the most devastating diagnoses, in particular for a confirmed glioblastoma 
multiforme (GBM) [11]. Despite  massive research efforts  and  advancements  in other  cancer 
types, like breast cancer [12] or prostate cancer [13], the life expectancy of a confirmed GBM with 
treatment, including chemotherapy, radiotherapy and surgery, is still only around one year [14]. 

Nevertheless, disease progression and treatment decisions are strongly dependent on maximum 
tumor diameter and tumor volume, as well as the corresponding morphological changes during a 
treatment period. The  imaging method of choice here is magnetic resonance imaging (MRI). 
However, MRI does not provide any semantic information for brain structures or the brain tumor 
per se. This has to be done manually, semi-manually or automatically, in a post-processing step, 
commonly referred to as a segmentation. Manually performed, however, a segmentation is very 
time-consuming  and  operator-dependent,  especially  when  performed  in  a  three-dimensional 
image  volume  [15],  which needs slice-by-slice contouring.  Hence,  an  automatic  (algorithmic) 
segmentation is desired, especially when large quantities of data volumes have to be processed. 
Even if it is still considered an unsolved problem, there has been steady progress from year to 
year; and data-driven approaches, like deep neural networks, currently provide the best (fully 
automatic) results. However, a segmentation with a data-driven approach, like deep learning [16], 
comes with several burdens: Firstly, the algorithm generally needs massive annotated training 
data.  Additionally,  for  inter-patient  disease  monitoring,  several  segmentations  have  to  be 
performed, and in addition, these scans have to be registered to each other (which also adds 
uncertainty to the overall procedure, especially when deformed soft-tissue comes into play [17]). 
In this regard, we want to tackle these problems with a personalized neural network that needs 
just the patient’s data, no annotations and no extra registration step. To the best of our knowledge, 
this is the first study using this little training data to train a deep neural network in the medical 
domain. The method addresses the issues of gathering big datasets in medicine and producing 
a  privacy-safe  network.  The  approach  is  considered  as  unsupervised  learning  as  no  data 
annotation is necessary. We evaluate the model with an ROC analysis as well as modified RANO 
criteria on two different datasets of longitudinal MRI images of patients with glioblastoma. 
 
2  Methods 
2.1  Model architecture and training 
The neural network architecture used in this study is based upon Wasserstein GANs [18]. This is 
a modified version of Generative Adversarial Networks (GAN) [6]. These are a form of deep neural 
networks in which two sub-models are trained adversarily in a sum-zero game. A generator is 
trained to create new images, while a discriminator is trained to distinguish between real and 
synthetic images. In Wasserstein GANs the discriminator is modified to a critic function which 
leads to more stable training [18]. 
Our network architecture is similar to the model used by Baumgartner et al [19]. The aim of the 
network is to create a map which transforms an image from the first timepoint (t1) to the second 
timepoint (t2). This will make the model learn to represent the changes between the images, more 
specifically tumor growth/reduction in our case. To do this, augmented versions of the image at 
t1 are used as input to the generator. The generator will try to create a map that, when added to 
the input image creates an image of t2. The critic will try to distinguish these generated synthetic 
t2 images from the real t2 images. Thereby forcing the generator to learn the differences between 
the two timepoints. 

文档加载中……请稍候！
如果长时间未打开，您也可以点击刷新试试。

下载文档到电脑，查找使用更方便

10 玖币 0人已下载

立即下载

摘要：

“Anetforeveryone”:fullypersonalizedandunsupervisedneuralnetworkstrainedwithlongitudinaldatafromasinglepatientChristianStrack1,2*,KelseyL.Pomykala3,Heinz-PeterSchlemmer1,5,JanEgger3,4JensKleesiek3,4,51DivisionofRadiology,GermanCancerResearchCenter(DKFZ),69120Heidelberg,Germany2MedicalFacultyHeidelber...

展开>> 收起<<

A net for everyone fully personalized and unsupervised neural networks trained with longitudinal data from a single patient.pdf

共15页,预览3页

还剩页未读，继续阅读

声明：本站为文档C2C交易模式，即用户上传的文档直接被用户下载，本站只是中间服务平台，本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间，仅对用户上传内容的表现方式做保护处理，对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私，请立即通知玖贝云文库，我们立即给予删除！

A net for everyone fully personalized and unsupervised neural networks trained with longitudinal data from a single patient

相关推荐

开通VIP享超值会员特权

作者详情

相关内容

热门标签

举报选择: