Improving sensitivity through data augmentation with synthetic lymph node metastases for AI-based analysis of PSMA PET-CT images

IF 1.3 4区医学 Q4 PHYSIOLOGY

Clinical Physiology and Functional Imaging Pub Date : 2024-04-02 DOI:10.1111/cpf.12879

Elin Trägårdh, Johannes Ulén, Olof Enqvist, Lars Edenbrandt, Måns Larsson

{"title":"Improving sensitivity through data augmentation with synthetic lymph node metastases for AI-based analysis of PSMA PET-CT images","authors":"Elin Trägårdh, Johannes Ulén, Olof Enqvist, Lars Edenbrandt, Måns Larsson","doi":"10.1111/cpf.12879","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (<i>n</i> = 420) was expanded by one synthetic image for every original image (<i>n</i> = 840), which was used to train an AI model. The performance of the AI model was compared to that of nuclear medicine physicians and a previously developed AI model. The human readers were alternately used as a reference and compared to either another reading or AI model.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The new AI model had an average sensitivity of 84% for detecting lymph node metastases compared with 78% for human readings. Our previously developed AI method without synthetic data had an average sensitivity of 79%. The number of false positive lesions were slightly higher for the new AI model (average 3.3 instances per patient) compared to human readings and the previous AI model (average 2.8 instances per patient), while the number of false negative lesions was lower.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>Creating synthetic lymph node metastases, as a form of data augmentation, on [18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT images improved the sensitivity of an AI model for detecting suspected lymph node metastases. However, the number of false positive lesions increased somewhat.</p>\n </section>\n </div>","PeriodicalId":10504,"journal":{"name":"Clinical Physiology and Functional Imaging","volume":"44 4","pages":"332-339"},"PeriodicalIF":1.3000,"publicationDate":"2024-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/cpf.12879","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical Physiology and Functional Imaging","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1111/cpf.12879","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"PHYSIOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background

We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set.

Methods

Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (n = 420) was expanded by one synthetic image for every original image (n = 840), which was used to train an AI model. The performance of the AI model was compared to that of nuclear medicine physicians and a previously developed AI model. The human readers were alternately used as a reference and compared to either another reading or AI model.

Results

The new AI model had an average sensitivity of 84% for detecting lymph node metastases compared with 78% for human readings. Our previously developed AI method without synthetic data had an average sensitivity of 79%. The number of false positive lesions were slightly higher for the new AI model (average 3.3 instances per patient) compared to human readings and the previous AI model (average 2.8 instances per patient), while the number of false negative lesions was lower.

Conclusions

Creating synthetic lymph node metastases, as a form of data augmentation, on [18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT images improved the sensitivity of an AI model for detecting suspected lymph node metastases. However, the number of false positive lesions increased somewhat.

Abstract Image

查看原文本刊更多论文

在基于人工智能的 PSMA PET-CT 图像分析中使用合成淋巴结转移来增强数据，从而提高灵敏度。

背景：我们开发了一种基于人工智能（AI）的全自动检测前列腺癌患者前列腺特异性膜抗原（PSMA）（PSMA）正电子发射计算机断层扫描（PET-CT）（PET-CT）图像中疑似淋巴结转移的方法：方法：合成数据来自原始训练图像，并在其中添加了新的合成淋巴结转移灶。因此，先前研究中的原始训练集（n = 420）每增加一张原始图像（n = 840）就增加一张合成图像，用于训练人工智能模型。人工智能模型的性能与核医学医生和之前开发的人工智能模型进行了比较。人类阅读器被交替用作参考，并与另一种阅读器或人工智能模型进行比较：结果：新的人工智能模型检测淋巴结转移的平均灵敏度为 84%，而人类读数的灵敏度为 78%。我们之前开发的无合成数据人工智能方法的平均灵敏度为 79%。与人类读数和之前的人工智能模型（平均每位患者 2.8 个实例）相比，新的人工智能模型的假阳性病变数量略高（平均每位患者 3.3 个实例），而假阴性病变数量较低：结论：在[18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT 图像上创建合成淋巴结转移，作为一种数据增强形式，提高了人工智能模型检测疑似淋巴结转移的灵敏度。不过，假阳性病灶的数量有所增加。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Clinical Physiology and Functional Imaging 医学-生理学

CiteScore

3.40

自引率

5.60%

发文量

审稿时长

6-12 weeks

期刊介绍： Clinical Physiology and Functional Imaging publishes reports on clinical and experimental research pertinent to human physiology in health and disease. The scope of the Journal is very broad, covering all aspects of the regulatory system in the cardiovascular, renal and pulmonary systems with special emphasis on methodological aspects. The focus for the journal is, however, work that has potential clinical relevance. The Journal also features review articles on recent front-line research within these fields of interest. Covered by the major abstracting services including Current Contents and Science Citation Index, Clinical Physiology and Functional Imaging plays an important role in providing effective and productive communication among clinical physiologists world-wide.