Identifying epidermal growth factor receptor mutation status in patients with lung adenocarcinoma by three-dimensional convolutional neural networks

Xiong, Junfeng; Jia, Tian-Ying; Li, Xiaoyang; Wen, Yu; Xu, Zhiyong; Cai, Xu-Wei; Fu, Ling; Zhang, Jie; Qin, Binjie; Fu, Xiaolong

doi:10.1259/bjr.20180334

Cited by 19 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although Liu et al [27] and Rizzo et al [29] achieved relatively higher AUC scores of 0.709 and 0.82, respectively, their studies did not include independent testing groups which are essential to establishing the robustness of predictive models. Xiong et al [23] and Li et al [19] showed impressive results by using 3D deep learning model trained from scratch and achieved AUC scores of 0.776 and 0.809, respectively. Our model was trained and validated using the same patient cohort as Li's work [19] and, in an independent testing group, achieved a higher AUC score than any previously published study in this area.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Implementation Strategy of a CNN Model Affects the Performance of CT Assessment of EGFR Mutation Status in Lung Cancer Patients

Xiong

Lin

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

To compare CNN models implemented using different strategies in the CT assessment of EGFR mutation status in patients with lung adenocarcinoma. 1,010 consecutive lung adenocarcinoma patients with known EGFR mutation status were randomly divided into a training set (n = 810) and a testing set (n = 200). The CNN models were constructed based on ResNet-101 architecture but implemented using different strategies: dimension filters (2D/3D), input sizes (small/middle/large and their fusion), slicing methods (transverse plane only and arbitrary multi-view planes), and training approaches (from scratch and finetuning a pre-trained CNN). The performance of the CNN models was compared using AUC. The fusion approach yielded consistently better performance than other input sizes, although the effect often did not reach statistical significance. Multi-view slicing was significantly superior to the transverse method when fine-tuning a pre-trained 2D CNN but not a CNN trained from scratch. The 3D CNN was significantly better than the 2D transverse plane method but only marginally better than the multi-view slicing method when trained from scratch. The highest performance (AUC = 0.838) was achieved for the fine-tuned 2D CNN model when built using the fusion input size and multi-view slicing method. The assessment of EGFR mutation status in patients is more accurate when CNN models use more spatial information and are finetuned by transfer learning. Our finding of the implementation strategy of a CNN model could be a guide to other medical 3D images applications. Compared with other published studies which used medical images to identify EGFR mutation status, our CNN model achieved the best performance in the biggest patient cohort.INDEX TERMS CNN, EGFR, implementation strategy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…CT images from 1,010 consecutive patients with known EGFR status were retrospectively collected from 2013 to 2017, including 510 patients whose tumors were EGFR-mutated and 500 who were wild type [23]. Details are shown in TABLE 1.…”

Section: A Clinical Datamentioning

confidence: 99%

Implementation Strategy of a CNN Model Affects the Performance of CT Assessment of EGFR Mutation Status in Lung Cancer Patients

Xiong

Lin

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…This approach is a non-invasive and easy-toimplement deep learning method. Other studies (27)(28)(29) also show that deep learning models can identify gene mutations in lung cancer.…”

Section: Original Articlementioning

confidence: 94%

Multi-channel multi-task deep learning for predicting EGFR and KRAS mutations of non-small cell lung cancer on CT images

Dong

Hou

Yang

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Predicting the mutation statuses of 2 essential pathogenic genes [epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS)] in non-small cell lung cancer (NSCLC) based on CT is valuable for targeted therapy because it is a non-invasive and less costly method. Although deep learning technology has realized substantial computer vision achievements, CT imaging being used to predict gene mutations remains challenging due to small dataset limitations. Methods:We propose a multi-channel and multi-task deep learning (MMDL) model for the simultaneous prediction of EGFR and KRAS mutation statuses based on CT images. First, we decomposed each 3D lung nodule into 9 views. Then, we used the pre-trained inception-attention-resnet model for each view to learn the features of the nodules. By combining 9 inception-attention-resnet models to predict the types of gene mutations in lung nodules, the models were adaptively weighted, and the proposed MMDL model could be trained end-to-end. The MMDL model utilized multiple channels to characterize the nodule more comprehensively and integrate patient personal information into our learning process. Results:We trained the proposed MMDL model using a dataset of 363 patients collected by our partner hospital and conducted a multi-center validation on 162 patients in The Cancer Imaging Archive (TCIA) public dataset. The accuracies for the prediction of EGFR and KRAS mutations were, respectively, 79.43% and 72.25% in the training dataset and 75.06% and 69.64% in the validation dataset. Conclusions:The experimental results demonstrated that the proposed MMDL model outperformed the latest methods in predicting EGFR and KRAS mutations in NSCLC.

show abstract

“…4 Development and validation of novel technologies to longitudinally assess tumour dynamics relevant to targeted therapies With active anticipation of targeted therapy resistance emergence, advances in radiological assessment and 'liquid biopsy' (Bodei et al 2016, Khan et al 2016) may foster new approaches to monitor for early signs of not only the dichotomous outcomes of tumour relapse, but quantitative closeto-real-time changes in tumour sub-clone genetics, metabolic phenotypes or other plastic effects. In the realm of image analysis, radiomics and convolutional neural networks have both been utilised to predict with favourable degrees of accuracy the presence of targetable mutations on CT imaging (Xiong et al 2018, Jia et al 2019 and also grade in pancreatic NEN using CT imaging (Luo et al 2020), suggesting that they could function not only as part of diagnostic solutions (direct targeted genetic sequencing) but also as follow-up (reduction of likelihood of mutation presence, or emergence of another) -this will require an expanded cross-institutional collaboration to develop such models. Circulating tumour cells or transcripts may also be aspects of real-time monitoring for waxing/ waning therapy efficacy.…”

Section: Incorporate Genetics As Part Of a Multi-omics Perspective Wimentioning

confidence: 99%

Using genetics to inform the pharmacological targeting of neuroendocrine neoplasms

Clift

Frilling

2020

Endocrine-Related Cancer

View full text Add to dashboard Cite

Neuroendocrine neoplasms (NEN) are a class of tumours heterogeneous in terms of their anatomical sites of origin and clinical behaviour. Outdated perspectives of indolence have been superseded by appreciation for their myriad clinical challenges, such as the high rates of regional and distant metastases at initial diagnosis, lack of clarity on optimal treatment strategies/sequencing, and incompletely elucidated genetic/other pathophysiological drivers. The first randomised controlled trials in this arena were published approximately a decade ago – since then, increased understanding of the genetic drivers and signalling pathway perturbations in these tumours have suggested promise for precision therapy influenced by an individual tumour’s molecular sub-type, but this is yet to be realised for manifold reasons. In this article, the authors review the genetic landscapes as currently understood for selected forms of NEN and discuss the current and developing evidence to support the use of genetic information to influence therapy. They provide a critical assessment of the potential limitations of using such approaches, and also posit avenues for future developments in this arena.

show abstract

Identifying epidermal growth factor receptor mutation status in patients with lung adenocarcinoma by three-dimensional convolutional neural networks

Abstract: The CNN showed some diagnostic power and its performance could be further improved by increasing the training set, optimizing the network structure and training strategy. Medical image based CNN has the potential to reflect spatial heterogeneity.

Cited by 19 publications

References 18 publications

Implementation Strategy of a CNN Model Affects the Performance of CT Assessment of EGFR Mutation Status in Lung Cancer Patients

Implementation Strategy of a CNN Model Affects the Performance of CT Assessment of EGFR Mutation Status in Lung Cancer Patients

Multi-channel multi-task deep learning for predicting EGFR and KRAS mutations of non-small cell lung cancer on CT images

Using genetics to inform the pharmacological targeting of neuroendocrine neoplasms

Contact Info

Product

Resources

About