A radiogenomic dataset of non-small cell lung cancer

Bakr, Shaimaa; Gevaert, Olivier; Echegaray, Sebastian; Ayers, Kelsey; Zhou, Mu; Shafiq, Mājid; Zheng, Hong; Benson, Jalen; Zhang, Weiruo; Leung, Ann N.; Kadoch, Michel; Hoang, Chuong D.; Shrager, Joseph B.; Quon, Andrew; Rubin, Daniel L.; Plevritis, Sylvia K.; Napel, Sandy

doi:10.1038/sdata.2018.202

Cited by 195 publications

(166 citation statements)

References 48 publications

Supporting

Mentioning

165

Contrasting

Order By: Relevance

“…The NSCLC-Radiogenomics dataset 13,21,22 comprises data collected between 2008 and 2012 from a cohort of 211 patients with NSCLC referred for surgical treatment, being the only public dataset which comprehends information regarding the mutation status of lung cancer-related genes (EGFR, KRAS and ALK). It contains a set of Computed Tomography (CT) images stored in DICOM format.…”

Section: Datasetmentioning

confidence: 99%

“…Since the samples were retrospectively collected, the scanning protocol and scanning parameters were not standardised, thus slice thickness varied from 0.625 mm to 3 mm (median:1.5 mm) and the X-ray current from 124 mA to 699 mA (mean: 220 mA) at 80-140 kVp (mean: 120 kVp). The subjects were in supine position with their arms to the side, while the scans were acquired from the top of the lung to the adrenal gland during a single breath 13 . The nodules segmentation masks are stored as DICOM Segmentation Objects 37 and are represented as 3D binary images, where voxels belonging to the tumour ROI are represented by the value 1 and voxels outside the tumour ROI are represented by 0.…”

Section: Datasetmentioning

confidence: 99%

“…The semantic terms that were used to characterise the patients are common in radiology clinical practice and derive from descriptions in the radiology literature 13 . Definitions of some of the terms used in this description can be found in 43 .…”

Section: Semantic Featuresmentioning

confidence: 99%

“…Medical image analysis can help to solve these issues in two ways: by providing tools capable of measuring characteristics of the lung and, more specifically, the tumour; and with models that use only image features to obtain results through automatic or semi-automatic processes. These models can either use qualitative features, obtained by semantic annotations from human observers, or use quantitative features, obtained through a radiomic approach, which extracts features directly from the image 13 . Radiogenomics, a specific field within radiomics, is defined by the correlation between quantitative features, directly extracted from radiological images (imaging phenotype), and genetic information (genotype) 14 .…”

Section: Introductionmentioning

confidence: 99%

“…Our previous work was a preliminary study which used a public database 13,21,22 to create predictive models for EGFR and KRAS 20 . In the current work, we apply a more robust approach based on multiple splits to define the train and test sets, preventing an eventual bias from specific patients and effectively assessing the variance in the data.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

Pinheiro

Pereira

Dias

et al. 2019

Preprint

View full text Add to dashboard Cite

EGFR and KRAS are the most frequently mutated genes in lung cancer, being active research topics in targeted therapy. Biopsy is the traditional method to genetically characterise a tumour. However, it is a risky procedure, painful for the patient, and, occasionally, the tumour might be inaccessible. This work aims to study and debate the nature of the relationships between imaging phenotypes and lung cancer-related mutation status. Until now, the literature has failed to point to new research directions, mainly consisting of results-oriented works in a field where there is still not enough available data to train clinically viable models. We intend to open a discussion about critical points and to present new possibilities for future radiogenomics studies. We conducted high-dimensional data visualisation and developed classifiers, which allowed us to analyse the results for EGFR and KRAS biological markers according to different combinations of input features. We show that EGFR mutation status might be correlated to CT scans imaging phenotypes, however, the same does not seem to hold true for KRAS mutation status. Also, the experiments suggest that the best way to approach this problem is by combining nodule-related features with features from other lung structures. 2/103/10 7/10 is balanced individually for each fold using SMOTE-NC, avoiding data leakage. After parameter optimisation, probabilistic outputs of each model with optimal parameters were analysed using the AUC of Receiver Operating Characteristic (ROC). ROC is a probability curve and AUC represents degree or measure of separability, telling how much model is capable of distinguishing between classes. The ROC curve is plotted with True Positive Rate (TPR) against the False Positive Rate (FPR), usually with TPR on the y-axis and FPR on the x-axis. Experimental DesignWe designed four experiments in order to test and compare which type of input features allow to achieve better performance in gene mutation status prediction. We first trained a model that took nodule-related radiomic features as input. Then, for direct comparison purposes and to allow a modular evaluation, we split the semantic data into three parts: nodule, non-nodule and hybrid. The first one contains only nodular information, the second one contains only information external to the nodule and the third one is the combination of both. The split can be seen in detail in Table 2 of the supplementary material. 10/10

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

Section: Semantic Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

Pinheiro

Pereira

Dias

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

Improving reproducibility and performance of radiomics in low‐dose CT using cycle GANs

Chen

Wee

Dekker

et al. 2022

J Applied Clin Med Phys

View full text Add to dashboard Cite

Background As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low‐dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics’ reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect. Purpose In this article, we investigate the possibility of denoising low‐dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets. Methods and materials Two cycle GANs were trained: (1) from paired data, by simulating low‐dose CTs (i.e., introducing noise) from high‐dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice‐paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low‐dose CT images and (2) same‐day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder–decoder network (EDN) trained on simulated paired data. Results The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]). Conclusion The results show that cycle GANs trained on both simulated and real data can improve radiomics’ reproducibility and performance in low‐dose CT and achieve similar results compared to CGANs and EDNs.

show abstract

A deep learning‐based framework (Co‐ReTr) for auto‐segmentation of non‐small cell‐lung cancer in computed tomography images

Kunkyab,

Bahrami,

Zhang

et al. 2024

J Applied Clin Med Phys

View full text Add to dashboard Cite

PurposeDeep learning‐based auto‐segmentation algorithms can improve clinical workflow by defining accurate regions of interest while reducing manual labor. Over the past decade, convolutional neural networks (CNNs) have become prominent in medical image segmentation applications. However, CNNs have limitations in learning long‐range spatial dependencies due to the locality of the convolutional layers. Transformers were introduced to address this challenge. In transformers with self‐attention mechanism, even the first layer of information processing makes connections between distant image locations. Our paper presents a novel framework that bridges these two unique techniques, CNNs and transformers, to segment the gross tumor volume (GTV) accurately and efficiently in computed tomography (CT) images of non‐small cell‐lung cancer (NSCLC) patients.MethodsUnder this framework, input of multiple resolution images was used with multi‐depth backbones to retain the benefits of high‐resolution and low‐resolution images in the deep learning architecture. Furthermore, a deformable transformer was utilized to learn the long‐range dependency on the extracted features. To reduce computational complexity and to efficiently process multi‐scale, multi‐depth, high‐resolution 3D images, this transformer pays attention to small key positions, which were identified by a self‐attention mechanism. We evaluated the performance of the proposed framework on a NSCLC dataset which contains 563 training images and 113 test images. Our novel deep learning algorithm was benchmarked against five other similar deep learning models.ResultsThe experimental results indicate that our proposed framework outperforms other CNN‐based, transformer‐based, and hybrid methods in terms of Dice score (0.92) and Hausdorff Distance (1.33). Therefore, our proposed model could potentially improve the efficiency of auto‐segmentation of early‐stage NSCLC during the clinical workflow. This type of framework may potentially facilitate online adaptive radiotherapy, where an efficient auto‐segmentation workflow is required.ConclusionsOur deep learning framework, based on CNN and transformer, performs auto‐segmentation efficiently and could potentially assist clinical radiotherapy workflow.

show abstract

A radiogenomic dataset of non-small cell lung cancer

Cited by 195 publications

References 48 publications

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS

Improving reproducibility and performance of radiomics in low‐dose CT using cycle GANs

A deep learning‐based framework (Co‐ReTr) for auto‐segmentation of non‐small cell‐lung cancer in computed tomography images

Contact Info

Product

Resources

About