Deep CNN Model Using CT Radiomics Feature Mapping Recognizes EGFR Gene Mutation Status of Lung Adenocarcinoma

Brain metastasis magnetic resonance imaging-based deep learning for predicting epidermal growth factor receptor (EGFR) mutation and subtypes in metastatic non-small cell lung cancer

Background

The preoperative identification of epidermal growth factor receptor (EGFR) mutations and subtypes based on magnetic resonance imaging (MRI) of brain metastases (BM) is necessary to facilitate individualized therapy. This study aimed to develop a deep learning model to preoperatively detect EGFR mutations and identify the location of EGFR mutations in patients with non-small cell lung cancer (NSCLC) and BM.

Methods

We included 160 and 72 patients who underwent contrast-enhanced T1-weighted (T1w-CE) and T2-weighted (T2W) MRI at Liaoning Cancer Hospital and Institute (center 1) and Shengjing Hospital of China Medical University (center 2) to form a training cohort and an external validation cohort, respectively. A multiscale feature fusion network (MSF-Net) was developed by adaptively integrating features based on different stages of residual network (ResNet) 50 and by introducing channel and spatial attention modules. The external validation set from center 2 was used to assess the performance of MSF-Net and to compare it with that of handcrafted radiomics features. Receiver operating characteristic (ROC) curves, accuracy, precision, recall, and F1-score were used to evaluate the effectiveness of the models. Gradient-weighted class activation mapping (Grad-CAM) was used to demonstrate the attention of the MSF-Net model.

Results

The developed MSF-Net generated a better diagnostic performance than did the handcrafted radiomics in terms of the microaveraged area under the curve (AUC) (MSF-Net: 0.91; radiomics: 0.80) and macroaveraged AUC (MSF-Net: 0.90; radiomics: 0.81) for predicting EGFR mutations and subtypes.

Conclusions

This study provides an end-to-end and noninvasive imaging tool for the preoperative prediction of EGFR mutation status and subtypes based on BM, which may be helpful for facilitating individualized clinical treatment plans.

GMILT: A Novel Transformer Network That Can Noninvasively Predict EGFR Mutation Status

Noninvasively and accurately predicting the epidermal growth factor receptor (EGFR) mutation status is a clinically vital problem. Moreover, further identifying the most suspicious area related to the EGFR mutation status can guide the biopsy to avoid false negatives. Deep learning methods based on computed tomography (CT) images may improve the noninvasive prediction of EGFR mutation status and potentially help clinicians guide biopsies by visual methods. Inspired by the potential inherent links between EGFR mutation status and invasiveness information, we hypothesized that the predictive performance of a deep learning network can be improved through extra utilization of the invasiveness information. Here, we created a novel explainable transformer network for EGFR classification named gated multiple instance learning transformer (GMILT) by integrating multi-instance learning and discriminative weakly supervised feature learning. Pathological invasiveness information was first introduced into the multitask model as embeddings. GMILT was trained and validated on a total of 512 patients with adenocarcinoma and tested on three datasets (the internal test dataset, the external test dataset, and The Cancer Imaging Archive (TCIA) public dataset). The performance (area under the curve (AUC) =0.772 on the internal test dataset) of GMILT exceeded that of previously published methods and radiomics-based methods (i.e., random forest and support vector machine) and attained a preferable generalization ability (AUC =0.856 in the TCIA test dataset and AUC =0.756 in the external dataset). A diameter-based subgroup analysis further verified the efficiency of our model (most of the AUCs exceeded 0.772) to noninvasively predict EGFR mutation status from computed tomography (CT) images. In addition, because our method also identified the "core area" of the most suspicious area related to the EGFR mutation status, it has the potential ability to guide biopsies.

A Multichannel CT and Radiomics-Guided CNN-ViT (RadCT-CNNViT) Ensemble Network for Diagnosis of Pulmonary Sarcoidosis

Pulmonary sarcoidosis is a multisystem granulomatous interstitial lung disease (ILD) with a variable presentation and prognosis. The early accurate detection of pulmonary sarcoidosis may prevent progression to pulmonary fibrosis, a serious and potentially life-threatening form of the disease. However, the lack of a gold-standard diagnostic test and specific radiographic findings poses challenges in diagnosing pulmonary sarcoidosis. Chest computed tomography (CT) imaging is commonly used but requires expert, chest-trained radiologists to differentiate pulmonary sarcoidosis from lung malignancies, infections, and other ILDs. In this work, we develop a multichannel, CT and radiomics-guided ensemble network (RadCT-CNNViT) with visual explainability for pulmonary sarcoidosis vs. lung cancer (LCa) classification using chest CT images. We leverage CT and hand-crafted radiomics features as input channels, and a 3D convolutional neural network (CNN) and vision transformer (ViT) ensemble network for feature extraction and fusion before a classification head. The 3D CNN sub-network captures the localized spatial information of lesions, while the ViT sub-network captures long-range, global dependencies between features. Through multichannel input and feature fusion, our model achieves the highest performance with accuracy, sensitivity, specificity, precision, F1-score, and combined AUC of 0.93 ± 0.04, 0.94 ± 0.04, 0.93 ± 0.08, 0.95 ± 0.05, 0.94 ± 0.04, and 0.97, respectively, in a five-fold cross-validation study with pulmonary sarcoidosis (n = 126) and LCa (n = 93) cases. A detailed ablation study showing the impact of CNN + ViT compared to CNN or ViT alone, and CT + radiomics input, compared to CT or radiomics alone, is also presented in this work. Overall, the AI model developed in this work offers promising potential for triaging the pulmonary sarcoidosis patients for timely diagnosis and treatment from chest CT.

Deep Learning Radiomics Model of Dynamic Contrast-Enhanced MRI for Evaluating Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma

BACKGROUND

Vessels encapsulating tumor cluster (VETC) is a critical prognostic factor and therapeutic predictor of hepatocellular carcinoma (HCC). However, noninvasive evaluation of VETC remains challenging.

PURPOSE

To develop and validate a deep learning radiomic (DLR) model of dynamic contrast-enhanced MRI (DCE-MRI) for the preoperative discrimination of VETC and prognosis of HCC.

STUDY TYPE

Retrospective.

POPULATION

A total of 221 patients with histologically confirmed HCC and stratified this cohort into training set (n = 154) and time-independent validation set (n = 67).

FIELD STRENGTH/SEQUENCE

A 1.5 T and 3.0 T; DCE imaging with T1-weighted three-dimensional fast spoiled gradient echo.

ASSESSMENT

Histological specimens were used to evaluate VETC status. VETC+ cases had a visible pattern (≥5% tumor area), while cases without any pattern were VETC-. The regions of intratumor and peritumor were segmented manually in the arterial, portal-venous and delayed phase (AP, PP, and DP, respectively) of DCE-MRI and reproducibility of segmentation was evaluated. Deep neural network and machine learning (ML) classifiers (logistic regression, decision tree, random forest, SVM, KNN, and Bayes) were used to develop nine DLR, 54 ML and clinical-radiological (CR) models based on AP, PP, and DP of DCE-MRI for evaluating VETC status and association with recurrence.

STATISTICAL TESTS

The Fleiss kappa, intraclass correlation coefficient, receiver operating characteristic curve, area under the curve (AUC), Delong test and Kaplan-Meier survival analysis. P value <0.05 was considered as statistical significance.

RESULTS

Pathological VETC+ were confirmed in 68 patients (training set: 46, validation set: 22). In the validation set, DLR model based on peritumor PP (peri-PP) phase had the best performance (AUC: 0.844) in comparison to CR (AUC: 0.591) and ML (AUC: 0.672) models. Significant differences in recurrence rates between peri-PP DLR model-predicted VETC+ and VETC- status were found.

DATA CONCLUSIONS

The DLR model provides a noninvasive method to discriminate VETC status and prognosis of HCC patients preoperatively.

EVIDENCE LEVEL

4.

TECHNICAL EFFICACY

Stage 2.

Hybrid deep multi-task learning radiomics approach for predicting EGFR mutation status of non-small cell lung cancer in CT images

Objective.Epidermal growth factor receptor (EGFR) mutation genotyping plays a pivotal role in targeted therapy for non-small cell lung cancer (NSCLC). We aimed to develop a computed tomography (CT) image-based hybrid deep radiomics model to predict EGFR mutation status in NSCLC and investigate the correlations between deep image and quantitative radiomics features.Approach.First, we retrospectively enrolled 818 patients from our centre and 131 patients from The Cancer Imaging Archive database to establish a training cohort (N= 654), an independent internal validation cohort (N= 164) and an external validation cohort (N= 131). Second, to predict EGFR mutation status, we developed three CT image-based models, namely, a multi-task deep neural network (DNN), a radiomics model and a feature fusion model. Third, we proposed a hybrid loss function to train the DNN model. Finally, to evaluate the model performance, we computed the areas under the receiver operating characteristic curves (AUCs) and decision curve analysis curves of the models.Main results.For the two validation cohorts, the feature fusion model achieved AUC values of 0.86 ± 0.03 and 0.80 ± 0.05, which were significantly higher than those of the single-task DNN and radiomics models (allP< 0.05). There was no significant difference between the feature fusion and the multi-task DNN models (P> 0.8). The binary prediction scores showed excellent prognostic value in predicting disease-free survival (P= 0.02) and overall survival (P< 0.005) for validation cohort 2.Significance.The results demonstrate that (1) the feature fusion and multi-task DNN models achieve significantly higher performance than that of the conventional radiomics and single-task DNN models, (2) the feature fusion model can decode the imaging phenotypes representing NSCLC heterogeneity related to both EGFR mutation and patient NSCLC prognosis, and (3) high correlations exist between some deep image and radiomics features.

AI/ML advances in non-small cell lung cancer biomarker discovery

Lung cancer is the leading cause of cancer deaths among both men and women, representing approximately 25% of cancer fatalities each year. The treatment landscape for non-small cell lung cancer (NSCLC) is rapidly evolving due to the progress made in biomarker-driven targeted therapies. While advancements in targeted treatments have improved survival rates for NSCLC patients with actionable biomarkers, long-term survival remains low, with an overall 5-year relative survival rate below 20%. Artificial intelligence/machine learning (AI/ML) algorithms have shown promise in biomarker discovery, yet NSCLC-specific studies capturing the clinical challenges targeted and emerging patterns identified using AI/ML approaches are lacking. Here, we employed a text-mining approach and identified 215 studies that reported potential biomarkers of NSCLC using AI/ML algorithms. We catalogued these studies with respect to BEST (Biomarkers, EndpointS, and other Tools) biomarker sub-types and summarized emerging patterns and trends in AI/ML-driven NSCLC biomarker discovery. We anticipate that our comprehensive review will contribute to the current understanding of AI/ML advances in NSCLC biomarker research and provide an important catalogue that may facilitate clinical adoption of AI/ML-derived biomarkers.

A review of radiomics and genomics applications in cancers: the way towards precision medicine

The application of radiogenomics in oncology has great prospects in precision medicine. Radiogenomics combines large volumes of radiomic features from medical digital images, genetic data from high-throughput sequencing, and clinical-epidemiological data into mathematical modelling. The amalgamation of radiomics and genomics provides an approach to better study the molecular mechanism of tumour pathogenesis, as well as new evidence-supporting strategies to identify the characteristics of cancer patients, make clinical decisions by predicting prognosis, and improve the development of individualized treatment guidance. In this review, we summarized recent research on radiogenomics applications in solid cancers and presented the challenges impeding the adoption of radiomics in clinical practice. More standard guidelines are required to normalize radiomics into reproducible and convincible analyses and develop it as a mature field.

A deep learning algorithm to quantify AVF stenosis and predict 6-month primary patency: a pilot study

Background

A deep convolutional neural network (DCNN) model that predicts the degree of arteriovenous fistula (AVF) stenosis and 6-month primary patency (PP) based on AVF shunt sounds was developed, and was compared with various machine learning (ML) models trained on patients' clinical data.

Methods

Forty dysfunctional AVF patients were recruited prospectively, and AVF shunt sounds were recorded before and after percutaneous transluminal angioplasty using a wireless stethoscope. The audio files were converted to melspectrograms to predict the degree of AVF stenosis and 6-month PP. The diagnostic performance of the melspectrogram-based DCNN model (ResNet50) was compared with that of other ML models [i.e. logistic regression (LR), decision tree (DT) and support vector machine (SVM)], as well as the DCNN model (ResNet50) trained on patients' clinical data.

Results

Melspectrograms qualitatively reflected the degree of AVF stenosis by exhibiting a greater amplitude at mid-to-high frequency in the systolic phase with a more severe degree of stenosis, corresponding to a high-pitched bruit. The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis. In predicting the 6-month PP, the area under the receiver operating characteristic curve of the melspectrogram-based DCNN model (ResNet50) (≥0.870) outperformed that of various ML models based on clinical data (LR, 0.783; DT, 0.766; SVM, 0.733) and that of the spiral-matrix DCNN model (0.828).

Conclusion

The proposed melspectrogram-based DCNN model successfully predicted the degree of AVF stenosis and outperformed ML-based clinical models in predicting 6-month PP.

Delta radiomics model for the prediction of progression-free survival time in advanced non-small-cell lung cancer patients after immunotherapy

Objective

To assess the validity of pre- and posttreatment computed tomography (CT)-based radiomics signatures and delta radiomics signatures for predicting progression-free survival (PFS) in stage III-IV non-small-cell lung cancer (NSCLC) patients after immune checkpoint inhibitor (ICI) therapy.

Methods

Quantitative image features of the largest primary lung tumours were extracted on CT-enhanced imaging at baseline (time point 0, TP0) and after the 2^nd-3^rd immunotherapy cycles (time point 1, TP1). The critical features were selected to construct TP0, TP1 and delta radiomics signatures for the risk stratification of patient survival after ICI treatment. In addition, a prediction model integrating the clinicopathologic risk characteristics and phenotypic signature was developed for the prediction of PFS.

Results

The C-index of TP0, TP1 and delta radiomics models in the training and validation cohort were 0.64, 0.75, 0.80, and 0.61, 0.68, 0.78, respectively. The delta radiomics score exhibited good accuracy for distinguishing patients with slow and rapid progression to ICI treatment. The predictive accuracy of the combined prediction model was higher than that of the clinical prediction model in both training and validation sets (P<0.05), with a C-index of 0.83 and 0.70, respectively. Additionally, the delta radiomics model (C-index of 0.86) had a higher predictive accuracy compared to PD-L1 expression (C-index of 0.50) (P<0.0001).

Conclusions

The combined prediction model including clinicopathologic characteristics (tumour anatomical classification and brain metastasis) and the delta radiomics signature could achieve the individualized prediction of PFS in ICIs-treated NSCLC patients.

Using combined CT-clinical radiomics models to identify epidermal growth factor receptor mutation subtypes in lung adenocarcinoma

Background

To investigate the value of computed tomography (CT)-based radiomics signatures in combination with clinical and CT morphological features to identify epidermal growth factor receptor (EGFR)-mutation subtypes in lung adenocarcinoma (LADC).

Methods

From February 2012 to October 2019, 608 patients were confirmed with LADC and underwent chest CT scans. Among them, 307 (50.5%) patients had a positive EGFR-mutation and 301 (49.5%) had a negative EGFR-mutation. Of the EGFR-mutant patients, 114 (37.1%) had a 19del -mutation, 155 (50.5%) had a L858R-mutation, and 38 (12.4%) had other rare mutations. Three combined models were generated by incorporating radiomics signatures, clinical, and CT morphological features to predict EGFR-mutation status. Patients were randomly split into training and testing cohorts, 80% and 20%, respectively. Model 1 was used to predict positive and negative EGFR-mutation, model 2 was used to predict 19del and non-19del mutations, and model 3 was used to predict L858R and non-L858R mutations. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate their performance.

Results

For the three models, model 1 had AUC values of 0.969 and 0.886 in the training and validation cohorts, respectively. Model 2 had AUC values of 0.999 and 0.847 in the training and validation cohorts, respectively. Model 3 had AUC values of 0.984 and 0.806 in the training and validation cohorts, respectively.

Conclusion

Combined models that incorporate radiomics signature, clinical, and CT morphological features may serve as an auxiliary tool to predict EGFR-mutation subtypes and contribute to individualized treatment for patients with LADC.

Predicting chemotherapy response in non-small-cell lung cancer via computed tomography radiomic features: Peritumoral, intratumoral, or combined?

Purpose

This study aims to evaluate the ability of peritumoral, intratumoral, or combined computed tomography (CT) radiomic features to predict chemotherapy response in non-small cell lung cancer (NSCLC).

Methods

After excluding subjects with incomplete data or other types of treatments, 272 (Dataset 1) and 43 (Dataset 2, external validation) NSCLC patients who were only treated with chemotherapy as the first-line treatment were enrolled between 2015 and 2019. All patients were divided into response and nonresponse based on the response evaluation criteria in solid tumors, version 1.1. By using 3D slicer and morphological operations in python, the intra- and peritumoral regions of lung tumors were segmented from pre-treatment CT images (unenhanced) and confirmed by two experienced radiologists. Then radiomic features (the first order, texture, shape, et al.) were extracted from the above regions of interest. The models were trained and tested in Dataset 1 and further validated in Dataset 2. The performance of models was compared using the area under curve (AUC), confusion matrix, accuracy, precision, recall, and F1-score.

Results

The radiomic model using features from the peritumoral region of 0–3 mm outperformed that using features from 3–6, 6–9, 9–12 mm peritumoral region, and intratumoral region (AUC: 0.95 versus 0.87, 0.86, 0.85, and 0.88). By the fusion of features from 0–3 and 3–6 mm peritumoral regions, the logistic regression model achieved the best performance, with an AUC of 0.97. This model achieved an AUC of 0.85 in the external cohort. Moreover, among the 20 selected features, seven features differed significantly between the two groups (p < 0.05).

Conclusions

CT radiomic features from both the peri- and intratumoral regions can predict chemotherapy response in NSCLC using machine learning models. Combined features from two peritumoral regions yielded better predictions.

Multi-scale segmentation squeeze-and-excitation UNet with conditional random field for segmenting lung tumor from CT images

BACKGROUND AND OBJECTIVE

Lung cancer counts among diseases with the highest global morbidity and mortality rates. The automatic segmentation of lung tumors from CT images is of vast significance. However, the segmentation faces several challenges, including variable shapes and different sizes, as well as complicated surrounding tissues.

METHODS

We propose a multi-scale segmentation squeeze-and-excitation UNet with a conditional random field (M-SegSEUNet-CRF) to automatically segment lung tumors from CT images. M-SegSEUNet-CRF employs a multi-scale strategy to solve the problem of variable tumor size. Through the spatially adaptive attention mechanism, the segmentation SE blocks embedded in 3D UNet are utilized to highlight tumor regions. The dense connected CRF framework is further added to delineate tumor boundaries at a detailed level. In total, 759 CT scans of patients with lung cancer were used to train and evaluate the M-SegSEUNet-CRF model (456 for training, 152 for validation, and 151 for test). Meanwhile, the public NSCLC-Radiomics and LIDC datasets have been utilized to validate the generalization of the proposed method. The role of different modules in the M-SegSEUNet-CRF model is analyzed by the ablation experiments, and the performance is compared with that of UNet, its variants and other state-of-the-art models.

RESULTS

M-SegSEUNet-CRF can achieve a Dice coefficient of 0.851 ± 0.071, intersection over union (IoU) of 0.747 ± 0.102, sensitivity of 0.827 ± 0.108, and positive predictive value (PPV) of 0.900 ± 0.107. Without a multi-scale strategy, the Dice coefficient drops to 0.820 ± 0.115; without CRF, it drops to 0.842 ± 0.082, and without both, it drops to 0.806 ± 0.120. M-SegSEUNet-CRF presented a higher Dice coefficient than 3D UNet (0.782 ± 0.115) and its variants (ResUNet, 0.797 ± 0.132; DenseUNet, 0.792 ± 0.111, and UNETR, 0.794 ± 0.130). Although the performance slightly declines with the decrease in tumor volume, M-SegSEUNet-CRF exhibits more obvious advantages than the other comparative models.

CONCLUSIONS

Our M-SegSEUNet-CRF model improves the segmentation ability of UNet through the multi-scale strategy and spatially adaptive attention mechanism. The CRF enables a more precise delineation of tumor boundaries. The M-SegSEUNet-CRF model integrates these characteristics and demonstrates outstanding performance in the task of lung tumor segmentation. It can furthermore be extended to deal with other segmentation problems in the medical imaging field.

PET/CT Radiomic Features: A Potential Biomarker for EGFR Mutation Status and Survival Outcome Prediction in NSCLC Patients Treated With TKIs

Backgrounds

Epidermal growth factor receptor (EGFR) mutation profiles play a vital role in treatment strategy decisions for non–small cell lung cancer (NSCLC). The purpose of this study was to evaluate the predictive efficacy of baseline ¹⁸F-FDG PET/CT-based radiomics analysis for EGFR mutation status, mutation site, and the survival benefit of targeted therapy.

Methods

A sum of 313 NSCLC patients with pre-treatment ¹⁸F-FDG PET/CT scans and genetic mutations detection were retrospectively studied. Clinical and PET metabolic parameters were incorporated into independent predictors of determining mutation status and mutation site. The dataset was randomly allocated into the training and the validation sets in a 7:3 ratio. Three-dimensional (3D) radiomics features were extracted from each PET- and CT-volume of interests (VOI) singularly, and then a radiomics signature (RS) associated with EGFR mutation profiles is built by feature selection. Three different prediction models based on support vector machine (SVM), decision tree (DT), and random forest (RF) classifiers were established. Furthermore, nomograms for estimation of overall survival (OS) and progression-free survival (PFS) were established by integrating PET/CT radiomics score (Rad-score), metabolic parameters, and clinical factors. Predictive performance was assessed by the receiver operating characteristic (ROC) analysis and the calibration curve analysis. The decision curve analysis (DCA) was applied to estimate and compare the clinical usefulness of nomograms.

Results

Three hundred thirteen NSCLC patients were classified into a training set (n=218) and a validation set (n=95). Multivariate analysis demonstrated that SUVmax and sex were independent indicators of EGFR mutation status and mutation site. Eight CT-derived RS, six PET-derived RS, and two clinical factors were retained to develop integrated models, which exhibited excellent ability to distinguish between EGFR wild type (EGFR-WT), EGFR 19 mutation type (EGFR-19-MT), and EGFR 21 mutation type (EGFR-21-MT). The SVM model outperformed the RF model and the DT model, yielding training area under the curves (AUC) of EGFR-WT, EGFR-19-WT, and EGFR-21-WT, with 0.881, 0.851, and 0.849, respectively, and validation AUCs of 0.926, 0.805 and 0.859, respectively. For prediction of OS, the integrated nomogram is superior to the clinical nomogram and the radiomics nomogram, with C-indexes of 0.80 in the training set and 0.83 in the validation set, respectively.

Conclusions

The PET/CT-based radiomics analysis might provide a novel approach to predict EGFR mutation status and mutation site in NSCLC patients and could serve as useful predictors for the patients’ survival outcome of targeted therapy in clinical practice.

Using an Improved Residual Network to Identify PIK3CA Mutation Status in Breast Cancer on Ultrasound Image

Background

The detection of phosphatidylinositol-3 kinase catalytic alpha (PIK3CA) gene mutations in breast cancer is a key step to design personalizing an optimal treatment strategy. Traditional genetic testing methods are invasive and time-consuming. It is urgent to find a non-invasive method to estimate the PIK3CA mutation status. Ultrasound (US), one of the most common methods for breast cancer screening, has the advantages of being non-invasive, fast imaging, and inexpensive. In this study, we propose to develop a deep convolutional neural network (DCNN) to identify PIK3CA mutations in breast cancer based on US images.

Materials and Methods

We retrospectively collected 312 patients with pathologically confirmed breast cancer who underwent genetic testing. All US images (n=800) of breast cancer patients were collected and divided into the training set (n=600) and test set (n=200). A DCNN-Improved Residual Network (ImResNet) was designed to identify the PIK3CA mutations. We also compared the ImResNet model with the original ResNet50 model, classical machine learning models, and other deep learning models.

Results

The proposed ImResNet model has the ability to identify PIK3CA mutations in breast cancer based on US images. Notably, our ImResNet model outperforms the original ResNet50, DenseNet201, Xception, MobileNetv2, and two machine learning models (SVM and KNN), with an average area under the curve (AUC) of 0.775. Moreover, the overall accuracy, average precision, recall rate, and F1-score of the ImResNet model achieved 74.50%, 74.17%, 73.35%, and 73.76%, respectively. All of these measures were significantly higher than other models.

Conclusion

The ImResNet model gives an encouraging performance in predicting PIK3CA mutations based on breast US images, providing a new method for noninvasive gene prediction. In addition, this model could provide the basis for clinical adjustments and precision treatment.

PET/CT Based EGFR Mutation Status Classification of NSCLC Using Deep Learning Features and Radiomics Features

Purpose: This study aimed to compare the performance of radiomics and deep learning in predicting EGFR mutation status in patients with lung cancer based on PET/CT images, and tried to explore a model with excellent prediction performance to accurately predict EGFR mutation status in patients with non-small cell lung cancer (NSCLC). Method: PET/CT images of 194 NSCLC patients from Xijing Hospital were collected and divided into a training set and a validation set according to the ratio of 7:3. Statistics were made on patients' clinical characteristics, and a large number of features were extracted based on their PET/CT images (4306 radiomics features and 2048 deep learning features per person) with the pyradiomics toolkit and 3D convolutional neural network. Then a radiomics model (RM), a deep learning model (DLM), and a hybrid model (HM) were established. The performance of the three models was compared by receiver operating characteristic (ROC) curves, sensitivity, specificity, accuracy, calibration curves, and decision curves. In addition, a nomogram based on a deep learning score (DS) and the most significant clinical characteristic was plotted. Result: In the training set composed of 138 patients (64 with EGFR mutation and 74 without EGFR mutation), the area under the ROC curve (AUC) of HM (0.91, 95% CI: 0.86-0.96) was higher than that of RM (0.82, 95% CI: 0.75-0.89) and DLM (0.90, 95% CI: 0.85-0.95). In the validation set composed of 57 patients (32 with EGFR mutation and 25 without EGFR mutation), the AUC of HM (0.85, 95% CI: 0.77-0.93) was also higher than that of RM (0.68, 95% CI: 0.52-0.84) and DLM (0.79, 95% CI: 0.67-0.91). In all, HM achieved better diagnostic performance in predicting EGFR mutation status in NSCLC patients than two other models. Conclusion: Our study showed that the deep learning model based on PET/CT images had better performance than radiomics model in diagnosing EGFR mutation status of NSCLC patients based on PET/CT images. Combined with the most statistically significant clinical characteristic (smoking) and deep learning features, our hybrid model had better performance in predicting EGFR mutation types of patients than two other models, which could enable NSCLC patients to choose more personalized treatment schemes.

Machine Learning-Based Radiomics for Prediction of Epidermal Growth Factor Receptor Mutations in Lung Adenocarcinoma

Identifying an epidermal growth factor receptor (EGFR) mutation is important because EGFR tyrosine kinase inhibitors are the first-line treatment of choice for patients with EGFR mutation-positive lung adenocarcinomas (LUAC). This study is aimed at developing and validating a radiomics-based machine learning (ML) approach to identify EGFR mutations in patients with LUAC. We retrospectively collected data from 201 patients with positive EGFR mutation LUAC (140 in the training cohort and 61 in the validation cohort). We extracted 1316 radiomics features from preprocessed CT images and selected 14 radiomics features and 1 clinical feature which were most relevant to mutations through filter method. Subsequently, we built models using 7 ML approaches and established the receiver operating characteristic (ROC) curve to assess the discriminating performance of these models. In terms of predicting EGFR mutation, the model derived from radiomics features and combined models (radiomics features and relevant clinical factors) had an AUC of 0.79 (95% confidence interval (CI): 0.77-0.82), 0.86 (0.87-0.88), respectively. Our study offers a radiomics-based ML model using filter methods to detect the EGFR mutation in patients with LUAC. This convenient and low-cost method may be of help to noninvasively identify patients before obtaining tumor sample for molecule testing.

Development and validation of novel radiomics-based nomograms for the prediction of EGFR mutations and Ki-67 proliferation index in non-small cell lung cancer

BACKGROUND

We developed and validated novel radiomics-based nomograms to identify epidermal growth factor receptor (EGFR) mutations and the Ki-67 proliferation index of non-small cell lung cancer.

METHODS

We enrolled 132 patients with histologically verified non-small cell lung cancer from four hospital institutions who underwent computed tomography (CT) scans. EGFR mutations and the Ki-67 proliferation index were measured from tumor tissues. A total of 1,287 radiomic features were extracted, and a three-stage feature selection method was implemented to acquire the most valuable radiomic features. Finally, the radiomic scores and nomograms of the two tasks were established and tested. Receiver operating characteristic curves, calibration curves, and decision curves were used to evaluate their prediction performance and clinical utility.

RESULTS

In task [1], smoking status and histological type were significantly associated with EGFR mutations. After feature selection, 10 features were used to establish radiomic score, which showed good performance [area under the curve (AUC) =0.800] in the validation cohort. The radiomic nomogram had an AUC of 0.798 (95% CI: 0.664 to 0.931) with a C-index of 0.798 in the validation cohort. In task [2], gender, smoking status, histological type, and stage showed a significant correlation with Ki-67 proliferation index expression. A total of 28 features were selected to develop a radiomic score, with an AUC of 0.820 in the validation cohort. The final nomogram showed an AUC of 0.828 (95% CI: 0.703 to 0.953) with a C-index of 0.828 in the validation cohort.

CONCLUSIONS

EGFR mutations and Ki-67 proliferation index in non-small cell lung cancer can be predicted efficiently by the novel radiomic scores and nomograms.

Towards Machine Learning-Aided Lung Cancer Clinical Routines: Approaches and Open Challenges

Advancements in the development of computer-aided decision (CAD) systems for clinical routines provide unquestionable benefits in connecting human medical expertise with machine intelligence, to achieve better quality healthcare. Considering the large number of incidences and mortality numbers associated with lung cancer, there is a need for the most accurate clinical procedures; thus, the possibility of using artificial intelligence (AI) tools for decision support is becoming a closer reality. At any stage of the lung cancer clinical pathway, specific obstacles are identified and "motivate" the application of innovative AI solutions. This work provides a comprehensive review of the most recent research dedicated toward the development of CAD tools using computed tomography images for lung cancer-related tasks. We discuss the major challenges and provide critical perspectives on future directions. Although we focus on lung cancer in this review, we also provide a more clear definition of the path used to integrate AI in healthcare, emphasizing fundamental research points that are crucial for overcoming current barriers.

Three-Dimensional Convolutional Neural Network-Based Prediction of Epidermal Growth Factor Receptor Expression Status in Patients With Non-Small Cell Lung Cancer

Objectives

EGFR testing is a mandatory step before targeted therapy for non-small cell lung cancer patients. Combining some quantifiable features to establish a predictive model of EGFR expression status, break the limitations of tissue biopsy.

Materials and Methods

We retrospectively analyzed 1074 patients of non-small cell lung cancer with complete reports of EGFR gene testing. Then manually segmented VOI, captured the clinicopathological features, analyzed traditional radiology features, and extracted radiomic, and deep learning features. The cases were randomly divided into training and test set. We carried out feature screening; then applied the light GBM algorithm, Resnet-101 algorithm, logistic regression to develop sole models, and fused models to predict EGFR mutation conditions. The efficiency of models was evaluated by ROC and PRC curves.

Results

We successfully established Model_clinical, Model_radiomic, Model_CNN (based on clinical-radiology, radiomic and deep learning features respectively), Model_{radiomic+clinical} (combining clinical-radiology and radiomic features), and Model_{CNN+radiomic+clinical} (combining clinical-radiology, radiomic, and deep learning features). Among the prediction models, Model_{CNN+radiomic+clinical} showed the highest performance, followed by Model_CNN, and then Model_{radiomic+clinical}. All three models were able to accurately predict EGFR mutation with AUC values of 0.751, 0.738, and 0.684, respectively. There was no significant difference in the AUC values between Model_{CNN+radiomic+clinical} and Model_CNN. Further analysis showed that Model_{CNN+radiomic+clinical} effectively improved the efficacy of Model_{radiomic+clinical} and showed better efficacy than Model_CNN. The inclusion of clinical-radiology features did not effectively improve the efficacy of Model_radiomic.

Conclusions

Either deep learning or radiomic signature-based models can provide a fairly accurate non-invasive prediction of EGFR expression status. The model combined both features effectively enhanced the performance of radiomic models and provided marginal enhancement to deep learning models. Collectively, fusion models offer a novel and more reliable way of providing the efficacy of currently developed prediction models, and have far-reaching potential for the optimization of noninvasive EGFR mutation status prediction methods.

Molecular typing of lung adenocarcinoma with computed tomography and CT image-based radiomics: a narrative review of research progress and prospects

Objective

The purpose of this paper was to perform a narrative review of current research evidence on conventional computed tomography (CT) imaging features and CT image-based radiomic features for predicting gene mutations in lung adenocarcinoma and discuss how to translate the research findings to guide future practice.

Background

Lung cancer, especially lung adenocarcinoma, is the leading cause of cancer-related deaths. With advances in the diagnosis and treatment of lung adenocarcinoma with the emergence of molecular testing, the prediction of oncogenes and even drug resistance gene mutations have become key to individualized and precise clinical treatment in order to prolong survival and improve quality of life. The progress of imageological examination includes the development of CT and radiomics are promising quantitative methods for predicting different gene mutations in lung adenocarcinoma, especially common mutations, such as epidermal growth factor receptor (EGFR) mutation, anaplastic lymphoma kinase (ALK) mutation and Kirsten rat sarcoma viral oncogene (KRAS) mutation.

Methods

The PubMed electronic database was searched along with a set of terms specific to lung adenocarcinoma, radiomics (including texture analysis), CT, computed tomography, EGFR, ALK, KRAS, rearranging transfection (RET) rearrangement and c-ros oncogene 1 (ROS-1), v-raf murine sarcoma viral oncogene homolog B1 (BRAF), and human epidermal growth factor receptor 2 (HER2) mutations et al. This review has been reported in compliance with the Narrative Review checklist guidelines. From each full-text article, information was extracted regarding a set of terms above.

Conclusions

Research on the application of conventional CT features and CT image-based radiomic features for predicting the gene mutation status of lung adenocarcinoma is still in a preliminary stage. Noninvasively determination of mutation status in lung adenocarcinoma before targeted therapy with conventional CT features and CT image-based radiomic features remains both hopes and challenges. Before radiomics could be applied in clinical practice, more work needs to be done.

OUP accepted manuscript

The recent, rapid advances in immuno-oncology have revolutionized cancer treatment and spurred further research into tumor biology. Yet, cancer patients respond variably to immunotherapy despite mounting evidence to support its efficacy. Current methods for predicting immunotherapy response are unreliable, as these tests cannot fully account for tumor heterogeneity and microenvironment. An improved method for predicting response to immunotherapy is needed. Recent studies have proposed radiomics—the process of converting medical images into quantitative data (features) that can be processed using machine learning algorithms to identify complex patterns and trends—for predicting response to immunotherapy. Because patients undergo numerous imaging procedures throughout the course of the disease, there exists a wealth of radiological imaging data available for training radiomics models. And because radiomic features reflect cancer biology, such as tumor heterogeneity and microenvironment, these models have enormous potential to predict immunotherapy response more accurately than current methods. Models trained on preexisting biomarkers and/or clinical outcomes have demonstrated potential to improve patient stratification and treatment outcomes. In this review, we discuss current applications of radiomics in oncology, followed by a discussion on recent studies that use radiomics to predict immunotherapy response and toxicity.

Deep Learning to Predict EGFR Mutation and PD-L1 Expression Status in Non-Small-Cell Lung Cancer on Computed Tomography Images

OBJECTIVE

The detection of epidermal growth factor receptor (EGFR) mutation and programmed death ligand-1 (PD-L1) expression status is crucial to determine the treatment strategies for patients with non-small-cell lung cancer (NSCLC). Recently, the rapid development of radiomics including but not limited to deep learning techniques has indicated the potential role of medical images in the diagnosis and treatment of diseases.

METHODS

Eligible patients diagnosed/treated at the West China Hospital of Sichuan University from January 2013 to April 2019 were identified retrospectively. The preoperative CT images were obtained, as well as the gene status regarding EGFR mutation and PD-L1 expression. Tumor region of interest (ROI) was delineated manually by experienced respiratory specialists. We used 3D convolutional neural network (CNN) with ROI information as input to construct a classification model and established a prognostic model combining deep learning features and clinical features to stratify survival risk of lung cancer patients.

RESULTS

The whole cohort (N = 1262) was divided into a training set (N = 882, 70%), validation set (N = 125, 10%), and test set (N = 255, 20%). We used a 3D convolutional neural network (CNN) to construct a prediction model, with AUCs of 0.96 (95% CI: 0.94-0.98), 0.80 (95% CI: 0.72-0.88), and 0.73 (95% CI: 0.63-0.83) in the training, validation, and test cohorts, respectively. The combined prognostic model showed a good performance on survival prediction in NSCLC patients (C-index: 0.71).

CONCLUSION

In this study, a noninvasive and effective model was proposed to predict EGFR mutation and PD-L1 expression status as a clinical decision support tool. Additionally, the combination of deep learning features with clinical features demonstrated great stratification capabilities in the prognostic model. Our team would continue to explore the application of imaging markers for treatment selection of lung cancer patients.

AIR-Net: A novel multi-task learning method with auxiliary image reconstruction for predicting EGFR mutation status on CT images of NSCLC patients

Automated and accurate EGFR mutation status prediction using computed tomography (CT) imagery is of great value for tailoring optimal treatments to non-small cell lung cancer (NSCLC) patients. However, existing deep learning based methods usually adopt a single task learning strategy to design and train EGFR mutation status prediction models with limited training data, which may be insufficient to learn distinguishable representations for promoting prediction performance. In this paper, a novel multi-task learning method named AIR-Net is proposed to precisely predict EGFR mutation status on CT images. First, an auxiliary image reconstruction task is effectively integrated with EGFR mutation status prediction, aiming at providing extra supervision at the training phase. Particularly, we adequately employ multi-level information in a shared encoder to generate more comprehensive representations of tumors. Second, a powerful feature consistency loss is further introduced to constrain semantic consistency of original and reconstructed images, which contributes to enhanced image reconstruction and offers more effective regularization to AIR-Net during training. Performance analysis of AIR-Net indicates that auxiliary image reconstruction plays an essential role in identifying EGFR mutation status. Furthermore, extensive experimental results demonstrate that our method achieves favorable performance against other competitive prediction methods. All the results executed in this study suggest that the effectiveness and superiority of AIR-Net in precisely predicting EGFR mutation status of NSCLC.

Convolutional Neural Network Addresses the Confounding Impact of CT Reconstruction Kernels on Radiomics Studies

Achieving high feature reproducibility while preserving biological information is one of the main challenges for the generalizability of current radiomics studies. Non-clinical imaging variables, such as reconstruction kernels, have shown to significantly impact radiomics features. In this study, we retrain an open-source convolutional neural network (CNN) to harmonize computerized tomography (CT) images with various reconstruction kernels to improve feature reproducibility and radiomic model performance using epidermal growth factor receptor (EGFR) mutation prediction in lung cancer as a paradigm. In the training phase, the CNN was retrained and tested on 32 lung cancer patients’ CT images between two different groups of reconstruction kernels (smooth and sharp). In the validation phase, the retrained CNN was validated on an external cohort of 223 lung cancer patients’ CT images acquired using different CT scanners and kernels. The results showed that the retrained CNN could be successfully applied to external datasets with different CT scanner parameters, and harmonization of reconstruction kernels from sharp to smooth could significantly improve the performance of radiomics model in predicting EGFR mutation status in lung cancer. In conclusion, the CNN based method showed great potential in improving feature reproducibility and generalizability by harmonizing medical images with heterogeneous reconstruction kernels.

Evaluation of the Radiomics Method for the Prediction of Atypical Adenomatous Hyperplasia in Patients With Subcentimeter Pulmonary Ground-Glass Nodules

Objectives

We aimed to develop a prediction model to distinguish atypical adenomatous hyperplasia (AAH) from early lung adenocarcinomas in patients with subcentimeter pulmonary ground-glass nodules (GGNs), which may help avoid aggressive surgical resection for patients with AAH.

Methods

Surgically confirmed cases of AAH and lung adenocarcinomas manifesting as GGNs of less than 1 cm were retrospectively collected. A prediction model based on radiomics and clinical features identified from a training set of cases was built to differentiate AAH from lung adenocarcinomas and tested on a validation set.

Results

Four hundred and eighty-five eligible cases were included and randomly assigned to the training (n = 339) or the validation sets (n = 146). The developed radiomics prediction model showed good discrimination performance to distinguish AAH from adenocarcinomas in both the training and the validation sets, with, respectively, 84.1% and 82.2% of accuracy, and AUCs of 0.899 (95% CI: 0.867–0.931) and 0.881 (95% CI: 0.827–0.936).

Conclusion

The prediction model based on radiomics and clinical features can help differentiate AAH from adenocarcinomas manifesting as subcentimeter GGNs and may prevent aggressive resection for AAH patients, while reserving this treatment for adenocarcinomas.