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

Habitat radiomics and deep learning fusion nomogram to predict EGFR mutation status in stage I non-small cell lung cancer: a multicenter study

Develop a radiomics nomogram that integrates deep learning, radiomics, and clinical variables to predict epidermal growth factor receptor (EGFR) mutation status in patients with stage I non-small cell lung cancer (NSCLC). We retrospectively included 438 patients who underwent curative surgery and completed driver-gene mutation tests for stage I NSCLC from four academic medical centers. Predictive models were established by extracting and analyzing radiomic features in intratumoral, peritumoral, and habitat regions of CT images to identify EGFR mutation status in stage I NSCLC. Additionally, three deep learning models based on the intratumoral region were constructed. A nomogram was developed by integrating representative radiomic signatures, deep learning, and clinical features. Model performance was assessed by calculating the area under the receiver operating characteristic (ROC) curve. The established habitat radiomics features demonstrated encouraging performance in discriminating between EGFR mutant and wild-type, with predictive ability superior to other single models (AUC 0.886, 0.812, and 0.790 for the training, validation, and external test sets, respectively). The radiomics-based nomogram exhibited excellent performance, achieving the highest AUC values of 0.917, 0.837, and 0.809 in the training, validation, and external test sets, respectively. Decision curve analysis (DCA) indicated that the nomogram provided a higher net benefit than other radiomics models, offering valuable information for treatment.

Automatic diagnosis of pediatric supracondylar humerus fractures using radiomics-based machine learning

The aim of this study was to construct a classification model for the automatic diagnosis of pediatric supracondylar humerus fractures using radiomics-based machine learning. We retrospectively collected elbow joint Radiographs of children aged 3 to 14 years and manually delineated regions of interest (ROI) using ITK-SNAP. Radiomics features were extracted using pyradiomics, a python-based feature extraction tool. T-tests and the least absolute shrinkage and selection operator (LASSO) algorithm were used to further select the most valuable radiomics features. A logistic regression (LR) model was trained, with an 8:2 split into training and testing sets, and 5-fold cross-validation was performed on the training set. The diagnostic performance of the model was evaluated using receiver operating characteristic curves (ROC) on the testing set. A total of 411 fracture samples and 190 normal samples were included. 1561 features were extracted from each ROI. After dimensionality reduction screening, 40 and 94 features with the most diagnostic value were selected for further classification modeling in anteroposterior and lateral elbow radiographs. The area under the curve (AUC) of anteroposterior and lateral elbow radiographs is 0.65 and 0.72. Radiomics can extract and select the most valuable features from a large number of image features. Supervised machine-learning models built using these features can be used for the diagnosis of pediatric supracondylar humerus fractures.

Using Vision Transformer for high robustness and generalization in predicting EGFR mutation status in lung adenocarcinoma

BACKGROUND

Lung adenocarcinoma is a common cause of cancer-related deaths worldwide, and accurate EGFR genotyping is crucial for optimal treatment outcomes. Conventional methods for identifying the EGFR genotype have several limitations. Therefore, we proposed a deep learning model using non-invasive CT images to predict EGFR mutation status with robustness and generalizability.

METHODS

A total of 525 patients were enrolled at the local hospital to serve as the internal data set for model training and validation. In addition, a cohort of 30 patients from the publicly available Cancer Imaging Archive Data Set was selected for external testing. All patients underwent plain chest CT, and their EGFR mutation status labels were categorized as either mutant or wild type. The CT images were analyzed using a self-attention-based ViT-B/16 model to predict the EGFR mutation status, and the model's performance was evaluated. To produce an attention map indicating the suspicious locations of EGFR mutations, Grad-CAM was utilized.

RESULTS

The ViT deep learning model achieved impressive results, with an accuracy of 0.848, an AUC of 0.868, a sensitivity of 0.924, and a specificity of 0.718 on the validation cohort. Furthermore, in the external test cohort, the model achieved comparable performances, with an accuracy of 0.833, an AUC of 0.885, a sensitivity of 0.900, and a specificity of 0.800.

CONCLUSIONS

The ViT model demonstrates a high level of accuracy in predicting the EGFR mutation status of lung adenocarcinoma patients. Moreover, with the aid of attention maps, the model can assist clinicians in making informed clinical decisions.

Effectiveness of CT radiomic features combined with clinical factors in predicting prognosis in patients with limited-stage small cell lung cancer

BACKGROUND

The prognosis of SCLC is poor and difficult to predict. The aim of this study was to explore whether a model based on radiomics and clinical features could predict the prognosis of patients with limited-stage small cell lung cancer (LS-SCLC).

METHODS

Simulated positioning CT images and clinical features were retrospectively collected from 200 patients with histological diagnosis of LS-SCLC admitted between 2013 and 2021, which were randomly divided into the training (n = 140) and testing (n = 60) groups. Radiomics features were extracted from simulated positioning CT images, and the t-test and the least absolute shrinkage and selection operator (LASSO) were used to screen radiomics features. We then constructed radiomic score (RadScore) based on the filtered radiomics features. Clinical factors were analyzed using the Kaplan-Meier method. The Cox proportional hazards model was used for further analyses of possible prognostic features and clinical factors to build three models including a radiomic model, a clinical model, and a combined model including clinical factors and RadScore. When a model has prognostic predictive value (AUC > 0.7) in both train and test groups, a nomogram will be created. The performance of three models was evaluated using area under the receiver operating characteristic curve (AUC) and Kaplan-Meier analysis.

RESULTS

A total of 1037 features were extracted from simulated positioning CT images which were contrast enhanced CT of the chest. The combined model showed the best prediction, with very poor AUC for the radiomic model and the clinical model. The combined model of OS included 4 clinical features and RadScore, with AUCs of 0.71 and 0.70 in the training and test groups. The combined model of PFS included 4 clinical features and RadScore, with AUCs of 0.72 and 0.71 in the training and test groups. T stages, ProGRP and smoke status were the independent variables for OS in the combined model, whereas T stages, ProGRP and prophylactic cranial irradiation (PCI) were the independent factors for PFS. There was a statistically significant difference between the low- and high-risk groups in the combined model of OS (training group, p < 0.0001; testing group, p = 0.0269) and PFS (training group, p < 0.0001; testing group, p < 0.0001).

CONCLUSION

Combined models involved RadScore and clinical factors can predict prognosis in LS-SCLC and show better performance than individual radiomics and clinical models.

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.

Development and validation of MRI-based radiomics model to predict recurrence risk in patients with endometrial cancer: a multicenter study

OBJECTIVES

To develop a fusion model based on clinicopathological factors and MRI radiomics features for the prediction of recurrence risk in patients with endometrial cancer (EC).

METHODS

A total of 421 patients with histopathologically proved EC (101 recurrence vs. 320 non-recurrence EC) from four medical centers were included in this retrospective study, and were divided into the training (n = 235), internal validation (n = 102), and external validation (n = 84) cohorts. In total, 1702 radiomics features were respectively extracted from areas with different extensions for each patient. The extreme gradient boosting (XGBoost) classifier was applied to establish the clinicopathological model (CM), radiomics model (RM), and fusion model (FM). The performance of the established models was assessed by the discrimination, calibration, and clinical utility. Kaplan-Meier analysis was conducted to further determine the prognostic value of the models by evaluating the differences in recurrence-free survival (RFS) between the high- and low-risk patients of recurrence.

RESULTS

The FMs showed better performance compared with the models based on clinicopathological or radiomics features alone but with a reduced tendency when the peritumoral area (PA) was extended. The FM based on intratumoral area (IA) [FM (IA)] had the optimal performance in predicting the recurrence risk in terms of the ROC, calibration curve, and decision curve analysis. Kaplan-Meier survival curves showed that high-risk patients of recurrence defined by FM (IA) had a worse RFS than low-risk ones of recurrence.

CONCLUSIONS

The FM integrating intratumoral radiomics features and clinicopathological factors could be a valuable predictor for the recurrence risk of EC patients.

CLINICAL RELEVANCE STATEMENT

An accurate prediction based on our developed FM (IA) for the recurrence risk of EC could facilitate making an individualized therapeutic decision and help avoid under- or over-treatment, therefore improving the prognosis of patients.

KEY POINTS

• The fusion model combined clinicopathological factors and radiomics features exhibits the highest performance compared with the clinicopathological model and radiomics model. • Although higher values of area under the curve were observed for all fusion models, the performance tended to decrease with the extension of the peritumoral region. • Identifying patients with different risks of recurrence, the developed models can be used to facilitate individualized management.

Radiomics-Based Machine Learning for Predicting the Injury Time of Rib Fractures in Gemstone Spectral Imaging Scans

This retrospective study aimed to predict the injury time of rib fractures in distinguishing fresh (30 days) or old (90 days) rib fractures. We enrolled 111 patients with chest trauma who had been scanned for rib fractures at our hospital between January 2018 and December 2018 using gemstone spectral imaging (GSI). The volume of interest of each broken end of the rib fractures was segmented using calcium-based material decomposition images derived from the GSI scans. The training and testing sets were randomly assigned in a 7:3 ratio. All cases were divided into groups distinguishing the injury time at 30 and 90 days. We constructed radiomics-based models to predict the injury time of rib fractures. The model performance was assessed by the area under the curve (AUC) obtained by the receiver operating characteristic analysis. We included 54 patients with 259 rib fracture segmentations (34 men; mean age, 52 years ± 12.02; and range, 19-72 years). Nine features were excluded by the least absolute shrinkage and selection operator logistic regression to build the radiomics signature. For distinguishing the injury time at 30 days, the Support Vector Machine (SVM) model and human-model collaboration resulted in an accuracy and AUC of 0.85 and 0.871 and 0.91 and 0.912, respectively, and 0.81 and 0.804 and 0.83 and 0.85, respectively, at 90 days in the testing set. The radiomics-based model displayed good accuracy in differentiating between the injury time of rib fractures at 30 and 90 days, and the human-model collaboration generated more accurate outcomes, which may help to add value to clinical practice and distinguish artificial injury in forensic medicine.

Intelligent and novel multi-type cancer prediction model using optimized ensemble learning

Cancer is known to be highly severe disease and gets incurable even when the treatment has started at the time of diagnosis owing to the occurrence of cancer cells. Diverse machine learning approaches are implemented for predicting the cancer recurrence that needs to be evaluated for showing the appropriate approach for cancer prediction. This paper provides intelligent optimized ensemble learning for predicting multiple types of cancers. At first, the different types of cancer data are collected and performed the data cleansing. Then, the feature extraction is done using statistical features, 'Linear Discriminant Analysis (LDA), and Principal Component Analysis (PCA)'. With these features, a new Adaptive Condition Searched-Harris hawks Whale Optimization (ACS-HWO) is used for selecting the optimal features and transformed into weighted features with meta-heuristic update. The prediction is carried out by Optimized Ensemble-based Multi-disease Detection (OEMD) with Support Vector Machine (SVM), Autoencoder, Adaboost, 'Deep Neural Network (DNN), and Recurrent Neural Network (RNN)' with high ranking strategy. The same ACS-HWO is used for improvising the weighted feature selection and optimized ensemble learning. The comparative analysis over existing models shows that the suggested method can be highly applicable for the healthcare system to ensure the consistent prediction with the multi-type of cancers.