Multiparametric MRI-Based Interpretable Radiomics Machine Learning Model Differentiates Medulloblastoma and Ependymoma in Children: A Two-Center Study

RATIONALE AND OBJECTIVES

Medulloblastoma (MB) and Ependymoma (EM) in children, share similarities in age group, tumor location, and clinical presentation. Distinguishing between them through clinical diagnosis is challenging. This study aims to explore the effectiveness of using radiomics and machine learning on multiparametric magnetic resonance imaging (MRI) to differentiate between MB and EM and validate its diagnostic ability with an external set.

MATERIALS AND METHODS

Axial T2 weighted image (T2WI) and contrast-enhanced T1weighted image (CE-T1WI) MRI sequences of 135 patients from two centers were collected as train/test sets. Volume of interest (VOI) was manually delineated by an experienced neuroradiologist, supervised by a senior. Feature selection analysis and the least absolute shrinkage and selection operator (LASSO) algorithm identified valuable features, and Shapley additive explanations (SHAP) evaluated their significance. Five machine-learning classifiers-extreme gradient boosting (XGBoost), Bernoulli naive Bayes (Bernoulli NB), Logistic Regression (LR), support vector machine (SVM), linear support vector machine (Linear SVC) classifiers were built based on T2WI (T2 model), CE-T1WI (T1 model), and T1 + T2WI (T1 + T2 model). A human expert diagnosis was developed and corrected by senior radiologists. External validation was performed at Sun Yat-Sen University Cancer Center.

RESULTS

31 valuable features were extracted from T2WI and CE-T1WI. XGBoost demonstrated the highest performance with an area under the curve (AUC) of 0.92 on the test set and maintained an AUC of 0.80 during external validation. For the T1 model, XGBoost achieved the highest AUC of 0.85 on the test set and the highest accuracy of 0.71 on the external validation set. In the T2 model, XGBoost achieved the highest AUC of 0.86 on the test set and the highest accuracy of 0.82 on the external validation set. The human expert diagnosis had an AUC of 0.66 on the test set and 0.69 on the external validation set. The integrated T1 + T2 model achieved an AUC of 0.92 on the test set, 0.80 on the external validation set, achieved the best performance. Overall, XGBoost consistently outperformed in different classification models.

CONCLUSION

The combination of radiomics and machine learning on multiparametric MRI effectively distinguishes between MB and EM in childhood, surpassing human expert diagnosis in training and testing sets.

Differentiation between cerebral alveolar echinococcosis and brain metastases with radiomics combined machine learning approach

BACKGROUND

Cerebral alveolar echinococcosis (CAE) and brain metastases (BM) share similar in locations and imaging appearance. However, they require distinct treatment approaches, with CAE typically treated with chemotherapy and surgery, while BM is managed with radiotherapy and targeted therapy for the primary malignancy. Accurate diagnosis is crucial due to the divergent treatment strategies.

PURPOSE

This study aims to evaluate the effectiveness of radiomics and machine learning techniques based on magnetic resonance imaging (MRI) to differentiate between CAE and BM.

METHODS

We retrospectively analyzed MRI images of 130 patients (30 CAE and 100 BM) from Xinjiang Medical University First Affiliated Hospital and The First People's Hospital of Kashi Prefecture, between January 2014 and December 2022. The dataset was divided into training (91 cases) and testing (39 cases) sets. Three dimensional tumors were segmented by radiologists from contrast-enhanced T1WI images on open resources software 3D Slicer. Features were extracted on Pyradiomics, further feature reduction was carried out using univariate analysis, correlation analysis, and least absolute shrinkage and selection operator (LASSO). Finally, we built five machine learning models, support vector machine, logistic regression, linear discrimination analysis, k-nearest neighbors classifier, and Gaussian naïve bias and evaluated their performance via several metrics including sensitivity (recall), specificity, positive predictive value (precision), negative predictive value, accuracy and the area under the curve (AUC).

RESULTS

The area under curve (AUC) of support vector classifier (SVC), linear discrimination analysis (LDA), k-nearest neighbors (KNN), and gaussian naïve bias (NB) algorithms in training (testing) sets are 0.99 (0.94), 1.00 (0.87), 0.98 (0.92), 0.97 (0.97), and 0.98 (0.93), respectively. Nested cross-validation demonstrated the robustness and generalizability of the models. Additionally, the calibration plot and decision curve analysis demonstrated the practical usefulness of these models in clinical practice, with lower bias toward different subgroups during decision-making.

CONCLUSION

The combination of radiomics and machine learning approach based on contrast enhanced T1WI images could well distinguish CAE and BM. This approach holds promise in assisting doctors with accurate diagnosis and clinical decision-making.

Deep learning and radiomics of longitudinal CT scans for early prediction of tuberculosis treatment outcomes

BACKGROUND

To predict tuberculosis (TB) treatment outcomes at an early stage, prevent poor outcomes ofdrug-resistant tuberculosis(DR-TB) and interrupt transmission.

METHODS

An internal cohort for model development consists of 204 bacteriologically-confirmed TB patients who completed anti-tuberculosis treatment, with one pretreatment and two follow-up CT images (612 scans). Three radiomics feature-based models (RM) with multiple classifiers of Bagging, Random forest and Gradient boosting and two deep-learning-based models (i.e., supervised deep-learning model, SDLM; weakly supervised deep-learning model, WSDLM) are developed independently. Prediction scores of RM and deep-learning models with respectively highest performance are fused to create new fusion models under different fusion strategies. An additional independent validation was conducted on the external cohort comprising 80 patients (160 scans).

RESULTS

For RM scheme, 16 optimal radiomics features are finally selected using longitudinal scans. The AUCs of RM for Bagging, Random forest and Gradient boosting were 0.789, 0.773 and 0.764 in the internal cohort and 0.840, 0.834 and 0.816 in the external cohort, respectively. For deep learning-based scheme, AUCs of SDLM and WSDLM were 0.767 and 0.661 in the internal cohort, and 0.823 and 0.651 in the external. The fusion model yields AUCs from 0.767 to 0.802 in the internal cohort, and from 0.831 to 0.857 in the external cohort.

CONCLUSIONS

Fusion of radiomics features and deep-learning model may have the potential to predict early failure outcome of DR-TB, which may be combined to help prevent poor TB treatment outcomes.

Deep learning on longitudinal CT scans: automated prediction of treatment outcomes in hospitalized tuberculosis patients

Three deep learning (DL)-based prediction models (PMs) using longitudinal CT images were developed to predict tuberculosis (TB) treatment outcomes. The internal dataset consists of 493 bacteriologically confirmed TB patients who completed the anti-tuberculosis treatment with three-time CT scans, including a pretreatment CT scan and two follow-up CT scans. PM1 was trained using only pretreatment CT scans, and PM2 and PM3 were developed by adding follow-up scans. An independent testing was performed on external dataset comprising 86 TB patients. The area under the curve for classifying success and drug-resistant (DR)-TB was improved on both internal (0.609 vs. 0.625 vs. 0.815) and external (0.627 vs. 0.705 vs. 0.735) dataset by adding follow-up scans. The accuracy and F1-score also showed an increasing tendency in the external test. Regular follow-up CT scans can aid in the treatment prediction, and special attention should be given to early intensive phase of treatment to identify high-risk DR-TB patients.

Deep learning based CT images automatic analysis model for active/non-active pulmonary tuberculosis differential diagnosis

Active pulmonary tuberculosis (ATB), which is more infectious and has a higher mortality rate compared with non-active pulmonary tuberculosis (non-ATB), needs to be diagnosed accurately and timely to prevent the tuberculosis from spreading and causing deaths. However, traditional differential diagnosis methods of active pulmonary tuberculosis involve bacteriological testing, sputum culturing and radiological images reading, which is time consuming and labour intensive. Therefore, an artificial intelligence model for ATB differential diagnosis would offer great assistance in clinical practice. In this study, computer tomography (CT) scans images and corresponding clinical information of 1160 ATB patients and 1131 patients with non-ATB were collected and divided into training, validation, and testing sets. A 3-dimension (3D) Nested UNet model was utilized to delineate lung field regions in the CT images, and three different pre-trained deep learning models including 3D VGG-16, 3D EfficientNet and 3D ResNet-50 were used for classification and differential diagnosis task. We also collected an external testing set with 100 ATB cases and 100 Non-ATB cases for further validation of the model. In the internal and external testing set, the 3D ResNet-50 model outperformed other models, reaching an AUC of 0.961 and 0.946, respectively. The 3D ResNet-50 model reached even higher levels of diagnostic accuracy than experienced radiologists, while the CT images reading and diagnosing speed was 10 times faster than human experts. The model was also capable of visualizing clinician interpretable lung lesion regions important for differential diagnosis, making it a powerful tool assisting ATB diagnosis. In conclusion, we developed an auxiliary tool to differentiate active and non-active pulmonary tuberculosis, which would have broad prospects in the bedside.

A symmetric prior knowledge based deep learning model for intracerebral hemorrhage lesion segmentation

Background: Accurate localization and classification of intracerebral hemorrhage (ICH) lesions are of great significance for the treatment and prognosis of patients with ICH. The purpose of this study is to develop a symmetric prior knowledge based deep learning model to segment ICH lesions in computed tomography (CT). Methods: A novel symmetric Transformer network (Sym-TransNet) is designed to segment ICH lesions in CT images. A cohort of 1,157 patients diagnosed with ICH is established to train (n = 857), validate (n = 100), and test (n = 200) the Sym-TransNet. A healthy cohort of 200 subjects is added, establishing a test set with balanced positive and negative cases (n = 400), to further evaluate the accuracy, sensitivity, and specificity of the diagnosis of ICH. The segmentation results are obtained after data pre-processing and Sym-TransNet. The DICE coefficient is used to evaluate the similarity between the segmentation results and the segmentation gold standard. Furthermore, some recent deep learning methods are reproduced to compare with Sym-TransNet, and statistical analysis is performed to prove the statistical significance of the proposed method. Ablation experiments are conducted to prove that each component in Sym-TransNet could effectively improve the DICE coefficient of ICH lesions. Results: For the segmentation of ICH lesions, the DICE coefficient of Sym-TransNet is 0.716 ± 0.031 in the test set which contains 200 CT images of ICH. The DICE coefficients of five subtypes of ICH, including intraparenchymal hemorrhage (IPH), intraventricular hemorrhage (IVH), extradural hemorrhage (EDH), subdural hemorrhage (SDH), and subarachnoid hemorrhage (SAH), are 0.784 ± 0.039, 0.680 ± 0.049, 0.359 ± 0.186, 0.534 ± 0.455, and 0.337 ± 0.044, respectively. Statistical results show that the proposed Sym-TransNet can significantly improve the DICE coefficient of ICH lesions in most cases. In addition, the accuracy, sensitivity, and specificity of Sym-TransNet in the diagnosis of ICH in 400 CT images are 91.25%, 98.50%, and 84.00%, respectively. Conclusion: Compared with recent mainstream deep learning methods, the proposed Sym-TransNet can segment and identify different types of lesions from CT images of ICH patients more effectively. Moreover, the Sym-TransNet can diagnose ICH more stably and efficiently, which has clinical application prospects.

MRI-Based Radiomics for Preoperative Prediction of Lymphovascular Invasion in Patients With Invasive Breast Cancer

Objective

Preoperative identification of lymphovascular invasion (LVI) in patients with invasive breast cancer is challenging due to absence of reliable biomarkers or tools in clinical settings. We aimed to establish and validate multiparametric magnetic resonance imaging (MRI)-based radiomic models to predict the risk of lymphovascular invasion (LVI) in patients with invasive breast cancer.

Methods

This retrospective study included a total of 175 patients with confirmed invasive breast cancer who had known LVI status and preoperative MRI from two tertiary centers. The patients from center 1 was randomly divided into a training set (n=99) and a validation set (n = 26), while the patients from center 2 was used as a test set (n=50). A total of 1409 radiomic features were extracted from the T2-weighted imaging (T2WI), dynamic contrast-enhanced (DCE) imaging, diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC), respectively. A three-step feature selection including SelectKBest, interclass correlation coefficients (ICC), and least absolute shrinkage and selection operator (LASSO) was performed to identify the features most associated with LVI. Subsequently, a Support Vector Machine (SVM) classifier was trained to develop single-layer radiomic models and fusion radiomic models. Model performance was evaluated and compared by the area under the curve (AUC), sensitivity, and specificity.

Results

Based on one feature of wavelet-HLH_gldm_GrayLevelVariance, the ADC radiomic model achieved an AUC of 0.87 (95% confidence interval [CI]: 0.80–0.94) in the training set, 0.87 (0.70-1.00) in the validation set, and 0.77 (95%CI: 0.64-0.86) in the test set. However, the combination of radiomic features derived from other MR sequences failed to yield incremental value.

Conclusions

ADC-based radiomic model demonstrated a favorable performance in predicting LVI prior to surgery in patients with invasive breast cancer. Such model holds the potential for improving clinical decision-making regarding treatment for breast cancer.

Bioartificial livers: a review of their design and manufacture

Acute liver failure (ALF) is a rapidly progressive disease with high morbidity and mortality rates. Liver transplantation and artificial liver support systems, such as artificial livers (ALs) and bioartificial livers (BALs), are the two major therapies for ALF. Compared to ALs, BALs are composed of functional hepatocytes that provide essential liver functions, including detoxification, metabolite synthesis, and biotransformation. Furthermore, BALs can potentially provide effective support as a form of bridging therapy to liver transplantation or spontaneous recovery for patients with ALF. In this review, we systematically discussed the currently available state-of-the-art designs and manufacturing processes for BAL support systems. Specifically, we classified the cell sources and bioreactors that are applied in BALs, highlighted the advanced technologies of hepatocyte culturing and bioreactor fabrication, and discussed the current challenges and future trends in developing next generation BALs for large scale clinical applications.

Artificial Intelligence Assisting the Early Detection of Active Pulmonary Tuberculosis From Chest X-Rays: A Population-Based Study

As a major infectious disease, tuberculosis (TB) still poses a threat to people’s health in China. As a triage test for TB, reading chest radiography with traditional approach ends up with high inter-radiologist and intra-radiologist variability, moderate specificity and a waste of time and medical resources. Thus, this study established a deep convolutional neural network (DCNN) based artificial intelligence (AI) algorithm, aiming at diagnosing TB on posteroanterior chest X-ray photographs in an effective and accurate way. Altogether, 5,000 patients with TB and 4,628 patients without TB were included in the study, totaling to 9,628 chest X-ray photographs analyzed. Splitting the radiographs into a training set (80.4%) and a testing set (19.6%), three different DCNN algorithms, including ResNet, VGG, and AlexNet, were trained to classify the chest radiographs as images of pulmonary TB or without TB. Both the diagnostic accuracy and the area under the receiver operating characteristic curve were used to evaluate the performance of the three AI diagnosis models. Reaching an accuracy of 96.73% and marking the precise TB regions on the radiographs, ResNet algorithm-based AI outperformed the rest models and showed excellent diagnostic ability in different clinical subgroups in the stratification analysis. In summary, the ResNet algorithm-based AI diagnosis system provided accurate TB diagnosis, which could have broad prospects in clinical application for TB diagnosis, especially in poor regions with high TB incidence.

Current progress and quality of radiomic studies for predicting EGFR mutation in patients with non-small cell lung cancer using PET/CT images: a systematic review

OBJECTIVES

To assess the methodological quality of radiomic studies based on positron emission tomography/computed tomography (PET/CT) images predicting epidermal growth factor receptor (EGFR) mutation status in patients with non-small cell lung cancer (NSCLC).

METHODS

We systematically searched for eligible studies in the PubMed and Web of Science datasets using the terms "radiomics", "PET/CT", "NSCLC", and "EGFR". The included studies were screened by two reviewers independently. The quality of the radiomic workflow of studies was assessed using the Radiomics Quality Score (RQS). Interclass correlation coefficient (ICC) was used to determine inter rater agreement for the RQS. An overview of the methodologies used in steps of the radiomics workflow and current results are presented.

RESULTS

Six studies were included with sample sizes of 973 ranging from 115 to 248 patients. Methodologies in the radiomic workflow varied greatly. The first-order statistics were the most reproducible features. The RQS scores varied from 13.9 to 47.2%. All studies were scored below 50% due to defects on multiple segmentations, phantom study on all scanners, imaging at multiple time points, cut-off analyses, calibration statistics, prospective study, potential clinical utility, and cost-effectiveness analysis. The ICC results for majority of RQS items were excellent. The ICC for summed RQS was 0.986 [95% confidence interval (CI): 0.898-0.998].

CONCLUSIONS

The PET/CT-based radiomics signature could serve as a diagnostic indicator of EGFR mutation status in NSCLC patients. However, the current conclusions should be interpreted with care due to the suboptimal quality of the studies. Consensus for standardization of PET/CT-based radiomic workflow for EGFR mutation status in NSCLC patients is warranted to further improve research.

ADVANCES IN KNOWLEDGE

Radiomics can offer clinicians better insight into the prediction of EGFR mutation status in NSCLC patients, whereas the quality of relative studies should be improved before application to the clinical setting.

Deep learning assistance for tuberculosis diagnosis with chest radiography in low-resource settings

Tuberculosis (TB) is a major health issue with high mortality rates worldwide. Recently, tremendous researches of artificial intelligence (AI) have been conducted targeting at TB to reduce the diagnostic burden. However, most researches are conducted in the developed urban areas. The feasibility of applying AI in low-resource settings remains unexplored. In this study, we apply an automated detection (AI) system to screen a large population in an underdeveloped area and evaluate feasibility and contribution of applying AI to help local radiologists detect and diagnose TB using chest X-ray (CXR) images. First, we divide image data into one training dataset including 2627 TB-positive cases and 7375 TB-negative cases and one testing dataset containing 276 TB-positive cases and 619 TB-negative cases, respectively. Next, in building AI system, the experiment includes image labeling and preprocessing, model training and testing. A segmentation model named TB-UNet is also built to detect diseased regions, which uses ResNeXt as the encoder of U-Net. We use AI-generated confidence score to predict the likelihood of each testing case being TB-positive. Then, we conduct two experiments to compare results between the AI system and radiologists with and without AI assistance. Study results show that AI system yields TB detection accuracy of 85%, which is much higher than detection accuracy of radiologists (62%) without AI assistance. In addition, with AI assistance, the TB diagnostic sensitivity of local radiologists is improved by 11.8%. Therefore, this study demonstrates that AI has great potential to help detection, prevention, and control of TB in low-resource settings, particularly in areas with more scant doctors and higher rates of the infected population.