Decoding COVID-19 pneumonia: comparison of deep learning and radiomics CT image signatures

Validated machine learning tools to distinguish immune checkpoint inhibitor, radiotherapy, COVID-19 and other infective pneumonitis

BACKGROUND

Pneumonitis is a well-described, potentially disabling, or fatal adverse effect associated with both immune checkpoint inhibitors (ICI) and thoracic radiotherapy. Accurate differentiation between checkpoint inhibitor pneumonitis (CIP) radiation pneumonitis (RP), and infective pneumonitis (IP) is crucial for swift, appropriate, and tailored management to achieve optimal patient outcomes. However, correct diagnosis is often challenging, owing to overlapping clinical presentations and radiological patterns.

METHODS

In this multi-centre study of 455 patients, we used machine learning with radiomic features extracted from chest CT imaging to develop and validate five models to distinguish CIP and RP from COVID-19, non-COVID-19 infective pneumonitis, and each other. Model performance was compared to that of two radiologists.

RESULTS

Models to distinguish RP from COVID-19, CIP from COVID-19 and CIP from non-COVID-19 IP out-performed radiologists (test set AUCs of 0.92 vs 0.8 and 0.8; 0.68 vs 0.43 and 0.4; 0.71 vs 0.55 and 0.63 respectively). Models to distinguish RP from non-COVID-19 IP and CIP from RP were not superior to radiologists but demonstrated modest performance, with test set AUCs of 0.81 and 0.8 respectively. The CIP vs RP model performed less well on patients with prior exposure to both ICI and radiotherapy (AUC 0.54), though the radiologists also had difficulty distinguishing this test cohort (AUC values 0.6 and 0.6).

CONCLUSION

Our results demonstrate the potential utility of such tools as a second or concurrent reader to support oncologists, radiologists, and chest physicians in cases of diagnostic uncertainty. Further research is required for patients with exposure to both ICI and thoracic radiotherapy.

Quantitative radiomics analysis of imaging features in adults and children Mycoplasma pneumonia

Purpose

This study aims to explore the value of clinical features, CT imaging signs, and radiomics features in differentiating between adults and children with Mycoplasma pneumonia and seeking quantitative radiomic representations of CT imaging signs.

Materials and methods

In a retrospective analysis of 981 cases of mycoplasmal pneumonia patients from November 2021 to December 2023, 590 internal data (adults:450, children: 140) randomly divided into a training set and a validation set with an 8:2 ratio and 391 external test data (adults:121; children:270) were included. Using univariate analysis, CT imaging signs and clinical features with significant differences (p < 0.05) were selected. After segmenting the lesion area on the CT image as the region of interest, 1,904 radiomic features were extracted. Then, Pearson correlation analysis (PCC) and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomic features. Based on the selected features, multivariable logistic regression analysis was used to establish the clinical model, CT image model, radiomic model, and combined model. The predictive performance of each model was evaluated using ROC curves, AUC, sensitivity, specificity, accuracy, and precision. The AUC between each model was compared using the Delong test. Importantly, the radiomics features and quantitative and qualitative CT image features were analyzed using Pearson correlation analysis and analysis of variance, respectively.

Results

For the individual model, the radiomics model, which was built using 45 selected features, achieved the highest AUCs in the training set, validation set, and external test set, which were 0.995 (0.992, 0.998), 0.952 (0.921, 0.978), and 0.969 (0.953, 0.982), respectively. In all models, the combined model achieved the highest AUCs, which were 0.996 (0.993, 0.998), 0.972 (0.942, 0.995), and 0.986 (0.976, 0.993) in the training set, validation set, and test set, respectively. In addition, we selected 11 radiomics features and CT image features with a correlation coefficient r greater than 0.35.

Conclusion

The combined model has good diagnostic performance for differentiating between adults and children with mycoplasmal pneumonia, and different CT imaging signs are quantitatively represented by radiomics.

Chest Computed Tomography Radiomics for Determining Macrolide Resistance-Associated Gene Mutation Status in Children with Mycoplasma pneumoniae Pneumonia: A Two-Center Study

RATIONALE AND OBJECTIVES

The mutations in the 23S ribosomal RNA (rRNA) gene are associated with an increase in resistance to macrolides in children with Mycoplasma pneumoniae pneumonia (MPP). This study aimed to develop and validate a chest computed tomography (CT) radiomics model for determining macrolide resistance-associated gene mutation status in MPP.

MATERIALS AND METHODS

A total of 258 MPP patients were retrospectively included from two institutions (training set: 194 patients from the first institution; external test set: 64 patients from the second). The 23S rRNA gene mutation status was tested by nasopharyngeal swab polymerase chain reaction. Radiomics features were extracted from chest CT images of pulmonary lesions segmented with semi-automatic delineation. Subsequently, radiomics feature reduction was applied to identify the most relevant features. Logistic regression and random forest algorithms were employed to establish the radiomics models, which were five-fold cross-validated in the training set and validated in the external test set.

RESULTS

The radiomics feature selection resulted in eight features. After five-fold cross-validation in the training set, the mean areas under the receiver operating characteristic curve (AUCs) of the logistic regression and random forest models were 0.868 (95% confidence interval (CI): 0.813-0.923) and 0.941 (95% CI: 0.907-0.975), respectively. In the external test set, the corresponding AUCs were 0.855 (95% CI: 0.758-0.952) and 0.815 (95% CI: 0.705-0.925).

CONCLUSION

Chest CT radiomics is a promising diagnostic tool for determining macrolide resistance gene mutation status in MPP.

AVAILABILITY OF DATA AND MATERIAL

The datasets generated or analyzed during the study are available from the corresponding author on reasonable request.

Bone age assessment based on three-dimensional ultrasound and artificial intelligence compared with paediatrician-read radiographic bone age: protocol for a prospective, diagnostic accuracy study

INTRODUCTION

Radiographic bone age (BA) assessment is widely used to evaluate children's growth disorders and predict their future height. Moreover, children are more sensitive and vulnerable to X-ray radiation exposure than adults. The purpose of this study is to develop a new, safer, radiation-free BA assessment method for children by using three-dimensional ultrasound (3D-US) and artificial intelligence (AI), and to test the diagnostic accuracy and reliability of this method.

METHODS AND ANALYSIS

This is a prospective, observational study. All participants will be recruited through Paediatric Growth and Development Clinic. All participants will receive left hand 3D-US and X-ray examination at the Shanghai Sixth People's Hospital on the same day, all images will be recorded. These image related data will be collected and randomly divided into training set (80% of all) and test set (20% of all). The training set will be used to establish a cascade network of 3D-US skeletal image segmentation and BA prediction model to achieve end-to-end prediction of image to BA. The test set will be used to evaluate the accuracy of AI BA model of 3D-US. We have developed a new ultrasonic scanning device, which can be proposed to automatic 3D-US scanning of hands. AI algorithms, such as convolutional neural network, will be used to identify and segment the skeletal structures in the hand 3D-US images. We will achieve automatic segmentation of hand skeletal 3D-US images, establish BA prediction model of 3D-US, and test the accuracy of the prediction model.

ETHICS AND DISSEMINATION

The Ethics Committee of Shanghai Sixth People's Hospital approved this study. The approval number is 2022-019. A written informed consent will be obtained from their parent or guardian of each participant. Final results will be published in peer-reviewed journals and presented at national and international conferences.

TRIAL REGISTRATION NUMBER

ChiCTR2200057236.

Deep Learning Based on ResNet-18 for Classification of Prostate Imaging-Reporting and Data System Category 3 Lesions

RATIONALE AND OBJECTIVES

To explore the classification and prediction efficacy of the deep learning model for benign prostate lesions, non-clinically significant prostate cancer (non-csPCa) and clinically significant prostate cancer (csPCa) in Prostate Imaging-Reporting and Data System (PI-RADS) 3 lesions.

MATERIALS AND METHODS

From January 2015 to December 2021, lesions diagnosed with PI-RADS 3 by multi-parametric MRI or bi-parametric MRI were retrospectively included. They were classified as benign prostate lesions, non-csPCa, and csPCa according to the pathological results. T2-weighted images of the lesions were divided into a training set and a test set according to 8:2. ResNet-18 was used for model training. All statistical analyses were performed using Python open-source libraries. The receiver operating characteristic curve (ROC) was used to evaluate the predictive effectiveness of the model. T-SNE was used for image semantic feature visualization. The class activation mapping was used to visualize the area focused by the model.

RESULTS

A total of 428 benign prostate lesion images, 158 non-csPCa images and 273 csPCa images were included. The precision in predicting benign prostate disease, non-csPCa and csPCa were 0.882, 0.681 and 0.851, and the area under the ROC were 0.875, 0.89 and 0.929, respectively. Semantic feature analysis showed strong classification separability between csPCa and benign prostate lesions. The class activation map showed that the deep learning model can focus on the area of the prostate or the location of PI-RADS 3 lesions.

CONCLUSION

Deep learning model with T2-weighted images based on ResNet-18 can realize accurate classification of PI-RADS 3 lesions.

Supervised training models with or without manual lesion delineation outperform clinicians in distinguishing pulmonary cryptococcosis from lung adenocarcinoma on chest CT

BACKGROUND

The role of artificial intelligence (AI) in the discrimination between pulmonary cryptococcosis (PC) and lung adenocarcinoma (LA) warrants further research.

OBJECTIVES

To compare the performances of AI models with clinicians in distinguishing PC from LA on chest CT.

METHODS

Patients diagnosed with confirmed PC or LA were retrospectively recruited from three tertiary hospitals in Guangzhou. A deep learning framework was employed to develop two models: an undelineated supervised training (UST) model utilising original CT images, and a delineated supervised training (DST) model utilising CT images with manual lesion annotations provided by physicians. A subset of 20 cases was randomly selected from the entire dataset and reviewed by clinicians through a network questionnaire. The sensitivity, specificity and accuracy of the models and the clinicians were calculated.

RESULTS

A total of 395 PC cases and 249 LA cases were included in the final analysis. The internal validation results for the UST model showed a sensitivity of 85.3%, specificity of 81.0%, accuracy of 83.6% and an area under the curve (AUC) of 0.93. Similarly, the DST model exhibited a sensitivity of 88.2%, specificity of 88.1%, accuracy of 88.2% and an AUC of 0.94. The external validation of the two models yielded AUC values of 0.74 and 0.77, respectively. The average sensitivity, specificity and accuracy of 102 clinicians were determined to be 63.1%, 53.7% and 59.3%, respectively.

CONCLUSIONS

Both models outperformed the clinicians in distinguishing between PC and LA on chest CT, with the UST model exhibiting comparable performance to the DST model.

Comparing three-dimensional and two-dimensional deep-learning, radiomics, and fusion models for predicting occult lymph node metastasis in laryngeal squamous cell carcinoma based on CT imaging: a multicentre, retrospective, diagnostic study

Background

The occult lymph node metastasis (LNM) of laryngeal squamous cell carcinoma (LSCC) affects the treatment and prognosis of patients. This study aimed to comprehensively compare the performance of the three-dimensional and two-dimensional deep learning models, radiomics model, and the fusion models for predicting occult LNM in LSCC.

Methods

In this retrospective diagnostic study, a total of 553 patients with clinical N0 stage LSCC, who underwent surgical treatment without distant metastasis and multiple primary cancers, were consecutively enrolled from four Chinese medical centres between January 01, 2016 and December 30, 2020. The participant data were manually retrieved from medical records, imaging databases, and pathology reports. The study cohort was divided into a training set (n = 300), an internal test set (n = 89), and two external test sets (n = 120 and 44, respectively). The three-dimensional deep learning (3D DL), two-dimensional deep learning (2D DL), and radiomics model were developed using CT images of the primary tumor. The clinical model was constructed based on clinical and radiological features. Two fusion strategies were utilized to develop the fusion model: the feature-based DLRad_FB model and the decision-based DLRad_DB model. The discriminative ability and correlation of 3D DL, 2D DL and radiomics features were analysed comprehensively. The performances of the predictive models were evaluated based on the pathological diagnosis.

Findings

The 3D DL features had superior discriminative ability and lower internal redundancy compared to 2D DL and radiomics features. The DLRad_DB model achieved the highest AUC (0.89-0.90) among all the study sets, significantly outperforming the clinical model (AUC = 0.73-0.78, P = 0.0001-0.042, Delong test). Compared to the DLRad_DB model, the AUC values for the DLRad_FB, 3D DL, 2D DL, and radiomics models were 0.82-0.84 (P = 0.025-0.46), 0.86-0.89 (P = 0.75-0.97), 0.83-0.86 (P = 0.029-0.66), and 0.79-0.82 (P = 0.0072-0.10), respectively in the study sets. Additionally, the DLRad_DB model exhibited the best sensitivity (82-88%) and specificity (79-85%) in the test sets.

Interpretation

The decision-based fusion model DLRad_DB, which combines 3D DL, 2D DL, radiomics, and clinical data, can be utilized to predict occult LNM in LSCC. This has the potential to minimize unnecessary lymph node dissection and prophylactic radiotherapy in patients with cN0 disease.

Funding

National Natural Science Foundation of China, Natural Science Foundation of Shandong Province.

Prediction of oxygen supplementation by a deep-learning model integrating clinical parameters and chest CT images in COVID-19

PURPOSE

As of March 2023, the number of patients with COVID-19 worldwide is declining, but the early diagnosis of patients requiring inpatient treatment and the appropriate allocation of limited healthcare resources remain unresolved issues. In this study we constructed a deep-learning (DL) model to predict the need for oxygen supplementation using clinical information and chest CT images of patients with COVID-19.

MATERIALS AND METHODS

We retrospectively enrolled 738 patients with COVID-19 for whom clinical information (patient background, clinical symptoms, and blood test findings) was available and chest CT imaging was performed. The initial data set was divided into 591 training and 147 evaluation data. We developed a DL model that predicted oxygen supplementation by integrating clinical information and CT images. The model was validated at two other facilities (n = 191 and n = 230). In addition, the importance of clinical information for prediction was assessed.

RESULTS

The proposed DL model showed an area under the curve (AUC) of 89.9% for predicting oxygen supplementation. Validation from the two other facilities showed an AUC > 80%. With respect to interpretation of the model, the contribution of dyspnea and the lactate dehydrogenase level was higher in the model.

CONCLUSIONS

The DL model integrating clinical information and chest CT images had high predictive accuracy. DL-based prediction of disease severity might be helpful in the clinical management of patients with COVID-19.

Multimodality deep learning radiomics nomogram for preoperative prediction of malignancy of breast cancer: a multicenter study

Background. Breast cancer is the most prevalent cancer diagnosed in women worldwide. Accurately and efficiently stratifying the risk is an essential step in achieving precision medicine prior to treatment. This study aimed to construct and validate a nomogram based on radiomics and deep learning for preoperative prediction of the malignancy of breast cancer (MBC).Methods. The clinical and ultrasound imaging data, including brightness mode (B-mode) and color Doppler flow imaging, of 611 breast cancer patients from multiple hospitals in China were retrospectively analyzed. Patients were divided into one primary cohort (PC), one validation cohort (VC) and two test cohorts (TC1 and TC2). A multimodality deep learning radiomics nomogram (DLRN) was constructed for predicting the MBC. The performance of the proposed DLRN was comprehensively assessed and compared with three unimodal models via the calibration curve, the area under the curve (AUC) of receiver operating characteristics and the decision curve analysis.Results. The DLRN discriminated well between the MBC in all cohorts [overall AUC (95% confidence interval): 0.983 (0.973-0.993), 0.972 (0.952-0.993), 0.897 (0.823-0.971), and 0.993 (0.977-1.000) on the PC, VC, test cohorts1 (TC1) and test cohorts2 TC2 respectively]. In addition, the DLRN performed significantly better than three unimodal models and had good clinical utility.Conclusion. The DLRN demonstrates good discriminatory ability in the preoperative prediction of MBC, can better reveal the potential associations between clinical characteristics, ultrasound imaging features and disease pathology, and can facilitate the development of computer-aided diagnosis systems for breast cancer patients. Our code is available publicly in the repository athttps://github.com/wupeiyan/MDLRN.

A general approach for automatic segmentation of pneumonia, pulmonary nodule, and tuberculosis in CT images

Proposing a general segmentation approach for lung lesions, including pulmonary nodules, pneumonia, and tuberculosis, in CT images will improve efficiency in radiology. However, the performance of generative adversarial networks is hampered by the limited availability of annotated samples and the catastrophic forgetting of the discriminator, whereas the universality of traditional morphology-based methods is insufficient for segmenting diverse lung lesions. A cascaded dual-attention network with a context-aware pyramid feature extraction module was designed to address these challenges. A self-supervised rotation loss was designed to mitigate discriminator forgetting. The proposed model achieved Dice coefficients of 70.92, 73.55, and 68.52% on multi-center pneumonia, lung nodule, and tuberculosis test datasets, respectively. No significant decrease in accuracy was observed (p > 0.10) when a small training sample size was used. The cyclic training of the discriminator was reduced with self-supervised rotation loss (p < 0.01). The proposed approach is promising for segmenting multiple lung lesion types in CT images.

Can radiomic features extracted from intra-oral radiographs predict physiological bone remodelling around dental implants? A hypothesis-generating study

AIM

The rate of physiological bone remodelling (PBR) occurring after implant placement has been associated with the later onset of progressive bone loss and peri-implantitis, leading to medium- and long-term implant therapy failure. It is still questionable, however, whether PBR is associated with specific bone characteristics. The aim of this study was to assess whether radiomic analysis could reveal not readily appreciable bone features useful for the prediction of PBR.

MATERIALS AND METHODS

Radiomic features were extracted from the radiographs taken at implant placement (T0) using LifeX software. Because of the multi-centre design of the source study, ComBat harmonization was applied to the cohort. Different machine-learning models were trained on selected radiomic features to develop and internally validate algorithms capable of predicting high PBR. In addition, results of the algorithm were included in a multivariate analysis with other clinical variables (tissue thickness and depth of implant position) to test their independent correlation with PBR.

RESULTS

Specific radiomic features extracted at T0 are associated with higher PBR around tissue-level implants after 3 months of unsubmerged healing (T1). In addition, taking advantage of machine-learning methods, a naive Bayes model was trained using radiomic features selected by fast correlation-based filter (FCBF), which showed the best performance in the prediction of PBR (AUC = 0.751, sensitivity = 66.0%, specificity = 68.4%, positive predictive value = 73.3%, negative predictive value = 60.5%). In addition, results of the whole model were included in a multivariate analysis with tissue thickness and depth of implant position, which were still found to be independently associated with PBR (p-value < .01).

CONCLUSION

The combination of radiomics and machine-learning methods seems to be a promising approach for the early prediction of PBR. Such an innovative approach could be also used for the study of not readily disclosed bone characteristics, thus helping to explain not fully understood clinical phenomena. Although promising, the performance of the radiomic model should be improved in terms of specificity and sensitivity by further studies in this field.

Development and validation of a CT-based radiomics model for differentiating pneumonia-like primary pulmonary lymphoma from infectious pneumonia: A multicenter study

BACKGROUND

Pneumonia-like primary pulmonary lymphoma (PPL) was commonly misdiagnosed as infectious pneumonia, leading to delayed treatment. The purpose of this study was to establish a computed tomography (CT)-based radiomics model to differentiate pneumonia-like PPL from infectious pneumonia.

METHODS

In this retrospective study, 79 patients with pneumonia-like PPL and 176 patients with infectious pneumonia from 12 medical centers were enrolled. Patients from center 1 to center 7 were assigned to the training or validation cohort, and the remaining patients from other centers were used as the external test cohort. Radiomics features were extracted from CT images. A three-step procedure was applied for radiomics feature selection and radiomics signature building, including the inter- and intra-class correlation coefficients (ICCs), a one-way analysis of variance (ANOVA), and least absolute shrinkage and selection operator (LASSO). Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical factor model. Two radiologists reviewed the CT images for the external test set. Performance of the radiomics model, clinical factor model, and each radiologist were assessed by receiver operating characteristic, and area under the curve (AUC) was compared.

RESULTS

A total of 144 patients (44 with pneumonia-like PPL and 100 infectious pneumonia) were in the training cohort, 38 patients (12 with pneumonia-like PPL and 26 infectious pneumonia) were in the validation cohort, and 73 patients (23 with pneumonia-like PPL and 50 infectious pneumonia) were in the external test cohort. Twenty-three radiomics features were selected to build the radiomics model, which yielded AUCs of 0.95 (95% confidence interval [CI]: 0.94-0.99), 0.93 (95% CI: 0.85-0.98), and 0.94 (95% CI: 0.87-0.99) in the training, validation, and external test cohort, respectively. The AUCs for the two readers and clinical factor model were 0.74 (95% CI: 0.63-0.83), 0.72 (95% CI: 0.62-0.82), and 0.73 (95% CI: 0.62-0.84) in the external test cohort, respectively. The radiomics model outperformed both the readers' interpretation and clinical factor model ( P <0.05).

CONCLUSIONS

The CT-based radiomics model may provide an effective and non-invasive tool to differentiate pneumonia-like PPL from infectious pneumonia, which might provide assistance for clinicians in tailoring precise therapy.

Automatic Diagnosis of Stage of COVID-19 Patients using an Ensemble of Transfer Learning with Convolutional Neural Networks Based on Computed Tomography Images

Background

Diagnosis of the stage of COVID-19 patients using the chest computed tomography (CT) can help the physician in making decisions on the length of time required for hospitalization and adequate selection of patient care. This diagnosis requires very expert radiologists who are not available everywhere and is also tedious and subjective. The aim of this study is to propose an advanced machine learning system to diagnose the stages of COVID-19 patients including normal, early, progressive, peak, and absorption stages based on lung CT images, using an automatic deep transfer learning ensemble.

Methods

Different strategies of deep transfer learning were used which were based on pretrained convolutional neural networks (CNNs). Pretrained CNNs were fine-tuned on the chest CT images, and then, the extracted features were classified by a softmax layer. Finally, we built an ensemble method based on majority voting of the best deep transfer learning outputs to further improve the recognition performance.

Results

The experimental results from 689 cases indicate that the ensemble of three deep transfer learning outputs based on EfficientNetB4, InceptionResV3, and NasNetlarge has the highest results in diagnosing the stage of COVID-19 with an accuracy of 91.66%.

Conclusion

The proposed method can be used for the classification of the stage of COVID-19 disease with good accuracy to help the physician in making decisions on patient care.

Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach

Artificial intelligence (AI) has revolutionized numerous industries, including medicine. In recent years, the integration of AI into medical practices has shown great promise in enhancing the accuracy and efficiency of diagnosing diseases, predicting patient outcomes, and personalizing treatment plans. This paper aims at the exploration of the AI-based medicine research using network approach and analysis of existing trends based on PubMed. Our findings are based on the results of PubMed search queries and analysis of the number of papers obtained by the different search queries. Our goal is to explore how are the AI-based methods used in healthcare research, which approaches and techniques are the most popular, and to discuss the potential reasoning behind the obtained results. Using analysis of the co-occurrence network constructed using VOSviewer software, we detected the main clusters of interest in AI-based healthcare research. Then, we proceeded with the thorough analysis of publication activity in various categories of medical AI research, including research on different AI-based methods applied to different types of medical data. We analyzed the results of query processing in the PubMed database over the past 5 years obtained via a specifically designed strategy for generating search queries based on the thorough selection of keywords from different categories of interest. We provide a comprehensive analysis of existing applications of AI-based methods to medical data of different modalities, including the context of various medical fields and specific diseases that carry the greatest danger to the human population.

Are deep models in radiomics performing better than generic models? A systematic review

BACKGROUND

Application of radiomics proceeds by extracting and analysing imaging features based on generic morphological, textural, and statistical features defined by formulas. Recently, deep learning methods were applied. It is unclear whether deep models (DMs) can outperform generic models (GMs).

METHODS

We identified publications on PubMed and Embase to determine differences between DMs and GMs in terms of receiver operating area under the curve (AUC).

RESULTS

Of 1,229 records (between 2017 and 2021), 69 studies were included, 61 (88%) on tumours, 68 (99%) retrospective, and 39 (56%) single centre; 30 (43%) used an internal validation cohort; and 18 (26%) applied cross-validation. Studies with independent internal cohort had a median training sample of 196 (range 41-1,455); those with cross-validation had only 133 (43-1,426). Median size of validation cohorts was 73 (18-535) for internal and 94 (18-388) for external. Considering the internal validation, in 74% (49/66), the DMs performed better than the GMs, vice versa in 20% (13/66); no difference in 6% (4/66); and median difference in AUC 0.045. On the external validation, DMs were better in 65% (13/20), GMs in 20% (4/20) cases; no difference in 3 (15%); and median difference in AUC 0.025. On internal validation, fused models outperformed GMs and DMs in 72% (20/28), while they were worse in 14% (4/28) and equal in 14% (4/28); median gain in AUC was + 0.02. On external validation, fused model performed better in 63% (5/8), worse in 25% (2/8), and equal in 13% (1/8); median gain in AUC was + 0.025.

CONCLUSIONS

Overall, DMs outperformed GMs but in 26% of the studies, DMs did not outperform GMs.

Relationship between the deep features of the full-scan pathological map of mucinous gastric carcinoma and related genes based on deep learning

Background

Long-term differential expression of disease-associated genes is a crucial driver of pathological changes in mucinous gastric carcinoma. Therefore, there should be a correlation between depth features extracted from pathology-based full-scan images using deep learning and disease-associated gene expression. This study tried to provides preliminary evidence that long-term differentially expressed (disease-associated) genes lead to subtle changes in disease pathology by exploring their correlation, and offer a new ideas for precise analysis of pathomics and combined analysis of pathomics and genomics.

Methods

Full pathological scans, gene sequencing data, and clinical data of patients with mucinous gastric carcinoma were downloaded from TCGA data. The VGG-16 network architecture was used to construct a binary classification model to explore the potential of VGG-16 applications and extract the deep features of the pathology-based full-scan map. Differential gene expression analysis was performed and a protein-protein interaction network was constructed to screen disease-related core genes. Differential, Lasso regression, and extensive correlation analyses were used to screen for valuable deep features. Finally, a correlation analysis was used to determine whether there was a correlation between valuable deep features and disease-related core genes.

Result

The accuracy of the binary classification model was 0.775 ± 0.129. A total of 24 disease-related core genes were screened, including ASPM, AURKA, AURKB, BUB1, BUB1B, CCNA2, CCNB1, CCNB2, CDCA8, CDK1, CENPF, DLGAP5, KIF11, KIF20A, KIF2C, KIF4A, MELK, PBK, RRM2, TOP2A, TPX2, TTK, UBE2C, and ZWINT. In addition, differential, Lasso regression, and extensive correlation analyses were used to screen eight valuable deep features, including features 51, 106, 109, 118, 257, 282, 326, and 487. Finally, the results of the correlation analysis suggested that valuable deep features were either positively or negatively correlated with core gene expression.

Conclusion

The preliminary results of this study support our hypotheses. Deep learning may be an important bridge for the joint analysis of pathomics and genomics and provides preliminary evidence for long-term abnormal expression of genes leading to subtle changes in pathology.

Radiomics approach with deep learning for predicting T4 obstructive colorectal cancer using CT image

OBJECTIVES

Patients with T4 obstructive colorectal cancer (OCC) have a high mortality rate. Therefore, an accurate distinction between T4 and T1-T3 (NT4) in OCC is an important part of preoperative evaluation, especially in the emergency setting. This paper introduces three models of radiomics, deep learning, and deep learning-based radiomics to identify T4 OCC.

METHODS

We established a dataset of computed tomography (CT) images of 164 patients with pathologically confirmed OCC, from which 2537 slides were extracted. First, since T4 tumors penetrate the bowel wall and involve adjacent organs, we explored whether the peritumoral region contributes to the assessment of T4 OCC. Furthermore, we visualized the radiomics and deep learning features using the t-distributed stochastic neighbor embedding technique (t-SNE). Finally, we built a merged model by fusing radiomic features with deep learning features. In this experiment, the performance of each model was evaluated by the area under the receiver operating characteristic curve (AUC).

RESULTS

In the test cohort, the AUC values predicted by the radiomics model in the dilated region of interest (dROI) was 0.770. And the AUC value of the deep learning model with the patches extended 20-pixel reached 0.936. Combining the characteristics of radiomics and deep learning, our method achieved an AUC value of 0.947 in the T4 and non-T4 (NT4) classification, and increased the AUC value to 0.950 after the addition of clinical features.

CONCLUSION

The prediction results of our merged model of deep learning radiomics outperformed the deep learning model and significantly outperformed the radiomics model. The experimental results demonstrate that combining the peritumoral region improves the prediction performance of the radiomics model and the deep learning model.

Nomogram Using CT Radiomics Features for Differentiation of Pneumonia-Type Invasive Mucinous Adenocarcinoma and Pneumonia: Multicenter Development and External Validation Study

BACKGROUND. Pneumonia-type invasive mucinous adenocarcinoma (IMA) and pneumonia show overlapping chest CT features as well as overlapping clinical characteristics. OBJECTIVE. The purpose of our study was to develop and validate a nomogram combining clinical and CT-based radiomics features to differentiate pneumonia-type IMA and pneumonia. METHODS. This retrospective study included 314 patients (172 men, 142 women; mean age, 60.3 ± 14.5 [SD] years) from six hospitals who underwent noncontrast chest CT showing consolidation and were diagnosed with pneumonia-type IMA (n = 106) or pneumonia (n = 208). Patients from three hospitals formed a training set (n = 195) and a validation set (n = 50), and patients from the other three hospitals formed the external test set (n = 69). A model for predicting pneumonia-type IMA was built using clinical characteristics that were significant independent predictors of this diagnosis. Radiomics features were extracted from CT images by placing ROIs on areas of consolidation, and a radiomics signature of pneumonia-type IMA was constructed. A nomogram for predicting pneumonia-type IMA was constructed that combined features in the clinical model and the radiomics signature. Two cardiothoracic radiologists independently reviewed CT images in the external test set to diagnose pneumonia-type IMA. Diagnostic performance was compared among models and radiologists. Decision curve analysis (DCA) was performed. RESULTS. The clinical model included fever and family history of lung cancer. The radiomics signature included 15 radiomics features. DCA showed higher overall net benefit from the nomogram than from the clinical model. In the external test set, AUC was higher for the nomogram (0.85) than for the clinical model (0.71, p = .01), radiologist 1 (0.70, p = .04), and radiologist 2 (0.67, p = .01). In the external test set, the nomogram had sensitivity of 46.9%, specificity of 94.6%, and accuracy of 72.5%. CONCLUSION. The nomogram combining clinical variables and CT-based radiomics features outperformed the clinical model and two cardiothoracic radiologists in differentiating pneumonia-type IMA from pneumonia. CLINICAL IMPACT. The findings support potential clinical use of the nomogram for diagnosing pneumonia-type IMA in patients with consolidation on chest CT.

Current and Emerging Knowledge in COVID-19

COVID-19 has emerged as a pandemic leading to a global public health crisis of unprecedented morbidity. A comprehensive insight into the imaging of COVID-19 has enabled early diagnosis, stratification of disease severity, and identification of potential sequelae. The evolution of COVID-19 can be divided into early infectious, pulmonary, and hyperinflammatory phases. Clinical features, imaging features, and management are different among the three phases. In the early stage, peripheral ground-glass opacities are predominant CT findings, and therapy directly targeting SARS-CoV-2 is effective. In the later stage, organizing pneumonia or diffuse alveolar damage pattern are predominant CT findings and anti-inflammatory therapies are more beneficial. The risk of severe disease or hospitalization is lower in breakthrough or Omicron variant infection compared with nonimmunized or Delta variant infections. The protection rates of the fourth dose of mRNA vaccination were 34% and 67% against overall infection and hospitalizations for severe illness, respectively. After acute COVID-19 pneumonia, most residual CT abnormalities gradually decreased in extent, but they may remain as linear or multifocal reticular or cystic lesions. Advanced insights into the pathophysiologic and imaging features of COVID-19 along with vaccine benefits have improved patient care, but emerging knowledge of post-COVID-19 condition, or long COVID, also presents radiology with new challenges.

Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Detection of abnormal extraocular muscles in small datasets of computed tomography images using a three-dimensional variational autoencoder

We sought to establish an unsupervised algorithm with a three-dimensional (3D) variational autoencoder model (VAE) for the detection of abnormal extraocular muscles in small datasets of orbital computed tomography (CT) images. 334 CT images of normal orbits and 96 of abnormal orbits diagnosed as thyroid eye disease were used for training and validation; 24 normal and 11 abnormal orbits were used for the test. A 3D VAE was developed and trained. All images were preprocessed to emphasize extraocular muscles and to suppress background noise (e.g., high signal intensity from bones). The optimal cut-off value was identified through receiver operating characteristic (ROC) curve analysis. The ability of the model to detect muscles of abnormal size was assessed by visualization. The model achieved a sensitivity of 79.2%, specificity of 72.7%, accuracy of 77.1%, F1-score of 0.667, and AUROC of 0.801. Abnormal CT images correctly identified by the model showed differences in the reconstruction of extraocular muscles. The proposed model showed potential to detect abnormalities in extraocular muscles using a small dataset, similar to the diagnostic approach used by physicians. Unsupervised learning could serve as an alternative detection method for medical imaging studies in which annotation is difficult or impossible to perform.

Artificial intelligence for differentiating COVID-19 from other viral pneumonias on CT: comparative analysis of different models based on quantitative and radiomic approaches

BACKGROUND

To develop a pipeline for automatic extraction of quantitative metrics and radiomic features from lung computed tomography (CT) and develop artificial intelligence (AI) models supporting differential diagnosis between coronavirus disease 2019 (COVID-19) and other viral pneumonia (non-COVID-19).

METHODS

Chest CT of 1,031 patients (811 for model building; 220 as independent validation set (IVS) with positive swab for severe acute respiratory syndrome coronavirus-2 (647 COVID-19) or other respiratory viruses (384 non-COVID-19) were segmented automatically. A Gaussian model, based on the HU histogram distribution describing well-aerated and ill portions, was optimised to calculate quantitative metrics (QM, n = 20) in both lungs (2L) and four geometrical subdivisions (GS) (upper front, lower front, upper dorsal, lower dorsal; n = 80). Radiomic features (RF) of first (RF1, n = 18) and second (RF2, n = 120) order were extracted from 2L using PyRadiomics tool. Extracted metrics were used to develop four multilayer-perceptron classifiers, built with different combinations of QM and RF: Model1 (RF1-2L); Model2 (QM-2L, QM-GS); Model3 (RF1-2L, RF2-2L); Model4 (RF1-2L, QM-2L, GS-2L, RF2-2L).

RESULTS

The classifiers showed accuracy from 0.71 to 0.80 and area under the receiving operating characteristic curve (AUC) from 0.77 to 0.87 in differentiating COVID-19 versus non-COVID-19 pneumonia. Best results were associated with Model3 (AUC 0.867 ± 0.008) and Model4 (AUC 0.870 ± 0.011. For the IVS, the AUC values were 0.834 ± 0.008 for Model3 and 0.828 ± 0.011 for Model4.

CONCLUSIONS

Four AI-based models for classifying patients as COVID-19 or non-COVID-19 viral pneumonia showed good diagnostic performances that could support clinical decisions.

Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan

Purpose

To compare the diagnostic performance of radiomic analysis with machine learning (ML) model with a convolutional neural network (CNN) in differentiating thymic epithelial tumors (TETs) from other prevascular mediastinal tumors (PMTs).

Methods

A retrospective study was performed in patients with PMTs and undergoing surgical resection or biopsy in National Cheng Kung University Hospital, Tainan, Taiwan, E-Da Hospital, Kaohsiung, Taiwan, and Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan between January 2010 and December 2019. Clinical data including age, sex, myasthenia gravis (MG) symptoms and pathologic diagnosis were collected. The datasets were divided into UECT (unenhanced computed tomography) and CECT (enhanced computed tomography) for analysis and modelling. Radiomics model and 3D CNN model were used to differentiate TETs from non-TET PMTs (including cyst, malignant germ cell tumor, lymphoma and teratoma). The macro F1-score and receiver operating characteristic (ROC) analysis were performed to evaluate the prediction models.

Result

In the UECT dataset, there were 297 patients with TETs and 79 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 83.95%, ROC-AUC = 0.9117) had better performance than the 3D CNN model (macro F1-score = 75.54%, ROC-AUC = 0.9015). In the CECT dataset, there were 296 patients with TETs and 77 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 85.65%, ROC-AUC = 0.9464) had better performance than the 3D CNN model (macro F1-score = 81.01%, ROC-AUC = 0.9275).

Conclusion

Our study revealed that the individualized prediction model integrating clinical information and radiomic features using machine learning demonstrated better predictive performance in the differentiation of TETs from other PMTs at chest CT scan than 3D CNN model.

Personalized intrahepatic cholangiocarcinoma prognosis prediction using radiomics: Application and development trend

Radiomics was proposed by Lambin et al. in 2012 and since then there has been an explosion of related research. There has been significant interest in developing high-throughput methods that can automatically extract a large number of quantitative image features from medical images for better diagnostic or predictive performance. There have also been numerous radiomics investigations on intrahepatic cholangiocarcinoma in recent years, but no pertinent review materials are readily available. This work discusses the modeling analysis of radiomics for the prediction of lymph node metastasis, microvascular invasion, and early recurrence of intrahepatic cholangiocarcinoma, as well as the use of deep learning. This paper briefly reviews the current status of radiomics research to provide a reference for future studies.

Habitat Imaging Biomarkers for Diagnosis and Prognosis in Cancer Patients Infected with COVID-19

OBJECTIVES

Cancer patients have worse outcomes from the COVID-19 infection and greater need for ventilator support and elevated mortality rates than the general population. However, previous artificial intelligence (AI) studies focused on patients without cancer to develop diagnosis and severity prediction models. Little is known about how the AI models perform in cancer patients. In this study, we aim to develop a computational framework for COVID-19 diagnosis and severity prediction particularly in a cancer population and further compare it head-to-head to a general population.

METHODS

We have enrolled multi-center international cohorts with 531 CT scans from 502 general patients and 420 CT scans from 414 cancer patients. In particular, the habitat imaging pipeline was developed to quantify the complex infection patterns by partitioning the whole lung regions into phenotypically different subregions. Subsequently, various machine learning models nested with feature selection were built for COVID-19 detection and severity prediction.

RESULTS

These models showed almost perfect performance in COVID-19 infection diagnosis and predicting its severity during cross validation. Our analysis revealed that models built separately on the cancer population performed significantly better than those built on the general population and locked to test on the cancer population. This may be because of the significant difference among the habitat features across the two different cohorts.

CONCLUSIONS

Taken together, our habitat imaging analysis as a proof-of-concept study has highlighted the unique radiologic features of cancer patients and demonstrated effectiveness of CT-based machine learning model in informing COVID-19 management in the cancer population.

Registered Clinical Trials for Artificial Intelligence in Lung Disease: A Scoping Review on ClinicalTrials.gov

Clinical trials are the most effective tools to evaluate the advantages of various diagnostic and treatment modalities. AI used in medical issues, including screening, diagnosis, and treatment decisions, improves health outcomes and patient experiences. This study's objective was to investigate the traits of registered trials on artificial intelligence for lung disease. Clinical studies on AI for lung disease that were present in the ClinicalTrials.gov database were searched, and fifty-three registered trials were included. Forty-six (72.1%) were observational trials, compared to seven (27.9%) that were interventional trials. Only eight trials (15.4%) were completed. Thirty (56.6%) trials were accepting applicants. Clinical studies often included a large number of cases; for example, 24 (32.0%) trials included samples of 100-1000 cases, while 14 (17.5%) trials included samples of 1000-2000 cases. Of the interventional trials, twenty (15.7%) were retrospective studies and twenty (65.7%) were prospective studies.

Application of Machine Learning and Deep Learning Techniques for COVID-19 Screening Using Radiological Imaging: A Comprehensive Review

Lung, being one of the most important organs in human body, is often affected by various SARS diseases, among which COVID-19 has been found to be the most fatal disease in recent times. In fact, SARS-COVID 19 led to pandemic that spreads fast among the community causing respiratory problems. Under such situation, radiological imaging-based screening [mostly chest X-ray and computer tomography (CT) modalities] has been performed for rapid screening of the disease as it is a non-invasive approach. Due to scarcity of physician/chest specialist/expert doctors, technology-enabled disease screening techniques have been developed by several researchers with the help of artificial intelligence and machine learning (AI/ML). It can be remarkably observed that the researchers have introduced several AI/ML/DL (deep learning) algorithms for computer-assisted detection of COVID-19 using chest X-ray and CT images. In this paper, a comprehensive review has been conducted to summarize the works related to applications of AI/ML/DL for diagnostic prediction of COVID-19, mainly using X-ray and CT images. Following the PRISMA guidelines, total 265 articles have been selected out of 1715 published articles till the third quarter of 2021. Furthermore, this review summarizes and compares varieties of ML/DL techniques, various datasets, and their results using X-ray and CT imaging. A detailed discussion has been made on the novelty of the published works, along with advantages and limitations.

CT-based radiomics in predicting pathological response in non-small cell lung cancer patients receiving neoadjuvant immunotherapy

Objectives

In radiomics, high-throughput algorithms extract objective quantitative features from medical images. In this study, we evaluated CT-based radiomics features, clinical features, in-depth learning features, and a combination of features for predicting a good pathological response (GPR) in non-small cell lung cancer (NSCLC) patients receiving immunotherapy-based neoadjuvant therapy (NAT).

Materials and methods

We reviewed 62 patients with NSCLC who received surgery after immunotherapy-based NAT and collected clinicopathological data and CT images before and after immunotherapy-based NAT. A series of image preprocessing was carried out on CT scanning images: tumor segmentation, conventional radiomics feature extraction, deep learning feature extraction, and normalization. Spearman correlation coefficient, principal component analysis (PCA), and least absolute shrinkage and selection operator (LASSO) were used to screen features. The pretreatment traditional radiomics combined with clinical characteristics (before_rad_cil) model and pretreatment deep learning characteristics (before_dl) model were constructed according to the data collected before treatment. The data collected after NAT created the after_rad_cil model and after_dl model. The entire model was jointly constructed by all clinical features, conventional radiomics features, and deep learning features before and after neoadjuvant treatment. Finally, according to the data obtained before and after treatment, the before_nomogram and after_nomogram were constructed.

Results

In the before_rad_cil model, four traditional radiomics features (“original_shape_flatness,” “wavelet hhl_firer_skewness,” “wavelet hlh_firer_skewness,” and “wavelet lll_glcm_correlation”) and two clinical features (“gender” and “N stage”) were screened out to predict a GPR. The average prediction accuracy (ACC) after modeling with k-nearest neighbor (KNN) was 0.707. In the after_rad_cil model, nine features predictive of GPR were obtained after feature screening, among which seven were traditional radiomics features: “exponential_firer_skewness,” “exponential_glrlm_runentropy,” “log- sigma-5-0-mm-3d_firer_kurtosis,” “logarithm_skewness,” “original_shape_elongation,” “original_shape_brilliance,” and “wavelet llh_glcm_clustershade”; two were clinical features: “after_CRP” and “after lymphocyte percentage.” The ACC after modeling with support vector machine (SVM) was 0.682. The before_dl model and after_dl model were modeled by SVM, and the ACC was 0.629 and 0.603, respectively. After feature screening, the entire model was constructed by multilayer perceptron (MLP), and the ACC of the GPR was the highest, 0.805. The calibration curve showed that the predictions of the GPR by the before_nomogram and after_nomogram were in consensus with the actual GPR.

Conclusion

CT-based radiomics has a good predictive ability for a GPR in NSCLC patients receiving immunotherapy-based NAT. Among the radiomics features combined with the clinicopathological information model, deep learning feature model, and the entire model, the entire model had the highest prediction accuracy.

Radiomics: a primer on high-throughput image phenotyping

Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.

Impact of image quality on radiomics applications

Radiomics features extracted from medical images have been widely reported to be useful in the patient specific outcome modeling for variety of assessment and prediction purposes. Successful application of radiomics features as imaging biomarkers, however, is dependent on the robustness of the approach to the variation in each step of the modeling workflow. Variation in the input image quality is one of the main sources that impacts the reproducibility of radiomics analysis when a model is applied to broader range of medical imaging data. The quality of medical image is generally affected by both the scanner related factors such as image acquisition/reconstruction settings and the patient related factors such as patient motion. This article aimed to review the published literatures in this field that reported the impact of various imaging factors on the radiomics features through the change in image quality. The literatures were categorized by different imaging modalities and also tabulated based on the imaging parameters and the class of radiomics features included in the study. Strategies for image quality standardization were discussed based on the relevant literatures and recommendations for reducing the impact of image quality variation on the radiomics in multi-institutional clinical trial were summarized at the end of this article.

Detection of stage of lung changes in COVID-19 disease based on CT images: a radiomics approach

The aim of this study is to classify patients suspected from COVID-19 to five stages as normal, early, progressive, peak, and absorption stages using radiomics approach based on lung computed tomography images. Lung CT scans of 683 people were evaluated. A set of statistical texture features was extracted from each CT image. The people were classified using the random forest algorithm as an ensemble method based on the decision trees outputs to five stages of COVID-19 disease. Proposed method attains the highest result with an accuracy of 93.55% (96.25% in normal, 74.39% in early, 100% in progressive, 82.19% in peak, and 96% in absorption stage) compared to the other three common classifiers. Radiomics method can be used for the classification of the stage of COVID-19 disease with good accuracy to help decide the length of time required to hospitalize patients, determine the type of treatment process required for patients in each category, and reduce the cost of care and treatment for hospitalized individuals.

SARS-CoV-2 Achieves Immune Escape by Destroying Mitochondrial Quality: Comprehensive Analysis of the Cellular Landscapes of Lung and Blood Specimens From Patients With COVID-19

Mitochondria get caught in the crossfire of coronavirus disease 2019 (COVID-19) and antiviral immunity. The mitochondria-mediated antiviral immunity represents the host’s first line of defense against viral infection, and the mitochondria are important targets of COVID-19. However, the specific manifestations of mitochondrial damage in patients with COVID-19 have not been systematically clarified. This study comprehensively analyzed one single-cell RNA-sequencing dataset of lung tissue and two bulk RNA-sequencing datasets of blood from COVID-19 patients. We found significant changes in mitochondrion-related gene expression, mitochondrial functions, and related metabolic pathways in patients with COVID-19. SARS-CoV-2 first infected the host alveolar epithelial cells, which may have induced excessive mitochondrial fission, inhibited mitochondrial degradation, and destroyed the mitochondrial calcium uniporter (MCU). The type II alveolar epithelial cell count decreased and the transformation from type II to type I alveolar epithelial cells was blocked, which exacerbated viral immune escape and replication in COVID-19 patients. Subsequently, alveolar macrophages phagocytized the infected alveolar epithelial cells, which decreased mitochondrial respiratory capacity and activated the ROS–HIF1A pathway in macrophages, thereby aggravating the pro-inflammatory reaction in the lungs. Infected macrophages released large amounts of interferon into the blood, activating mitochondrial IFI27 expression and destroying energy metabolism in immune cells. The plasma differentiation of B cells and lung-blood interaction of regulatory T cells (Tregs) was exacerbated, resulting in a cytokine storm and excessive inflammation. Thus, our findings systematically explain immune escape and excessive inflammation seen during COVID-19 from the perspective of mitochondrial quality imbalance.

Dopamine transporter single-photon emission computed tomography-derived radiomics signature for detecting Parkinson's disease

BACKGROUND

We hypothesised that the radiomics signature, which includes texture information of dopamine transporter single-photon emission computed tomography (DAT-SPECT) images for Parkinson's disease (PD), may assist semi-quantitative indices. Herein, we constructed a radiomics signature using DAT-SPECT-derived radiomics features that effectively discriminated PD from healthy individuals and evaluated its classification performance.

RESULTS

We analysed 413 cases of both normal control (NC, n = 101) and PD (n = 312) groups from the Parkinson's Progression Markers Initiative database. Data were divided into the training and two test datasets with different SPECT manufacturers. DAT-SPECT images were spatially normalised to the Montreal Neurologic Institute space. We calculated 930 radiomics features, including intensity- and texture-based features in the caudate, putamen, and pallidum volumes of interest. The striatum uptake ratios (SURs) of the caudate, putamen, and pallidum were also calculated as conventional semi-quantification indices. The least absolute shrinkage and selection operator was used for feature selection and construction of the radiomics signature. The four classification models were constructed using a radiomics signature and/or semi-quantitative indicator. Furthermore, we compared the classification performance of the semi-quantitative indicator alone and the combination with the radiomics signature for the classification models. The receiver operating characteristics (ROC) analysis was used to evaluate the classification performance. The classification performance of SUR_putamen was higher than that of other semi-quantitative indicators. The radiomics signature resulted in a slightly increased area under the ROC curve (AUC) compared to SUR_putamen in each test dataset. When combined with SUR_putamen and radiomics signature, all classification models showed slightly higher AUCs than that of SUR_putamen alone.

CONCLUSION

We constructed a DAT-SPECT image-derived radiomics signature. Performance analysis showed that the current radiomics signature would be helpful for the diagnosis of PD and has the potential to provide robust diagnostic performance.

Development of Machine-Learning Model to Predict COVID-19 Mortality: Application of Ensemble Model and Regarding Feature Impacts

This study was designed to develop machine-learning models to predict COVID-19 mortality and identify its key features based on clinical characteristics and laboratory tests. For this, deep-learning (DL) and machine-learning (ML) models were developed using receiver operating characteristic (ROC) area under the curve (AUC) and F1 score optimization of 87 parameters. Of the two, the DL model exhibited better performance (AUC 0.8721, accuracy 0.84, and F1 score 0.76). However, we also blended DL with ML, and the ensemble model performed the best (AUC 0.8811, accuracy 0.85, and F1 score 0.77). The DL model is generally unable to extract feature importance; however, we succeeded by using the Shapley Additive exPlanations method for each model. This study demonstrated both the applicability of DL and ML models for classifying COVID-19 mortality using hospital-structured data and that the ensemble model had the best predictive ability.

Deep learning combined with radiomics for the classification of enlarged cervical lymph nodes

PURPOSE

To investigate the application of deep learning combined with traditional radiomics methods for classifying enlarged cervical lymph nodes.

METHODS

The clinical and computed tomography (CT) imaging data of 276 patients with enlarged cervical lymph nodes (150 with lymph-node metastasis, 65 with lymphoma, and 61 with benign lymphadenopathy) who were treated at the hospital from January 2015 to January 2021 were retrospectively analysed. The patients were randomly divided into a training group and a test group at a ratio of 8:2. The radiomics features were extracted using one-by-one convolution and neural network activation, filtered with the least absolute shrinkage and selection operator (LASSO) model, and used to construct a discrimination model with PyTorch. Then, the performance of the model was compared with the radiologists' diagnostic performance. The neural network model was evaluated using the area under the receiver-operator characteristic curve (AUC), and the accuracy, sensitivity, and specificity were analysed.

RESULTS

A total of 102 features, comprising five traditional radiomic features and 97 deep learning features, were selected with LASSO and used to construct a discrimination model, which achieved a total accuracy of 87.50%. The AUC value, specificity, and sensitivity were, respectively, 0.92, 92.30%, and 90.00% for metastatic lymph nodes, 0.87, 95.45%, and 83.33% for benign lymphadenopathy, and 0.88, 90.47%, and 85.71% for lymphoma. The accuracies of the radiologists' diagnoses were 62.68% and 62.68%. The diagnostic performance of the model was significantly different from that of the radiologists (p < 0.05).

CONCLUSION

CT-based deep learning combined with the traditional radiomics methods has a high diagnostic value for the classification of cervical enlarged lymph nodes.

Machine learning based on routine laboratory indicators promoting the discrimination between active tuberculosis and latent tuberculosis infection

BACKGROUND

Discriminating active tuberculosis (ATB) from latent tuberculosis infection (LTBI) remains challenging. The present study aims to evaluate the performance of diagnostic models established using machine learning based on routine laboratory indicators in differentiating ATB from LTBI.

METHODS

Participants were respectively enrolled at Tongji Hospital (discovery cohort) and Sino-French New City Hospital (validation cohort). Diagnostic models were established based on routine laboratory indicators using machine learning.

RESULTS

A total of 2619 participants (1025 ATB and 1594 LTBI) were enrolled in discovery cohort and another 942 subjects (388 ATB and 554 LTBI) were recruited in validation cohort. ATB patients had significantly higher levels of tuberculosis-specific antigen/phytohemagglutinin ratio and coefficient variation of red blood cell volume distribution width, and lower levels of albumin and lymphocyte count than those of LTBI individuals. Six models were built and the optimal performance was obtained from GBM model. GBM model derived from training set (n = 1965) differentiated ATB from LTBI in the test set (n = 654) with a sensitivity of 84.38% (95% CI, 79.42%-88.31%) and a specificity of 92.71% (95% CI, 89.73%-94.88%). Further validation by an independent cohort confirmed its encouraging value with a sensitivity of 87.63% (95% CI, 83.98%-90.54%) and specificity of 91.34% (95% CI, 88.70%-93.40%), respectively.

CONCLUSIONS

We successfully developed a model with promising diagnostic value based on machine learning for the first time. Our study proposed that GBM model may be of great benefit served as a tool for the accurate identification of ATB.

Facilitating standardized COVID-19 suspicion prediction based on computed tomography radiomics in a multi-demographic setting

Objective

To develop an automatic COVID-19 Reporting and Data System (CO-RADS)–based classification in a multi-demographic setting.

Methods

This multi-institutional review boards–approved retrospective study included 2720 chest CT scans (mean age, 58 years [range 18–100 years]) from Italian and Russian patients. Three board-certified radiologists from three countries assessed randomly selected subcohorts from each population and provided CO-RADS–based annotations. CT radiomic features were extracted from the selected subcohorts after preprocessing steps like lung lobe segmentation and automatic noise reduction. We compared three machine learning models, logistic regression (LR), multilayer perceptron (MLP), and random forest (RF) for the automated CO-RADS classification. Model evaluation was carried out in two scenarios, first, training on a mixed multi-demographic subcohort and testing on an independent hold-out dataset. In the second scenario, training was done on a single demography and externally validated on the other demography.

Results

The overall inter-observer agreement for the CO-RADS scoring between the radiologists was substantial (k = 0.80). Irrespective of the type of validation test scenario, suspected COVID-19 CT scans were identified with an accuracy of 84%. SHapley Additive exPlanations (SHAP) interpretation showed that the “wavelet_(LH)_GLCM_Imc1” feature had a positive impact on COVID prediction both with and without noise reduction. The application of noise reduction improved the overall performance between the classifiers for all types.

Conclusion

Using an automated model based on the COVID-19 Reporting and Data System (CO-RADS), we achieved clinically acceptable performance in a multi-demographic setting. This approach can serve as a standardized tool for automated COVID-19 assessment.

Keypoints

• Automatic CO-RADS scoring of large-scale multi-demographic chest CTs with mean AUC of 0.93 ± 0.04.

• Validation procedure resembles TRIPOD 2b and 3 categories, enhancing the quality of experimental design to test the cross-dataset domain shift between institutions aiding clinical integration.

• Identification of COVID-19 pneumonia in the presence of community-acquired pneumonia and other comorbidities with an AUC of 0.92.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00330-022-08730-6.

An externally validated fully automated deep learning algorithm to classify COVID-19 and other pneumonias on chest CT

Purpose

In this study, we propose an artificial intelligence (AI) framework based on three-dimensional convolutional neural networks to classify computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19), influenza/community-acquired pneumonia (CAP), and no infection, after automatic segmentation of the lungs and lung abnormalities.

Methods

The AI classification model is based on inflated three-dimensional Inception architecture and was trained and validated on retrospective data of CT images of 667 adult patients (no infection n=188, COVID-19 n=230, influenza/CAP n=249) and 210 adult patients (no infection n=70, COVID-19 n=70, influenza/CAP n=70), respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients (no infection n=55, COVID-19 n= 94, influenza/CAP n=124) and an external validation set from a different centre (305 adult patients: COVID-19 n=169, no infection n=76, influenza/CAP n=60).

Results

The model showed excellent performance in the external validation set with area under the curve of 0.90, 0.92 and 0.92 for COVID-19, influenza/CAP and no infection, respectively. The selection of the input slices based on automatic segmentation of the abnormalities in the lung reduces analysis time (56 s per scan) and computational burden of the model. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score of the proposed model is 47% (15 out of 32 TRIPOD items).

Conclusion

This AI solution provides rapid and accurate diagnosis in patients suspected of COVID-19 infection and influenza.

A fully automated artificial intelligence-based network is proposed to classify CT volumes of patients affected with COVID-19 or influenza/CAP, and in the uninfectedhttps://bit.ly/3MJrVRi

The value of CT radiomic in differentiating mycoplasma pneumoniae pneumonia from streptococcus pneumoniae pneumonia with similar consolidation in children under 5 years

OBJECTIVE

To investigate the value of CT radiomics in the differentiation of mycoplasma pneumoniae pneumonia (MPP) from streptococcus pneumoniae pneumonia (SPP) with similar CT manifestations in children under 5 years.

METHODS

A total of 102 children with MPP (n = 52) or SPP (n = 50) with similar consolidation and surrounding halo on CT images in Qilu Hospital and Qilu Children's Hospital between January 2017 and March 2022 were enrolled in the retrospective study. Radiomic features of the both lesions on plain CT images were extracted including the consolidation part of the pneumonia or both consolidation and surrounding halo area which were respectively delineated at region of interest (ROI) areas on the maximum axial image. The training cohort (n = 71) and the validation cohort (n = 31) were established by stratified random sampling at a ratio of 7:3. By means of variance threshold, the effective radiomics features, SelectKBest and least absolute shrinkage and selection operator (LASSO) regression method were employed for feature selection and combined to calculate the radiomics score (Rad-score). Six classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) were used to construct the models based on radiomic features. The diagnostic performance of these models and the radiomic nomogram was estimated and compared using the area under the receiver operating characteristic (ROC) curve (AUC), and the decision curve analysis (DCA) was used to evaluate which model achieved the most net benefit.

RESULTS

RF outperformed other classifiers and was selected as the backbone in the classifier with the consolidation + the surrounding halo was taken as ROI to differentiate MPP from SPP in validation cohort. The AUC value of MPP in validation cohort was 0.822, the sensitivity and specificity were 0.81 and 0.81, respectively.

CONCLUSION

The RF model has the best classification efficiency in the identification of MPP from SPP in children, and the ROI with both consolidation and surrounding halo is most suitable for the delineation.

Methodological quality of machine learning-based quantitative imaging analysis studies in esophageal cancer: a systematic review of clinical outcome prediction after concurrent chemoradiotherapy

PURPOSE

Studies based on machine learning-based quantitative imaging techniques have gained much interest in cancer research. The aim of this review is to critically appraise the existing machine learning-based quantitative imaging analysis studies predicting outcomes of esophageal cancer after concurrent chemoradiotherapy in accordance with PRISMA guidelines.

METHODS

A systematic review was conducted in accordance with PRISMA guidelines. The citation search was performed via PubMed and Embase Ovid databases for literature published before April 2021. From each full-text article, study characteristics and model information were summarized. We proposed an appraisal matrix with 13 items to assess the methodological quality of each study based on recommended best-practices pertaining to quality.

RESULTS

Out of 244 identified records, 37 studies met the inclusion criteria. Study endpoints included prognosis, treatment response, and toxicity after concurrent chemoradiotherapy with reported discrimination metrics in validation datasets between 0.6 and 0.9, with wide variation in quality. A total of 30 studies published within the last 5 years were evaluated for methodological quality and we found 11 studies with at least 6 "good" item ratings.

CONCLUSION

A substantial number of studies lacked prospective registration, external validation, model calibration, and support for use in clinic. To further improve the predictive power of machine learning-based models and translate into real clinical applications in cancer research, appropriate methodologies, prospective registration, and multi-institution validation are recommended.

Classification of Clinically Significant Prostate Cancer on Multi-Parametric MRI: A Validation Study Comparing Deep Learning and Radiomics

The computer-aided analysis of prostate multiparametric MRI (mpMRI) could improve significant-prostate-cancer (PCa) detection. Various deep-learning- and radiomics-based methods for significant-PCa segmentation or classification have been reported in the literature. To be able to assess the generalizability of the performance of these methods, using various external data sets is crucial. While both deep-learning and radiomics approaches have been compared based on the same data set of one center, the comparison of the performances of both approaches on various data sets from different centers and different scanners is lacking. The goal of this study was to compare the performance of a deep-learning model with the performance of a radiomics model for the significant-PCa diagnosis of the cohorts of various patients. We included the data from two consecutive patient cohorts from our own center (n = 371 patients), and two external sets of which one was a publicly available patient cohort (n = 195 patients) and the other contained data from patients from two hospitals (n = 79 patients). Using multiparametric MRI (mpMRI), the radiologist tumor delineations and pathology reports were collected for all patients. During training, one of our patient cohorts (n = 271 patients) was used for both the deep-learning- and radiomics-model development, and the three remaining cohorts (n = 374 patients) were kept as unseen test sets. The performances of the models were assessed in terms of their area under the receiver-operating-characteristic curve (AUC). Whereas the internal cross-validation showed a higher AUC for the deep-learning approach, the radiomics model obtained AUCs of 0.88, 0.91 and 0.65 on the independent test sets compared to AUCs of 0.70, 0.73 and 0.44 for the deep-learning model. Our radiomics model that was based on delineated regions resulted in a more accurate tool for significant-PCa classification in the three unseen test sets when compared to a fully automated deep-learning model.

Artificial Intelligence in Prenatal Ultrasound Diagnosis

The application of artificial intelligence (AI) technology to medical imaging has resulted in great breakthroughs. Given the unique position of ultrasound (US) in prenatal screening, the research on AI in prenatal US has practical significance with its application to prenatal US diagnosis improving work efficiency, providing quantitative assessments, standardizing measurements, improving diagnostic accuracy, and automating image quality control. This review provides an overview of recent studies that have applied AI technology to prenatal US diagnosis and explains the challenges encountered in these applications.

Trends in the application of deep learning networks in medical image analysis: Evolution between 2012 and 2020

PURPOSE

To evaluate the general rules and future trajectories of deep learning (DL) networks in medical image analysis through bibliometric and hot spot analysis of original articles published between 2012 and 2020.

METHODS

Original articles related to DL and medical imaging were retrieved from the PubMed database. For the analysis, data regarding radiological subspecialties; imaging techniques; DL networks; sample size; study purposes, setting, origins and design; statistical analysis; funding sources; authors; and first authors' affiliation was manually extracted from each article. The Bibliographic Item Co-Occurrence Matrix Builder and VOSviewer were used to identify the research topics of the included articles and illustrate the future trajectories of studies.

RESULTS

The study included 2685 original articles. The number of publications on DL and medical imaging has increased substantially since 2017, accounting for 97.2% of all included articles. We evaluated the rules of the application of 47 DL networks to eight radiological tasks on 11 human organ sites. Neuroradiology, thorax, and abdomen were frequent research subjects, while thyroid was under-represented. Segmentation and classification tasks were the primary purposes. U-Net, ResNet, and VGG were the most frequently used Convolutional neural network-derived networks. GAN-derived networks were widely developed and applied in 2020, and transfer learning was highlighted in the COVID-19 studies. Brain, prostate, and diabetic retinopathy-related studies were mature research topics in the field. Breast- and lung-related studies were in a stage of rapid development.

CONCLUSIONS

This study evaluates the general rules and future trajectories of DL network application in medical image analyses and provides guidance for future studies.

Artificial intelligence for imaging-based COVID-19 detection: Systematic review comparing added value of AI versus human readers

PURPOSE

A growing number of studies have examined whether Artificial Intelligence (AI) systems can support imaging-based diagnosis of COVID-19-caused pneumonia, including both gains in diagnostic performance and speed. However, what is currently missing is a combined appreciation of studies comparing human readers and AI.

METHODS

We followed PRISMA-DTA guidelines for our systematic review, searching EMBASE, PUBMED and Scopus databases. To gain insights into the potential value of AI methods, we focused on studies comparing the performance of human readers versus AI models or versus AI-supported human readings.

RESULTS

Our search identified 1270 studies, of which 12 fulfilled specific selection criteria. Concerning diagnostic performance, in testing datasets reported sensitivity was 42-100% (human readers, n = 9 studies), 60-95% (AI systems, n = 10) and 81-98% (AI-supported readers, n = 3), whilst reported specificity was 26-100% (human readers, n = 8), 61-96% (AI systems, n = 10) and 78-99% (AI-supported readings, n = 2). One study highlighted the potential of AI-supported readings for the assessment of lung lesion burden changes, whilst two studies indicated potential time savings for detection with AI.

CONCLUSIONS

Our review indicates that AI systems or AI-supported human readings show less performance variability (interquartile range) in general, and may support the differentiation of COVID-19 pneumonia from other forms of pneumonia when used in high-prevalence and symptomatic populations. However, inconsistencies related to study design, reporting of data, areas of risk of bias, as well as limitations of statistical analyses complicate clear conclusions. We therefore support efforts for developing critical elements of study design when assessing the value of AI for diagnostic imaging.

Combining 18F-DOPA PET and MRI with perfusion-weighted imaging improves delineation of high-grade subregions in enhancing and non-enhancing gliomas prior treatment: a biopsy-controlled study

PURPOSE

We aimed to compare spatial extent of high-grade subregions detected with combined [¹⁸F]-dihydroxyphenylalanine (¹⁸F-DOPA) PET and MRI to the one provided by advanced multimodal MRI alone including Contrast-enhanced (CE) and Perfusion weighted imaging (PWI). Then, we compared the accuracy between imaging modalities, in a per biopsy analysis.

METHODS

Participants with suspected diffuse glioma were prospectively included between June 2018 and September 2019. Volumes of high-grade subregions were delineated respectively on ¹⁸F-DOPA PET and MRI (CE and PWI). Up to three per-surgical neuronavigation-guided biopsies were performed per patient.

RESULTS

Thirty-eight biopsy samples from sixteen participants were analyzed. Six participants (38%) had grade IV IDH wild-type glioblastoma, six (38%) had grade III IDH-mutated astrocytoma and four (24%) had grade II IDH-mutated gliomas. Three patients had intratumoral heterogeneity with coexisting high- and low-grade tumor subregions. High-grade volumes determined with combined ¹⁸F-DOPA PET/MRI (median of 1.7 [interquartile range (IQR) 0.0, 19.1] mL) were larger than with multimodal MRI alone (median 1.3 [IQR 0.0, 12.8] mL) with low overlap (median Dice's coefficient 0.24 [IQR 0.08, 0.59]). Delineation volumes were substantially increased in five (31%) patients. In a per biopsy analysis, combined ¹⁸F-DOPA PET/MRI detected high-grade subregions with an accuracy of 58% compared to 42% (p = 0.03) with CE MRI alone and 50% (p = 0.25) using multimodal MRI (CE + PWI).

CONCLUSIONS

The addition of ¹⁸F-DOPA PET to multimodal MRI (CE and PWI) enlarged the delineation volumes and enhanced overall accuracy for detection of high-grade subregions. Thus, combining ¹⁸F-DOPA with advanced MRI may improve treatment planning in newly diagnosed gliomas.

A Promising and Challenging Approach: Radiologists' Perspective on Deep Learning and Artificial Intelligence for Fighting COVID-19

Chest X-rays (CXR) and computed tomography (CT) are the main medical imaging modalities used against the increased worldwide spread of the 2019 coronavirus disease (COVID-19) epidemic. Machine learning (ML) and artificial intelligence (AI) technology, based on medical imaging fully extracting and utilizing the hidden information in massive medical imaging data, have been used in COVID-19 research of disease diagnosis and classification, treatment decision-making, efficacy evaluation, and prognosis prediction. This review article describes the extensive research of medical image-based ML and AI methods in preventing and controlling COVID-19, and summarizes their characteristics, differences, and significance in terms of application direction, image collection, and algorithm improvement, from the perspective of radiologists. The limitations and challenges faced by these systems and technologies, such as generalization and robustness, are discussed to indicate future research directions.

Reliable and Interpretable Mortality Prediction With Strong Foresight in COVID-19 Patients: An International Study From China and Germany

Cohort-independent robust mortality prediction model in patients with COVID-19 infection is not yet established. To build up a reliable, interpretable mortality prediction model with strong foresight, we have performed an international, bi-institutional study from China (Wuhan cohort, collected from January to March) and Germany (Würzburg cohort, collected from March to September). A Random Forest-based machine learning approach was applied to 1,352 patients from the Wuhan cohort, generating a mortality prediction model based on their clinical features. The results showed that five clinical features at admission, including lymphocyte (%), neutrophil count, C-reactive protein, lactate dehydrogenase, and α-hydroxybutyrate dehydrogenase, could be used for mortality prediction of COVID-19 patients with more than 91% accuracy and 99% AUC. Additionally, the time-series analysis revealed that the predictive model based on these clinical features is very robust over time when patients are in the hospital, indicating the strong association of these five clinical features with the progression of treatment as well. Moreover, for different preexisting diseases, this model also demonstrated high predictive power. Finally, the mortality prediction model has been applied to the independent Würzburg cohort, resulting in high prediction accuracy (with above 90% accuracy and 85% AUC) as well, indicating the robustness of the model in different cohorts. In summary, this study has established the mortality prediction model that allowed early classification of COVID-19 patients, not only at admission but also along the treatment timeline, not only cohort-independent but also highly interpretable. This model represents a valuable tool for triaging and optimizing the resources in COVID-19 patients.