Fusion-based tensor radiomics using reproducible features: Application to survival prediction in head and neck cancer

A radiomics approach to distinguish Progressive Supranuclear Palsy Richardson's syndrome from other phenotypes starting from MR images

BACKGROUND AND OBJECTIVE

Progressive Supranuclear Palsy (PSP) is an uncommon neurodegenerative disorder with different clinical onset, including Richardson's syndrome (PSP-RS) and other variant phenotypes (vPSP). Recognising the clinical progression of different phenotypes would enhance the accuracy of detection and treatment of PSP. The study goal was to identify radiomic biomarkers for distinguishing PSP phenotypes extracted from T1-weighted magnetic resonance images (MRI).

METHODS

Forty PSP patients (20 PSP-RS and 20 vPSP) took part in the present work. Radiomic features were collected from 21 regions of interest (ROIs) mainly from frontal cortex, supratentorial white matter, basal nuclei, brainstem, cerebellum, 3rd and 4th ventricles. After features selection, three tree-based machine learning (ML) classifiers were implemented to classify PSP phenotypes.

RESULTS

10 out of 21 ROIs performed best about sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUCROC). Particularly, features extracted from the pons region obtained the best accuracy (0.92) and AUCROC (0.83) values while by using the other 10 ROIs, evaluation metrics range from 0.67 to 0.83. Eight features of the Gray Level Dependence Matrix were recurrently extracted for the 10 ROIs. Furthermore, by combining these ROIs, the results exceeded 0.83 in phenotypes classification and the selected areas were brain stem, pons, occipital white matter, precentral gyrus and thalamus regions.

CONCLUSIONS

Based on the achieved results, our proposed approach could represent a promising tool for distinguishing PSP-RS from vPSP.

A Novel Multi-Modal Population-Graph Based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction

Prognostic risk prediction is pivotal for clinicians to appraise the patient's esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized therapy treatment plans. Currently, CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative prognostic risk assessment in the early stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and explore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a novel multi-modal population-graph based framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. Moreover, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task and an unsupervised-based task. Sufficient experimental results show that our model achieved state-of-the-art performance compared with other baseline models as well as the gold standard on discriminative ability, risk stratification, and clinical utility.

Landscape of 2D Deep Learning Segmentation Networks Applied to CT Scan from Lung Cancer Patients: A Systematic Review

BACKGROUND

The increasing rates of lung cancer emphasize the need for early detection through computed tomography (CT) scans, enhanced by deep learning (DL) to improve diagnosis, treatment, and patient survival. This review examines current and prospective applications of 2D- DL networks in lung cancer CT segmentation, summarizing research, highlighting essential concepts and gaps; Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines, a systematic search of peer-reviewed studies from 01/2020 to 12/2024 on data-driven population segmentation using structured data was conducted across databases like Google Scholar, PubMed, Science Direct, IEEE (Institute of Electrical and Electronics Engineers) and ACM (Association for Computing Machinery) library. 124 studies met the inclusion criteria and were analyzed.

RESULTS

The LIDC-LIDR dataset was the most frequently used; The finding particularly relies on supervised learning with labeled data. The UNet model and its variants were the most frequently used models in medical image segmentation, achieving Dice Similarity Coefficients (DSC) of up to 0.9999. The reviewed studies primarily exhibit significant gaps in addressing class imbalances (67%), underuse of cross-validation (21%), and poor model stability evaluations (3%). Additionally, 88% failed to address the missing data, and generalizability concerns were only discussed in 34% of cases.

CONCLUSIONS

The review emphasizes the importance of Convolutional Neural Networks, particularly UNet, in lung CT analysis and advocates for a combined 2D/3D modeling approach. It also highlights the need for larger, diverse datasets and the exploration of semi-supervised and unsupervised learning to enhance automated lung cancer diagnosis and early detection.

Worldwide research trends on artificial intelligence in head and neck cancer: a bibliometric analysis

OBJECTIVE

This bibliometric analysis aims to explore scientific data on Artificial Intelligence (AI) and Head and Neck Cancer (HNC).

STUDY DESIGN

AI-related HNC articles from the Web of Science Core Collection were searched. VosViewer and Biblioshiny/Bibiometrix for R Studio were used for data synthesis. This analysis covered key characteristics such as sources, authors, affiliations, countries, citations and top cited articles, keyword analysis, and trending topics.

RESULTS

A total of 1,019 papers from 1995 to 2024 were included. Among them, 71.6% were original research articles, 7.6% were reviews, and 20.8% took other forms. The fifty most cited documents highlighted radiology as the most explored specialty, with an emphasis on deep learning models for segmentation. The publications have been increasing, with an annual growth rate of 94.4% after 2016. Among the 20 most productive countries, 14 are high-income economies. The keywords of strong citation revealed 2 main clusters: radiomics and radiotherapy. The most frequently keywords include machine learning, deep learning, artificial intelligence, and head and neck cancer, with recent emphasis on diagnosis, survival prediction, and histopathology.

CONCLUSIONS

There has been an increase in the use of AI in HNC research since 2016 and indicated a notable disparity in publication quantity between high-income and low/middle-income countries. Future research should prioritize clinical validation and standardization to facilitate the integration of AI in HNC management, particularly in underrepresented regions.

Assessing Patient Health Dynamics by Comparative CT Analysis: An Automatic Approach to Organ and Body Feature Evaluation

Background/Objectives: The integration of machine learning into the domain of radiomics has revolutionized the approach to personalized medicine, particularly in oncology. Our research presents RadTA (RADiomics Trend Analysis), a novel framework developed to facilitate the automatic analysis of quantitative imaging biomarkers (QIBs) from time-series CT volumes. Methods: RadTA is designed to bridge a technical gap for medical experts and enable sophisticated radiomic analyses without deep learning expertise. The core of RadTA includes an automated command line interface, streamlined image segmentation, comprehensive feature extraction, and robust evaluation mechanisms. RadTA utilizes advanced segmentation models, specifically TotalSegmentator and Body Composition Analysis (BCA), to accurately delineate anatomical structures from CT scans. These models enable the extraction of a wide variety of radiomic features, which are subsequently processed and compared to assess health dynamics across timely corresponding CT series. Results: The effectiveness of RadTA was tested using the HNSCC-3DCT-RT dataset, which includes CT scans from oncological patients undergoing radiation therapy. The results demonstrate significant changes in tissue composition and provide insights into the physical effects of the treatment. Conclusions: RadTA demonstrates a step of clinical adoption in the field of radiomics, offering a user-friendly, robust, and effective tool for the analysis of patient health dynamics. It can potentially also be used for other medical specialties.

A diffusion model multi-scale feature fusion network for imbalanced medical image classification research

BACKGROUND AND OBJECTIVE

Medicine image classification are important methods of traditional medical image analysis, but the trainable data in medical image classification is highly imbalanced and the accuracy of medical image classification models is low. In view of the above two common problems in medical image classification. This study aims to: (i) effectively solve the problem of poor training effect caused by the imbalance of class imbalanced data sets. (ii) propose a network framework suitable for improving medical image classification results, which needs to be superior to existing methods.

METHODS

In this paper, we put in the diffusion model multi-scale feature fusion network (DMSFF), which mainly uses the diffusion generation model to overcome imbalanced classes (DMOIC) on highly imbalanced medical image datasets. At the same time, it is processed according to the cropped image augmentation strategy through cropping (IASTC). Based on this, we use the new dataset to design a multi-scale feature fusion network (MSFF) that can fully utilize multiple hierarchical features. The DMSFF network can effectively solve the problems of small and imbalanced samples and low accuracy in medical image classification.

RESULTS

We evaluated the performance of the DMSFF network on highly imbalanced medical image classification datasets APTOS2019 and ISIC2018. Compared with other classification models, our proposed DMSFF network achieved significant improvements in classification accuracy and F1 score on two datasets, reaching 0.872, 0.731, and 0.906, 0.836, respectively.

CONCLUSIONS

Our newly proposed DMSFF architecture outperforms existing methods on two datasets, and verifies the effectiveness of generative model inverse balance for imbalance class datasets and feature enhancement by multi-scale feature fusion. Further, the method can be applied to other class imbalanced data sets where the results will be improved.

The prognostic role of MRI-based radiomics in tongue carcinoma: a multicentric validation study

PURPOSE

Radiomics is an emerging field that utilizes quantitative features extracted from medical images to predict clinically meaningful outcomes. Validating findings is crucial to assess radiomics applicability. We aimed to validate previously published magnetic resonance imaging (MRI) radiomics models to predict oncological outcomes in oral tongue squamous cell carcinoma (OTSCC).

MATERIALS AND METHODS

Retrospective multicentric study on OTSCC surgically treated from 2010 to 2019. All patients performed preoperative MRI, including contrast-enhanced T1-weighted (CE-T1), diffusion-weighted sequences and apparent diffusion coefficient map. We evaluated overall survival (OS), locoregional recurrence-free survival (LRRFS), cause-specific mortality (CSM). We elaborated different models based on clinical and radiomic data. C-indexes assessed the prediction accuracy of the models.

RESULTS

We collected 112 consecutive independent patients from three Italian Institutions to validate the previously published MRI radiomic models based on 79 different patients. The C-indexes for the hybrid clinical-radiomic models in the validation cohort were lower than those in the training cohort but remained > 0.5 in most cases. CE-T1 sequence provided the best fit to the models: the C-indexes obtained were 0.61, 0.59, 0.64 (pretreatment model) and 0.65, 0.69, 0.70 (posttreatment model) for OS, LRRFS and CSM, respectively.

CONCLUSION

Our clinical-radiomic models retain a potential to predict OS, LRRFS and CSM in heterogeneous cohorts across different centers. These findings encourage further research, aimed at overcoming current limitations, due to the variability of imaging acquisition, processing and tumor volume delineation.

Role of Radiology in the Diagnosis and Treatment of Breast Cancer in Women: A Comprehensive Review

Breast cancer remains a leading cause of morbidity and mortality among women worldwide. Early detection and precise diagnosis are critical for effective treatment and improved patient outcomes. This review explores the evolving role of radiology in the diagnosis and treatment of breast cancer, highlighting advancements in imaging technologies and the integration of artificial intelligence (AI). Traditional imaging modalities such as mammography, ultrasound, and magnetic resonance imaging have been the cornerstone of breast cancer diagnostics, with each modality offering unique advantages. The advent of radiomics, which involves extracting quantitative data from medical images, has further augmented the diagnostic capabilities of these modalities. AI, particularly deep learning algorithms, has shown potential in improving diagnostic accuracy and reducing observer variability across imaging modalities. AI-driven tools are increasingly being integrated into clinical workflows to assist in image interpretation, lesion classification, and treatment planning. Additionally, radiology plays a crucial role in guiding treatment decisions, particularly in the context of image-guided radiotherapy and monitoring response to neoadjuvant chemotherapy. The review also discusses the emerging field of theranostics, where diagnostic imaging is combined with therapeutic interventions to provide personalized cancer care. Despite these advancements, challenges such as the need for large annotated datasets and the integration of AI into clinical practice remain. The review concludes that while the role of radiology in breast cancer management is rapidly evolving, further research is required to fully realize the potential of these technologies in improving patient outcomes.

Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer

PURPOSE

A practical noninvasive method is needed to identify lymph node (LN) status in breast cancer patients diagnosed with a suspicious axillary lymph node (ALN) at ultrasound but a negative clinical physical examination. To predict ALN metastasis effectively and noninvasively, we developed an artificial intelligence-assisted ultrasound system and validated it in a retrospective study.

METHODS

A total of 266 patients treated with sentinel LN biopsy and ALN dissection at Peking Union Medical College & Hospital(PUMCH) between the year 2017 and 2019 were assigned to training, validation and test sets (8:1:1). A deep learning model architecture named DeepLabV3 + was used together with ResNet-101 as the backbone network to create an ultrasound image segmentation diagnosis model. Subsequently, the segmented images are classified by a Convolutional Neural Network to predict ALN metastasis.

RESULTS

The area under the receiver operating characteristic curve of the model for identifying metastasis was 0.799 (95% CI: 0.514-1.000), with good end-to-end classification accuracy of 0.889 (95% CI: 0.741-1.000). Moreover, the specificity and positive predictive value of this model was 100%, providing high accuracy for clinical diagnosis.

CONCLUSION

This model can be a direct and reliable tool for the evaluation of individual LN status. Our study focuses on predicting ALN metastasis by radiomic analysis, which can be used to guide further treatment planning in breast cancer.

Development and validation of radiomics nomogram for metastatic status of epithelial ovarian cancer

To develop and validate an enhanced CT-based radiomics nomogram for evaluating preoperative metastasis risk of epithelial ovarian cancer (EOC). One hundred and nine patients with histologically confirmed EOC were retrospectively enrolled. The volume of interest (VOI) was delineated in preoperative enhanced CT images, and 851 radiomics features were extracted. The radiomics features were selected by the least absolute shrinkage and selection operator (LASSO), and the rad-score was calculated using the formula of the radiomics label. A clinical model, radiomics model, and combined model were constructed using the logistic regression classification algorithm. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were used to evaluate the diagnostic performance of the models. Seventy-five patients (68.8%) were histologically confirmed to have metastasis. Eleven optimal radiomics features were retained by the LASSO algorithm to develop the radiomic model. The combined model for evaluating metastasis of EOC achieved area under the curve (AUC) values of 0.929 (95% CI 0.8593-0.9996) in the training cohort and 0.909 (95% CI 0.7921-1.0000) in the test cohort. To facilitate clinical use, a radiomic nomogram was built by combining the clinical characteristics with rad-score. The DCA indicated that the nomogram had the most significant net benefit when the threshold probability exceeded 15%, surpassing the benefits of both the treat-all and treat-none strategies. Compared with clinical model and radiomics model, the radiomics nomogram has the best diagnostic performance in evaluating EOC metastasis. The nomogram is a useful and convenient tool for clinical doctors to develop personalized treatment plans for EOC patients.

Radiomic biomarkers of locoregional recurrence: prognostic insights from oral cavity squamous cell carcinoma preoperative CT scans

Introduction

This study aimed to identify CT-based imaging biomarkers for locoregional recurrence (LR) in Oral Cavity Squamous Cell Carcinoma (OSCC) patients.

Methods

Computed tomography scans were collected from 78 patients with OSCC who underwent surgical treatment at a single medical center. We extracted 1,092 radiomic features from gross tumor volume in each patient's pre-treatment CT. Clinical characteristics were also obtained, including race, sex, age, tobacco and alcohol use, tumor staging, and treatment modality. A feature selection algorithm was used to eliminate the most redundant features, followed by a selection of the best subset of the Logistic regression model (LRM). The best LRM model was determined based on the best prediction accuracy in terms of the area under Receiver operating characteristic curve. Finally, significant radiomic features in the final LRM model were identified as imaging biomarkers.

Results and discussion

Two radiomics biomarkers, Large Dependence Emphasis (LDE) of the Gray Level Dependence Matrix (GLDM) and Long Run Emphasis (LRE) of the Gray Level Run Length Matrix (GLRLM) of the 3D Laplacian of Gaussian (LoG σ=3), have demonstrated the capability to preoperatively distinguish patients with and without LR, exhibiting exceptional testing specificity (1.00) and sensitivity (0.82). The group with LRE > 2.99 showed a 3-year recurrence-free survival rate of 0.81, in contrast to 0.49 for the group with LRE ≤ 2.99. Similarly, the group with LDE > 120 showed a rate of 0.82, compared to 0.49 for the group with LDE ≤ 120. These biomarkers broaden our understanding of using radiomics to predict OSCC progression, enabling personalized treatment plans to enhance patient survival.

Construction of a nomogram for predicting compensated cirrhosis with Wilson's disease based on non-invasive indicators

BACKGROUND

Wilson's disease (WD) often leads to liver fibrosis and cirrhosis, and early diagnosis of WD cirrhosis is essential. Currently, there are few non-invasive prediction models for WD cirrhosis. The purpose of this study is to non-invasively predict the occurrence risk of compensated WD cirrhosis based on ultrasound imaging features and clinical characteristics.

METHODS

A retrospective analysis of the clinical characteristics and ultrasound examination data of 102 WD patients from November 2018 to November 2020 was conducted. According to the staging system for WD liver involvement, the patients were divided into a cirrhosis group (n = 43) and a non-cirrhosis group (n = 59). Multivariable logistic regression analysis was used to identify independent influencing factors for WD cirrhosis. A nomogram for predicting WD cirrhosis was constructed using R analysis software, and validation of the model's discrimination, calibration, and clinical applicability was completed. Due to the low incidence of WD and the small sample size, bootstrap internal sampling with 500 iterations was adopted for validation to prevent overfitting of the model.

RESULTS

Acoustic Radiation Force Impulse (ARFI), portal vein diameter (PVD), and serum albumin (ALB) are independent factors affecting WD cirrhosis. A nomogram for WD cirrhosis was constructed based on these factors. The area under the ROC curve (AUC) of the model's predictive ability is 0.927 (95% CI: 0.88-0.978). As demonstrated by 500 Bootstrap internal sampling validations, the model has high discrimination and calibration. Clinical decision curve analysis shows that the model has high clinical practical value. ROC curve analysis of the model's rationality indicates that the model's AUC is greater than the AUC of using ALB, ARFI, and PVD alone.

CONCLUSION

The nomogram model constructed based on ARFI, PVD, and ALB can serve as a non-invasive tool to effectively predict the risk of developing WD cirrhosis.

Channel-wise attention enhanced and structural similarity constrained cycleGAN for effective synthetic CT generation from head and neck MRI images

BACKGROUND

Magnetic resonance imaging (MRI) plays an increasingly important role in radiotherapy, enhancing the accuracy of target and organs at risk delineation, but the absence of electron density information limits its further clinical application. Therefore, the aim of this study is to develop and evaluate a novel unsupervised network (cycleSimulationGAN) for unpaired MR-to-CT synthesis.

METHODS

The proposed cycleSimulationGAN in this work integrates contour consistency loss function and channel-wise attention mechanism to synthesize high-quality CT-like images. Specially, the proposed cycleSimulationGAN constrains the structural similarity between the synthetic and input images for better structural retention characteristics. Additionally, we propose to equip a novel channel-wise attention mechanism based on the traditional generator of GAN to enhance the feature representation capability of deep network and extract more effective features. The mean absolute error (MAE) of Hounsfield Units (HU), peak signal-to-noise ratio (PSNR), root-mean-square error (RMSE) and structural similarity index (SSIM) were calculated between synthetic CT (sCT) and ground truth (GT) CT images to quantify the overall sCT performance.

RESULTS

One hundred and sixty nasopharyngeal carcinoma (NPC) patients who underwent volumetric-modulated arc radiotherapy (VMAT) were enrolled in this study. The generated sCT of our method were more consistent with the GT compared with other methods in terms of visual inspection. The average MAE, RMSE, PSNR, and SSIM calculated over twenty patients were 61.88 ± 1.42, 116.85 ± 3.42, 36.23 ± 0.52 and 0.985 ± 0.002 for the proposed method. The four image quality assessment metrics were significantly improved by our approach compared to conventional cycleGAN, the proposed cycleSimulationGAN produces significantly better synthetic results except for SSIM in bone.

CONCLUSIONS

We developed a novel cycleSimulationGAN model that can effectively create sCT images, making them comparable to GT images, which could potentially benefit the MRI-based treatment planning.

Coarse-to-fine visual representation learning for medical images via class activation maps

The value of coarsely labeled datasets in learning transferable representations for medical images is investigated in this work. Compared to fine labels which require meticulous effort to annotate, coarse labels can be acquired at a significantly lower cost and can provide useful training signals for data-hungry deep neural networks. We consider coarse labels in the form of binary labels differentiating a normal (healthy) image from an abnormal (diseased) image and propose CAMContrast, a two-stage representation learning framework for medical images. Using class activation maps, CAMContrast makes use of the binary labels to generate heatmaps as positive views for contrastive representation learning. Specifically, the learning objective is optimized to maximize the agreement within fixed crops of image-heatmap pair to learn fine-grained representations that are generalizable to different downstream tasks. We empirically validate the transfer learning performance of CAMContrast on several public datasets, covering classification and segmentation tasks on fundus photographs and chest X-ray images. The experimental results showed that our method outperforms other self-supervised and supervised pretrain methods in terms of data efficiency and downstream performance.

Intra- and peritumoral radiomics features based on multicenter automatic breast volume scanner for noninvasive and preoperative prediction of HER2 status in breast cancer: a model ensemble research

The aim to investigate the predictive efficacy of automatic breast volume scanner (ABVS), clinical and serological features alone or in combination at model level for predicting HER2 status. The model weighted combination method was developed to identify HER2 status compared with single data source model method and feature combination method. 271 patients with invasive breast cancer were included in the retrospective study, of which 174 patients in our center were randomized into the training and validation sets, and 97 patients in the external center were as the test set. Radiomics features extracted from the ABVS-based tumor, peritumoral 3 mm region, and peritumoral 5 mm region and clinical features were used to construct the four types of the optimal single data source models, Tumor, R3mm, R5mm, and Clinical model, respectively. Then, the model weighted combination and feature combination methods were performed to optimize the combination models. The proposed weighted combination models in predicting HER2 status achieved better performance both in validation set and test set. For the validation set, the single data source model, the feature combination model, and the weighted combination model achieved the highest area under the curve (AUC) of 0.803 (95% confidence interval [CI] 0.660-947), 0.739 (CI 0.556,0.921), and 0.826 (95% CI 0.689,0.962), respectively; with the sensitivity and specificity were 100%, 62.5%; 81.8%, 66.7%; 90.9%,75.0%; respectively. For the test set, the single data source model, the feature combination model, and the weighted combination model attained the best AUC of 0.695 (95% CI 0.583, 0.807), 0.668 (95% CI 0.555,0.782), and 0.700 (95% CI 0.590,0.811), respectively; with the sensitivity and specificity were 86.1%, 41.9%; 61.1%, 71.0%; 86.1%, 41.9%; respectively. The model weighted combination was a better method to construct a combination model. The optimized weighted combination models composed of ABVS-based intratumoral and peritumoral radiomics features and clinical features may be potential biomarkers for the noninvasive and preoperative prediction of HER2 status in breast cancer.

Ultrasound characteristics of normal parathyroid glands and analysis of the factors affecting their display

BACKGROUND

Parathyroid glands are important endocrine glands, and the identification of normal parathyroid glands is crucial for their protection. The aim of this study is to explore the sonographic characteristics of normal parathyroid glands and analyze the factors affecting their display.

METHODS

Seven hundred three subjects who underwent physical examination at our hospital were included. The number, location, size, morphology, echogenicity and blood flow distribution of parathyroid glands were recorded. The ultrasound characteristics and display rate were also summarized. Meanwhile, shear wave elastography was performed in 50 cases to provide the stiffness measurements, and 26 cases received contrast-enhanced ultrasonography for the assessment of microcirculatory perfusion. Furthermore, we analyzed the factors affecting parathyroid display, including basic information of the subjects and ultrasound features of the thyroid.

RESULTS

① A total of 1038 parathyroid glands were detected, among which, 79.29% were hyperechoic, 20.71% were isoechoic, 88.15% were oval-shaped, and 86.71% had blood flow of grade 0-I. ② 81.79% of the subjects had at least one parathyroid gland detected. ③ The Emean, Emax, PI and AUC of the parathyroid glands were significantly lower than those of the adjacent thyroid tissue (P < 0.05). ④ The display of normal parathyroid glands was related to BMI, thyroid echogenicity and thyroid volume of the subjects (P < 0.05).

CONCLUSIONS

Normal parathyroid glands tend to appear as oval-shaped hyperechoic nodules with blood flow of grade 0-I. BMI, thyroid echogenicity and thyroid volume are independent factors affecting the display of parathyroid glands.

Multi-omics and Multi-VOIs to predict esophageal fistula in esophageal cancer patients treated with radiotherapy

OBJECTIVE

This study aimed to develop a prediction model for esophageal fistula (EF) in esophageal cancer (EC) patients treated with intensity-modulated radiation therapy (IMRT), by integrating multi-omics features from multiple volumes of interest (VOIs).

METHODS

We retrospectively analyzed pretreatment planning computed tomographic (CT) images, three-dimensional dose distributions, and clinical factors of 287 EC patients. Nine groups of features from different combination of omics [Radiomics (R), Dosiomics (D), and RD (the combination of R and D)], and VOIs [esophagus (ESO), gross tumor volume (GTV), and EG (the combination of ESO and GTV)] were extracted and separately selected by unsupervised (analysis of variance (ANOVA) and Pearson correlation test) and supervised (Student T test) approaches. The final model performance was evaluated using five metrics: average area under the receiver-operator-characteristics curve (AUC), accuracy, precision, recall, and F1 score.

RESULTS

For multi-omics using RD features, the model performance in EG model shows: AUC, 0.817 ± 0.031; 95% CI 0.805, 0.825; p < 0.001, which is better than single VOI (ESO or GTV).

CONCLUSION

Integrating multi-omics features from multi-VOIs enables better prediction of EF in EC patients treated with IMRT. The incorporation of dosiomics features can enhance the model performance of the prediction.

Generation of tissues outside the field of view (FOV) of radiation therapy simulation imaging based on machine learning and patient body outline (PBO)

BACKGROUND

It is not unusual to see some parts of tissues are excluded in the field of view of CT simulation images. A typical mitigation is to avoid beams entering the missing body parts at the cost of sub-optimal planning.

METHODS

This study is to solve the problem by developing 3 methods, (1) deep learning (DL) mechanism for missing tissue generation, (2) using patient body outline (PBO) based on surface imaging, and (3) hybrid method combining DL and PBO. The DL model was built upon a Globally and Locally Consistent Image Completion to learn features by Convolutional Neural Networks-based inpainting, based on Generative Adversarial Network. The database used comprised 10,005 CT training slices of 322 lung cancer patients and 166 CT evaluation test slices of 15 patients. CT images were from the publicly available database of the Cancer Imaging Archive. Since existing data were used PBOs were acquired from the CT images. For evaluation, Structural Similarity Index Metric (SSIM), Root Mean Square Error (RMSE) and Peak signal-to-noise ratio (PSNR) were evaluated. For dosimetric validation, dynamic conformal arc plans were made with the ground truth images and images generated by the proposed method. Gamma analysis was conducted at relatively strict criteria of 1%/1 mm (dose difference/distance to agreement) and 2%/2 mm under three dose thresholds of 1%, 10% and 50% of the maximum dose in the plans made on the ground truth image sets.

RESULTS

The average SSIM in generation part only was 0.06 at epoch 100 but reached 0.86 at epoch 1500. Accordingly, the average SSIM in the whole image also improved from 0.86 to 0.97. At epoch 1500, the average values of RMSE and PSNR in the whole image were 7.4 and 30.9, respectively. Gamma analysis showed excellent agreement with the hybrid method (equal to or higher than 96.6% of the mean of pass rates for all scenarios).

CONCLUSIONS

It was first demonstrated that missing tissues in simulation imaging could be generated with high similarity, and dosimetric limitation could be overcome. The benefit of this study can be significantly enlarged when MR-only simulation is considered.

Prediction of positive pulmonary nodules based on machine learning algorithm combined with central carbon metabolism data

BACKGROUND

Lung cancer causes a huge disease burden, and early detection of positive pulmonary nodules (PPNs) as an early sign of lung cancer is extremely important for effective intervention. It is necessary to develop PPNs risk recognizer based on machine learning algorithm combined with central carbon metabolomics.

METHODS

The study included 2248 participants at high risk for lung cancer from the Ma'anshan Community Lung Cancer Screening cohort. The Least Absolute Shrinkage and Selection Operator (LASSO) was used to screen 18 central carbon-related metabolites in plasma, recursive feature elimination (RFE) was used to select all 42 features, followed by five machine learning algorithms for model development. The performance of the model was evaluated using area under the receiver operator characteristic curve (AUC), accuracy, precision, recall, and F1 scores. In addition, SHapley Additive exPlanations (SHAP) was performed to assess the interpretability of the final selected model and to gain insight into the impact of features on the predicted results.

RESULTS

Finally, the two prediction models based on the random forest (RF) algorithm performed best, with AUC values of 0.87 and 0.83, respectively, better than other models. We found that homogentisic acid, fumaric acid, maleic acid, hippuric acid, gluconic acid, and succinic acid played a significant role in both PPNs prediction model and NPNs vs PPNs model, while 2-oxadipic acid only played a role in the former model and phosphopyruvate only played a role in the NPNs vs PPNs model. This model demonstrates the potential of central carbon metabolism for PPNs risk prediction and identification.

CONCLUSION

We developed a series of predictive models for PPNs, which can help in the early detection of PPNs and thus reduce the risk of lung cancer.

Radiomic Biomarkers of Locoregional Recurrence: Prognostic Insights from Oral Cavity Squamous Cell Carcinoma preoperative CT scans

This study aimed to identify CT-based imaging biomarkers for locoregional recurrence (LR) in Oral Cavity Squamous Cell Carcinoma (OSCC) patients. Our study involved a retrospective review of 78 patients with OSCC who underwent surgical treatment at a single medical center. An approach involving feature selection and statistical model diagnostics was utilized to identify biomarkers. Two radiomics biomarkers, Large Dependence Emphasis (LDE) of the Gray Level Dependence Matrix (GLDM) and Long Run Emphasis (LRE) of the Gray Level Run Length Matrix (GLRLM) of the 3D Laplacian of Gaussian (LoG σ = 3), have demonstrated the capability to preoperatively distinguish patients with and without LR, exhibiting exceptional testing specificity (1.00) and sensitivity (0.82). The group with LRE > 2.99 showed a 3-year recurrence-free survival rate of 0.81, in contrast to 0.49 for the group with LRE ≤ 2.99. Similarly, the group with LDE > 120 showed a rate of 0.82, compared to 0.49 for the group with LDE ≤ 120. These biomarkers broaden our understanding of using radiomics to predict OSCC progression, enabling personalized treatment plans to enhance patient survival.

Artificial intelligence performance in detecting lymphoma from medical imaging: a systematic review and meta-analysis

BACKGROUND

Accurate diagnosis and early treatment are essential in the fight against lymphatic cancer. The application of artificial intelligence (AI) in the field of medical imaging shows great potential, but the diagnostic accuracy of lymphoma is unclear. This study was done to systematically review and meta-analyse researches concerning the diagnostic performance of AI in detecting lymphoma using medical imaging for the first time.

METHODS

Searches were conducted in Medline, Embase, IEEE and Cochrane up to December 2023. Data extraction and assessment of the included study quality were independently conducted by two investigators. Studies that reported the diagnostic performance of an AI model/s for the early detection of lymphoma using medical imaging were included in the systemic review. We extracted the binary diagnostic accuracy data to obtain the outcomes of interest: sensitivity (SE), specificity (SP), and Area Under the Curve (AUC). The study was registered with the PROSPERO, CRD42022383386.

RESULTS

Thirty studies were included in the systematic review, sixteen of which were meta-analyzed with a pooled sensitivity of 87% (95%CI 83-91%), specificity of 94% (92-96%), and AUC of 97% (95-98%). Satisfactory diagnostic performance was observed in subgroup analyses based on algorithms types (machine learning versus deep learning, and whether transfer learning was applied), sample size (≤ 200 or >  200), clinicians versus AI models and geographical distribution of institutions (Asia versus non-Asia).

CONCLUSIONS

Even if possible overestimation and further studies with a better standards for application of AI algorithms in lymphoma detection are needed, we suggest the AI may be useful in lymphoma diagnosis.

A predictive nomogram for surgical site infection in patients who received clean orthopedic surgery: a retrospective study

BACKGROUND

Surgical site infection (SSI) is a common and serious complication of elective clean orthopedic surgery that can lead to severe adverse outcomes. However, the prognostic efficacy of the current staging systems remains uncertain for patients undergoing elective aseptic orthopedic procedures. This study aimed to identify high-risk factors independently associated with SSI and develop a nomogram prediction model to accurately predict the occurrence of SSI.

METHODS

A total of 20,960 patients underwent elective clean orthopedic surgery in our hospital between January 2020 and December 2021, of whom 39 developed SSI; we selected all 39 patients with a postoperative diagnosis of SSI and 305 patients who did not develop postoperative SSI for the final analysis. The patients were randomly divided into training and validation cohorts in a 7:3 ratio. Univariate and multivariate logistic regression analyses were conducted in the training cohort to screen for independent risk factors of SSI, and a nomogram prediction model was developed. The predictive performance of the nomogram was compared with that of the National Nosocomial Infections Surveillance (NNIS) system. Decision curve analysis (DCA) was used to assess the clinical decision-making value of the nomogram.

RESULTS

The SSI incidence was 0.186%. Univariate and multivariate logistic regression analysis identified the American Society of Anesthesiology (ASA) class (odds ratio [OR] 1.564 [95% confidence interval (CI) 1.029-5.99, P = 0.046]), operative time (OR 1.003 [95% CI 1.006-1.019, P < 0.001]), and D-dimer level (OR 1.055 [95% CI 1.022-1.29, P = 0.046]) as risk factors for postoperative SSI. We constructed a nomogram prediction model based on these independent risk factors. In the training and validation cohorts, our predictive model had concordance indices (C-indices) of 0.777 (95% CI 0.672-0.882) and 0.732 (95% CI 0.603-0.861), respectively, both of which were superior to the C-indices of the NNIS system (0.668 and 0.543, respectively). Calibration curves and DCA confirmed that our nomogram model had good consistency and clinical predictive value, respectively.

CONCLUSIONS

Operative time, ASA class, and D-dimer levels are important clinical predictive indicators of postoperative SSI in patients undergoing elective clean orthopedic surgery. The nomogram predictive model based on the three clinical features demonstrated strong predictive performance, calibration capabilities, and clinical decision-making abilities for SSI.

Multi-parametric assessment of cardiac magnetic resonance images to distinguish myocardial infarctions: A tensor-based radiomics feature

AIM

This study assessed the myocardial infarction (MI) using a novel fusion approach (multi-flavored or tensor-based) of multi-parametric cardiac magnetic resonance imaging (CMRI) at four sequences; T1-weighted (T1W) in the axial plane, sense-balanced turbo field echo (sBTFE) in the axial plane, late gadolinium enhancement of heart short axis (LGE-SA) in the sagittal plane, and four-chamber views of LGE (LGE-4CH) in the axial plane.

METHODS

After considering the inclusion and exclusion criteria, 115 patients (83 with MI diagnosis and 32 as healthy control patients), were included in the present study. Radiomic features were extracted from the whole left ventricular myocardium (LVM). Feature selection methods were Least Absolute Shrinkage and Selection Operator (Lasso), Minimum Redundancy Maximum Relevance (MRMR), Chi-Square (Chi2), Analysis of Variance (Anova), Recursive Feature Elimination (RFE), and SelectPersentile. The classification methods were Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF). Different metrics, including receiver operating characteristic curve (AUC), accuracy, F1- score, precision, sensitivity, and specificity were calculated for radiomic features extracted from CMR images using stratified five-fold cross-validation.

RESULTS

For the MI detection, Lasso (as the feature selection) and RF/LR (as the classifiers) in sBTFE sequences had the best performance (AUC: 0.97). All features and classifiers of T1 + sBTFE sequences with the weighted method (as the fused image), had a good performance (AUC: 0.97). In addition, the results of the evaluated metrics, especially mean AUC and accuracy for all models, determined that the T1 + sBTFE-weighted fused method had strong predictive performance (AUC: 0.93±0.05; accuracy: 0.93±0.04), followed by T1 + sBTFE-PCA fused method (AUC: 0.85±0.06; accuracy: 0.84±0.06).

CONCLUSION

Our selected CMRI sequences demonstrated that radiomics analysis enables to detection of MI accurately. Among the investigated sequences, the T1 + sBTFE-weighted fused method with the highest AUC and accuracy values was chosen as the best technique for MI detection.

A radiomics based method for prediction of prostate cancer Gleason score using enlarged region of interest

BACKGROUND

Prostate cancer (PCa) is one of the most common cancers in men worldwide, and its timely diagnosis and treatment are becoming increasingly important. MRI is in increasing use to diagnose cancer and to distinguish between non-clinically significant and clinically significant PCa, leading to more precise diagnosis and treatment. The purpose of this study is to present a radiomics-based method for determining the Gleason score (GS) for PCa using tumour heterogeneity on multiparametric MRI (mp-MRI).

METHODS

Twenty-six patients with biopsy-proven PCa were included in this study. The quantitative T2 values, apparent diffusion coefficient (ADC) and signal enhancement rates (α) were calculated using multi-echo T2 images, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI), for the annotated region of interests (ROI). After texture feature analysis, ROI range expansion and feature filtering was performed. Then obtained data were put into support vector machine (SVM), K-Nearest Neighbor (KNN) and other classifiers for binary classification.

RESULTS

The highest classification accuracy was 73.96% for distinguishing between clinically significant (Gleason 3 + 4 and above) and non-significant cancers (Gleason 3 + 3) and 83.72% for distinguishing between Gleason 3 + 4 from Gleason 4 + 3 and above, which was achieved using initial ROIs drawn by the radiologists. The accuracy improved when using expanded ROIs to 80.67% using SVM and 88.42% using Bayesian classification for distinguishing between clinically significant and non-significant cancers and Gleason 3 + 4 from Gleason 4 + 3 and above, respectively.

CONCLUSIONS

Our results indicate the research significance and value of this study for determining the GS for prostate cancer using the expansion of the ROI region.

Multi-parametric radiomics of conventional T1 weighted and susceptibility-weighted imaging for differential diagnosis of idiopathic Parkinson's disease and multiple system atrophy

OBJECTIVES

This study aims to investigate the potential of radiomics with multiple parameters from conventional T1 weighted imaging (T1WI) and susceptibility weighted imaging (SWI) in distinguishing between idiopathic Parkinson's disease (PD) and multiple system atrophy (MSA).

METHODS

A total of 201 participants, including 57 patients with PD, 74 with MSA, and 70 healthy control (HCs) individuals, underwent T1WI and SWI scans. From the 12 subcortical nuclei (e.g. red nucleus, substantia nigra, subthalamic nucleus, putamen, globus pallidus, and caudate nucleus), 2640 radiomic features were extracted from both T1WI and SWI scans. Three classification models - logistic regression (LR), support vector machine (SVM), and light gradient boosting machine (LGBM) - were used to distinguish between MSA and PD, as well as among MSA, PD, and HC. These classifications were based on features extracted from T1WI, SWI, and a combination of T1WI and SWI. Five-fold cross-validation was used to evaluate the performance of the models with metrics such as sensitivity, specificity, accuracy, and area under the receiver operating curve (AUC). During each fold, the ANOVA and least absolute shrinkage and selection operator (LASSO) methods were used to identify the most relevant subset of features for the model training process.

RESULTS

The LGBM model trained by the features combination of T1WI and SWI exhibited the most outstanding differential performance in both the three-class classification task of MSA vs. PD vs. HC and the binary classification task of MSA vs. PD, with an accuracy of 0.814 and 0.854, and an AUC of 0.904 and 0.881, respectively. The texture-based differences (GLCM) of the SN and the shape-based differences of the GP were highly effective in discriminating between the three classes and two classes, respectively.

CONCLUSIONS

Radiomic features combining T1WI and SWI can achieve a satisfactory differential diagnosis for PD, MSA, and HC groups, as well as for PD and MSA groups, thus providing a useful tool for clinical decision-making based on routine MRI sequences.

Using machine learning-based radiomics to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes

OBJECTIVE

To establish a machine learning-based radiomics model to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes, thereby achieving accurate preoperative classification.

MATERIALS AND METHODS

A retrospective analysis was conducted on MRI T1WI-enhanced images of 105 patients with glioma and 172 patients with solitary brain metastasis from lung cancer, which were confirmed pathologically. The patients were divided into the training group and validation group in an 8:2 ratio for image segmentation, extraction, and filtering; multiple layer perceptron (MLP), support vector machine (SVM), random forest (RF), and logistic regression (LR) were used for modeling; fivefold cross-validation was used to train the model; the validation group was used to evaluate and assess the predictive performance of the model, ROC curve was used to calculate the accuracy, sensitivity, and specificity of the model, and the area under curve (AUC) was used to assess the predictive performance of the model.

RESULTS

The accuracy and AUC of the MLP differentiation model for high-grade glioma and solitary brain metastasis in the validation group was 0.992, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.968, respectively. The accuracy and AUC for the MLP and SVM differentiation model for high-grade glioma and small cell lung cancer brain metastasis in the validation group was 0.966, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.929, respectively. The accuracy and AUC for the MLP differentiation model for high-grade glioma and non-small cell lung cancer brain metastasis in the validation group was 0.982, 0.999, respectively, while the sensitivity and specificity were 0.958, 1.000, respectively.

CONCLUSION

The application of machine learning-based radiomics has a certain clinical value in differentiating glioma from solitary brain metastasis from lung cancer and its subtypes. In the HGG/SBM and HGG/NSCLC SBM validation groups, the MLP model had the best diagnostic performance, while in the HGG/SCLC SBM validation group, the MLP and SVM models had the best diagnostic performance.

Clinico-biological-radiomics (CBR) based machine learning for improving the diagnostic accuracy of FDG-PET false-positive lymph nodes in lung cancer

BACKGROUND

The main problem of positron emission tomography/computed tomography (PET/CT) for lymph node (LN) staging is the high false positive rate (FPR). Thus, we aimed to explore a clinico-biological-radiomics (CBR) model via machine learning (ML) to reduce FPR and improve the accuracy for predicting the hypermetabolic mediastinal-hilar LNs status in lung cancer than conventional PET/CT.

METHODS

A total of 260 lung cancer patients with hypermetabolic mediastinal-hilar LNs (SUVmax ≥ 2.5) were retrospectively reviewed. Patients were treated with surgery with systematic LN resection and pathologically divided into the LN negative (LN-) and positive (LN +) groups, and randomly assigned into the training (n = 182) and test (n = 78) sets. Preoperative CBR dataset containing 1738 multi-scale features was constructed for all patients. Prediction models for hypermetabolic LNs status were developed using the features selected by the supervised ML algorithms, and evaluated using the classical diagnostic indicators. Then, a nomogram was developed based on the model with the highest area under the curve (AUC) and the lowest FPR, and validated by the calibration plots.

RESULTS

In total, 109 LN- and 151 LN + patients were enrolled in this study. 6 independent prediction models were developed to differentiate LN- from LN + patients using the selected features from clinico-biological-image dataset, radiomics dataset, and their combined CBR dataset, respectively. The DeLong test showed that the CBR Model containing all-scale features held the highest predictive efficiency and the lowest FPR among all of established models (p < 0.05) in both the training and test sets (AUCs of 0.90 and 0.89, FPRs of 12.82% and 6.45%, respectively) (p < 0.05). The quantitative nomogram based on CBR Model was validated to have a good consistency with actual observations.

CONCLUSION

This study presents an integrated CBR nomogram that can further reduce the FPR and improve the accuracy of hypermetabolic mediastinal-hilar LNs evaluation than conventional PET/CT in lung cancer, thereby greatly reducing the risk of overestimation and assisting for precision treatment.

Assessment of axial spondyloarthritis activity using a magnetic resonance imaging-based multi-region-of-interest fusion model

BACKGROUND

Identifying axial spondyloarthritis (axSpA) activity early and accurately is essential for treating physicians to adjust treatment plans and guide clinical decisions promptly. The current literature is mostly focused on axSpA diagnosis, and there has been thus far, no study that reported the use of a radiomics approach for differentiating axSpA disease activity. In this study, the aim was to develop a radiomics model for differentiating active from non-active axSpA based on fat-suppressed (FS) T2-weighted (T2w) magnetic resonance imaging (MRI) of sacroiliac joints.

METHODS

This retrospective study included 109 patients diagnosed with non-active axSpA (n = 68) and active axSpA (n = 41); patients were divided into training and testing cohorts at a ratio of 8:2. Radiomics features were extracted from 3.0 T sacroiliac MRI using two different heterogeneous regions of interest (ROIs, Circle and Facet). Various methods were used to select relevant and robust features, and different classifiers were used to build Circle-based, Facet-based, and a fusion prediction model. Their performance was compared using various statistical parameters. p < 0.05 is considered statistically significant.

RESULTS

For both Circle- and Facet-based models, 2284 radiomics features were extracted. The combined fusion ROI model accurately differentiated between active and non-active axSpA, with high accuracy (0.90 vs.0.81), sensitivity (0.90 vs. 0.75), and specificity (0.90 vs. 0.85) in both training and testing cohorts.

CONCLUSION

The multi-ROI fusion radiomics model developed in this study differentiated between active and non-active axSpA using sacroiliac FS T2w-MRI. The results suggest MRI-based radiomics of the SIJ can distinguish axSpA activity, which can improve the therapeutic result and patient prognosis. To our knowledge, this is the only study in the literature that used a radiomics approach to determine axSpA activity.

A radiomics based approach using adrenal gland and periadrenal fat CT images to allocate COVID-19 health care resources fairly

BACKGROUND

The value of radiomics features from the adrenal gland and periadrenal fat CT images for predicting disease progression in patients with COVID-19 has not been studied extensively. We assess the value of radiomics features from the adrenal gland and periadrenal fat CT images in predicting COVID-19 disease exacerbation.

METHODS

A total of 1,245 patients (685 moderate and 560 severe patients) were enrolled in a retrospective study. We proposed a 3D V-net to segment adrenal glands in onset CT images automatically, and periadrenal fat was obtained using inflation operation around the adrenal gland. Next, we built a clinical model (CM), three radiomics models (adrenal gland model [AM], periadrenal fat model [PM], and fusion of adrenal gland and periadrenal fat model [FM]), and radiomics nomogram (RN) after radiomics features extracted.

RESULTS

The auto-segmentation framework yielded a dice value 0.79 in the training set. CM, AM, PM, FM, and RN obtained AUCs of 0.717, 0.716, 0.736, 0.760, and 0.833 in the validation set. FM and RN had better predictive efficacy than CM (P < 0.0001) in the training set. RN showed that there was no significant difference in the validation set (mean absolute error [MAE] = 0.04) and test set (MAE = 0.075) between predictive and actual results. Decision curve analysis showed that if the threshold probability was between 0.4 and 0.8 in the validation set or between 0.3 and 0.7 in the test set, it could gain more net benefits using RN than FM and CM.

CONCLUSIONS

Radiomics features extracted from the adrenal gland and periadrenal fat CT images are related to disease exacerbation in patients with COVID-19.

Assessing Machine Learning Models for Predicting Age with Intracranial Vessel Tortuosity and Thickness Information

This study aimed to develop and validate machine learning (ML) models that predict age using intracranial vessels' tortuosity and diameter features derived from magnetic resonance angiography (MRA) data. A total of 171 subjects' three-dimensional (3D) time-of-flight MRA image data were considered for analysis. After annotations of two endpoints in each arterial segment, tortuosity features such as the sum of the angle metrics, triangular index, relative length, and product of the angle distance, as well as the vessels' diameter features, were extracted and used to train and validate the ML models for age prediction. Features extracted from the right and left internal carotid arteries (ICA) and basilar arteries were considered as the inputs to train and validate six ML regression models with a four-fold cross validation. The random forest regression model resulted in the lowest root mean square error of 14.9 years and the highest average coefficient of determination of 0.186. The linear regression model showed the lowest average mean absolute percentage error (MAPE) and the highest average Pearson correlation coefficient (0.532). The mean diameter of the right ICA vessel segment was the most important feature contributing to prediction of age in two out of the four regression models considered. An ML of tortuosity descriptors and diameter features extracted from MRA data showed a modest correlation between real age and ML-predicted age. Further studies are warranted for the assessment of the model's age predictions in patients with intracranial vessel diseases.

Comparative analysis of batch correction methods for FDG PET/CT using metabolic radiogenomic data of lung cancer patients

In radiomics research, the issue of different instruments being used is significant. In this study, we compared three correction methods to reduce the batch effects in radiogenomic data from fluorodeoxyglucose (FDG) PET/CT images of lung cancer patients. Texture features of the FDG PET/CT images and genomic data were retrospectively obtained. The features were corrected with different methods: phantom correction, ComBat method, and Limma method. Batch effects were estimated using three analytic tools: principal component analysis (PCA), the k-nearest neighbor batch effect test (kBET), and the silhouette score. Finally, the associations of features and gene mutations were compared between each correction method. Although the kBET rejection rate and silhouette score were lower in the phantom-corrected data than in the uncorrected data, a PCA plot showed a similar variance. ComBat and Limma methods provided correction with low batch effects, and there was no significant difference in the results of the two methods. In ComBat- and Limma-corrected data, more texture features exhibited a significant association with the TP53 mutation than in those in the phantom-corrected data. This study suggests that correction with ComBat or Limma methods can be more effective or equally as effective as the phantom method in reducing batch effects.

Fully automated 3D body composition analysis and its association with overall survival in head and neck squamous cell carcinoma patients

Objectives

We developed a method for a fully automated deep-learning segmentation of tissues to investigate if 3D body composition measurements are significant for survival of Head and Neck Squamous Cell Carcinoma (HNSCC) patients.

Methods

3D segmentation of tissues including spine, spine muscles, abdominal muscles, subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), and internal organs within volumetric region limited by L1 and L5 levels was accomplished using deep convolutional segmentation architecture - U-net implemented in a nnUnet framework. It was trained on separate dataset of 560 single-channel CT slices and used for 3D segmentation of pre-radiotherapy (Pre-RT) and post-radiotherapy (Post-RT) whole body PET/CT or abdominal CT scans of 215 HNSCC patients. Percentages of tissues were used for overall survival analysis using Cox proportional hazard (PH) model.

Results

Our deep learning model successfully segmented all mentioned tissues with Dice's coefficient exceeding 0.95. The 3D measurements including difference between Pre-RT and post-RT abdomen and spine muscles percentage, difference between Pre-RT and post-RT VAT percentage and sum of Pre-RT abdomen and spine muscles percentage together with BMI and Cancer Site were selected and significant at the level of 5% for the overall survival. Aside from Cancer Site, the lowest hazard ratio (HR) value (HR, 0.7527; 95% CI, 0.6487-0.8735; p = 0.000183) was observed for the difference between Pre-RT and post-RT abdomen and spine muscles percentage.

Conclusion

Fully automated 3D quantitative measurements of body composition are significant for overall survival in Head and Neck Squamous Cell Carcinoma patients.

Radiation pneumonia predictive model for radiotherapy in esophageal carcinoma patients

BACKGROUND

The machine learning models with dose factors and the deep learning models with dose distribution matrix have been used to building lung toxics models for radiotherapy and achieve promising results. However, few studies have integrated clinical features into deep learning models. This study aimed to explore the role of three-dimension dose distribution and clinical features in predicting radiation pneumonitis (RP) in esophageal cancer patients after radiotherapy and designed a new hybrid deep learning network to predict the incidence of RP.

METHODS

A total of 105 esophageal cancer patients previously treated with radiotherapy were enrolled in this study. The three-dimension (3D) dose distributions within the lung were extracted from the treatment planning system, converted into 3D matrixes and used as inputs to predict RP with ResNet. In total, 15 clinical factors were normalized and converted into one-dimension (1D) matrixes. A new prediction model (HybridNet) was then built based on a hybrid deep learning network, which combined 3D ResNet18 and 1D convolution layers. Machine learning-based prediction models, which use the traditional dosiomic factors with and without the clinical factors as inputs, were also constructed and their predictive performance compared with that of HybridNet using tenfold cross validation. Accuracy and area under the receiver operator characteristic curve (AUC) were used to evaluate the model effect. DeLong test was used to compare the prediction results of the models.

RESULTS

The deep learning-based model achieved superior prediction results compared with machine learning-based models. ResNet performed best in the group that only considered dose factors (accuracy, 0.78 ± 0.05; AUC, 0.82 ± 0.25), whereas HybridNet performed best in the group that considered both dose factors and clinical factors (accuracy, 0.85 ± 0.13; AUC, 0.91 ± 0.09). HybridNet had higher accuracy than that of Resnet (p = 0.009).

CONCLUSION

Based on prediction results, the proposed HybridNet model could predict RP in esophageal cancer patients after radiotherapy with significantly higher accuracy, suggesting its potential as a useful tool for clinical decision-making. This study demonstrated that the information in dose distribution is worth further exploration, and combining multiple types of features contributes to predict radiotherapy response.

Preoperative prediction of cervical cancer survival using a high-resolution MRI-based radiomics nomogram

BACKGROUND

Cervical cancer patients receiving radiotherapy and chemotherapy require accurate survival prediction methods. The objective of this study was to develop a prognostic analysis model based on a radiomics score to predict overall survival (OS) in cervical cancer patients.

METHODS

Predictive models were developed using data from 62 cervical cancer patients who underwent radical hysterectomy between June 2020 and June 2021. Radiological features were extracted from T2-weighted (T2W), T1-weighted (T1W), and diffusion-weighted (DW) magnetic resonance images prior to treatment. We obtained the radiomics score (rad-score) using least absolute shrinkage and selection operator (LASSO) regression and Cox's proportional hazard model. We divided the patients into low- and high-risk groups according to the critical rad-score value, and generated a nomogram incorporating radiological features. We evaluated the model's prediction performance using area under the receiver operating characteristic (ROC) curve (AUC) and classified the participants into high- and low-risk groups based on radiological characteristics.

RESULTS

The 62 patients were divided into high-risk (n = 43) and low-risk (n = 19) groups based on the rad-score. Four feature parameters were selected via dimensionality reduction, and the scores were calculated after modeling. The AUC values of ROC curves for prediction of 3- and 5-year OS using the model were 0.84 and 0.93, respectively.

CONCLUSION

Our nomogram incorporating a combination of radiological features demonstrated good performance in predicting cervical cancer OS. This study highlights the potential of radiomics analysis in improving survival prediction for cervical cancer patients. However, further studies on a larger scale and external validation cohorts are necessary to validate its potential clinical utility.

Comparison of the diagnostic efficacy of mathematical models in distinguishing ultrasound imaging of breast nodules

This study compared the diagnostic efficiency of benign and malignant breast nodules using ultrasonographic characteristics coupled with several machine-learning models, including logistic regression (Logistics), partial least squares discriminant analysis (PLS-DA), linear support vector machine (Linear SVM), linear discriminant analysis (LDA), K-nearest neighbor (KNN), artificial neural network (ANN) and random forest (RF). The clinical information and ultrasonographic characteristics of 926 female patients undergoing breast nodule surgery were collected and their relationships were analyzed using Pearson's correlation. The stepwise regression method was used for variable selection and the Monte Carlo cross-validation method was used to randomly divide these nodule cases into training and prediction sets. Our results showed that six independent variables could be used for building models, including age, background echotexture, shape, calcification, resistance index, and axillary lymph node. In the prediction set, Linear SVM had the highest diagnosis rate of benign nodules (0.881), and Logistics, ANN and LDA had the highest diagnosis rate of malignant nodules (0.910~0.912). The area under the ROC curve (AUC) of Linear SVM was the highest (0.890), followed by ANN (0.883), LDA (0.880), Logistics (0.878), RF (0.874), PLS-DA (0.866), and KNN (0.855), all of which were better than that of individual variances. On the whole, the diagnostic efficacy of Linear SVM was better than other methods.

Predicting overall survival in chordoma patients using machine learning models: a web-app application

OBJECTIVE

The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox proportional hazards (CoxPH) model.

METHODS

Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities.

RESULTS

A total of 724 chordoma patients were divided into training (n = 508) and validation (n = 216) cohorts. Cox regression identified nine significant prognostic factors (p < 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (p < 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/ .

CONCLUSION

ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration.

Prediction of Parkinson's disease pathogenic variants using hybrid Machine learning systems and radiomic features

PURPOSE

In Parkinson's disease (PD), 5-10% of cases are of genetic origin with mutations identified in several genes such as leucine-rich repeat kinase 2 (LRRK2) and glucocerebrosidase (GBA). We aim to predict these two gene mutations using hybrid machine learning systems (HMLS), via imaging and non-imaging data, with the long-term goal to predict conversion to active disease.

METHODS

We studied 264 and 129 patients with known LRRK2 and GBA mutations status from PPMI database. Each dataset includes 513 features such as clinical features (CFs), conventional imaging features (CIFs) and radiomic features (RFs) extracted from DAT-SPECT images. Features, normalized by Z-score, were univariately analyzed for statistical significance by the t-test and chi-square test, adjusted by Benjamini-Hochberg correction. Multiple HMLSs, including 11 features extraction (FEA) or 10 features selection algorithms (FSA) linked with 21 classifiers were utilized. We also employed Ensemble Voting (EV) to classify the genes.

RESULTS

For prediction of LRRK2 mutation status, a number of HMLSs resulted in accuracies of 0.98 ± 0.02 and 1.00 in 5-fold cross-validation (80% out of total data points) and external testing (remaining 20%), respectively. For predicting GBA mutation status, multiple HMLSs resulted in high accuracies of 0.90 ± 0.08 and 0.96 in 5-fold cross-validation and external testing, respectively. We additionally showed that SPECT-based RFs added value to the specific prediction of of GBA mutation status.

CONCLUSION

We demonstrated that combining medical information with SPECT-based imaging features, and optimal utilization of HMLS can produce excellent prediction of the mutations status in PD patients.

Comparison of Ruptured Intracranial Aneurysms Identification Using Different Machine Learning Algorithms and Radiomics

Different machine learning algorithms have different characteristics and applicability. This study aims to predict ruptured intracranial aneurysms by radiomics models based on different machine learning algorithms and evaluate their differences in the same data condition. A total of 576 patients with intracranial aneurysms (192 ruptured and 384 unruptured intracranial aneurysms) from two institutions are included and randomly divided into training and validation cohorts in a ratio of 7:3. Of the 107 radiomics features extracted from computed tomography angiography images, seven features stood out. Then, radiomics features and 12 common machine learning algorithms, including the decision-making tree, support vector machine, logistic regression, Gaussian Naive Bayes, k-nearest neighbor, random forest, extreme gradient boosting, bagging classifier, AdaBoost, gradient boosting, light gradient boosting machine, and CatBoost were applied to construct models for predicting ruptured intracranial aneurysms, and the predictive performance of all models was compared. In the validation cohort, the area under curve (AUC) values of models based on AdaBoost, gradient boosting, and CatBoost for predicting ruptured intracranial aneurysms were 0.889, 0.883, and 0.864, respectively, with no significant differences among them. Of note, the performance of these models was significantly superior to that of the other nine models. The AUC of the AdaBoost model in the cross-validation was within the range of 0.842 to 0.918. Radiomics models based on the machine learning algorithms can be used to predict ruptured intracranial aneurysms, and the prediction efficacy differs among machine learning algorithms. The boosting algorithms might be superior in the application of radiomics combined with the machine learning algorithm to predict aneurysm ruptures.