Search Results (5)

Background: Cardiotoxicity is a major limitation of chemotherapy and radiotherapy for thoracic and systemic cancers, contributing significantly to morbidity and mortality among survivors. Early prediction and prevention are critical to balance oncologic efficacy with cardiovascular safety. Artificial intelligence (AI) offers powerful tools to improve risk stratification, enable earlier detection of subclinical injury, and guide treatment planning in cardio-oncology. Methods: We performed a comprehensive review of the literature on AI applications for cancer therapy-related cardiotoxicity. Evidence was identified from PubMed, Scopus, and Web of Science, focusing on electrocardiography, biomarkers, proteomics, extracellular vesicles, genomics, advanced imaging (echocardiography, cardiac magnetic resonance, computed tomography, nuclear imaging), and radiotherapy dose modeling (dosiomics). Translational insights from animal models and in vitro systems were also included. Methodological quality was appraised with reference to TRIPOD-AI, PROBAST-AI, and CLAIM standards. Results: AI applications span multiple domains. Machine learning models integrating biomarkers, exosomes, and extracellular vesicles show promise for noninvasive early detection. Deep learning enables automated analysis of echocardiographic strain and cardiac MRI mapping, while radiomics and dosiomics approaches combine imaging with cardiac substructure dose maps to predict and prevent late radiation-induced injury. Preclinical studies demonstrate AI-driven advances in small-animal imaging, histopathology quantification, and multi-omics data integration, supporting the discovery of translational biomarkers. Despite encouraging performance, most models remain limited by small cohorts, methodological heterogeneity, and scarce external validation. Conclusions: AI has the potential to transform cardio-oncology by shifting from reactive detection to proactive prevention of cardiotoxicity. Future research should prioritize multimodal integration, harmonized multicenter datasets, prospective validation, and guideline-based clinical trials. As emerging data are incorporated, the field is expanding rapidly—dynamic, complex, and evolving. Full article

This study compared the risks for developing second primary cancers and cardiotoxicity following radiotherapy for thymoma. Three different 3D-CRT, IMRT, and VMAT plans were generated with 6 MV photons for 12 females with thymoma. Dose-volume histogram data were employed to estimate the second cancer risks using a mechanistic non-linear model. The radiation doses to the heart and cardiac substructures were combined with linear models to assess the probability of cardiotoxicity. The mean lifetime risk for lung, esophageal, thyroid, left breast, and right breast cancer induction was 4.34–4.49%, 0.30–0.31%, 0.05–0.07%, 2.06–2.30%, and 2.04–2.34%, respectively, depending upon the radiotherapy technique. The relative risk for major cardiac events, including myocardial infarction, coronary revascularization, and death, was 1.43–1.55, whereas that for chronic heart failure was 1.20–1.29. The IMRT and VMAT significantly reduced the risk for cardiotoxicity with respect to 3D-CRT (p ≤ 0.023). Small but significant reductions were observed for most organ-specific cancer risks with IMRT compared to conformal treatment (p ≤ 0.008). Similar decreases were detected only for esophageal and thyroid cancer with VMAT (p ≤ 0.033). No difference was found in the probability for radiation-induced lung cancer with the three techniques (p ≥ 0.06). Healthcare professionals may use these data to select the appropriate radiotherapy technique and restrict the risk of late effects. Full article

Purpose: In the past decade, there has been a rapid increase in the development of automatic cardiac segmentation methods. However, the automatic quality control (QC) of these segmentation methods has received less attention. This study aims to address this gap by developing an automatic pipeline that incorporates DL-based cardiac segmentation and radiomics-based quality control. Methods: In the DL-based localization and segmentation part, the entire heart was first located and cropped. Then, the cropped images were further utilized for the segmentation of the right ventricle cavity (RVC), myocardium (MYO), and left ventricle cavity (LVC). As for the radiomics-based QC part, a training radiomics dataset was created with segmentation tasks of various quality. This dataset was used for feature extraction, selection, and QC model development. The model performance was then evaluated using both internal and external testing datasets. Results: In the internal testing dataset, the segmentation model demonstrated a great performance with a dice similarity coefficient (DSC) of 0.954 for whole heart segmentations. Images were then appropriately cropped to 160 × 160 pixels. The models also performed well for cardiac substructure segmentations. The DSC values were 0.863, 0.872, and 0.940 for RVC, MYO, and LVC for 2D masks and 0.928, 0.886, and 0.962 for RVC, MYO, and LVC for 3D masks with an attention-UNet. After feature selection with the radiomics dataset, we developed a series of models to predict the automatic segmentation quality and its DSC value for the RVC, MYO, and LVC structures. The mean absolute values for our best prediction models were 0.060, 0.032, and 0.021 for 2D segmentations and 0.027, 0.017, and 0.011 for 3D segmentations, respectively. Additionally, the radiomics-based classification models demonstrated a high negative detection rate of >0.85 in all 2D groups. In the external dataset, models showed similar results. Conclusions: We developed a pipeline including cardiac substructure segmentation and QC at both the slice (2D) and subject (3D) levels. Our results demonstrate that the radiomics method possesses great potential for the automatic QC of cardiac segmentation. Full article

Artificial Intelligence (AI) technologies have recently been applied to medical imaging for diagnostic support. With respect to fetal ultrasound screening of congenital heart disease (CHD), it is still challenging to achieve consistently accurate diagnoses owing to its manual operation and the technical differences among examiners. Hence, we proposed an architecture of Supervised Object detection with Normal data Only (SONO), based on a convolutional neural network (CNN), to detect cardiac substructures and structural abnormalities in fetal ultrasound videos. We used a barcode-like timeline to visualize the probability of detection and calculated an abnormality score of each video. Performance evaluations of detecting cardiac structural abnormalities utilized videos of sequential cross-sections around a four-chamber view (Heart) and three-vessel trachea view (Vessels). The mean value of abnormality scores in CHD cases was significantly higher than normal cases (p < 0.001). The areas under the receiver operating characteristic curve in Heart and Vessels produced by SONO were 0.787 and 0.891, respectively, higher than the other conventional algorithms. SONO achieves an automatic detection of each cardiac substructure in fetal ultrasound videos, and shows an applicability to detect cardiac structural abnormalities. The barcode-like timeline is informative for examiners to capture the clinical characteristic of each case, and it is also expected to acquire one of the important features in the field of medical AI: the development of “explainable AI.” Full article

Image segmentation is the pixel-by-pixel detection of objects, which is the most challenging but informative in the fundamental tasks of machine learning including image classification and object detection. Pixel-by-pixel segmentation is required to apply machine learning to support fetal cardiac ultrasound screening; we have to detect cardiac substructures precisely which are small and change shapes dynamically with fetal heartbeats, such as the ventricular septum. This task is difficult for general segmentation methods such as DeepLab v3+, and U-net. Hence, here we proposed a novel segmentation method named Cropping-Segmentation-Calibration (CSC) that is specific to the ventricular septum in ultrasound videos in this study. CSC employs the time-series information of videos and specific section information to calibrate the output of U-net. The actual sections of the ventricular septum were annotated in 615 frames from 421 normal fetal cardiac ultrasound videos of 211 pregnant women who were screened. The dataset was assigned a ratio of 2:1, which corresponded to a ratio of the training to test data, and three-fold cross-validation was conducted. The segmentation results of DeepLab v3+, U-net, and CSC were evaluated using the values of the mean intersection over union (mIoU), which were 0.0224, 0.1519, and 0.5543, respectively. The results reveal the superior performance of CSC. Full article