Journal: Radiation Oncology (London, England)

Article Title: Comparison of the dose on specific 3DCT images and the accumulated dose for cardiac structures in esophageal tumors radiotherapy: whether specific 3DCT images can be used for dose assessment?

doi: 10.1186/s13014-019-1450-6

Figure Lengend Snippet: Delineation of the heart, pericardium and left ventricular myocardium (LVM) in transverse section. ( a ) Delineation of the heart, pericardium and LVM on a phase image of 4DCT. ( b ) Delineation of the heart, pericardium and LVM on MIP images. ( c ) Delineation of the heart, pericardium and LVM on AIP images. ( d ) Delineation of the heart, pericardium and LVM on Min-IP images. The heart delineation is shown in cyan, the pericardium delineation is shown in red and the LVM delineation is shown in blue

Article Snippet: The ECG-gated 4DCT images of all patients were acquired with a Siemens dual-source CT (Siemens SOMATOM Definition, DER).

Techniques:

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: ECG signal with annotated features.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques:

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: Block diagram of the proposed ECG classification framework.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques: Blocking Assay

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: Representative ECG waveforms from the dataset. Horizontal axis: time (seconds); vertical axis: amplitude (mV). Key takeaway: Normal and abnormal ECGs display clear differences in waveform morphology, supporting their use for classification.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques:

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: Boxplot distribution of statistical features (mean, standard deviation, minimum, maximum, and range) across Normal and Abnormal classes.Key takeaway: Abnormal ECG signals exhibit higher variability, providing discriminative cues for classification.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques: Standard Deviation

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: Confusion matrix of the Random Forest model for ECG classification, summarizing classification outcomes across Normal and Abnormal classes. Key takeaway: Abnormal ECG signals exhibit higher variability, providing discriminative cues for classification.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques:

Journal: Scientific Reports

Article Title: Automated heart disease detection using Swin Transformer and ECG signal processing: a high-accuracy approach

doi: 10.1038/s41598-025-23097-6

Figure Lengend Snippet: Sample ECG signals from Swin Transformer analysis.

Article Snippet: The raw ECG images of the Kaggle ECG dataset were pre-arranged into two binary classes: Normal and Abnormal as presented in Table .

Techniques: