Objective : To develop and evaluate an algorithm for the selection of the best-performing QRS detections from multiple algorithms and ECG leads. Approach : The detections produced by several publicly available single-lead QRS detectors are segmented in 20 s consecutive windows; then a statistical model is trained to estimate a quality metric that is used to rank each 20 s segment of detections. The model describes each heartbeat in terms of six features calculated from the RR interval series, and one feature proportional to the number of heartbeats detected in other leads in a neighborhood of the current heartbeat. With the highest ranked segments, we defined several lead selection strategies (LSS) that were evaluated in a set of 1754 ECG recordings from 14 ECG databases. The LSS proposed were compared with simple strategies such as selecting lead II or the first lead available in a recording. The performance was calculated in terms of the average sensitivity, positive predictive value, and F score. Main results : The best-performing LSS, based on wavedet algorithm, achieved an F score of 98.7, with sensitivity S = 99.2 and positive predictive value P = 98.3. The F score for the simpler strategy using the same algorithm was 92.7. The LSS studied in this work have been made available in an open-source toolbox to ease the reproducibility and result comparison. Significance : The results suggest that the use of LSS is convenient for purposes of selecting the best heartbeat locations among those provided by different detectors in different leads, obtaining better results than any of the algorithms individually.
Background The anti-cancer MEK inhibitor trametinib (alone or with the RAF inhibitor dabrafenib) causes cardiac dysfunction or heart failure in some patients. Our hypothesis is that cardiotoxicity is exacerbated by an underlying co-morbidity such as hypertension causing early cardiac dysfunction detectable on echocardiograms. Objectives The objectives were to assess the effects of trametinib on cardiac function in a mouse model of hypertension-induced cardiac hypertrophy and determine if this was moderated by dabrafenib. Methods Male mice were treated with vehicle, trametinib or dabrafenib/trametinib in the absence/presence of angiotensin II (AngII; 0.8 mg/kg/d to increase blood pressure over 7 d). Hearts were imaged using echocardiography. Results Inhibitors alone had a limited effect on mouse hearts over 28 d. Trametinib or trametinib/dabrafenib inhibited cardiac hypertrophy induced by AngII over 7 d, reducing left ventricular (LV) wall thickness and mass. AngII did not significantly affect cardiac function, but the inhibitors caused significant functional deterioration. Segmental analysis revealed variation of contraction around the LV, with selective effects of AngII and trametinib or dabrafenib/trametinib in basal/mid-regional segments. Frame-by-frame analysis of radial (not longitudinal) displacement of the LV endocardial wall demonstrated variation between consecutive cardiac cycles that enabled a high degree of classification according to treatment. Conclusions Trametinib inhibits AngII-induced cardiac hypertrophy in mice but is detrimental to cardiac function, responses that are not moderated by dabrafenib. AngII and MEK/RAF inhibition have regional effects around the LV with greater effects on radial displacement in basal/mid-regional segments. Assessment of such changes may facilitate early identification of developing cardiotoxicity. Competencies in Medical knowledge The anti-cancer drugs trametinib and dabrafenib are cardiotoxic in some patients. These drugs had limited effects themselves on mouse hearts, but suppressed cardiac hypertrophy in a mouse model of hypertension whilst proving detrimental to cardiac function. Segments around the left ventricle were differentially affected by hypertension and inhibitors,with variation between consecutive cardiac cycles. Translational outlook Further research is needed to establish the relationship between hypertension and cardiotoxicity of trametinib in patients, and determine if regional effects in the ventricle wall can predict cardiac dysfunction. If so, a diagnostic algorithm may be a useful tool in identifying developing cardiotoxicity. Inhibiting ERK1/2 suppresses cardiac fibrosis and cardiomyocyte hypertrophy induced by angiotensin II. This results in a decline in cardiac function, with particular effects on radial wall movement and in different segments of the left ventricle.
Connexin-43 (CX43) lateralization in ventricular myocardium has been associated with abnormal impulse propagation and increased arrhythmia susceptibility. Its quantitative assessment in histological sections remains challenging because previous methods require segmentation of individual cardiomyocytes and rely on geometric rules applied to segmented cell profiles. Here, we present CLARISA, a segmentation-free, ROI-based deep learning framework that classifies CX43-positive regions as terminal or lateralized directly from fluorescence images. An expert-annotated dataset was generated from left-ventricular cryosections of Wistar rat hearts, in which CX43-positive regions were labeled according to their distribution pattern. A dual-stream EfficientNetV2-S classifier was trained to capture both local and contextual ROI morphology. We also developed a semi-automated whole-section inference module to generate spatial lateralization probability maps and global percent lateralization estimates. On the held-out test set, CLARISA achieved a ROC-AUC of 0.904 (95% bootstrap CI: 0.828–0.960) and a PR-AUC of 0.808 (95% bootstrap CI: 0.682–0.913), supporting the feasibility of automated ROI classification for CX43 lateralization assessment. When deployed on whole tissue sections, including an independently analyzed section not used during model development, CLARISA generated spatial maps that captured heterogeneous CX43 organization and produced a global percent lateralization estimate closely aligned with expert annotation, differing by only 1.30 percentage points over the same detected CX43-positive area. Comparison with a previously published segmentation-based method further indicated that ROI-based and cell-segmentation-based approaches provide related but non-equivalent readouts of CX43 lateralization. The ROI-based design additionally reduces annotation burden—requiring classification of discrete CX43-positive signal rather than complex cardiomyocyte delineation—and ensures that all detected CX43-positive signal contributes to the lateralization estimate regardless of cell boundaries. These results establish CLARISA as a proof-of-principle framework for scalable, segmentation-free CX43 lateralization assessment in cardiac tissue. Further validation across larger, independent, and more heterogeneous datasets will be required to assess robustness, portability across imaging conditions, and translational applicability. The complete codebase, pretrained model, image data, and expert annotation tool are publicly available.
Connexin-43 (CX43) lateralization in ventricular myocardium has been associated with abnormal impulse propagation and increased arrhythmia susceptibility. Its quantitative assessment in histological sections remains challenging because of the difficulty of segmenting individual cardiomyocytes and the reliance of previous methods on geometric rules applied to segmented cell profiles. Here, we present CLARISA, a deep learning framework for classifying CX43-positive regions as either terminal or lateralized directly from fluorescence images, without requiring cardiomyocyte segmentation. An expert-annotated dataset was generated from left-ventricular cryosections of Wistar rat hearts, in which CX43-positive regions were labeled according to their distribution pattern. A dual-stream convolutional classifier based on EfficientNetV2-S was trained to capture both the local and contextual morphology of each region. In addition, an inference module applicable to whole tissue sections was developed to generate spatial lateralization probability maps and global percent lateralization estimates consistent with expert annotation. On the test set, CLARISA achieved a ROC-AUC of 0.905 and a PR-AUC of 0.810. These results support the feasibility of automated assessment of CX43 distribution patterns without explicit cardiomyocyte segmentation. The complete codebase is publicly available, together with access to the pretrained model and the image data used in this study. The Hugging Face model card reports the same held-out test metrics and states that the checkpoint is intended to be used with the main repository.
Wavelet-based entropy and statistical complexity can quantify subtle alterations in the multiscale organization of ventricular depolarization that are not necessarily apparent during standard electrocardiographic inspection. This study evaluates the transferability, robustness, and methodological sensitivity of these descriptors in a large two-database post-myocardial-infarction setting. We analyzed 12-lead ECG records from the PTB Diagnostic Electrocardiogram Database and PTB-XL. A predefined analysis cohort contained 5,887 control (CTRL), 118 early/healing post-infarction (MI7), and 294 healed/chronic post-infarction (MI60) records. The supplied QRS matrices already contained segmented and aligned QRS windows. Because beat-level rejection metadata were not retained in these stored matrices, feature calculation was based on the QRS complexes available for analysis. Normalized wavelet entropy and statistical complexity were computed from relative wavelet energy and summarized by lead and by a multi-lead criterion. Statistical analyses accounted for repeated patients, age, sex, database origin, class imbalance, and patient-level separation during validation. In patient-grouped nested validation, the joint entropy-complexity representation yielded AUCs of 0.858 (95% CI 0.808–0.902) for CTRL versus MI7, 0.621 (0.584–0.660) for CTRL versus MI60, and 0.759 (0.705–0.809) for MI7 versus MI60. Physically harmonized frequency analyses weakened several contrasts, particularly CTRL versus MI60. The descriptors remained associated with post-infarction group status after covariate adjustment, but their magnitude and discriminative performance depended partly on database composition and frequency definition. Wavelet entropy and statistical complexity are therefore best interpreted as exploratory, complementary signal-processing descriptors of multiscale QRS organization rather than as validated diagnostic or prognostic markers.