Mohamad Forouzanfar

Niloufar Delfan, Hamid Abrishami Moghaddam, Mohammadreza Modaresi et al.

Segmentation of lung tissue in computed tomography (CT) images is a precursor to most pulmonary image analysis applications. Semantic segmentation methods using deep learning have exhibited top-tier performance in recent years, however designing accurate and robust segmentation models for lung tissue is challenging due to the variations in shape, size, and orientation. Additionally, medical image artifacts and noise can affect lung tissue segmentation and degrade the accuracy of downstream analysis. The practicality of current deep learning methods for lung tissue segmentation is limited as they require significant computational resources and may not be easily deployable in clinical settings. This paper presents a fully automatic method that identifies the lungs in three-dimensional (3D) pulmonary CT images using deep networks and transfer learning. We introduce (1) a novel 2.5-dimensional image representation from consecutive CT slices that succinctly represents volumetric information and (2) a U-Net architecture equipped with pre-trained InceptionV3 blocks to segment 3D CT scans while maintaining the number of learnable parameters as low as possible. Our method was quantitatively assessed using one public dataset, LUNA16, for training and testing and two public datasets, namely, VESSEL12 and CRPF, only for testing. Due to the low number of learnable parameters, our method achieved high generalizability to the unseen VESSEL12 and CRPF datasets while obtaining superior performance over Luna16 compared to existing methods (Dice coefficients of 99.7, 99.1, and 98.8 over LUNA16, VESSEL12, and CRPF datasets, respectively). We made our method publicly accessible via a graphical user interface at medvispy.ee.kntu.ac.ir.

Mohammadreza Shahsavari, Niloufar Delfan, Mohamad Forouzanfar

Idiopathic ventricular arrhythmia (IVAs) is extra abnormal heartbeats disturbing the regular heart rhythm that can become fatal if left untreated. Cardiac catheter ablation is the standard approach to treat IVAs, however, a crucial prerequisite for the ablation is the localization of IVAs' origin. The current IVA localization techniques are invasive, rely on expert interpretation, or are inaccurate. In this study, we developed a new deep-learning algorithm that can automatically identify the origin of IVAs from ECG signals without the need for expert manual analysis. Our developed deep learning algorithm was comprised of a spatial fusion to extract the most informative features from multichannel ECG data, temporal modeling to capture the evolving pattern of the ECG time series, and an attention mechanism to weigh the most important temporal features and improve the model interpretability. The algorithm was validated on a 12-lead ECG dataset collected from 334 patients (230 females) who experienced IVA and successfully underwent a catheter ablation procedure that determined IVA's exact origins. The proposed method achieved an area under the curve of 93%, an accuracy of 94%, a sensitivity of 97%, a precision of 95%, and an F1 score of 96% in locating the origin of IVAs and outperformed existing automatic and semi-automatic algorithms. The proposed method shows promise toward automatic and noninvasive evaluation of IVA patients before cardiac catheter ablation.

Boshra Khajehpiri, Eric Granger, Massimiliano de Zambotti et al.

Despite extensive research on the relationship between sleep and cognition, the connection between sleep microstructure and human performance across specific cognitive domains remains underexplored. This study investigates whether deep learning models can predict executive functions, particularly cognitive adaptability and conceptual reasoning from physiological processes during a night's sleep. To address this, we introduce CogPSGFormer, a multi-scale convolutional-transformer model designed to process multi-modal polysomnographic data. This model integrates one-channel ECG and EEG signals along with extracted features, including EEG power bands and heart rate variability parameters, to capture complementary information across modalities. A thorough evaluation of the CogPSGFormer architecture was conducted to optimize the processing of extended sleep signals and identify the most effective configuration. The proposed framework was evaluated on 817 individuals from the STAGES dataset using cross-validation. The model achieved 80.3\% accuracy in classifying individuals into low vs. high cognitive performance groups on unseen data based on Penn Conditional Exclusion Test (PCET) scores. These findings highlight the effectiveness of our multi-scale feature extraction and multi-modal learning approach in leveraging sleep-derived signals for cognitive performance prediction. To facilitate reproducibility, our code is publicly accessible (https://github.com/boshrakh95/CogPSGFormer.git).

Bijan Roudini, Boshra Khajehpiri, Hamid Abrishami Moghaddam et al.

Precise estimation of cardiac patients' current and future comorbidities is an important factor in prioritizing continuous physiological monitoring and new therapies. ML models have shown satisfactory performance in short-term mortality prediction of patients with heart disease, while their utility in long-term predictions is limited. This study aims to investigate the performance of tree-based ML models on long-term mortality prediction and the effect of two recently introduced biomarkers on long-term mortality. This study utilized publicly available data from CCHIA at the Ministry of Health and Welfare, Taiwan, China. Medical records were used to gather demographic and clinical data, including age, gender, BMI, percutaneous coronary intervention (PCI) status, and comorbidities such as hypertension, dyslipidemia, ST-segment elevation myocardial infarction (STEMI), and non-STEMI. Using medical and demographic records as well as two recently introduced biomarkers, brachial pre-ejection period (bPEP) and brachial ejection time (bET), collected from 139 patients with acute myocardial infarction, we investigated the performance of advanced ensemble tree-based ML algorithms (random forest, AdaBoost, and XGBoost) to predict all-cause mortality within 14 years. The developed ML models achieved significantly better performance compared to the baseline LR (C-Statistic, 0.80 for random forest, 0.79 for AdaBoost, and 0.78 for XGBoost, vs 0.77 for LR) (P-RF<0.001, PAdaBoost<0.001, PXGBoost<0.05). Adding bPEP and bET to our feature set significantly improved the algorithms' performance, leading to an absolute increase in C-Statistic of up to 0.03 (C-Statistic, 0.83 for random forest, 0.82 for AdaBoost, and 0.80 for XGBoost, vs 0.74 for LR) (P-RF<0.001, PAdaBoost<0.001, PXGBoost<0.05). This advancement may enable better treatment prioritization for high-risk individuals.