AI-Driven Model for Automatic Emphysema Detection in Low-Dose Computed Tomography Using Disease-Specific Augmentation.

The objective of this study is to evaluate the feasibility of a disease-specific deep learning (DL) model based on minimum intensity projection (minIP) for automated emphysema detection in low-dose computed tomography (LDCT) scans. LDCT scans of 240 individuals from a population-based cohort in the Netherlands (ImaLife study, mean age ± SD = 57 ± 6 years) were retrospectively chosen for training and internal validation of the DL model. For independent testing, LDCT scans of 125 individuals from a lung cancer screening cohort in the USA (NLST study, mean age ± SD = 64 ± 5 years) were used. Dichotomous emphysema diagnosis based on radiologists' annotation was used to develop the model. The automated model included minIP processing (slab thickness range: 1 mm to 11 mm), classification, and detection maps generation. The data-split for the pipeline evaluation involved class-balanced and imbalanced settings. The proposed DL pipeline showed the highest performance (area under receiver operating characteristics curve) for 11 mm slab thickness in both the balanced (ImaLife = 0.90 ± 0.05) and the imbalanced dataset (NLST = 0.77 ± 0.06). For ImaLife subcohort, the variation in minIP slab thickness from 1 to 11 mm increased the DL model's sensitivity from 75 to 88% and decreased the number of false-negative predictions from 10 to 5. The minIP-based DL model can automatically detect emphysema in LDCTs. The performance of thicker minIP slabs was better than that of thinner slabs. LDCT can be leveraged for emphysema detection by applying disease specific augmentation.

STQS: Interpretable multi-modal Spatial-Temporal-seQuential model for automatic Sleep scoring.

Sleep scoring is an important step for the detection of sleep disorders and usually performed by visual analysis. Since manual sleep scoring is time consuming, machine-learning based approaches have been proposed. Though efficient, these algorithms are black-box in nature and difficult to interpret by clinicians. In this paper, we propose a deep learning architecture for multi-modal sleep scoring, investigate the model's decision making process, and compare the model's reasoning with the annotation guidelines in the AASM manual. Our architecture, called STQS, uses convolutional neural networks (CNN) to automatically extract spatio-temporal features from 3 modalities (EEG, EOG and EMG), a bidirectional long short-term memory (Bi-LSTM) to extract sequential information, and residual connections to combine spatio-temporal and sequential features. We evaluated our model on two large datasets, obtaining an accuracy of 85% and 77% and a macro F1 score of 79% and 73% on SHHS and an in-house dataset, respectively. We further quantify the contribution of various architectural components and conclude that adding LSTM layers improves performance over a spatio-temporal CNN, while adding residual connections does not. Our interpretability results show that the output of the model is well aligned with AASM guidelines, and therefore, the model's decisions correspond to domain knowledge. We also compare multi-modal models and single-channel models and suggest that future research should focus on improving multi-modal models.

Prediction of Incident Cancers in the Lifelines Population-Based Cohort.

Cancer incidence is rising, and accurate prediction of incident cancers could be relevant to understanding and reducing cancer incidence. The aim of this study was to develop machine learning (ML) models that could predict an incident diagnosis of cancer. Participants without any history of cancer within the Lifelines population-based cohort were followed for a median of 7 years. Data were available for 116,188 cancer-free participants and 4232 incident cancer cases. At baseline, socioeconomic, lifestyle, and clinical variables were assessed. The main outcome was an incident cancer during follow-up (excluding skin cancer), based on linkage with the national pathology registry. The performance of three ML algorithms was evaluated using supervised binary classification to identify incident cancers among participants. Elastic net regularization and Gini index were used for variables selection. An overall area under the receiver operator curve (AUC) <0.75 was obtained, the highest AUC value was for prostate cancer (random forest AUC = 0.82 (95% CI 0.77-0.87), logistic regression AUC = 0.81 (95% CI 0.76-0.86), and support vector machines AUC = 0.83 (95% CI 0.78-0.88), respectively); age was the most important predictor in these models. Linear and non-linear ML algorithms including socioeconomic, lifestyle, and clinical variables produced a moderate predictive performance of incident cancers in the Lifelines cohort.

Electroencephalogram Based Detection of Deep Sedation in ICU Patients Using Atomic Decomposition.

OBJECTIVE: This study was performed to evaluate how well states of deep sedation in ICU patients can be detected from the frontal electroencephalogram (EEG) using features based on the method of atomic decomposition (AD). METHODS: We analyzed a clinical dataset of 20 min of EEG recordings per patient from 44 mechanically ventilated adult patients receiving sedatives in an intensive care unit (ICU) setting. Several features derived from AD of the EEG signal were used to discriminate between awake and sedated states. We trained support vector machine (SVM) classifiers using AD features and compared the classification performance with SVM classifiers trained using standard spectral and entropy features using leave-one-subject-out validation. The potential of each feature to discriminate between awake and sedated states was quantified using area under the receiver operating characteristic curve (AUC). RESULTS: The sedation level classification system using AD was able to reliably discriminate between sedated and awake states achieving an average AUC of 0.90, which was significantly better () than performance achieved using spectral (AUC = 0.86) and entropy (AUC = 0.81) domain features. A combined feature set consisting of AD, entropy, and spectral features provided better discrimination (AUC = 0.91, ) than any individual feature set. CONCLUSIONS: Features derived from the atomic decomposition of EEG signals provide useful discriminative information about the depth of sedation in ICU patients. SIGNIFICANCE: With further refinement and external validation, the proposed system may be able to assist clinical staff with continuous surveillance of sedation levels in mechanically ventilated critically ill ICU patients.

Neonatal seizure detection using atomic decomposition with a novel dictionary.

Atomic decomposition (AD) can be used to efficiently decompose an arbitrary signal. In this paper, we present a method to detect neonatal electroencephalogram (EEG) seizure based on AD via orthogonal matching pursuit using a novel, application-specific, dictionary. The dictionary consists of pseudoperiodic Duffing oscillator atoms which are designed to be coherent with the seizure epochs. The relative structural complexity (a measure of the rate of convergence of AD) is used as the sole feature for seizure detection. The proposed feature was tested on a large clinical dataset of 826 h of EEG data from 18 full-term newborns with 1389 seizures. The seizure detection system using the proposed dictionary was able to achieve a median receiver operator characteristic area of 0.91 (IQR 0.87-0.95) across 18 neonates.

A novel dictionary for neonatal EEG seizure detection using atomic decomposition.

The development of automated methods of electroencephalogram (EEG) seizure detection is an important problem in neonatology. This paper proposes improvements to a previously described method of seizure detection based on atomic decomposition by developing a new time-frequency (TF) dictionary that is highly coherent with the newborn EEG seizure. We compare the performance of the proposed dictionary on neonatal EEG signals with that achieved using Gabor, Fourier and wavelet dictionaries. Through the analysis of real newborn EEG data, we show first, that dictionary selection can influence the seizure detection accuracy and second, that the proposed dictionary outperforms other dictionaries by at least 10% in seizure detection accuracy and 5% improvement in the area under the Receiver Operator Characteristic curve.