Fully automated sinogram-based deep learning model for detection and classification of intracranial hemorrhage

PURPOSE

To propose an automated approach for detecting and classifying Intracranial Hemorrhages (ICH) directly from sinograms using a deep learning framework. This method is proposed to overcome the limitations of the conventional diagnosis by eliminating the time-consuming reconstruction step and minimizing the potential noise and artifacts that can occur during the Computed Tomography (CT) reconstruction process.

METHODS

This study proposes a two-stage automated approach for detecting and classifying ICH from sinograms using a deep learning framework. The first stage of the framework is Intensity Transformed Sinogram Sythesizer, which synthesizes sinograms that are equivalent to the intensity-transformed CT images. The second stage comprises of a cascaded Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) model that detects and classifies hemorrhages from the synthesized sinograms. The CNN module extracts high-level features from each input sinogram, while the RNN module provides spatial correlation of the neighborhood regions in the sinograms. The proposed method was evaluated on a publicly available RSNA dataset consisting of a large sample size of 8652 patients.

RESULTS

The results showed that the proposed method had a notable improvement as high as 27% in patient-wise accuracies when compared to state-of-the-art methods like ResNext-101, Inception-v3 and Vision Transformer. Furthermore, the sinogram-based approach was found to be more robust to noise and offset errors in comparison to CT image-based approaches. The proposed model was also subjected to a multi-label classification analysis to determine the hemorrhage type from a given sinogram. The learning patterns of the proposed model were also examined for explainability using the activation maps.

CONCLUSION

The proposed sinogram-based approach can provide an accurate and efficient diagnosis of ICH without the need for the time-consuming reconstruction step and can potentially overcome the limitations of CT image-based approaches. The results show promising outcomes for the use of sinogram-based approaches in detecting hemorrhages, and further research can explore the potential of this approach in clinical settings.

Hemorrhage Detection Based on 3D CNN Deep Learning Framework and Feature Fusion for Evaluating Retinal Abnormality in Diabetic Patients

Diabetic retinopathy (DR) is the main cause of blindness in diabetic patients. Early and accurate diagnosis can improve the analysis and prognosis of the disease. One of the earliest symptoms of DR are the hemorrhages in the retina. Therefore, we propose a new method for accurate hemorrhage detection from the retinal fundus images. First, the proposed method uses the modified contrast enhancement method to improve the edge details from the input retinal fundus images. In the second stage, a new convolutional neural network (CNN) architecture is proposed to detect hemorrhages. A modified pre-trained CNN model is used to extract features from the detected hemorrhages. In the third stage, all extracted feature vectors are fused using the convolutional sparse image decomposition method, and finally, the best features are selected by using the multi-logistic regression controlled entropy variance approach. The proposed method is evaluated on 1509 images from HRF, DRIVE, STARE, MESSIDOR, DIARETDB0, and DIARETDB1 databases and achieves the average accuracy of 97.71%, which is superior to the previous works. Moreover, the proposed hemorrhage detection system attains better performance, in terms of visual quality and quantitative analysis with high accuracy, in comparison with the state-of-the-art methods.

Development of hemorrhage identification model using non-invasive vital signs

OBJECTIVE

Early detection and timely management of bleeding is critical as failure to recognize physiologically significant bleeding is associated with significant morbidity and mortality. Many such instances are detected late, even in highly monitored environments, contributing to delay in recognition and intervention. We propose a non-invasive early identification model to detect bleeding events using continuously collected photoplethysmography (PPG) and electrocardiography (ECG) waveforms.

APPROACH

Fifty-nine York pigs undergoing fixed-rate, controlled hemorrhage were involved in this study and a least absolute shrinkage and selection operator regression-based early detection model was developed and tested using PPG and ECG derived features. The output of the early detection model was a risk trajectory indicating the future probability of bleeding.

MAIN RESULTS

Our proposed models were generally accurate in predicting bleeding with an area under the curve of 0.89 (95% CI 0.87-0.92) and achieved an average time of 16.1 mins to detect 16.8% blood loss when a false alert rate of 1% was tolerated. Models developed on non-invasive data performed with similar discrimination and lead time to hemorrhage compared to models using invasive arterial blood pressure as monitoring data.

SIGNIFICANCE

A bleed detection model using only non-invasive monitoring performs as well as those using invasive arterial pressure monitoring.