Automatic thoracic aorta calcium quantification using deep learning in non-contrast ECG-gated CT images.

Thoracic aorta calcium (TAC) can be assessed from cardiac computed tomography (CT) studies to improve cardiovascular risk prediction. The aim of this study was to develop a fully automatic system to detect TAC and to evaluate its performance for classifying the patients into four TAC risk categories. The method started by segmenting the thoracic aorta, combining three UNets trained with axial, sagittal and coronal CT images. Afterwards, the surrounding lesion candidates were classified using three combined convolutional neural networks (CNNs) trained with orthogonal patches. Image datasets included 1190 non-enhanced ECG-gated cardiac CT studies from a cohort of cardiovascular patients (age 57 ± 9 years, 80% men, 65% TAC > 0). In the test set (N = 119), the combination of UNets was able to successfully segment the thoracic aorta with a mean volume difference of 0.3 ± 11.7 ml (<6%) and a median Dice coefficient of 0.947. The combined CNNs accurately classified the lesion candidates and 87% of the patients (N = 104) were accurately placed in their corresponding risk categories (Kappa = 0.826, ICC = 0.9915). TAC measurement can be estimated automatically from cardiac CT images using UNets to isolate the thoracic aorta and CNNs to classify calcified lesions.

A Novel Automatic Quantification Protocol for Biomarkers of Tauopathies in the Hippocampus and Entorhinal Cortex of Post-Mortem Samples Using an Extended Semi-Siamese U-Net.

Efforts have been made to diagnose and predict the course of different neurodegenerative diseases through various imaging techniques. Particularly tauopathies, where the tau polypeptide is a key participant in molecular pathogenesis, have significantly increased their morbidity and mortality in the human population over the years. However, the standard approach to exploring the phenomenon of neurodegeneration in tauopathies has not been directed at understanding the molecular mechanism that causes the aberrant polymeric and fibrillar behavior of the tau protein, which forms neurofibrillary tangles that replace neuronal populations in the hippocampal and cortical regions. The main objective of this work is to implement a novel quantification protocol for different biomarkers based on pathological post-translational modifications undergone by tau in the brains of patients with tauopathies. The quantification protocol consists of an adaptation of the U-Net neural network architecture. We used the resulting segmentation masks for the quantification of combined fluorescent signals of the different molecular changes tau underwent in neurofibrillary tangles. The quantification considers the neurofibrillary tangles as an individual study structure separated from the rest of the quadrant present in the images. This allows us to detect unconventional interaction signals between the different biomarkers. Our algorithm provides information that will be fundamental to understanding the pathogenesis of dementias with another computational analysis approach in subsequent studies.

Radiomics Diagnostic Tool Based on Deep Learning for Colposcopy Image Classification.

BACKGROUND: Colposcopy imaging is widely used to diagnose, treat and follow-up on premalignant and malignant lesions in the vulva, vagina, and cervix. Thus, deep learning algorithms are being used widely in cervical cancer diagnosis tools. In this study, we developed and preliminarily validated a model based on the Unet network plus SVM to classify cervical lesions on colposcopy images. Methodology: Two sets of images were used: the Intel & Mobile ODT Cervical Cancer Screening public dataset, and a private dataset from a public hospital in Ecuador during a routine colposcopy, after the application of acetic acid and lugol. For the latter, the corresponding clinical information was collected, specifically cytology on the PAP smear and the screening of human papillomavirus testing, prior to colposcopy. The lesions of the cervix or regions of interest were segmented and classified by the Unet and the SVM model, respectively. Results: The CAD system was evaluated for the ability to predict the risk of cervical cancer. The lesion segmentation metric results indicate a DICE of 50%, a precision of 65%, and an accuracy of 80%. The classification results' sensitivity, specificity, and accuracy were 70%, 48.8%, and 58%, respectively. Randomly, 20 images were selected and sent to 13 expert colposcopists for a statistical comparison between visual evaluation experts and the CAD tool (p-value of 0.597). Conclusion: The CAD system needs to improve but could be acceptable in an environment where women have limited access to clinicians for the diagnosis, follow-up, and treatment of cervical cancer; better performance is possible through the exploration of other deep learning methods with larger datasets.

Dual U-Net-Based Conditional Generative Adversarial Network for Blood Vessel Segmentation with Reduced Cerebral MR Training Volumes.

Segmenting vessels in brain images is a critical step for many medical interventions and diagnoses of illnesses. Recent advances in artificial intelligence provide better models, achieving a human-like level of expertise in many tasks. In this paper, we present a new approach to segment Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) images, relying on fewer training samples than state-of-the-art methods. We propose a conditional generative adversarial network with an adapted generator based on a concatenated U-Net with a residual U-Net architecture (UUr-cGAN) to carry out blood vessel segmentation in TOF-MRA images, relying on data augmentation to diminish the drawback of having few volumes at disposal for training the model, while preventing overfitting by using regularization techniques. The proposed model achieves 89.52% precision and 87.23% in Dice score on average from the cross-validated experiment for brain blood vessel segmentation tasks, which is similar to other state-of-the-art methods while using considerably fewer training samples. UUr-cGAN extracts important features from small datasets while preventing overfitting compared to other CNN-based methods and still achieve a relatively good performance in image segmentation tasks such as brain blood vessels from TOF-MRA.

Effective residual convolutional neural network for Chagas disease parasite segmentation.

Considered a neglected tropical pathology, Chagas disease is responsible for thousands of deaths per year and it is caused by the parasite Trypanosoma cruzi. Since many infected people can remain asymptomatic, a fast diagnosis is necessary for proper intervention. Parasite microscopic observation in blood samples is the gold standard method to diagnose Chagas disease in its initial phase; however, this is a time-consuming procedure, requires expert intervention, and there is currently no efficient method to automatically perform this task. Therefore, we propose an efficient residual convolutional neural network, named Res2Unet, to perform a semantic segmentation of Trypanosoma cruzi parasites, with an active contour loss and improved residual connections, whose design is based on Heun's method for solving ordinary differential equations. The model was trained on a dataset of 626 blood sample images and tested on a dataset of 207 images. Validation experiments report that our model achieved a Dice coefficient score of 0.84, a precision value of 0.85, and a recall value of 0.82, outperforming current state-of-the-art methods. Since Chagas disease is a severe and silent illness, our computational model may benefit health care providers to give a prompt diagnose for this worldwide affection.

Segmentation of Masses on Mammograms Using Data Augmentation and Deep Learning.

The diagnosis of breast cancer in early stage is essential for successful treatment. Detection can be performed in several ways, the most common being through mammograms. The projections acquired by this type of examination are directly affected by the composition of the breast, which density can be similar to the suspicious masses, being a challenge the identification of malignant lesions. In this article, we propose a computer-aided detection (CAD) system to aid in the diagnosis of masses in digitized mammograms using a model based in the U-Net, allowing specialists to monitor the lesion over time. Unlike most of the studies, we propose the use of an entire base of digitized mammograms using normal, benign, and malignant cases. Our research is divided into four stages: (1) pre-processing, with the removal of irrelevant information, enhancement of the contrast of 7989 images of the Digital Database for Screening Mammography (DDSM), and obtaining regions of interest. (2) Data augmentation, with horizontal mirroring, zooming, and resizing of images; (3) training, with tests of six-based U-Net models, with different characteristics; (4) testing, evaluating four metrics, accuracy, sensitivity, specificity, and Dice Index. The tested models obtained different results regarding the assessed parameters. The best model achieved a sensitivity of 92.32%, specificity of 80.47%, accuracy of 85.95% Dice Index of 79.39%, and AUC of 86.40%. Even using a full base without case selection bias, the results obtained demonstrate that the use of a complete database can provide knowledge to the CAD expert.