Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

From Early Morphometrics to Machine Learning-What Future for Cardiovascular Imaging of the Pulmonary Circulation?

In Diagnostics (Basel, Switzerland)

Imaging plays a cardinal role in the diagnosis and management of diseases of the pulmonary circulation. Behind the picture itself, every digital image contains a wealth of quantitative data, which are hardly analysed in current routine clinical practice and this is now being transformed by radiomics. Mathematical analyses of these data using novel techniques, such as vascular morphometry (including vascular tortuosity and vascular volumes), blood flow imaging (including quantitative lung perfusion and computational flow dynamics), and artificial intelligence, are opening a window on the complex pathophysiology and structure-function relationships of pulmonary vascular diseases. They have the potential to make dramatic alterations to how clinicians investigate the pulmonary circulation, with the consequences of more rapid diagnosis and a reduction in the need for invasive procedures in the future. Applied to multimodality imaging, they can provide new information to improve disease characterization and increase diagnostic accuracy. These new technologies may be used as sophisticated biomarkers for risk prediction modelling of prognosis and for optimising the long-term management of pulmonary circulatory diseases. These innovative techniques will require evaluation in clinical trials and may in themselves serve as successful surrogate end points in trials in the years to come.

Gopalan Deepa, Gibbs J Simon R


AI and pulmonary vasculature, blood flow imaging, deep learning and pulmonary circulation, machine learning and pulmonary circulation, pulmonary perfusion imaging, pulmonary vascular imaging, pulmonary vascular morphometrics, radiomics

Public Health Public Health

Reusable Self-Sterilization Masks Based on Electrothermal Graphene Filters.

In ACS applied materials & interfaces ; h5-index 147.0

Surgical mask is recommended by the World Health Organization for personal protection against disease transmission. However, most of the surgical masks on the market are disposable that cannot be self-sterilized for reuse. Thus, when confronting the global public health crisis, a severe shortage of mask resource is inevitable. In this paper, a novel low-cost electrothermal mask with excellent self-sterilization performance and portability is reported to overcome this shortage. First, a flexible, ventilated, and conductive cloth tape is patterned and adhered to the surface of a filter layer made of melt-blown nonwoven fabrics (MNF), which functions as interdigital electrodes. Then, a graphene layer with premier electric and thermal conductivity is coated onto the MNF. Operating under a low voltage of 3 V, the graphene-modified MNF (mod-MNF) can quickly generate large amounts of heat to achieve a high temperature above 80 °C, which can kill the majority of known viruses attached to the filter layer and the mask surface. Finally, the optimized graphene-modified masks based on the mod-MNF filter retain a relatively high particulate matter (PM) removal efficiency and a low-pressure drop. Moreover, the electrothermal masks can maintain almost the same PM removal efficiency over 10 times of electrifying, suggesting its outstanding reusability.

Shan Xiaoli, Zhang Han, Liu Cihui, Yu Liyan, Di Yunsong, Zhang Xiaowei, Dong Lifeng, Gan Zhixing


COVID-19, electrothermal effect, graphene ink, self-sterilization, surgical masks

Pathology Pathology

Extraction of the molecular level biomedical event trigger based on gene ontology using radial belief neural network techniques.

In Bio Systems

Detection of molecular level biomedical event extraction plays a vital role in creating and visualizing the applications related to natural language processing. Cystic Fibrosis is an inherited genetic and debilitating pathology involving the respiratory and digestive systems. The excessive production of thick sticky mucus on the outside of the cells is the main consequence of such disease. This includes disease prevention and medical search to signify the occurrence and detection of event triggers, which is regarded as a proper step in an event extraction of molecular level in biomedical applications. In this model, use a rich set of extracted features to feed the machine learning classifier that helps in better extraction of events. The study uses an automatic feature selection and a classification model using Radial Belief Neural Network (RBNN) for the optimal detection of molecular biomedical event detection. The Radial Belief Neural Network (RBNN) is the proposed system is implemented and it is the classifier to give accurate result of the disease detection. These three algorithms are used to enhance the generalization performance and scalability of detecting the molecular event triggers. The validation is conducted on the cystic fibrosis event trigger based on the gene ontology bio system using the RBNN model with a lung molecular event-level extraction dataset. The extensive computation shows that the Radial Belief Neural Network (RBNN) is proposed to given the better performance results like Accuracy, Sensitivity, Specificity, F-measure and Execution time.

Devendra Kumar R N, Chakrapani Arvind, Srihari K


Artificial intelligence, Biomedical, Cystic fibrosis, Gene ontology biosystems, Machine learning, Neural network, Radial belief neural network (RBNN)

General General

A phenotypic switch in the dispersal strategy of breast cancer cells selected for metastatic colonization.

In Proceedings. Biological sciences

An important question in cancer evolution concerns which traits make a cell likely to successfully metastasize. Cell motility phenotypes, mediated by cell shape change, are strong candidates. We experimentally evolved breast cancer cells in vitro for metastatic capability, using selective regimes designed to simulate stages of metastasis, then quantified their motility behaviours using computer vision. All evolved lines showed changes to motility phenotypes, and we have identified a previously unknown density-dependent motility phenotype only seen in cells selected for colonization of decellularized lung tissue. These cells increase their rate of morphological change with an increase in migration speed when local cell density is high. However, when the local cell density is low, we find the opposite relationship: the rate of morphological change decreases with an increase in migration speed. Neither the ancestral population, nor cells selected for their ability to escape or invade extracellular matrix-like environments, displays this dynamic behavioural switch. Our results suggest that cells capable of distant-site colonization may be characterized by dynamic morphological phenotypes and the capacity to respond to the local social environment.

Butler George, Keeton Shirley J, Johnson Louise J, Dash Philip R


cancer evolution, cell morphology, experimental evolution, machine learning, metastasis

General General

EPTool: A New Enhancing PSSM Tool for Protein Secondary Structure Prediction.

In Journal of computational biology : a journal of computational molecular cell biology

Recently, a deep learning-based enhancing Position-Specific Scoring Matrix (PSSM) method (Bagging Multiple Sequence Alignment [MSA] Learning) Guo et al. has been proposed, and its effectiveness has been empirically proved. Program EPTool is the implementation of Bagging MSA Learning, which provides a complete training and evaluation workflow for the enhancing PSSM model. It is capable of handling different input data set and various computing algorithms to train the enhancing model, then eventually improve the PSSM quality for those proteins with insufficient homologous sequences. In addition, EPTool equips several convenient applications, such as PSSM features calculator, and PSSM features visualization. In this article, we propose designed EPTool and briefly introduce its functionalities and applications. The detailed accessible instructions are also provided.

Guo Yuzhi, Wu Jiaxiang, Ma Hehuan, Wang Sheng, Huang Junzhou


deep learning, enhancing PSSM, protein secondary structure prediction, unsupervised learning

oncology Oncology

Improving CBCT Quality to CT Level using Deep-Learning with Generative Adversarial Network.

In Medical physics ; h5-index 59.0

PURPOSE : To improve image quality and CT number accuracy of daily cone-beam computed tomography (CBCT) through a deep-learning methodology with Generative Adversarial Network.

METHODS : 150 paired pelvic CT and CBCT scans were used for model training and validation. An unsupervised deep-learning method, 2.5D pixel-to-pixel generative adversarial network (GAN) model with feature mapping was proposed. A total of 12000 slice pairs of CT and CBCT were used for model training, while 10-cross validation was applied to verify model robustness. Paired CT-CBCT scans from an additional 15 pelvic patients and 10 head-and-neck (HN) patients with CBCT images collected at a different machine were used for independent testing purpose. Besides the proposed method above, other network architectures were also tested as: 2D vs. 2.5D; GAN model with vs. without feature mapping; GAN model with vs. without additional perceptual loss; and previously reported models as U-net and cycleGAN with or without identity loss. Image quality of deep-learning generated synthetic CT (sCT) images were quantitatively compared against the reference CT (rCT) image using mean absolute error (MAE) of Hounsfield units (HU) and peak signal-to-noise ratio (PSNR). The dosimetric calculation accuracy was further evaluated with both photon and proton beams.

RESULTS : The deep-learning generated synthetic CTs (sCT) showed improved image quality with reduced artifact distortion and improved soft tissue contrast. The proposed algorithm of 2.5 Pix2pix GAN with feature matching (FM) was shown to be the best model among all tested methods producing the highest PSNR and the lowest MAE to reference CT (rCT) . The dose distribution demonstrated a high accuracy in the scope of photon based planning, yet more work is needed for proton based treatment. Once the model was trained, it took 11-12 ms to process one slice, and could generate a 3D-volume of dCBCT (80 slices) in less than a second using a NVIDIA GeForce GTX Titan X GPU (12GB, Maxwell architecture).

CONCLUSION : The proposed deep-learning algorithm is promising to improve CBCT image quality in an efficient way, thus has a potential to support online CBCT-based adaptive radiotherapy.

Zhang Yang, Yue Ning, Su Min-Ying, Liu Bo, Ding Yi, Zhou Yongkang, Wang Hao, Kuang Yu, Nie Ke