Deep Learning for Automated Detection and Localization of Traumatic Abdominal Solid Organ Injuries on CT Scans.

Computed tomography (CT) is the most commonly used diagnostic modality for blunt abdominal trauma (BAT), significantly influencing management approaches. Deep learning models (DLMs) have shown great promise in enhancing various aspects of clinical practice. There is limited literature available on the use of DLMs specifically for trauma image evaluation. In this study, we developed a DLM aimed at detecting solid organ injuries to assist medical professionals in rapidly identifying life-threatening injuries. The study enrolled patients from a single trauma center who received abdominal CT scans between 2008 and 2017. Patients with spleen, liver, or kidney injury were categorized as the solid organ injury group, while others were considered negative cases. Only images acquired from the trauma center were enrolled. A subset of images acquired in the last year was designated as the test set, and the remaining images were utilized to train and validate the detection models. The performance of each model was assessed using metrics such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, and negative predictive value based on the best Youden index operating point. The study developed the models using 1302 (87%) scans for training and tested them on 194 (13%) scans. The spleen injury model demonstrated an accuracy of 0.938 and a specificity of 0.952. The accuracy and specificity of the liver injury model were reported as 0.820 and 0.847, respectively. The kidney injury model showed an accuracy of 0.959 and a specificity of 0.989. We developed a DLM that can automate the detection of solid organ injuries by abdominal CT scans with acceptable diagnostic accuracy. It cannot replace the role of clinicians, but we can expect it to be a potential tool to accelerate the process of therapeutic decisions for trauma care.

DeepVariant-on-Spark: Small-Scale Genome Analysis Using a Cloud-Based Computing Framework.

Although sequencing a human genome has become affordable, identifying genetic variants from whole-genome sequence data is still a hurdle for researchers without adequate computing equipment or bioinformatics support. GATK is a gold standard method for the identification of genetic variants and has been widely used in genome projects and population genetic studies for many years. This was until the Google Brain team developed a new method, DeepVariant, which utilizes deep neural networks to construct an image classification model to identify genetic variants. However, the superior accuracy of DeepVariant comes at the cost of computational intensity, largely constraining its applications. Accordingly, we present DeepVariant-on-Spark to optimize resource allocation, enable multi-GPU support, and accelerate the processing of the DeepVariant pipeline. To make DeepVariant-on-Spark more accessible to everyone, we have deployed the DeepVariant-on-Spark to the Google Cloud Platform (GCP). Users can deploy DeepVariant-on-Spark on the GCP following our instruction within 20 minutes and start to analyze at least ten whole-genome sequencing datasets using free credits provided by the GCP. DeepVaraint-on-Spark is freely available for small-scale genome analysis using a cloud-based computing framework, which is suitable for pilot testing or preliminary study, while reserving the flexibility and scalability for large-scale sequencing projects.

CoMutPlotter: a web tool for visual summary of mutations in cancer cohorts.

BACKGROUND: CoMut plot is widely used in cancer research publications as a visual summary of mutational landscapes in cancer cohorts. This summary plot can inspect gene mutation rate and sample mutation burden with their relevant clinical details, which is a common first step for analyzing the recurrence and co-occurrence of gene mutations across samples. The cBioPortal and iCoMut are two web-based tools that allow users to create intricate visualizations from pre-loaded TCGA and ICGC data. For custom data analysis, only limited command-line packages are available now, making the production of CoMut plots difficult to achieve, especially for researchers without advanced bioinformatics skills. To address the needs for custom data and TCGA/ICGC data comparison, we have created CoMutPlotter, a web-based tool for the production of publication-quality graphs in an easy-of-use and automatic manner. RESULTS: We introduce a web-based tool named CoMutPlotter to lower the barriers between complex cancer genomic data and researchers, providing intuitive access to mutational profiles from TCGA/ICGC projects as well as custom cohort studies. A wide variety of file formats are supported by CoMutPlotter to translate cancer mutation profiles into biological insights and clinical applications, which include Mutation Annotation Format (MAF), Tab-separated values (TSV) and Variant Call Format (VCF) files. CONCLUSIONS: In summary, CoMutPlotter is the first tool of its kind that supports VCF file, the most widely used file format, as its input material. CoMutPlotter also provides the most-wanted function for comparing mutation patterns between custom cohort and TCGA/ICGC project. Contributions of COSMIC mutational signatures in individual samples are also included in the summary plot, which is a unique feature of our tool. CoMutPlotter is freely available at http://tardis.cgu.edu.tw/comutplotter .