Search

The coronavirus disease 2019 (COVID-19) pandemic has revealed that even the best-resourced hospitals may lack sufficient ventilators to support patients under surge conditions. During a pandemic or mass trauma, an affordable, low-maintenance, off-the-shelf device that would allow health care teams to rapidly expand their ventilator capacity could prove lifesaving, but only if it can be safely integrated into a complex and rapidly changing clinical environment. Here, we define an approach to safe ventilator sharing that prioritizes predictable and independent care of patients sharing a ventilator. Subsequently, we detail the design and testing of a ventilator-splitting circuit that follows this approach and describe our clinical experience with this circuit during the COVID-19 pandemic. This circuit was able to provide individualized and titratable ventilatory support with individualized positive end-expiratory pressure (PEEP) to 2 critically ill patients at the same time, while insulating each patient from changes in the other's condition. We share insights from our experience using this technology in the intensive care unit and outline recommendations for future clinical applications.

Splenosis, commonly occurs incidentally and locates to bowel surfaces, parietal peritoneum, mesentery, and diaphragm, but can potentially occur anywhere in the peritoneal cavity. Patients frequently have a history of splenectomy or trauma. On the other hand, hepatic splenosis is a rare entity and may present itself clinically. Indeterminate liver lesions can pose a clinical dilemma and may lead to additional investigations, anxiety, follow-up imaging and even to invasive procedures. MRI usually performs extremely well. In difficult cases, scintigraphy can be of great value -especially with novel SPECT-CT and SPECT-MR techniques-. We describe a case of a 29-year-old lady with hepatic splenosis and the impact of hybrid imaging.

The aim of this research was to indicate the possibilities of using synthetic measure to find and analyse spatial disparities of the natural environment in 102 diagnostic communities of the Świętokrzyskie Voivodeship as a peripheral area. The research was conducted on the basis of selected diagnostic features. The data presented refer to the years 2009, 2012 and 2015 and come from the Local Data Bank. Bearing in mind the research aim, the following hypothesis was formed: The use of proper synthetic measures makes it possible to recognise spatial disparities which appear in the natural environment. This paper is a continuation of the work entitled: Synyhetic Measure Used as Assessment of Spatial Disparities of the Natural Environment (Przybytniowski, Dziekański, 2019). The analysis of the natural environment of municipalities occurs through human activities, and having a direct impact on the environment (indirectly related to the environment).

Recent advances in artificial intelligence (AI) are providing an opportunity to enhance existing clinical decision support (CDS) tools to improve patient safety and drive value-based imaging. We discuss the advantages and potential applications that may be realized with the synergy between AI and CDS systems. From the perspective of both radiologist and ordering provider, CDS could be significantly empowered using AI. CDS enhanced by AI could reduce friction in radiology workflows and can aid AI developers to identify relevant imaging features their tools should be seeking to extract from images. Furthermore, these systems can generate structured data to be used as input to develop machine learning algorithms, which can drive downstream care pathways. For referring providers, an AI-enabled CDS solution could enable an evolution from existing imaging-centric CDS toward decision support that takes into account a holistic patient perspective. More intelligent CDS could suggest imaging examinations in highly complex clinical scenarios, assist on the identification of appropriate imaging opportunities at the health system level, suggest appropriate individualized screening, or aid health care providers to ensure continuity of care. AI has the potential to enable the next generation of CDS, improving patient care and enhancing providers' and radiologists' experience.

The growing interest in machine learning (ML) in healthcare is driven by the promise of improved patient care. However, how many ML algorithms are currently being used in clinical practice? While the technology is present, as demonstrated in a variety of commercial products, clinical integration is hampered by a lack of infrastructure, processes, and tools. In particular, automating the selection of relevant series for a particular algorithm remains challenging. In this work, we propose a methodology to automate the identification of brain MRI sequences so that we can automatically route the relevant inputs for further image-related algorithms. The method relies on metadata required by the Digital Imaging and Communications in Medicine (DICOM) standard, resulting in generalizability and high efficiency (less than 0.4 ms/series). To support our claims, we test our approach on two large brain MRI datasets (40,000 studies in total) from two different institutions on two different continents. We demonstrate high levels of accuracy (ranging from 97.4 to 99.96%) and generalizability across the institutions. Given the complexity and variability of brain MRI protocols, we are confident that similar techniques could be applied to other forms of radiological imaging.

We propose a 4D convolutional neural network (CNN) for the segmentation of retrospective ECG-gated cardiac CT, a series of single-channel volumetric data over time. While only a small subset of volumes in the temporal sequence is annotated, we define a sparse loss function on available labels to allow the network to leverage unlabeled images during training and generate a fully segmented sequence. We investigate the accuracy of the proposed 4D network to predict temporally consistent segmentations and compare with traditional 3D segmentation approaches. We demonstrate the feasibility of the 4D CNN and establish its performance on cardiac 4D CCTA (video: https://drive.google.com/uc?id=1n-GJX5nviVs8R7tque2zy2uHFcN_Ogn1.).

Recent advances and future perspectives of machine learning techniques offer promising applications in medical imaging. Machine learning has the potential to improve different steps of the radiology workflow including order scheduling and triage, clinical decision support systems, detection and interpretation of findings, postprocessing and dose estimation, examination quality control, and radiology reporting. In this article, the authors review examples of current applications of machine learning and artificial intelligence techniques in diagnostic radiology. In addition, the future impact and natural extension of these techniques in radiology practice are discussed. © RSNA, 2018

With the advent of three-dimensional (3D) printers and the advancement of medical imaging software, 3D printing is being incorporated into the medical field in myriad ways. .

Background: Diffusion-weighted imaging (DWI) is the gold standard for detection of acute ischemic stroke (AIS) and may guide patient selection for endovascular therapy. Machine learning algorithms can enhance clinical workflow in suspected AIS by providing early diagnosis and quantitative imaging biomarkers. We tested the hypothesis that our deep learning algorithm for detection of acute ischemia performs robustly in a real-world environment. Methods: We developed a novel deep neural network architecture (YNet) that operates on MRI diffusion data at full resolution. YNet demonstrated strong performance in AIS detection and segmentation on test and validation datasets. After validation, we challenged YNet to assess 1081 consecutive brain MRIs acquired from 9 different scanners at our institution over a 2-week period. Studies were labeled as having AIS by a radiologist who used the final clinical imaging report. A series selection algorithm was applied to each study to identify DWI and apparent diffusion coefficient (ADC) series for input to the YNet using DICOM metadata to ensure relevant criteria are met (B value = 1000, axial plane, etc.). Patients with known diagnoses were excluded. Results: The series selection algorithm identified 826 studies that had DWI and ADC series with the established criteria. After exclusion of patients with known diagnoses, 378 studies were assessed by the YNet algorithm for the presence of AIS. The prevalence of AIS was 11.9% within this consecutive cohort. The algorithm detected 43 out of the 45 studies with AIS. Sensitivity and specificity for detection were 95.5% and 97.0%, respectively. Conclusion: Our YNet algorithm demonstrated excellent performance in detecting AIS in a serially-acquired dataset. Fully automated implementation will require further refinement of the series selection algorithm.

Background: Machine learning algorithms have proven accurate in the detection of intracranial hemorrhage (ICH) on head CT. Most reported algorithms, however, are limited to binary detection and global lesion volume estimation. We developed a pipeline to additionally perform subtype classification for clinical risk stratification, while also providing visual displays to improve interpretability of algorithm output (“black box problem”) and enable clinical systems integration. Methods: We developed a convolutional neural network (CNN) for ICH detection and subtype classification. The algorithm was trained on 2,209 head CT exams (hemorrhage-negative controls and the 5 major ICH subtypes) and outputs class-activation heatmaps to aid interpretability. We quantify intraparenchymal hemorrhage (IPH) volume using a modified U-Net CNN trained on a cohort of 110 manually-segmented hematomas to precisely delineate lesion boundaries. Algorithm output was stored as DICOM segmentation objects which can be overlaid on native images within our existing viewer applications, enabling the user to dynamically adjust characteristics such as color and transparency. Results: Diagnostic performance for ICH detection was high with ROC area-under-curve of 0.98. Fig 1A shows a heatmap highlighting different ICH foci. IPH subtype classification performance is summarized in Fig 1B with area-under-curve of 0.95. Fig 1C shows IPH segmentation and volume estimation overlays with automatically generated text for the medical record. Dice similarity coefficient for segmentation was 0.87. Conclusion: We describe a machine-learning approach for ICH detection, subtype classification, and IPH-specific volume estimation. Utilizing easily interpretable heatmaps, dynamically-adjustable overlays, and automated result text generation, our pipeline is capable of providing accurate information optimized for clinical integration.

Three-dimensional (3D) printing has recently erupted into the medical arena due to decreased costs and increased availability of printers and software tools. Due to lack of detailed information in the medical literature on the methods for 3D printing, we have reviewed the medical and engineering literature on the various methods for 3D printing and compiled them into a practical "how to" format, thereby enabling the novice to start 3D printing with very limited funds. We describe (1) background knowledge, (2) imaging parameters, (3) software, (4) hardware, (5) post-processing, and (6) financial aspects required to cost-effectively reproduce a patient's disease ex vivo so that the patient, engineer and surgeon may hold the anatomy and associated pathology in their hands.

Background: Digital Imaging and Communications in Medicine (DICOM®) is the standard for the representation, storage, and communication of medical images and related information. A DICOM file format and communication protocol for pathology have been defined; however, adoption by vendors and in the field is pending. Here, we implemented the essential aspects of the standard and assessed its capabilities and limitations in a multisite, multivendor healthcare network. Methods: We selected relevant DICOM attributes, developed a program that extracts pixel data and pixel-related metadata, integrated patient and specimen-related metadata, populated and encoded DICOM attributes, and stored DICOM files. We generated the files using image data from four vendor-specific image file formats and clinical metadata from two departments with different laboratory information systems. We validated the generated DICOM files using recognized DICOM validation tools and measured encoding, storage, and access efficiency for three image compression methods. Finally, we evaluated storing, querying, and retrieving data over the web using existing DICOM archive software. Results: Whole slide image data can be encoded together with relevant patient and specimen-related metadata as DICOM objects. These objects can be accessed efficiently from files or through RESTful web services using existing software implementations. Performance measurements show that the choice of image compression method has a major impact on data access efficiency. For lossy compression, JPEG achieves the fastest compression/decompression rates. For lossless compression, JPEG-LS significantly outperforms JPEG 2000 with respect to data encoding and decoding speed. Conclusion: Implementation of DICOM allows efficient access to image data as well as associated metadata. By leveraging a wealth of existing infrastructure solutions, the use of DICOM facilitates enterprise integration and data exchange for digital pathology.

Improved outcome in patients with ischemic stroke is achieved through acute diagnosis and early restoration of cerebral flow in appropriate patients. Diffusion-weighted MR imaging (DWI) plays a central role in these efforts by enabling rapid early localization and quantification of ischemic lesions. Automated detection and quantification can potentially accelerate diagnosis, improve treatment safety and efficacy and reduce costs. However, the manual quantification of acute ischemic stroke volumes for algorithm training is time consuming and imprecise. We present YNet as a novel fully-automated deep learning algorithm for detection and volumetric segmentation and quantification of acute cerebral ischemic lesions from DWI. The algorithm is a semi-supervised multi-tasking deep neural network architecture we developed that enables the combination of both weak labels derived from radiology report classification and manually delineated pixel level training data. The model is trained on a very large dataset of 10000 studies, achieves detection sensitivity 0.981, detection specificity 0.980 and segmentation Dice score 0.623 on a heterogeneous test set.

Data diversity is critical to success when training deep learning models. Medical imaging data sets are often imbalanced as pathologic findings are generally rare, which introduces significant challenges when training deep learning models. In this work, we propose a method to generate synthetic abnormal MRI images with brain tumors by training a generative adversarial network using two publicly available data sets of brain MRI. We demonstrate two unique benefits that the synthetic images provide. First, we illustrate improved performance on tumor segmentation by leveraging the synthetic images as a form of data augmentation. Second, we demonstrate the value of generative models as an anonymization tool, achieving comparable tumor segmentation results when trained on the synthetic data versus when trained on real subject data. Together, these results offer a potential solution to two of the largest challenges facing machine learning in medical imaging, namely the small incidence of pathological findings, and the restrictions around sharing of patient data.

The amounts of muscle and fat in a person's body, known as body composition, are correlated with cancer risks, cancer survival, and cardiovascular risk. The current gold standard for measuring body composition requires time-consuming manual segmentation of CT images by an expert reader. In this work, we describe a two-step process to fully automate the analysis of CT body composition using a DenseNet to select the CT slice and U-Net to perform segmentation. We train and test our methods on independent cohorts. Our results show Dice scores (0.95-0.98) and correlation coefficients (R=0.99) that are favorable compared to human readers. These results suggest that fully automated body composition analysis is feasible, which could enable both clinical use and large-scale population studies.

Purpose To evaluate the effect of tomosynthesis in diagnostic mammography on the Breast Imaging Reporting and Data System (BI-RADS) final assessment categories over time. Materials and Methods This retrospective study was approved by the institutional review board. The authors reviewed all diagnostic mammograms obtained during a 12-month interval before (two-dimensional [2D] mammography [June 2, 2010, to June 1, 2011]) and for 3 consecutive years after (tomosynthesis year 1 [2012], tomosynthesis year 2 [2013], and tomosynthesis year 3 [2014]) the implementation of tomosynthesis. The requirement to obtain informed consent was waived. The rates of BI-RADS final assessment categories 1-5 were compared between the 2D and tomosynthesis groups. The positive predictive values after biopsy (PPV3) for BI-RADS category 4 and 5 cases were compared. The mammographic features (masses, architectural distortions, calcifications, focal asymmetries) of lesions categorized as probably benign (BI-RADS category 3) and those for which biopsy was recommended (BI-RADS category 4 or 5) were reviewed. The χ(2) test was used to compare the rates of BI-RADS final assessment categories 1-5 between the two groups, and multivariate logistic regression analysis was performed to compare all diagnostic studies categorized as BI-RADS 3-5. Results There was an increase in the percentage of cases reported as negative or benign (BI-RADS category 1 or 2) with tomosynthesis (58.7% with 2D mammography vs 75.8% with tomosynthesis at year 3, P < .0001). A reduction in the percentage of probably benign (BI-RADS category 3) final assessments also occurred (33.3% with 2D mammography vs 16.4% with tomosynthesis at year 3, P < .0001). Although the rates of BI-RADS 4 or 5 assessments did not change significantly with tomosynthesis (8.0% with 2D mammography vs 7.8% with tomosynthesis at year 3, P = .2), there was a significant increase in the PPV3 (29.6% vs 50%, respectively; P < .0001). These trends increased during the 3 years of tomosynthesis use. Conclusion Tomosynthesis in the diagnostic setting resulted in progressive shifts in the BI-RADS final assessment categories over time, with a significant increase in the proportion of studies classified as normal, a continued decrease in the rate of studies categorized as probably benign, and improved diagnostic confidence in biopsy recommendations. (©) RSNA, 2016.

The ability of humans to distinguish the delicate differences in food flavors depends mostly on retronasal smell, in which food volatiles entrained into the airway at the back of the oral cavity are transported by exhaled air through the nasal cavity to stimulate the olfactory receptor neurons. Little is known whether food volatiles are preferentially carried by retronasal flow toward the nasal cavity rather than by orthonasal flow into the lung. To study the differences between retronasal and orthonasal flow, we obtained computed tomography (CT) images of the orthonasal airway from a healthy human subject, printed an experimental model using a 3D printer, and analyzed the flow field inside the airway. The results show that, during inhalation, the anatomical structure of the oropharynx creates an air curtain outside a virtual cavity connecting the oropharynx and the back of the mouth, which prevents food volatiles from being transported into the main stream toward the lung. In contrast, during exhalation, the flow preferentially sweeps through this virtual cavity and effectively enhances the entrainment of food volatiles into the main retronasal flow. This asymmetrical transport efficiency is also found to have a nonmonotonic Reynolds number dependence: The asymmetry peaks at a range of an intermediate Reynolds number close to 800, because the air curtain effect during inhalation becomes strongest in this range. This study provides the first experimental evidence, to our knowledge, for adaptations of the geometry of the human oropharynx for efficient transport of food volatiles toward the olfactory receptors in the nasal cavity.

e15121 Background: Intra-tumor heterogeneity is an independent determinant of patient survival outcomes in several tumor subtypes. Spatial variations in tumor enhancement on MRI is a macroscopic imaging marker of tumor heterogeneity. The goal of this study is to evaluate the potential role of MRI-based enhancement heterogeneity measures as predictors of survival in patients with metastatic colorectal cancer. Methods: We retrospectively analyzed T1-weighted contrast-enhanced MRI images of metastatic hepatic lesions in 41 patients (mean age 57.2 ±14.2 years) who were diagnosed with stage IV colorectal cancer between 2007 and 2013. Tumor Kras mutation status and patient survival data for up to 95 months was available for all patients. The largest metastatic hepatic lesion was identified by a radiologist and manually segmented. 14 Haralick texture features were extracted from each lesion. Cox proportional hazards regression analysis was used to assess the association between the enhancement heterogeneity measures and patient survival, with adjustment for Kras mutation status as a potential confounder. Backward stepwise feature selection was performed using p > 0.1 (Wald test) to select for statistically significant features. Results:Mean survival time was 39±3.9 months for the study population (51±4.1 months for Kras-wildtype and 37±5.1 for Kras-mutants). 68% of the patients had left-sided colon cancer; 21% had concurrent pulmonary metastases and 0.5% had concurrent brain metastasis. 61%, 27% and 12% of patients were on Flofox, Folfiri or other chemotherapeutic regimen, respectively. Texture matrix homogeneity (HR > 10; p = 0.016), inverse difference moment (HR < 0.1; p = 0.020), entropy (HR < 0.1; p = 0.033) and standard deviation (HR > 10; p = 0.006) exhibited significant independent association with patient survival. With the exception of entropy, these features maintained significant contribution to survival prediction independent of Kras mutation status. Conclusions: MRI-based quantitativeintra-metastasis heterogeneity measures are associated with patient survival and may add information beyond genetic mutation status to optimize prognosis prediction in metastatic colon cancer.

In the last decade of the 19th century and in the first two decades of the 20th century, the German Empire and the Austria-Hungary empire (Dual Monarchy) came forward with the value of bold erotic. The Erotic was generally regarded as an animalistic relic that was located beyond, which could give meaning to human life. Heinrich Rickert began his philosophical career in fashion with good neo-Kantian epistemology and philosophy of science studies, which are reflected mainly in two large and several subsequent editions with repeatedly revised works. In the event of conflict between subjective and objective values, the achievement of objective values has to give priority to the implementation of subjective values, because independent of specific evaluative filing application provides a higher principle. The use of human freedom provides more challenging stage with a dependent specific evaluative acts. The original text of the chapter is in German. Keywords: Austria-Hungary empire; erotic value; Heinrich Rickert; human freedom; neo-Kantian epistemology; subjective values