Search

Breast cancer is deadly cancer causing a considerable number of fatalities among women in worldwide. To enhance patient outcomes as well as survival rates, early and accurate detection is crucial. Machine learning techniques, particularly deep learning, have demonstrated impressive success in various image recognition tasks, including breast cancer classification. However, the reliance on large labeled datasets poses challenges in the medical domain due to privacy issues and data silos. This study proposes a novel transfer learning approach integrated into a federated learning framework to solve the limitations of limited labeled data and data privacy in collaborative healthcare settings. For breast cancer classification, the mammography and MRO images were gathered from three different medical centers. Federated learning, an emerging privacy-preserving paradigm, empowers multiple medical institutions to jointly train the global model while maintaining data decentralization. Our proposed methodology capitalizes on the power of pre-trained ResNet, a deep neural network architecture, as a feature extractor. By fine-tuning the higher layers of ResNet using breast cancer datasets from diverse medical centers, we enable the model to learn specialized features relevant to different domains while leveraging the comprehensive image representations acquired from large-scale datasets like ImageNet. To overcome domain shift challenges caused by variations in data distributions across medical centers, we introduce domain adversarial training. The model learns to minimize the domain discrepancy while maximizing classification accuracy, facilitating the acquisition of domain-invariant features. We conducted extensive experiments on diverse breast cancer datasets obtained from multiple medical centers. Comparative analysis was performed to evaluate the proposed approach against traditional standalone training and federated learning without domain adaptation. When compared with traditional models, our proposed model showed a classification accuracy of 98.8% and a computational time of 12.22 s. The results showcase promising enhancements in classification accuracy and model generalization, underscoring the potential of our method in improving breast cancer classification performance while upholding data privacy in a federated healthcare environment. [ABSTRACT FROM AUTHOR]

Sensitive images represent a new challenge in enterprise imaging. These images, often containing nudity or gruesome content, have the potential to cause emotional harm to patients and people who view the images. Unfortunately, the interoperability standards used in imaging informatics have not yet addressed this issue. Because of this, the software solutions used in healthcare information technology are not able to offer patients and other viewers of image protections. In this Health Information Management Systems Society (HIMSS)/Society for Imaging Informatics in Medicine (SIIM) Enterprise Imaging Community Whitepaper, we define sensitive images, identify unique challenges related to their management, and provide recommendations for future solutions to protect our patients. [ABSTRACT FROM AUTHOR]

During radiologic interpretation, radiologists read patient identifiers from the metadata of medical images to recognize the patient being examined. However, it is challenging for radiologists to identify "incorrect" metadata and patient identification errors. We propose a method that uses a patient re-identification technique to link correct metadata to an image set of computed tomography images of a trunk with lost or wrongly assigned metadata. This method is based on a feature vector matching technique that uses a deep feature extractor to adapt to the cross-vendor domain contained in the scout computed tomography image dataset. To identify "incorrect" metadata, we calculated the highest similarity score between a follow-up image and a stored baseline image linked to the correct metadata. The re-identification performance tests whether the image with the highest similarity score belongs to the same patient, i.e., whether the metadata attached to the image are correct. The similarity scores between the follow-up and baseline images for the same "correct" patients were generally greater than those for "incorrect" patients. The proposed feature extractor was sufficiently robust to extract individual distinguishable features without additional training, even for unknown scout computed tomography images. Furthermore, the proposed augmentation technique further improved the re-identification performance of the subset for different vendors by incorporating changes in width magnification due to changes in patient table height during each examination. We believe that metadata checking using the proposed method would help detect the metadata with an "incorrect" patient identifier assigned due to unavoidable errors such as human error. [ABSTRACT FROM AUTHOR]

Developmental dysplasia of the hip (DDH) is one of the most common orthopedic disorders in infants and young children. Accurate identification and localization of anatomical landmarks are prerequisites for the diagnosis of DDH. In recent years, various works have employed deep learning algorithms on radiography images for DDH diagnosis. However, none of these works have considered the incorporation of multimodal information. The pelvis exhibits distinct structures at different developmental stages, and there are also gender-based differences. In light of this, this study proposes a method to enhance the performance of deep learning models in diagnosing DDH by incorporating age and gender information into the channels. The study utilizes YOLO5 to construct a deep learning network for detecting hip joint landmarks. Moreover, a comprehensive dataset of 7750 pelvic X-ray images is established, covering ages from 4 months to 16 years and encompassing various conditions, such as deformities and post-operative cases, which authentically capture the temporal diversity and pathological complexities of DDH. Experimental results show that the YOLO5 model with integrated multimodal information achieves a mAP0.5–0.95 of 83.1% and a diagnostic accuracy of 86.7% in test dataset. The F1 scores for diagnosing cases of normal (NM), suspected dislocation (SD), mild dislocation (MD), and heavily dislocation (HD) are 90.9%, 79.8%, 63.5%, and 97.4%, respectively. Furthermore, experiments conducted on datasets of different sizes and networks of different sizes demonstrate the beneficial impact of multimodal information in improving the effectiveness of deep learning in diagnosing DDH. [ABSTRACT FROM AUTHOR]

Alignment of DICOM (Digital Imaging and Communications in Medicine) capabilities among vendors is crucial to improve interoperability in the healthcare industry and advance medical imaging 2. However, a sustainable model for sharing DICOM samples is not available. To address this issue, Integrating the Healthcare Enterprise (IHE) has introduced the IHE SHARAZONE, a continuous cross-vendor DICOM data sharing test service. IHE is a highly regarded organization known for profiling standards such as DICOM, HL7 v2 (Health Level Seven, version 2), HL7 CDA (Clinical Document Architecture), and HL7 FHIR (Fast Healthcare Interoperability Resources) into practical solutions for clinical practice. The primary goal of the IHE SHARAZONE is to provide a reliable and consistent cross-vendor DICOM data sharing system. To evaluate its effectiveness, a 5-month pilot was conducted with ten imaging vendors. The pilot concluded with a participant survey, which yielded valuable insights into the initial experience with the IHE SHARAZONE. These findings can inform future improvements and developments to this important service. [ABSTRACT FROM AUTHOR]

Medical imaging technology is producing a growing number of medical images types as well as patient-related information. The benefits of using modern medical imaging systems in healthcare are undeniable. Picture archiving and communication system (PACS) have revolutionized medical imaging practice. PACS have widely impacted the accessibility of medical images, reduced imaging costs, eliminated the physical storage of films, improved time management of radiologists, and allowed automated decision-making and diagnosis. Many health organizations and manufacturers have invested on developing commercial PACS. However, commercial PACS are not affordable for all hospitals while open-source PACS are increasingly becoming a viable option. Our research project is looking for an open-source PACS for the Donka University hospital of Guinea. Open-source PACS are currently available and are offering varying functionalities, documentation, and technical support from their developer communities. Selecting an open-source PACS is not an easy task and not only depends on the hospital requirements but also requires assessing each open-source PACS to find the best match. In this paper, the most popular open-source PACS are evaluated using a simple comparison approach based on four criteria. The result of this assessment shows that Orthanc, DCM4CHE, DCMTK, and Dicoogle are the most mature open-source PACS according to our criteria and the needs of Donka. [ABSTRACT FROM AUTHOR]

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible. [ABSTRACT FROM AUTHOR]

The Protecting Access to Medicare Act (PAMA) mandates clinical decision support mechanism (CDSM) consultation for all advanced imaging. There are a growing number of studies examining the association of CDSM use with imaging appropriateness, but a paucity of multicenter data. This observational study evaluates the association between changes in advanced imaging appropriateness scores with increasing provider exposure to CDSM. Each provider's first 200 consecutive anonymized requisitions for advanced imaging (CT, MRI, ultrasound, nuclear medicine) using a single CDSM (CareSelect, Change Healthcare) between January 1, 2017 and December 31, 2019 were collected from 288 US institutions. Changes in imaging requisition proportions among four appropriateness categories ("usually appropriate" [green], "may be appropriate" [yellow], "usually not appropriate" [red], and unmapped [gray]) were evaluated in relation to the chronological order of the requisition for each provider and total provider exposure to CDSM using logistic regression fits and Wald tests. The number of providers and requisitions included was 244,158 and 7,345,437, respectively. For 10,123 providers with ≥ 200 requisitions (2,024,600 total requisitions), the fraction of green, yellow, and red requisitions among the last 10 requisitions changed by +3.0% (95% confidence interval +2.6% to +3.4%), -0.8% (95% CI -0.5% to -1.1%), and -3.0% (95% CI 3.3% to -2.7%) in comparison with the first 10, respectively. Providers with > 190 requisitions had 8.5% (95% CI 6.3% to 10.7%) more green requisitions, 2.3% (0.7% to 3.9%) fewer yellow requisitions, and 0.5% (95% CI -1.0% to 2.0%) fewer red (not statistically significant) requisitions relative to providers with ≤ 10 requisitions. Increasing provider exposure to CDSM is associated with improved appropriateness scores for advanced imaging requisitions.

Carimas is a multi-purpose medical imaging data processing tool, which can be used to visualize, analyze, and model different medical images in research. Originally, it was developed only for positron emission tomography data in 2009, but the use of this software has extended to many other tomography imaging modalities, such as computed tomography and magnetic resonance imaging. Carimas is especially well-suited for analysis of three- and four-dimensional image data and creating polar maps in modeling of cardiac perfusion. This article explores various parts of Carimas, including its key features, program structure, and application possibilities. [ABSTRACT FROM AUTHOR]

This study demonstrates the high performance of deep learning in identification of body regions covering the entire human body from magnetic resonance (MR) and computed tomography (CT) axial images across diverse acquisition protocols and modality manufacturers. Pixel-based analysis of anatomy contained in image sets can provide accurate anatomic labeling. For this purpose, a convolutional neural network (CNN)–based classifier was developed to identify body regions in CT and MRI studies. Seventeen CT (18 MRI) body regions covering the entire human body were defined for the classification task. Three retrospective datasets were built for the AI model training, validation, and testing, with a balanced distribution of studies per body region. The test datasets originated from a different healthcare network than the train and validation datasets. Sensitivity and specificity of the classifier was evaluated for patient age, patient sex, institution, scanner manufacturer, contrast, slice thickness, MRI sequence, and CT kernel. The data included a retrospective cohort of 2891 anonymized CT cases (training, 1804 studies; validation, 602 studies; test, 485 studies) and 3339 anonymized MRI cases (training, 1911 studies; validation, 636 studies; test, 792 studies). Twenty-seven institutions from primary care hospitals, community hospitals, and imaging centers contributed to the test datasets. The data included cases of all sexes in equal proportions and subjects aged from 18 years old to + 90 years old. Image-level weighted sensitivity of 92.5% (92.1–92.8) for CT and 92.3% (92.0–92.5) for MRI and weighted specificity of 99.4% (99.4–99.5) for CT and 99.2% (99.1–99.2) for MRI were achieved. Deep learning models can classify CT and MR images by body region including lower and upper extremities with high accuracy. [ABSTRACT FROM AUTHOR]

Current AI-driven research in radiology requires resources and expertise that are often inaccessible to small and resource-limited labs. The clinicians who are able to participate in AI research are frequently well-funded, well-staffed, and either have significant experience with AI and computing, or have access to colleagues or facilities that do. Current imaging data is clinician-oriented and is not easily amenable to machine learning initiatives, resulting in inefficient, time consuming, and costly efforts that rely upon a crew of data engineers and machine learning scientists, and all too often preclude radiologists from driving AI research and innovation. We present the system and methodology we have developed to address infrastructure and platform needs, while reducing the staffing and resource barriers to entry. We emphasize a data-first and modular approach that streamlines the AI development and deployment process while providing efficient and familiar interfaces for radiologists, such that they can be the drivers of new AI innovations. [ABSTRACT FROM AUTHOR]

This study aimed to evaluate radiology technicians' view on the use of medical imaging devices and related technology. A total of 142 radiology technicians from Turkey were included on a voluntary basis in this cross-sectional questionnaire-based study. The questionnaire form elicited items on sociodemographic and occupational characteristics and personal opinions regarding the use of medical imaging devices and related technology. Majority of technicians agreed or strongly agreed that they prefer the latest technology medical imaging devices (32.4 and 54.2%) and there is an increase in the number of medical imaging devices (36.6 and 35.9%) and medical imaging examinations (32.4 and 43.7%), while the growing societal demands in field of health have a role in the increase in the number of medical imaging devices (34.5 and 32.4%). However, a relatively lower percentage of technicians agreed or strongly agreed that the latest technology medical imaging devices should be purchased no matter how much it costs (31.7 and 33.8%) and the yearly increase in the number of imaging examinations indicates provision of an improved healthcare (21.1 and 23.2%). A higher agreement was reported by private hospital (3.9 ± 1.1, p = 0.035) and university hospital (4.1 ± 1.1, p = 0.009) employees vs. state hospital employees (3.4 ± 1.3) on the growing societal demands in field of health to have a role in the increase in the number of medical imaging devices. Apart from this, no significant difference was noted in opinions of technicians on the use of medical imaging devices and related technology with respect to hospital types. Our findings indicate that radiology technicians report a considerable imaging workload volume and a preference for working with higher number of medical imaging devices particularly those with the latest technology, whereas they also emphasize that the yearly increase in the number of imaging examinations does not indicate provision of an improved healthcare, and the cost should always be a criterion when purchasing the latest technology devices. [ABSTRACT FROM AUTHOR]

Augmented and virtual reality devices are being actively investigated and implemented for a wide range of medical uses. However, significant gaps in the evaluation of these medical devices and applications hinder their regulatory evaluation. Addressing these gaps is critical to demonstrating the devices' safety and effectiveness. We outline the key technical and clinical evaluation challenges discussed during the US Food and Drug Administration's public workshop, "Medical Extended Reality: Toward Best Evaluation Practices for Virtual and Augmented Reality in Medicine" and future directions for evaluation method development. Evaluation challenges were categorized into several key technical and clinical areas. Finally, we highlight current efforts in the standards communities and illustrate connections between the evaluation challenges and the intended uses of the medical extended reality (MXR) devices. Participants concluded that additional research is needed to assess the safety and effectiveness of MXR devices across the use cases. [ABSTRACT FROM AUTHOR]

At the first annual Conference on Machine Intelligence in Medical Imaging (C-MIMI), held in September 2016, a conference session on medical image data and datasets for machine learning identified multiple issues. The common theme from attendees was that everyone participating in medical image evaluation with machine learning is data starved. There is an urgent need to find better ways to collect, annotate, and reuse medical imaging data. Unique domain issues with medical image datasets require further study, development, and dissemination of best practices and standards, and a coordinated effort among medical imaging domain experts, medical imaging informaticists, government and industry data scientists, and interested commercial, academic, and government entities. High-level attributes of reusable medical image datasets suitable to train, test, validate, verify, and regulate ML products should be better described. NIH and other government agencies should promote and, where applicable, enforce, access to medical image datasets. We should improve communication among medical imaging domain experts, medical imaging informaticists, academic clinical and basic science researchers, government and industry data scientists, and interested commercial entities.

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for various imaging related tasks such as artificial image generation to support AI training. GANs are especially useful for medical imaging–related tasks where training datasets are usually limited in size and heavily imbalanced against the diseased class. We present a systematic review, following the PRISMA guidelines, of recent GAN architectures used for medical image analysis to help the readers in making an informed decision before employing GANs in developing medical image classification and segmentation models. We have extracted 54 papers that highlight the capabilities and application of GANs in medical imaging from January 2015 to August 2020 and inclusion criteria for meta-analysis. Our results show four main architectures of GAN that are used for segmentation or classification in medical imaging. We provide a comprehensive overview of recent trends in the application of GANs in clinical diagnosis through medical image segmentation and classification and ultimately share experiences for task-based GAN implementations. [ABSTRACT FROM AUTHOR]

Deep convolutional neural network (CNN)-assisted classification of images is one of the most discussed topics in recent years. Continuously innovation of neural network architectures is making it more correct and efficient every day. But training a neural network from scratch is very time-consuming and requires a lot of sophisticated computational equipment and power. So, using some pre-trained neural network as feature extractor for any image classification task or "transfer learning" is a very popular approach that saves time and computational power for practical use of CNNs. In this paper, an efficient way of building full model from any pre-trained model with high accuracy and low memory is proposed using knowledge distillation. Using the distilled knowledge of the last layer of pre-trained networks passes through fully connected layers with different hidden layers, followed by Softmax layer. The accuracies of student networks are mildly lesser than the whole models, but accuracy of student models clearly indicates the accuracy of the real network. In this way, the best number of hidden layers for dense layer for that pre-trained network with best accuracy and no-overfitting can be found with less time. Here, VGG16 and VGG19 (pre-trained upon "ImageNet" dataset) is tested upon chest X-rays (pneumonia and COVID-19). For finding the best total number of hidden layers, it saves nearly 44 min for VGG19 and 36 min and 37 s for VGG16 feature extractor. [ABSTRACT FROM AUTHOR]

Artificial or augmented intelligence, machine learning, and deep learning will be an increasingly important part of clinical practice for the next generation of radiologists. It is therefore critical that radiology residents develop a practical understanding of deep learning in medical imaging. Certain aspects of deep learning are not intuitive and may be better understood through hands-on experience; however, the technical requirements for setting up a programming and computing environment for deep learning can pose a high barrier to entry for individuals with limited experience in computer programming and limited access to GPU-accelerated computing. To address these concerns, we implemented an introductory module for deep learning in medical imaging within a self-contained, web-hosted development environment. Our initial experience established the feasibility of guiding radiology trainees through the module within a 45-min period typical of educational conferences. [ABSTRACT FROM AUTHOR]

In medical devices, nonconformance with Digital Imaging and Communications in Medicine (DICOM) standard is a serious risk. DICOM nonconformance radiology devices could cause undetected image loss, increasing examination time, and costs in health centers and could even result in the wrong patient treatment. However, there is a rich literature on medical standards that identify the best practices for producing safe and effective medical software. However, these standards do not expressly provide tools to deal with all the relevant DICOM compatibility issues in a specific case. This study aims to introduce a systematic software development workflow that complies with medical standards and ensures DICOM conformance of a new or upgraded radiology software project. In this approach, DICOM conformance gets the highest priority, and the whole software project is organized around it. Software requirement analysis, risk evaluation, and test management tasks are arranged systematically to make the final device DICOM conformant. This conceptual framework was developed during the R&D work towards a novel radiography device, and it could be employed as a roadmap in other medical imaging software projects. The proposed methodology controls the DICOM compatibility risk of the final software, and its systematic evaluation complied with medical standards. [ABSTRACT FROM AUTHOR]

Cross-platform development of medical applications in extended-reality (XR) head-mounted displays (HMDs) often relies on game engines with rendering capabilities currently not standardized in the context of medical visualizations. Many aspects of the visualization pipeline including the characterization of color have yet to be consistently defined across rendering models and platforms. We examined the transfer of color properties from digital objects, through the rendering and image processing steps, to the RGB values sent to the display device. Five rendering pipeline configurations within the Unity engine were evaluated using 24 digital color patches. In the second experiment, the same configurations were evaluated with a tissue slide sample image. Measurements of the change in color associated with each configuration were characterized using the CIE 1976 color difference ( Δ E ). We found that the distribution of Δ E for the first experiment ranges from zero, as in the case using an Unlit Shader, to 25.97, as in the case using default configurations. The default Unity configuration consistently returned the highest Δ E across all 24 colors and also the largest range of color differences. In the second experiment, Δ E E ranged from 7.49 to 34.18. The Unlit configuration resulted in the highest Δ E in three of four selected pixels in the tissue sample image. Changes in color image properties associated with texture import settings were then evaluated in a third experiment using the TG18-QC test pattern. Differences in pixel values were found in all nine of the investigated texture import settings. The findings provide an initial characterization of color transfer and a basis for future work on standardization, consistency, and optimization of color in medical XR applications. [ABSTRACT FROM AUTHOR]

Medical image data plays a critical role in health care today. Whatever the context of image processing (research and educational activities, diagnostic or forensic purposes, etc.), they are supposed to be treated as highly sensitive. Unfortunately, currently available image-processing tools also enable very sophisticated malicious modification of their content. This paper is focused on the assessment of the effectiveness of selected so-called zero watermarking methods (ones that do not cause any modification of an image sample), in the protection of the integrity, and proving authorship, of these medical image studies. We have studied many zero watermarking methods and selected one representative from each type of known algorithms for comparison. We have conducted a series of simulations over a huge research database of anonymized medical image studies (patient examinations). [ABSTRACT FROM AUTHOR]

This article provides an overview on the literature published on the topic of cybersecurity for PACS (Picture Archiving and Communications Systems) and medical imaging. From a practical perspective, PACS specific security measures must be implemented together with the measures applicable to the IT infrastructure as a whole, in order to prevent incidents such as PACS systems exposed to access from the Internet. Therefore, the article first offers an overview of the physical, technical and organizational mitigation measures that are proposed in literature on cybersecurity in healthcare information technology in general, followed by an overview on publications discussing specific cybersecurity topics that apply to PACS and medical imaging and present the "building blocks" for a secure PACS environment available in the literature. These include image de-identification, transport security, the selective encryption of the DICOM (Digital Imaging and Communications in Medicine) header, encrypted DICOM files, digital signatures and watermarking techniques. The article concludes with a discussion of gaps in the body of published literature and a summary. [ABSTRACT FROM AUTHOR]

Nowadays usage paradigms of medical imaging resources are requesting vendor-neutral archives, accessible through standard interfaces, with multi-repository support. Regional repositories shared by distinct institutions, tele-radiology as a service at cloud, teaching, and research archives are illustrative examples of this new reality. However, traditional production environments have a server archive instance per functional domain where every registered client application has access to all studies. This paper proposes an innovator ownership concept and access control mechanisms that provide a multi-repository environment and integrates well with standard protocols. A secure accounting mechanism for medical imaging repositories was designed and instantiated as an extension of a well-known open-source archive. A new web service layer was implemented to provide a vendor-neutral solution compliant with modern DICOM Web protocols for storage, search, and retrieval of medical imaging data. The concept validation was done through the integration of proposed architecture in an open-source solution. A quantitative assessment was performed for evaluating the impact of the mechanism in the usual DICOM Web operations. This article proposes a secure accounting architecture able to easily convert a standard medical imaging archive server in a multi-repository solution. The proposal validation was done through a set of tests that demonstrated its robustness and usage feasibility in a production environment. The proposed system offers new services, fundamental in a new era of cloud-based operations, with acceptable temporal costs. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is an irreversible devastative neurodegenerative disorder associated with progressive impairment of memory and cognitive functions. Its early diagnosis is crucial for the development of possible future treatment option(s). Structural magnetic resonance images (sMRI) play an important role to help in understanding the anatomical changes related to AD especially in its early stages. Conventional methods require the expertise of domain experts and extract hand-picked features such as gray matter substructures and train a classifier to distinguish AD subjects from healthy subjects. Different from these methods, this paper proposes to construct multiple deep 2D convolutional neural networks (2D-CNNs) to learn the various features from local brain images which are combined to make the final classification for AD diagnosis. The whole brain image was passed through two transfer learning architectures; Inception version 3 and Xception, as well as a custom Convolutional Neural Network (CNN) built with the help of separable convolutional layers which can automatically learn the generic features from imaging data for classification. Our study is conducted using cross-sectional T1-weighted structural MRI brain images from Open Access Series of Imaging Studies (OASIS) database to maintain the size and contrast over different MRI scans. Experimental results show that the transfer learning approaches exceed the performance of non-transfer learning-based approaches demonstrating the effectiveness of these approaches for the binary AD classification task. [ABSTRACT FROM AUTHOR]

A device-independent software package, named iBEX, is developed to accelerate the research and development efforts for X-ray imaging setups such as chest radiography, linear and multidirectional tomography, and dental and skeletal radiography. Its extension mechanism makes the software adaptable for a wide range of digital X-ray imaging hardware combinations and provides capabilities for researchers to develop image processing plug-ins. Independent of the X-ray sensor technology, iBEX could integrate with heterogeneous communication channels of digital detectors. iBEX is a freeware option for preclinical and early clinical testing of radiography devices. It provides tools to calibrate the device, integrate to health information infrastructure, acquire image, store studies on local storage, and send them to Picture Archiving and Communication System (PACS). iBEX is a unique open-source project bringing X-ray imaging devices' software into the scope of the open-source community to reduce the X-ray scanners' research effort, potentially increase the image quality, and cut down the production and testing costs of radiography devices. [ABSTRACT FROM AUTHOR]

Collecting and curating large medical-image datasets for deep neural network (DNN) algorithm development is typically difficult and resource-intensive. While transfer learning (TL) decreases reliance on large data collections, current TL implementations are tailored to two-dimensional (2D) datasets, limiting applicability to volumetric imaging (e.g., computed tomography). Targeting performance enhancement of a DNN algorithm based on a small image dataset, we assessed incremental impact of 3D-to-2D projection methods, one supporting novel data augmentation (DA); photometric grayscale-to-color conversion (GCC); and/or TL on training of an algorithm from a small coronary computed tomography angiography (CCTA) dataset (200 examinations, 50% with atherosclerosis and 50% atherosclerosis-free) producing 245 diseased and 1127 normal coronary arteries/branches. Volumetric CCTA data was converted to a 2D format creating both an Aggregate Projection View (APV) and a Mosaic Projection View (MPV), supporting DA per vessel; both grayscale and color-mapped versions of each view were also obtained. Training was performed both without and with TL, and algorithm performance of all permutations was compared using area under the receiver operating characteristics curve. Without TL, APV performance was 0.74 and 0.87 on grayscale and color images, respectively, compared to 0.90 and 0.87 for MPV. With TL, APV performance was 0.78 and 0.88 on grayscale and color images, respectively, compared with 0.93 and 0.91 for MPV. In conclusion, TL enhances performance of a DNN algorithm from a small volumetric dataset after proposed 3D-to-2D reformatting, but additive gain is achieved with application of either GCC to APV or the proposed novel MPV technique for DA. [ABSTRACT FROM AUTHOR]

Surgical telementoring systems have gained lots of interest, especially in remote locations. However, bandwidth constraint has been the primary bottleneck for efficient telementoring systems. This study aims to establish an efficient surgical telementoring system, where the qualified surgeon (mentor) provides real-time guidance and technical assistance for surgical procedures to the on-spot physician (surgeon). High Efficiency Video Coding (HEVC/H.265)–based video compression has shown promising results for telementoring applications. However, there is a trade-off between the bandwidth resources required for video transmission and quality of video received by the remote surgeon. In order to efficiently compress and transmit real-time surgical videos, a hybrid lossless-lossy approach is proposed where surgical incision region is coded in high quality whereas the background region is coded in low quality based on distance from the surgical incision region. For surgical incision region extraction, state-of-the-art deep learning (DL) architectures for semantic segmentation can be used. However, the computational complexity of these architectures is high resulting in large training and inference times. For telementoring systems, encoding time is crucial; therefore, very deep architectures are not suitable for surgical incision extraction. In this study, we propose a shallow convolutional neural network (S-CNN)–based segmentation approach that consists of encoder network only for surgical region extraction. The segmentation performance of S-CNN is compared with one of the state-of-the-art image segmentation networks (SegNet), and results demonstrate the effectiveness of the proposed network. The proposed telementoring system is efficient and explicitly considers the physiological nature of the human visual system to encode the video by providing good overall visual impact in the location of surgery. The results of the proposed S-CNN-based segmentation demonstrated a pixel accuracy of 97% and a mean intersection over union accuracy of 79%. Similarly, HEVC experimental results showed that the proposed surgical region–based encoding scheme achieved an average bitrate reduction of 88.8% at high-quality settings in comparison with default full-frame HEVC encoding. The average gain in encoding performance (signal-to-noise) of the proposed algorithm is 11.5 dB in the surgical region. The bitrate saving and visual quality of the proposed optimal bit allocation scheme are compared with the mean shift segmentation–based coding scheme for fair comparison. The results show that the proposed scheme maintains high visual quality in surgical incision region along with achieving good bitrate saving. Based on comparison and results, the proposed encoding algorithm can be considered as an efficient and effective solution for surgical telementoring systems for low-bandwidth networks. [ABSTRACT FROM AUTHOR]

The Deep Convolutional Neural Network (DCNN) is one of the most powerful and successful deep learning approaches. DCNNs have already provided superior performance in different modalities of medical imaging including breast cancer classification, segmentation, and detection. Breast cancer is one of the most common and dangerous cancers impacting women worldwide. In this paper, we have proposed a method for breast cancer classification with the Inception Recurrent Residual Convolutional Neural Network (IRRCNN) model. The IRRCNN is a powerful DCNN model that combines the strength of the Inception Network (Inception-v4), the Residual Network (ResNet), and the Recurrent Convolutional Neural Network (RCNN). The IRRCNN shows superior performance against equivalent Inception Networks, Residual Networks, and RCNNs for object recognition tasks. In this paper, the IRRCNN approach is applied for breast cancer classification on two publicly available datasets including BreakHis and Breast Cancer (BC) classification challenge 2015. The experimental results are compared against the existing machine learning and deep learning–based approaches with respect to image-based, patch-based, image-level, and patient-level classification. The IRRCNN model provides superior classification performance in terms of sensitivity, area under the curve (AUC), the ROC curve, and global accuracy compared to existing approaches for both datasets. [ABSTRACT FROM AUTHOR]

There is recent popularity in applying machine learning to medical imaging, notably deep learning, which has achieved state-of-the-art performance in image analysis and processing. The rapid adoption of deep learning may be attributed to the availability of machine learning frameworks and libraries to simplify their use. In this tutorial, we provide a high-level overview of how to build a deep neural network for medical image classification, and provide code that can help those new to the field begin their informatics projects. [ABSTRACT FROM AUTHOR]

Nerve morphometry is known to produce relevant information for the evaluation of several phenomena, such as nerve repair, regeneration, implant, transplant, aging, and different human neuropathies. Manual morphometry is laborious, tedious, time consuming, and subject to many sources of error. Therefore, in this paper, we propose a new method for the automated morphometry of myelinated fibers in cross-section light microscopy images. Images from the recurrent laryngeal nerve of adult rats and the vestibulocochlear nerve of adult guinea pigs were used herein. The proposed pipeline for fiber segmentation is based on the techniques of competitive clustering and concavity analysis. The evaluation of the proposed method for segmentation of images was done by comparing the automatic segmentation with the manual segmentation. To further evaluate the proposed method considering morphometric features extracted from the segmented images, the distributions of these features were tested for statistical significant difference. The method achieved a high overall sensitivity and very low false-positive rates per image. We detect no statistical difference between the distribution of the features extracted from the manual and the pipeline segmentations. The method presented a good overall performance, showing widespread potential in experimental and clinical settings allowing large-scale image analysis and, thus, leading to more reliable results. [ABSTRACT FROM AUTHOR]

The production of medical imaging is a continuing trend in healthcare institutions. Quality assurance for planned radiation exposure situations (e.g. X-ray, computer tomography) requires examination-specific set-ups according to several parameters, such as patient's age and weight, body region and clinical indication. These data are normally stored in several formats and with different nomenclatures, which hinder the continuous and automatic monitoring of these indicators and the comparison between several institutions and equipment. This article proposes a framework that aggregates, normalizes and provides different views over collected indicators. The developed tool can be used to improve the quality of radiologic procedures and also for benchmarking and auditing purposes. Finally, a case study and several experimental results related to radiation exposure and productivity are presented and discussed. [ABSTRACT FROM AUTHOR]

Our objective is to design, implement, and phantom-test a device to automatically obtain point-of-care patient photographs along with portable radiographs. Such photographs could help with detection of wrong-patient errors. Our device consists of a camera controller (CC) and a camera that can be mounted on a portable conventional radiography (CR) machine. Radiation from the CR machine triggers an identification module (IM) embedded in the CR cassette. The IM then sends the cassette identifier- Plate_ID-to the CC along with a trigger to activate the camera. This trigger ensures simultaneous acquisition of radiograph and photograph, and the Plate_ID along with a time stamp ensures binding of the two images. We conducted phantom tests to determine if clinical portable radiography exposure settings (90 to 120 kVp and exposure time ranging from 0.63 to 8.0 ms) are sufficient to trigger the IM. Phantom experiments demonstrate acceptable sensor performance for clinical portable radiography exposures. Simultaneous acquisition of photographs is achieved by integrating a low-cost identification module containing a scintillator-detector into the radiographic cassette. Incident X-rays activate the scintillator-detector triggering photograph acquisition by a camera controller. [ABSTRACT FROM AUTHOR]

This article summarizes the consensus reached at the Summit on Color in Medical Imaging held at the Food and Drug Administration (FDA) on May 8-9, 2013, co-sponsored by the FDA and ICC (International Color Consortium). The purpose of the meeting was to gather information on how color is currently handled by medical imaging systems to identify areas where there is a need for improvement, to define objective requirements, and to facilitate consensus development of best practices. Participants were asked to identify areas of concern and unmet needs. This summary documents the topics that were discussed at the meeting and recommendations that were made by the participants. Key areas identified where improvements in color would provide immediate tangible benefits were those of digital microscopy, telemedicine, medical photography (particularly ophthalmic and dental photography), and display calibration. Work in these and other related areas has been started within several professional groups, including the creation of the ICC Medical Imaging Working Group. [ABSTRACT FROM AUTHOR]

Web educational resources integrating interactive simulation tools provide students with an in-depth understanding of the medical imaging process. The aim of this work was the development of a purely Web-based, open access, interactive application, as an ancillary learning tool in graduate and postgraduate medical imaging education, including a systematic evaluation of learning effectiveness. The pedagogic content of the educational Web portal was designed to cover the basic concepts of medical imaging reconstruction and processing, through the use of active learning and motivation, including learning simulations that closely resemble actual tomographic imaging systems. The user can implement image reconstruction and processing algorithms under a single user interface and manipulate various factors to understand the impact on image appearance. A questionnaire for pre- and post-training self-assessment was developed and integrated in the online application. The developed Web-based educational application introduces the trainee in the basic concepts of imaging through textual and graphical information and proceeds with a learning-by-doing approach. Trainees are encouraged to participate in a pre- and post-training questionnaire to assess their knowledge gain. An initial feedback from a group of graduate medical students showed that the developed course was considered as effective and well structured. An e-learning application on medical imaging integrating interactive simulation tools was developed and assessed in our institution. [ABSTRACT FROM AUTHOR]