Search

Ensuring the transparency of machine learning models is vital for their ethical application in various industries. There has been a concurrent trend of distributed machine learning designed to limit access to training data for privacy concerns. Such models, trained over horizontally or vertically partitioned data, present a challenge for explainable AI because the explaining party may have a biased view of background data or a partial view of the feature space. As a result, explanations obtained from different participants of distributed machine learning might not be consistent with one another, undermining trust in the product. This paper presents an Explainable Data Collaboration Framework based on a model-agnostic additive feature attribution algorithm (KernelSHAP) and Data Collaboration method of privacy-preserving distributed machine learning. In particular, we present three algorithms for different scenarios of explainability in Data Collaboration and verify their consistency with experiments on open-access datasets. Our results demonstrated a significant (by at least a factor of 1.75) decrease in feature attribution discrepancies among the users of distributed machine learning. The proposed method improves consistency among explanations obtained from different participants, which can enhance trust in the product and enable ethical application in various industries. [ABSTRACT FROM AUTHOR]

Machine learning and deep learning are two subsets of artificial intelligence that involve teaching computers to learn and make decisions from any sort of data. Most recent developments in artificial intelligence are coming from deep learning, which has proven revolutionary in almost all fields, from computer vision to health sciences. The effects of deep learning in medicine have changed the conventional ways of clinical application significantly. Although some sub-fields of medicine, such as pediatrics, have been relatively slow in receiving the critical benefits of deep learning, related research in pediatrics has started to accumulate to a significant level, too. Hence, in this paper, we review recently developed machine learning and deep learning-based solutions for neonatology applications. We systematically evaluate the roles of both classical machine learning and deep learning in neonatology applications, define the methodologies, including algorithmic developments, and describe the remaining challenges in the assessment of neonatal diseases by using PRISMA 2020 guidelines. To date, the primary areas of focus in neonatology regarding AI applications have included survival analysis, neuroimaging, analysis of vital parameters and biosignals, and retinopathy of prematurity diagnosis. We have categorically summarized 106 research articles from 1996 to 2022 and discussed their pros and cons, respectively. In this systematic review, we aimed to further enhance the comprehensiveness of the study. We also discuss possible directions for new AI models and the future of neonatology with the rising power of AI, suggesting roadmaps for the integration of AI into neonatal intensive care units. [ABSTRACT FROM AUTHOR]

Communication between sensors spread everywhere in healthcare systems may cause some missing in the transferred features. Repairing the data problems of sensing devices by artificial intelligence technologies have facilitated the Medical Internet of Things (MIoT) and its emerging applications in Healthcare. MIoT has great potential to affect the patient's life. Data collected from smart wearable devices size dramatically increases with data collected from millions of patients who are suffering from diseases such as diabetes. However, sensors or human errors lead to missing some values of the data. The major challenge of this problem is how to predict this value to maintain the data analysis model performance within a good range. In this paper, a complete healthcare system for diabetics has been used, as well as two new algorithms are developed to handle the crucial problem of missed data from MIoT wearable sensors. The proposed work is based on the integration of Random Forest, mean, class' mean, interquartile range (IQR), and Deep Learning to produce a clean and complete dataset. Which can enhance any machine learning model performance. Moreover, the outliers repair technique is proposed based on dataset class detection, then repair it by Deep Learning (DL). The final model accuracy with the two steps of imputation and outliers repair is 97.41% and 99.71% Area Under Curve (AUC). The used healthcare system is a web-based diabetes classification application using flask to be used in hospitals and healthcare centers for the patient diagnosed with an effective fashion. [ABSTRACT FROM AUTHOR]

Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images. [ABSTRACT FROM AUTHOR]

AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. We aimed to test the ability of AI-enabled ECGs to predict sex in the pediatric population and study the influence of pubertal development. AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 90,133 unique pediatric patients (aged ≤18 years) recorded between 1987–2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0–7 years), peripubertal (8–14 years), and postpubertal (15–18 years) patients. The cohort was 46.7% male, with 21,678 prepubertal, 26,740 peripubertal, and 41,715 postpubertal children. The de novo pediatric model demonstrated 81% accuracy and an area under the curve (AUC) of 0.91. Model sensitivity was 0.79, specificity was 0.83, positive predicted value was 0.84, and the negative predicted value was 0.78, for the entire test cohort. The model's discriminatory ability was highest in postpubertal (AUC = 0.98), lower in the peripubertal age group (AUC = 0.91), and poor in the prepubertal age group (AUC = 0.67). There was no significant performance difference observed between the transfer learning and de novo models. AI-enabled interpretation of ECG can estimate sex in peripubertal and postpubertal children with high accuracy. [ABSTRACT FROM AUTHOR]

Healthcare datasets are becoming larger and more complex, necessitating the development of accurate and generalizable AI models for medical applications. Unstructured datasets, including medical imaging, electrocardiograms, and natural language data, are gaining attention with advancements in deep convolutional neural networks and large language models. However, estimating the generalizability of these models to new healthcare settings without extensive validation on external data remains challenging. In experiments across 13 datasets including X-rays, CTs, ECGs, clinical discharge summaries, and lung auscultation data, our results demonstrate that model performance is frequently overestimated by up to 20% on average due to shortcut learning of hidden data acquisition biases (DAB). Shortcut learning refers to a phenomenon in which an AI model learns to solve a task based on spurious correlations present in the data as opposed to features directly related to the task itself. We propose an open source, bias-corrected external accuracy estimate, PEst, that better estimates external accuracy to within 4% on average by measuring and calibrating for DAB-induced shortcut learning. [ABSTRACT FROM AUTHOR]

Distribution shifts remain a problem for the safe application of regulated medical AI systems, and may impact their real-world performance if undetected. Postmarket shifts can occur for example if algorithms developed on data from various acquisition settings and a heterogeneous population are predominantly applied in hospitals with lower quality data acquisition or other centre-specific acquisition factors, or where some ethnicities are over-represented. Therefore, distribution shift detection could be important for monitoring AI-based medical products during postmarket surveillance. We implemented and evaluated three deep-learning based shift detection techniques (classifier-based, deep kernel, and multiple univariate kolmogorov-smirnov tests) on simulated shifts in a dataset of 130'486 retinal images. We trained a deep learning classifier for diabetic retinopathy grading. We then simulated population shifts by changing the prevalence of patients' sex, ethnicity, and co-morbidities, and example acquisition shifts by changes in image quality. We observed classification subgroup performance disparities w.r.t. image quality, patient sex, ethnicity and co-morbidity presence. The sensitivity at detecting referable diabetic retinopathy ranged from 0.50 to 0.79 for different ethnicities. This motivates the need for detecting shifts after deployment. Classifier-based tests performed best overall, with perfect detection rates for quality and co-morbidity subgroup shifts at a sample size of 1000. It was the only method to detect shifts in patient sex, but required large sample sizes ( > 3 0 ′ 000 ). All methods identified easier-to-detect out-of-distribution shifts with small (≤300) sample sizes. We conclude that effective tools exist for detecting clinically relevant distribution shifts. In particular classifier-based tests can be easily implemented components in the post-market surveillance strategy of medical device manufacturers. [ABSTRACT FROM AUTHOR]

Today, the internet of things (IoT) is becoming more common and finds applications in several domains, especially in the healthcare sector. Due to the rising demands of IoT, a massive quantity of sensing data gets generated from diverse sensing devices. Artificial intelligence (AI) techniques are vital for providing a scalable and precise analysis of data in real time. But the design and development of a useful big data analysis technique face a few challenges, like centralized architecture, security, and privacy, resource constraints, and the lack of adequate training data. On the other hand, the rising blockchain technology offers a decentralized architecture. It enables secure sharing of data and resources to the different nodes of the IoT network and is promoted for removing centralized control and resolving the problems of AI. This study develops an optimal deep-learning-based secure blockchain (ODLSB) enabled intelligent IoT and healthcare diagnosis model. The proposed model involves three major processes: secure transaction, hash value encryption, and medical diagnosis. The ODLSB technique comprises the orthogonal particle swarm optimization (OPSO) algorithm for the secret sharing of medical images. In addition, the hash value encryption process takes place using neighborhood indexing sequence (NIS) algorithm. At last, the optimal deep neural network (ODNN) is applied as a classification model to diagnose the diseases. The utilization of OPSO algorithm for secret sharing and optimal parameter tuning process shows the novelty of the work. We carried out detailed experiments to validate the outcome of the proposed method, and several aspects of the results are considered. At the time of the diagnosis process, the OPSO-DNN model has yielded superior results, with the highest sensitivity (92.75%), specificity (91.42%), and accuracy (93.68%). [ABSTRACT FROM AUTHOR]

The monitoring of physiological parameters is a crucial topic in promoting human health and an indispensable approach for assessing physiological status and diagnosing diseases. Particularly, it holds significant value for patients who require long-term monitoring or with underlying cardiovascular disease. To this end, Visual Contactless Physiological Monitoring (VCPM) is capable of using videos recorded by a consumer camera to monitor blood volume pulse (BVP) signal, heart rate (HR), respiratory rate (RR), oxygen saturation (SpO2) and blood pressure (BP). Recently, deep learning-based pipelines have attracted numerous scholars and achieved unprecedented development. Although VCPM is still an emerging digital medical technology and presents many challenges and opportunities, it has the potential to revolutionize clinical medicine, digital health, telemedicine as well as other areas. The VCPM technology presents a viable solution that can be integrated into these systems for measuring vital parameters during video consultation, owing to its merits of contactless measurement, cost-effectiveness, user-friendly passive monitoring and the sole requirement of an off-the-shelf camera. In fact, the studies of VCPM technologies have been rocketing recently, particularly AI-based approaches, but few are employed in clinical settings. Here we provide a comprehensive overview of the applications, challenges, and prospects of VCPM from the perspective of clinical settings and AI technologies for the first time. The thorough exploration and analysis of clinical scenarios will provide profound guidance for the research and development of VCPM technologies in clinical settings. [ABSTRACT FROM AUTHOR]

Objective: Clinical and surgical decisions for glioblastoma patients depend on a tumor imaging-based evaluation. Artificial Intelligence (AI) can be applied to magnetic resonance imaging (MRI) assessment to support clinical practice, surgery planning and prognostic predictions. In a real-world context, the current obstacles for AI are low-quality imaging and postoperative reliability. The aim of this study is to train an automatic algorithm for glioblastoma segmentation on a clinical MRI dataset and to obtain reliable results both pre- and post-operatively. Methods: The dataset used for this study comprises 237 (71 preoperative and 166 postoperative) MRIs from 71 patients affected by a histologically confirmed Grade IV Glioma. The implemented U-Net architecture was trained by transfer learning to perform the segmentation task on postoperative MRIs. The training was carried out first on BraTS2021 dataset for preoperative segmentation. Performance is evaluated using DICE score (DS) and Hausdorff 95% (H95). Results: In preoperative scenario, overall DS is 91.09 (± 0.60) and H95 is 8.35 (± 1.12), considering tumor core, enhancing tumor and whole tumor (ET and edema). In postoperative context, overall DS is 72.31 (± 2.88) and H95 is 23.43 (± 7.24), considering resection cavity (RC), gross tumor volume (GTV) and whole tumor (WT). Remarkably, the RC segmentation obtained a mean DS of 63.52 (± 8.90) in postoperative MRIs. Conclusions: The performances achieved by the algorithm are consistent with previous literature for both pre-operative and post-operative glioblastoma's MRI evaluation. Through the proposed algorithm, it is possible to reduce the impact of low-quality images and missing sequences. [ABSTRACT FROM AUTHOR]

The bold vision of AI-driven pervasive physiological monitoring, through the proliferation of off-the-shelf wearables that began a decade ago, has created immense opportunities to extract actionable information for precision medicine. These AI algorithms model input-output relationships of a system that, in many cases, exhibits complex nature and personalization requirements. A particular example is cuffless blood pressure estimation using wearable bioimpedance. However, these algorithms need training over significant amount of ground truth data. In the context of biomedical applications, collecting ground truth data, particularly at the personalized level is challenging, burdensome, and in some cases infeasible. Our objective is to establish physics-informed neural network (PINN) models for physiological time series data that would use minimal ground truth information to extract complex cardiovascular information. We achieve this by building Taylor's approximation for gradually changing known cardiovascular relationships between input and output (e.g., sensor measurements to blood pressure) and incorporating this approximation into our proposed neural network training. The effectiveness of the framework is demonstrated through a case study: continuous cuffless BP estimation from time series bioimpedance data. We show that by using PINNs over the state-of-the-art time series models tested on the same datasets, we retain high correlations (systolic: 0.90, diastolic: 0.89) and low error (systolic: 1.3 ± 7.6 mmHg, diastolic: 0.6 ± 6.4 mmHg) while reducing the amount of ground truth training data on average by a factor of 15. This could be helpful in developing future AI algorithms to help interpret pervasive physiologic data using minimal amount of training data. [ABSTRACT FROM AUTHOR]

Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports. [ABSTRACT FROM AUTHOR]

Under the black-box nature in the deep learning model, it is uncertain how the change in contrast level and format affects the performance. We aimed to investigate the effect of contrast level and image format on the effectiveness of deep learning for diagnosing pneumothorax on chest radiographs. We collected 3316 images (1016 pneumothorax and 2300 normal images), and all images were set to the standard contrast level (100%) and stored in the Digital Imaging and Communication in Medicine and Joint Photographic Experts Group (JPEG) formats. Data were randomly separated into 80% of training and 20% of test sets, and the contrast of images in the test set was changed to 5 levels (50%, 75%, 100%, 125%, and 150%). We trained the model to detect pneumothorax using ResNet-50 with 100% level images and tested with 5-level images in the two formats. While comparing the overall performance between each contrast level in the two formats, the area under the receiver-operating characteristic curve (AUC) was significantly different (all p < 0.001) except between 125 and 150% in JPEG format (p = 0.382). When comparing the two formats at same contrast levels, AUC was significantly different (all p < 0.001) except 50% and 100% (p = 0.079 and p = 0.082, respectively). The contrast level and format of medical images could influence the performance of the deep learning model. It is required to train with various contrast levels and formats of image, and further image processing for improvement and maintenance of the performance. [ABSTRACT FROM AUTHOR]

Artificial intelligence has been widely studied on solving intelligent surveillance analysis and security problems in recent years. Although many multimedia security approaches have been proposed by using deep learning network model, there are still some challenges on their performances which deserve in-depth research. On the one hand, high computational complexity of current deep learning methods makes it hard to be applied to real-time scenario. On the other hand, it is difficult to obtain the specific features of a video by fine-tuning the network online with the object state of the first frame, which fails to capture rich appearance variations of the object. To solve above two issues, in this paper, an effective object tracking method with learning attention is proposed to achieve the object localization and reduce the training time in adversarial learning framework. First, a prediction network is designed to track the object in video sequences. The object positions of the first ten frames are employed to fine-tune prediction network, which can fully mine a specific features of an object. Second, the prediction network is integrated into the generative adversarial network framework, which randomly generates masks to capture object appearance variations via adaptively dropout input features. Third, we present a spatial attention mechanism to improve the tracking performance. The proposed network can identify the mask that maintains the most robust features of the objects over a long temporal span. Extensive experiments on two large-scale benchmarks demonstrate that the proposed algorithm performs favorably against state-of-the-art methods. [ABSTRACT FROM AUTHOR]

To automatically detect dynamic EEG signals to reduce the time cost of epilepsy diagnosis. In the signal recognition of electroencephalogram (EEG) of epilepsy, traditional machine learning and statistical methods require manual feature labeling engineering in order to show excellent results on a single data set. And the artificially selected features may carry a bias, and cannot guarantee the validity and expansibility in real-world data. In practical applications, deep learning methods can release people from feature engineering to a certain extent. As long as the focus is on the expansion of data quality and quantity, the algorithm model can learn automatically to get better improvements. In addition, the deep learning method can also extract many features that are difficult for humans to perceive, thereby making the algorithm more robust. Based on the design idea of ResNeXt deep neural network, this paper designs a Time-ResNeXt network structure suitable for time series EEG epilepsy detection to identify EEG signals. The accuracy rate of Time-ResNeXt in the detection of EEG epilepsy can reach 91.50%. The Time-ResNeXt network structure produces extremely advanced performance on the benchmark dataset (Berne-Barcelona dataset) and has great potential for improving clinical practice. [ABSTRACT FROM AUTHOR]

There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model—GatorTron—using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on five clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve five clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og. [ABSTRACT FROM AUTHOR]

The development of medical image analysis algorithm is a complex process including the multiple sub-steps of model training, data visualization, human–computer interaction and graphical user interface (GUI) construction. To accelerate the development process, algorithm developers need a software tool to assist with all the sub-steps so that they can focus on the core function implementation. Especially, for the development of deep learning (DL) algorithms, a software tool supporting training data annotation and GUI construction is highly desired. In this work, we constructed AnatomySketch, an extensible open-source software platform with a friendly GUI and a flexible plugin interface for integrating user-developed algorithm modules. Through the plugin interface, algorithm developers can quickly create a GUI-based software prototype for clinical validation. AnatomySketch supports image annotation using the stylus and multi-touch screen. It also provides efficient tools to facilitate the collaboration between human experts and artificial intelligent (AI) algorithms. We demonstrate four exemplar applications including customized MRI image diagnosis, interactive lung lobe segmentation, human-AI collaborated spine disc segmentation and Annotation-by-iterative-Deep-Learning (AID) for DL model training. Using AnatomySketch, the gap between laboratory prototyping and clinical testing is bridged and the development of MIA algorithms is accelerated. The software is opened at https://github.com/DlutMedimgGroup/AnatomySketch-Software. [ABSTRACT FROM AUTHOR]

Preparing radiology examinations for interpretation requires prefetching relevant prior examinations and implementing hanging protocols to optimally display the examination along with comparisons. Body part is a critical piece of information to facilitate both prefetching and hanging protocols, but body part information encoded using the Digital Imaging and Communications in Medicine (DICOM) standard is widely variable, error-prone, not granular enough, or missing altogether. This results in inappropriate examinations being prefetched or relevant examinations left behind; hanging protocol optimization suffers as well. Modern artificial intelligence (AI) techniques, particularly when harnessing federated deep learning techniques, allow for highly accurate automatic detection of body part based on the image data within a radiological examination; this allows for much more reliable implementation of this categorization and workflow. Additionally, new avenues to further optimize examination viewing such as dynamic hanging protocol and image display can be implemented using these techniques. [ABSTRACT FROM AUTHOR]

Purpose: A deep learning artificial intelligence (AI) algorithm has been demonstrated to outperform embryologists in identifying euploid embryos destined to implant with an accuracy of 75.3% (1). Our aim was to evaluate the performance of highly trained embryologists in selecting top quality day 5 euploid blastocysts with and without the aid of a deep learning algorithm. Materials and methods: A non-overlapping series of 200 sets of day 5 euploid embryo images with known implantation outcomes was distributed to 17 highly trained embryologists. One embryo in each set was known to have implanted and one failed implantation. They were asked to select which embryo to transfer from each set. The same 200 sets of embryos, with indication of which embryo in each set had been identified by the algorithm as more likely to implant was then distributed. Chi-squared, t-test, and receiver operating curves were performed to compare the embryologist performeance with and without AI. Results: Fourteen embryologists completed both assessments. Embryologists provided with AI results selected successfully implanted embryos in 73.6% of cases compared to 65.5% for those selected using visual assessments alone (p < 0.001). All embryologists improved in their ability to select embryos with the aid of the AI algorithm with a mean percent improvement of 11.1% (range 1.4% to 15.5%). There were no differences in degree of improvement by embryologist level of experience (junior, intermediate, senior). Conclusions: The incorporation of an AI framework for blastocyst selection enhanced the performance of trained embryologists in identifying PGT-A euploid embryos destined to implant. [ABSTRACT FROM AUTHOR]

The objective of the study was to determine if the pathology depicted on a mammogram is either benign or malignant (ductal or non-ductal carcinoma) using deep learning and artificial intelligence techniques. A total of 559 patients underwent breast ultrasound, mammography, and ultrasound-guided breast biopsy. Based on the histopathological results, the patients were divided into three categories: benign, ductal carcinomas, and non-ductal carcinomas. The mammograms in the cranio-caudal view underwent pre-processing and segmentation. Given the large variability of the areola, an algorithm was used to remove it and the adjacent skin. Therefore, patients with breast lesions close to the skin were removed. The remaining breast image was resized on the Y axis to a square image and then resized to 512 × 512 pixels. A variable square of 322,622 pixels was searched inside every image to identify the lesion. Each image was rotated with no information loss. For data augmentation, each image was rotated 360 times and a crop of 227 × 227 pixels was saved, resulting in a total of 201,240 images. The reason why our images were cropped at this size is because the deep learning algorithm transfer learning used from AlexNet network has an input image size of 227 × 227. The mean accuracy was 95.8344% ± 6.3720% and mean AUC 0.9910% ± 0.0366%, computed on 100 runs of the algorithm. Based on the results, the proposed solution can be used as a non-invasive and highly accurate computer-aided system based on deep learning that can classify breast lesions based on changes identified on mammograms in the cranio-caudal view. [ABSTRACT FROM AUTHOR]

This study aimed to develop a method for detection of femoral neck fracture (FNF) including displaced and non-displaced fractures using convolutional neural network (CNN) with plain X-ray and to validate its use across hospitals through internal and external validation sets. This is a retrospective study using hip and pelvic anteroposterior films for training and detecting femoral neck fracture through residual neural network (ResNet) 18 with convolutional block attention module (CBAM) + +. The study was performed at two tertiary hospitals between February and May 2020 and used data from January 2005 to December 2018. Our primary outcome was favorable performance for diagnosis of femoral neck fracture from negative studies in our dataset. We described the outcomes as area under the receiver operating characteristic curve (AUC), accuracy, Youden index, sensitivity, and specificity. A total of 4,189 images that contained 1,109 positive images (332 non-displaced and 777 displaced) and 3,080 negative images were collected from two hospitals. The test values after training with one hospital dataset were 0.999 AUC, 0.986 accuracy, 0.960 Youden index, and 0.966 sensitivity, and 0.993 specificity. Values of external validation with the other hospital dataset were 0.977, 0.971, 0.920, 0.939, and 0.982, respectively. Values of merged hospital datasets were 0.987, 0.983, 0.960, 0.973, and 0.987, respectively. A CNN algorithm for FNF detection in both displaced and non-displaced fractures using plain X-rays could be used in other hospitals to screen for FNF after training with images from the hospital of interest. [ABSTRACT FROM AUTHOR]

Deep learning for MRI detection of sports injuries poses unique challenges. To address these difficulties, this study examines the feasibility and incremental benefit of several customized network architectures in evaluation of complete anterior cruciate ligament (ACL) tears. Two hundred sixty patients, ages 18–40, were identified in a retrospective review of knee MRIs obtained from September 2013 to March 2016. Half of the cases demonstrated a complete ACL tear (624 slices), the other half a normal ACL (3520 slices). Two hundred cases were used for training and validation, and the remaining 60 cases as an independent test set. For each exam with an ACL tear, coronal proton density non-fat suppressed sequence was manually annotated to delineate: (1) a bounding-box around the cruciate ligaments; (2) slices containing the tear. Multiple convolutional neural network (CNN) architectures were implemented including variations in input field-of-view and dimensionality. For single-slice CNN architectures, validation accuracy of a dynamic patch-based sampling algorithm (0.765) outperformed both cropped slice (0.720) and full slice (0.680) strategies. Using the dynamic patch-based sampling algorithm as a baseline, a five-slice CNN input (0.915) outperformed both three-slice (0.865) and single-slice (0.765) inputs. The final highest performing five-slice dynamic patch-based sampling algorithm resulted in independent test set AUC, sensitivity, specificity, PPV, and NPV of 0.971, 0.967, 1.00, 0.938, and 1.00. A customized 3D deep learning architecture based on dynamic patch-based sampling demonstrates high performance in detection of complete ACL tears with over 96% test set accuracy. A cropped field-of-view and 3D inputs are critical for high algorithm performance. [ABSTRACT FROM AUTHOR]

To determine whether cmAssist™, an artificial intelligence-based computer-aided detection (AI-CAD) algorithm, can be used to improve radiologists' sensitivity in breast cancer screening and detection. A blinded retrospective study was performed with a panel of seven radiologists using a cancer-enriched data set from 122 patients that included 90 false-negative mammograms obtained up to 5.8 years prior to diagnosis and 32 BIRADS 1 and 2 patients with a 2-year follow-up of negative diagnosis. The mammograms were performed between February 7, 2008 (earliest) and January 8, 2016 (latest), and were all originally interpreted as negative in conjunction with R2 ImageChecker CAD, version 10.0. In this study, the readers analyzed the 122 studies before and after review of cmAssist™, an AI-CAD software for mammography. The statistical significance of our findings was evaluated using Student's t test and bootstrap statistical analysis. There was a substantial and significant improvement in radiologist accuracy with use of cmAssist, as demonstrated in the 7.2% increase in the area-under-the-curve (AUC) of the receiver operating characteristic (ROC) curve with two-sided p value < 0.01 for the reader group. All radiologists showed a significant improvement in their cancer detection rate (CDR) with the use of cmAssist (two-sided p value = 0.030, confidence interval = 95%). The readers detected between 25 and 71% (mean 51%) of the early cancers without assistance. With cmAssist, the overall reader CDR was 41 to 76% (mean 62%). The percentage increase in CDR for the reader panel was significant, ranging from 6 to 64% (mean 27%) with the use of cmAssist. There was less than 1% increase in the readers' false-positive recalls with use of cmAssist. With the use of cmAssist TM, there was a substantial and statistically significant improvement in radiologists' accuracy and sensitivity for detection of cancers that were originally missed. The percentage increase in CDR for the radiologists in the reader panel ranged from 6 to 64% (mean 27%) with the use of cmAssist, with negligible increase in false-positive recalls. [ABSTRACT FROM AUTHOR]

Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends. [ABSTRACT FROM AUTHOR]