Purpose: Hip fractures are a common cause of morbidity and mortality. Automatic identification and classification of hip fractures using deep learning may improve outcomes by reducing diagnostic errors and decreasing time to operation. Methods: Hip and pelvic radiographs from 1118 studies were reviewed and 3034 hips were labeled via bounding boxes and classified as normal, displaced femoral neck fracture, nondisplaced femoral neck fracture, intertrochanteric fracture, previous ORIF, or previous arthroplasty. A deep learning-based object detection model was trained to automate the placement of the bounding boxes. A Densely Connected Convolutional Neural Network (DenseNet) was trained on a subset of the bounding box images, and its performance evaluated on a held out test set and by comparison on a 100-image subset to two groups of human observers: fellowshiptrained radiologists and orthopaedists, and senior residents in emergency medicine, radiology, and orthopaedics. Results: The binary accuracy for fracture of our model was 93.8% (95% CI, 91.3-95.8%), with sensitivity of 92.7% (95% CI, 88.7-95.6%), and specificity 95.0% (95% CI, 91.5-97.3%). Multiclass classification accuracy was 90.4% (95% CI, 87.4-92.9%). When compared to human observers, our model achieved at least expert-level classification under all conditions. Additionally, when the model was used as an aid, human performance improved, with aided resident performance approximating unaided fellowship-trained expert performance. Conclusions: Our deep learning model identified and classified hip fractures with at least expert-level accuracy, and when used as an aid improved human performance, with aided resident performance approximating that of unaided fellowship-trained attendings.
Using DNA methylation profiles ( n = 15,456) from 348 mammalian species, we constructed phyloepigenetic trees that bear marked similarities to traditional phylogenetic ones. Using unsupervised clustering across all samples, we identified 55 distinct cytosine modules, of which 30 are related to traits such as maximum life span, adult weight, age, sex, and human mortality risk. Maximum life span is associated with methylation levels in HOXL subclass homeobox genes and developmental processes and is potentially regulated by pluripotency transcription factors. The methylation state of some modules responds to perturbations such as caloric restriction, ablation of growth hormone receptors, consumption of high-fat diets, and expression of Yamanaka factors. This study reveals an intertwined evolution of the genome and epigenome that mediates the biological characteristics and traits of different mammalian species.
Claims surrounding exceptional longevity are sometimes disputed or dismissed for lack of credible evidence. Here, we present three DNA methylation-based age estimators (epigenetic clocks) for verifying age claims of centenarians. The three centenarian clocks were developed based on n = 7039 blood and saliva samples from individuals older than 40, including n = 184 samples from centenarians, 122 samples from semi-supercentenarians (aged 105 +), and 25 samples from supercentenarians (aged 110 +). The oldest individual was 115 years old. Our most accurate centenarian clock resulted from applying a neural network model to a training set composed of individuals older than 40. An epigenome-wide association study of age in different age groups revealed that age effects in young individuals (age < 40) are correlated (r = 0.55) with age effects in old individuals (age > 90). We present a chromatin state analysis of age effects in centenarians. The centenarian clocks are expected to be useful for validating claims surrounding exceptional old age.
Deep Learning has shown potential in accelerating Magnetic Resonance Image acquisition and reconstruction. Nevertheless, there is a dearth of tailored methods to guarantee that the reconstruction of small features is achieved with high fidelity. In this work, we employ adversarial attacks to generate small synthetic perturbations that when added to the input MRI, they are not reconstructed by a trained DL reconstruction network. Then, we use robust training to increase the network's sensitivity to small features and encourage their reconstruction. Next, we investigate the generalization of said approach to real world features. For this, a musculoskeletal radiologist annotated a set of cartilage and meniscal lesions from the knee Fast-MRI dataset, and a classification network was devised to assess the features reconstruction. Experimental results show that by introducing robust training to a reconstruction network, the rate (4.8%) of false negative features in image reconstruction can be reduced. The results are encouraging and highlight the necessity for attention on this problem by the image reconstruction community, as a milestone for the introduction of DL reconstruction in clinical practice. To support further research, we make our annotation publicly available at https://github.com/fcaliva/fastMRI_BB_abnormalities_annotation.
The use of semantic segmentation for masking and cropping input images has proven to be a significant aid in medical imaging classification tasks by decreasing the noise and variance of the training dataset. However, implementing this approach with classical methods is challenging: the cost of obtaining a dense segmentation is high, and the precise input area that is most crucial to the classification task is difficult to determine a-priori. We propose a novel joint-training deep reinforcement learning framework for image augmentation. A segmentation network, weakly supervised with policy gradient optimization, acts as an agent, and outputs masks as actions given samples as states, with the goal of maximizing reward signals from the classification network. In this way, the segmentation network learns to mask unimportant imaging features. Our method, Adversarial Policy Gradient Augmentation (APGA), shows promising results on Stanford's MURA dataset and on a hip fracture classification task with an increase in global accuracy of up to 7.33% and improved performance over baseline methods in 9/10 tasks evaluated. We discuss the broad applicability of our joint training strategy to a variety of medical imaging tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.