Deep learning in veterinary medicine, an approach based on CNN to detect pulmonary abnormalities from lateral thoracic radiographs in cats.
Ontology highlight
ABSTRACT:
SUBMITTER: Dumortier L
PROVIDER: S-EPMC9258008 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:PurposeThis study evaluated the performance of a commercially available deep-learning algorithm (DLA) (Insight CXR, Lunit, Seoul, South Korea) for referable thoracic abnormalities on chest X-ray (CXR) using a consecutively collected multicenter health screening cohort.Methods and materialsA consecutive health screening cohort of participants who underwent both CXR and chest computed tomography (CT) within 1 month was retrospectively collected from three institutions' health care clinics (n = 5,887). Referable thoracic abnormalities were defined as any radiologic findings requiring further diagnostic evaluation or management, including DLA-target lesions of nodule/mass, consolidation, or pneumothorax. We evaluated the diagnostic performance of the DLA for referable thoracic abnormalities using the area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, and specificity using ground truth based on chest CT (CT-GT). In addition, for CT-GT-positive cases, three independent radiologist readings were performed on CXR and clear visible (when more than two radiologists called) and visible (at least one radiologist called) abnormalities were defined as CXR-GTs (clear visible CXR-GT and visible CXR-GT, respectively) to evaluate the performance of the DLA.ResultsAmong 5,887 subjects (4,329 males; mean age 54±11 years), referable thoracic abnormalities were found in 618 (10.5%) based on CT-GT. DLA-target lesions were observed in 223 (4.0%), nodule/mass in 202 (3.4%), consolidation in 31 (0.5%), pneumothorax in one 1 (<0.1%), and DLA-non-target lesions in 409 (6.9%). For referable thoracic abnormalities based on CT-GT, the DLA showed an AUC of 0.771 (95% confidence interval [CI], 0.751-0.791), a sensitivity of 69.6%, and a specificity of 74.0%. Based on CXR-GT, the prevalence of referable thoracic abnormalities decreased, with visible and clear visible abnormalities found in 405 (6.9%) and 227 (3.9%) cases, respectively. The performance of the DLA increased significantly when using CXR-GTs, with an AUC of 0.839 (95% CI, 0.829-0.848), a sensitivity of 82.7%, and s specificity of 73.2% based on visible CXR-GT and an AUC of 0.872 (95% CI, 0.863-0.880, P <0.001 for the AUC comparison of GT-CT vs. clear visible CXR-GT), a sensitivity of 83.3%, and a specificity of 78.8% based on clear visible CXR-GT.ConclusionThe DLA provided fair-to-good stand-alone performance for the detection of referable thoracic abnormalities in a multicenter consecutive health screening cohort. The DLA showed varied performance according to the different methods of ground truth.
| S-EPMC7894861 | biostudies-literature
Project description:This Perspectives in Veterinary Medicine article seeks to define, describe putative causes, and discuss key diagnostic tests for primary and secondary bronchiolar disorders to propose a classification scheme in cats with support from a literature review and case examples. The small airways (bronchioles with inner diameters <2 mm), located at the transitional zone between larger conducting airways and the pulmonary acinus, have been overlooked as major contributors to clinical syndromes of respiratory disease in cats. Because the trigger for many bronchiolar disorders is environmental and humans live in a shared environment with similar susceptibility, understanding these diseases in pet cats has relevance to One Health. Thoracic radiography, the major imaging modality used in the diagnostic evaluation of respiratory disease in cats, has low utility in detection of bronchiolar disease. Computed tomography (CT) with paired inspiratory and expiratory scans can detect pathology centered on small airways. In humans, treatment of bronchiolar disorders is not well established because of heterogeneous presentations and often late definitive diagnosis. A review of the human and veterinary medical literature will serve as the basis for a proposed classification scheme in cats. A case series of cats with CT or histopathologic evidence of bronchiolar lesions or both, either as a primary disorder or secondary to extension from large airway disease or interstitial lung disease, will be presented. Future multi-institutional and multidisciplinary discussions among clinicians, radiologists, and pathologists will help refine and develop this classification scheme to promote early and specific recognition and optimize treatment.
| S-EPMC6524100 | biostudies-literature
Project description:The real cause of breast cancer is very challenging to determine and therefore early detection of the disease is necessary for reducing the death rate due to risks of breast cancer. Early detection of cancer boosts increasing the survival chance up to 8%. Primarily, breast images emanating from mammograms, X-Rays or MRI are analyzed by radiologists to detect abnormalities. However, even experienced radiologists face problems in identifying features like micro-calcifications, lumps and masses, leading to high false positive and high false negative. Recent advancement in image processing and deep learning create some hopes in devising more enhanced applications that can be used for the early detection of breast cancer. In this work, we have developed a Deep Convolutional Neural Network (CNN) to segment and classify the various types of breast abnormalities, such as calcifications, masses, asymmetry and carcinomas, unlike existing research work, which mainly classified the cancer into benign and malignant, leading to improved disease management. Firstly, a transfer learning was carried out on our dataset using the pre-trained model ResNet50. Along similar lines, we have developed an enhanced deep learning model, in which learning rate is considered as one of the most important attributes while training the neural network. The learning rate is set adaptively in our proposed model based on changes in error curves during the learning process involved. The proposed deep learning model has achieved a performance of 88% in the classification of these four types of breast cancer abnormalities such as, masses, calcifications, carcinomas and asymmetry mammograms.
| S-EPMC8389446 | biostudies-literature
Project description:ObjectivesThis study aimed to compare the diagnostic performance of deep learning algorithm trained by single view (anterior-posterior (AP) or lateral view) with that trained by multiple views (both views together) in diagnosis of mastoiditis on mastoid series and compare the diagnostic performance between the algorithm and radiologists.MethodsTotal 9,988 mastoid series (AP and lateral views) were classified as normal or abnormal (mastoiditis) based on radiographic findings. Among them 792 image sets with temporal bone CT were classified as the gold standard test set and remaining sets were randomly divided into training (n = 8,276) and validation (n = 920) sets by 9:1 for developing a deep learning algorithm. Temporal (n = 294) and geographic (n = 308) external test sets were also collected. Diagnostic performance of deep learning algorithm trained by single view was compared with that trained by multiple views. Diagnostic performance of the algorithm and two radiologists was assessed. Inter-observer agreement between the algorithm and radiologists and between two radiologists was calculated.ResultsArea under the receiver operating characteristic curves of algorithm using multiple views (0.971, 0.978, and 0.965 for gold standard, temporal, and geographic external test sets, respectively) showed higher values than those using single view (0.964/0.953, 0.952/0.961, and 0.961/0.942 for AP view/lateral view of gold standard, temporal external, and geographic external test sets, respectively) in all test sets. The algorithm showed statistically significant higher specificity compared with radiologists (p = 0.018 and 0.012). There was substantial agreement between the algorithm and two radiologists and between two radiologists (κ = 0.79, 0.8, and 0.76).ConclusionThe deep learning algorithm trained by multiple views showed better performance than that trained by single view. The diagnostic performance of the algorithm for detecting mastoiditis on mastoid series was similar to or higher than that of radiologists.
| S-EPMC7657495 | biostudies-literature
Project description:ObjectiveThis study aimed to develop and validate a deep learning (DL) algorithm for the quantitative measurement of thoracolumbar (TL) fracture features, and to evaluate its efficacy across varying levels of clinical expertise.MethodsUsing the pretrained Mask Region-Based Convolutional Neural Networks model, originally developed for vertebral body segmentation and fracture detection, we fine-tuned the model and added a new module for measuring fracture metrics-compression rate (CR), Cobb angle (CA), Gardner angle (GA), and sagittal index (SI)-from lumbar spine lateral radiographs. These metrics were derived from six-point labeling by 3 radiologists, forming the ground truth (GT). Training utilized 1,000 nonfractured and 318 fractured radiographs, while validations employed 213 internal and 200 external fractured radiographs. The accuracy of the DL algorithm in quantifying fracture features was evaluated against GT using the intraclass correlation coefficient. Additionally, 4 readers with varying expertise levels, including trainees and an attending spine surgeon, performed measurements with and without DL assistance, and their results were compared to GT and the DL model.ResultsThe DL algorithm demonstrated good to excellent agreement with GT for CR, CA, GA, and SI in both internal (0.860, 0.944, 0.932, and 0.779, respectively) and external (0.836, 0.940, 0.916, and 0.815, respectively) validations. DL-assisted measurements significantly improved most measurement values, particularly for trainees.ConclusionThe DL algorithm was validated as an accurate tool for quantifying TL fracture features using radiographs. DL-assisted measurement is expected to expedite the diagnostic process and enhance reliability, particularly benefiting less experienced clinicians.
| S-EPMC10992637 | biostudies-literature
Project description:BackgroundIdentification of vertebral fractures (VFs) is critical for effective secondary fracture prevention owing to their association with the increasing risks of future fractures. Plain abdominal frontal radiographs (PARs) are a common investigation method performed for a variety of clinical indications and provide an ideal platform for the opportunistic identification of VF. This study uses a deep convolutional neural network (DCNN) to identify the feasibility for the screening, detection, and localization of VFs using PARs.MethodsA DCNN was pretrained using ImageNet and retrained with 1306 images from the PARs database obtained between August 2015 and December 2018. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated. The visualization algorithm gradient-weighted class activation mapping (Grad-CAM) was used for model interpretation.ResultsOnly 46.6% (204/438) of the VFs were diagnosed in the original PARs reports. The algorithm achieved 73.59% accuracy, 73.81% sensitivity, 73.02% specificity, and an AUC of 0.72 in the VF identification.ConclusionComputer driven solutions integrated with the DCNN have the potential to identify VFs with good accuracy when used opportunistically on PARs taken for a variety of clinical purposes. The proposed model can help clinicians become more efficient and economical in the current clinical pathway of fragile fracture treatment.
| S-EPMC7842883 | biostudies-literature
Project description:This study aimed to develop and evaluate a deep learning-based system for the automatic measurement of angles (specifically, Meary's angle and calcaneal pitch) in weight-bearing lateral radiographs of the foot for flatfoot diagnosis. We utilized 3960 lateral radiographs, either from the left or right foot, sourced from a pool of 4000 patients to construct and evaluate a deep learning-based model. These radiographs were captured between June and November 2021, and patients who had undergone total ankle replacement surgery or ankle arthrodesis surgery were excluded. Various methods, including correlation analysis, Bland-Altman plots, and paired T-tests, were employed to assess the concordance between the angles automatically measured using the system and those assessed by clinical experts. The evaluation dataset comprised 150 weight-bearing radiographs from 150 patients. In all test cases, the angles automatically computed using the deep learning-based system were in good agreement with the reference standards (Meary's angle: Pearson correlation coefficient (PCC) = 0.964, intraclass correlation coefficient (ICC) = 0.963, concordance correlation coefficient (CCC) = 0.963, p-value = 0.632, mean absolute error (MAE) = 1.59°; calcaneal pitch: PCC = 0.988, ICC = 0.987, CCC = 0.987, p-value = 0.055, MAE = 0.63°). The average time required for angle measurement using only the CPU to execute the deep learning-based system was 11 ± 1 s. The deep learning-based automatic angle measurement system, a tool for diagnosing flatfoot, demonstrated comparable accuracy and reliability with the results obtained by medical professionals for patients without internal fixation devices.
| S-EPMC11310201 | biostudies-literature
Project description:Human spinal balance assessment relies considerably on sagittal radiographic parameter measurement. Deep learning could be applied for automatic landmark detection and alignment analysis, with mild to moderate standard errors and favourable correlations with manual measurement. In this study, based on 2210 annotated images of various spinal disease aetiologies, we developed deep learning models capable of automatically locating 45 anatomic landmarks and subsequently generating 18 radiographic parameters on a whole-spine lateral radiograph. In the assessment of model performance, the localisation accuracy and learning speed were the highest for landmarks in the cervical area, followed by those in the lumbosacral, thoracic, and femoral areas. All the predicted radiographic parameters were significantly correlated with ground truth values (all p < 0.001). The human and artificial intelligence comparison revealed that the deep learning model was capable of matching the reliability of doctors for 15/18 of the parameters. The proposed automatic alignment analysis system was able to localise spinal anatomic landmarks with high accuracy and to generate various radiographic parameters with favourable correlations with manual measurements.
| S-EPMC8027006 | biostudies-literature
Project description:Pectus excavatum, thoracic spine deformities, tracheal hypoplasia and lateral heart displacement are frequently described in brachycephalic dog breeds. Pectus carinatum is described sporadically, although the authors' observations demonstrate that it may occur in certain brachycephalic dog breeds. It was hypothesised that dogs of screw-tailed brachycephalic breeds carry a greater risk of these anomalies than normal-tailed brachycephalic breeds, and that there could a relation between the presence of pectus excavatum or pectus carinatum and thoracic spine deformities, tracheal hypoplasia and lateral heart displacement. During retrospective studies, these anomalies were identified in lateral and dorso-ventral radiographs of the thorax in brachycephalic dog breeds. A statistical analysis revealed that the frequency of pectus excavatum occurrence in screw-tailed and normal-tailed brachycephalic dog breeds is similar. The greatest risk of pectus excavatum occurrence is carried by two breeds: Maltese (60%) and English Bulldog (58%), while for pectus carinatum: Pug (41%) and French Bulldog (18%). Dogs of screw-tailed brachycephalic breeds carry a greater risk of kyphosis (p < 0.0001), tracheal hypoplasia occurrence (p < 0.0001), compared to "normal-tailed" breeds. The hypothesis concerning a relation between the presence of pectus excavatum or pectus carinatum and the other anomalies studied was not confirmed (p > 0.05). It was demonstrated that in dogs of brachycephalic breeds there was a greater risk of co-incidence between kyphosis of the thoracic spine and lateral heart displacement (p = 0.038), as well as kyphosis of the thoracic spine and tracheal hypoplasia (p = 0.003).
| S-EPMC6786652 | biostudies-literature
Project description:BackgroundAcute respiratory distress syndrome (ARDS) is a common, but under-recognised, critical illness syndrome associated with high mortality. An important factor in its under-recognition is the variability in chest radiograph interpretation for ARDS. We sought to train a deep convolutional neural network (CNN) to detect ARDS findings on chest radiographs.MethodsCNNs were pretrained on 595 506 radiographs from two centres to identify common chest findings (eg, opacity and effusion), and then trained on 8072 radiographs annotated for ARDS by multiple physicians using various transfer learning approaches. The best performing CNN was tested on chest radiographs in an internal and external cohort, including a subset reviewed by six physicians, including a chest radiologist and physicians trained in intensive care medicine. Chest radiograph data were acquired from four US hospitals.FindingsIn an internal test set of 1560 chest radiographs from 455 patients with acute hypoxaemic respiratory failure, a CNN could detect ARDS with an area under the receiver operator characteristics curve (AUROC) of 0·92 (95% CI 0·89-0·94). In the subgroup of 413 images reviewed by at least six physicians, its AUROC was 0·93 (95% CI 0·88-0·96), sensitivity 83·0% (95% CI 74·0-91·1), and specificity 88·3% (95% CI 83·1-92·8). Among images with zero of six ARDS annotations (n=155), the median CNN probability was 11%, with six (4%) assigned a probability above 50%. Among images with six of six ARDS annotations (n=27), the median CNN probability was 91%, with two (7%) assigned a probability below 50%. In an external cohort of 958 chest radiographs from 431 patients with sepsis, the AUROC was 0·88 (95% CI 0·85-0·91). When radiographs annotated as equivocal were excluded, the AUROC was 0·93 (0·92-0·95).InterpretationA CNN can be trained to achieve expert physician-level performance in ARDS detection on chest radiographs. Further research is needed to evaluate the use of these algorithms to support real-time identification of ARDS patients to ensure fidelity with evidence-based care or to support ongoing ARDS research.FundingNational Institutes of Health, Department of Defense, and Department of Veterans Affairs.
| S-EPMC8182690 | biostudies-literature