A Novel Deep Learning Approach for Automated Diagnosis of Acute Ischemic Infarction on Computed Tomography (original) (raw)
Related papers
Scientific Reports, 2021
There is little evidence on the applicability of deep learning (DL) in the segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n = 2986) and B (n = 3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80%), validation (10%), and internal test (10%) sets, and six neuroradiologists created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B. The models subsequently fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist’s performance, but demonstrated lower performance t...
Head CT deep learning model is highly accurate for early infarct estimation
Scientific Reports
Non-contrast head CT (NCCT) is extremely insensitive for early (< 3–6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61–66% (specificity 90–92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r2 > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of in...
JAMA Network Open, 2020
IMPORTANCE Predicting infarct size and location is important for decision-making and prognosis in patients with acute stroke. OBJECTIVES To determine whether a deep learning model can predict final infarct lesions using magnetic resonance images (MRIs) acquired at initial presentation (baseline) and to compare the model with current clinical prediction methods. DESIGN, SETTING, AND PARTICIPANTS In this multicenter prognostic study, a specific type of neural network for image segmentation (U-net) was trained, validated, and tested using patients from the Imaging Collaterals in Acute Stroke (iCAS) study from April 14, 2014, to April 15, 2018, and the Diffusion Weighted Imaging Evaluation for Understanding Stroke Evolution Study-2 (DEFUSE-2) study from July 14, 2008, to September 17, 2011 (reported in October 2012). Patients underwent baseline perfusion-weighted and diffusion-weighted imaging and MRI at 3 to 7 days after baseline. Patients were grouped into unknown, minimal, partial, and major reperfusion status based on 24-hour imaging results. Baseline images acquired at presentation were inputs, and the final true infarct lesion at 3 to 7 days was considered the ground truth for the model. The model calculated the probability of infarction for every voxel, which can be thresholded to produce a prediction. Data were analyzed from July 1, 2018, to March 7, 2019. MAIN OUTCOMES AND MEASURES Area under the curve, Dice score coefficient (DSC) (a metric from 0-1 indicating the extent of overlap between the prediction and the ground truth; a DSC of Ն0.5 represents significant overlap), and volume error. Current clinical methods were compared with model performance in subgroups of patients with minimal or major reperfusion. RESULTS Among the 182 patients included in the model (97 women [53.3%]; mean [SD] age, 65 [16] years), the deep learning model achieved a median area under the curve of 0.92 (interquartile range [IQR], 0.87-0.96), DSC of 0.53 (IQR, 0.31-0.68), and volume error of 9 (IQR, −14 to 29) mL. In subgroups with minimal (DSC, 0.58 [IQR, 0.31-0.67] vs 0.55 [IQR, 0.40-0.65]; P = .37) or major (DSC, 0.48 [IQR, 0.29-0.65] vs 0.45 [IQR, 0.15-0.54]; P = .002) reperfusion for which comparison with existing clinical methods was possible, the deep learning model had comparable or better performance. CONCLUSIONS AND RELEVANCE The deep learning model appears to have successfully predicted infarct lesions from baseline imaging without reperfusion information and achieved comparable performance to existing clinical methods. Predicting the subacute infarct lesion may help clinicians prepare for decompression treatment and aid in patient selection for neuroprotective clinical trials.
Machine learning and deep learning approach for medical image analysis: diagnosis to detection
Multimedia Tools and Applications
Computer-aided detection using Deep Learning (DL) and Machine Learning (ML) shows tremendous growth in the medical field. Medical images are considered as the actual origin of appropriate information required for diagnosis of disease. Detection of disease at the initial stage, using various modalities, is one of the most important factors to decrease mortality rate occurring due to cancer and tumors. Modalities help radiologists and doctors to study the internal structure of the detected disease for retrieving the required features. ML has limitations with the present modalities due to large amounts of data, whereas DL works efficiently with any amount of data. Hence, DL is considered as the enhanced technique of ML where ML uses the learning techniques and DL acquires details on how machines should react around people. DL uses a multilayered neural network to get more information about the used datasets. This study aims to present a systematic literature review related to applications of ML and DL for the detection along with classification of multiple diseases. A detailed analysis of 40 primary studies acquired from the well-known journals and conferences between Jan 2014-2022 was done. It provides an overview of different approaches based on ML and DL for the detection along with the classification of multiple diseases, modalities for medical imaging, tools and techniques used for the evaluation, description of datasets. Further, experiments are performed using MRI dataset to provide a comparative analysis of ML classifiers and DL models. This study will assist the healthcare community by enabling medical practitioners and researchers to choose an appropriate diagnosis technique for a given disease with reduced time and high accuracy.
The Lancet Digital Health
Background Deep learning offers considerable promise for medical diagnostics. We aimed to evaluate the diagnostic accuracy of deep learning algorithms versus health-care professionals in classifying diseases using medical imaging. Methods In this systematic review and meta-analysis, we searched Ovid-MEDLINE, Embase, Science Citation Index, and Conference Proceedings Citation Index for studies published from Jan 1, 2012, to June 6, 2019. Studies comparing the diagnostic performance of deep learning models and health-care professionals based on medical imaging, for any disease, were included. We excluded studies that used medical waveform data graphics material or investigated the accuracy of image segmentation rather than disease classification. We extracted binary diagnostic accuracy data and constructed contingency tables to derive the outcomes of interest: sensitivity and specificity. Studies undertaking an out-of-sample external validation were included in a meta-analysis, using a unified hierarchical model. This study is registered with PROSPERO, CRD42018091176. Findings Our search identified 31 587 studies, of which 82 (describing 147 patient cohorts) were included. 69 studies provided enough data to construct contingency tables, enabling calculation of test accuracy, with sensitivity ranging from 9•7% to 100•0% (mean 79•1%, SD 0•2) and specificity ranging from 38•9% to 100•0% (mean 88•3%, SD 0•1). An out-of-sample external validation was done in 25 studies, of which 14 made the comparison between deep learning models and health-care professionals in the same sample. Comparison of the performance between health-care professionals in these 14 studies, when restricting the analysis to the contingency table for each study reporting the highest accuracy, found a pooled sensitivity of 87•0% (95% CI 83•0-90•2) for deep learning models and 86•4% (79•9-91•0) for health-care professionals, and a pooled specificity of 92•5% (95% CI 85•1-96•4) for deep learning models and 90•5% (80•6-95•7) for health-care professionals. Interpretation Our review found the diagnostic performance of deep learning models to be equivalent to that of health-care professionals. However, a major finding of the review is that few studies presented externally validated results or compared the performance of deep learning models and health-care professionals using the same sample. Additionally, poor reporting is prevalent in deep learning studies, which limits reliable interpretation of the reported diagnostic accuracy. New reporting standards that address specific challenges of deep learning could improve future studies, enabling greater confidence in the results of future evaluations of this promising technology.
Bilişim Teknolojileri Dergisi, 2022
Deep learning is a machine learning technique that uses deep neural networks, which are multilayer neural networks that contain two or more hidden layers. In recent years, deep learning algorithms are also used to solve machine learning problems in medicine. Carotid artery disease is a type of cardiovascular disease that can result in a stroke. If a stroke is not diagnosed early, it is in the first place among the disabling diseases and the third place for the most common cause of death after cancer and heart disease. In this study, the classification performances of deep learning architectures in the biomedical field are compared, and Carotid Artery (CA) Intima-Media Thickness (IMT) Ultrasound (US) images were used. For an early diagnosis, AlexNet, ZFNet, VGGNet (16-19), which had successful results in the ImageNet competition, and authors' original CNNcc models were used for comparison. An image database of CA-IMT-US which contains 501 ultrasound images from 153 patients was used to test the models' classification performances. It is seen that AlexNet, ZFNet, VGG16, VGG19, and CNNcc models achieved rates of 91%, 89.1%, 93%, 90%, and 89.1% respectively. The CNNcc model was found to produce successful classification results on CAIMTUS images when different performance indicators are also taken into account. In addition, different performance indicators including confusion matrices were investigated and the results were announced. The results showed that deep architectures are promising in the biomedical field and can provide proper classification on biomedical images so; this can help clinics to diagnose the disease early.
Deep Learning Applications in Medical Imaging
Advances in Medical Technologies and Clinical Practice, 2021
Artificial intelligence (AI) broadly concerns analytical algorithms that iteratively learn from big datasets, allowing computers to find concealed insights. These encompass a range of operations comprising several terms, including machine learning(ML), cognitive learning, deep learning, and reinforcement learning-based methods that can be used to incorporate and comprehend complex biomedical and healthcare data in scenarios where traditional statistical approaches cannot be implemented. For cardiovascular imaging in particular, machine learning guarantees to be a transformative tool that can address many unmet needs for patient-specific management, accurate prediction of disease progression, and the tracking of identifiable biomarkers of disease processes. In this chapter, the authors discuss fundamentals of machine learning algorithms for image analysis in the cardiovascular system by evaluating the need for ML in this field and examining the potential obstacles and challenges of i...
Journal of Computer Science and Technology Studies, 2024
This paper aims to provide a systematic review of the state of the art in the use of deep neural networks (DNNs) in medical imaging, an area that has been recently developed because of the emergence of artificial intelligence (AI) and machine learning (ML). Deep Neural Networks including Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) have shown excellence in handling of a gigantic imaging data and assisting in diagnostics, treatment planning and patient care. This review also focuses on the breakthroughs of DNNs in different imaging tasks including classification, segmentation, registration, and detection, and has highlighted its potential to enhance diagnostic accuracy in different organs like the brain, lung and chest. Some of the key problems related to DNN deployment are also considered, including the problems that arise due to limitations of data, computational power, and model interpretability. That is why innovations such as transfer learning and synthetic data acquisition contributed to reducing these problems, thereby improving model performance with limited data. The paper concludes by discussing future works where the emphasis is made on the higher interpretability of the models and the combination of clinical records with images. In this paper, we attempt to offer a comprehensive review of the latest developments in DNNs in medical image analysis and delineate potential research directions to help researchers and practitioners interested in applying DNNs for medical imaging tasks.
A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative
PLOS ONE
Background Recently, artificial intelligence (AI)-based applications for chest imaging have emerged as potential tools to assist clinicians in the diagnosis and management of patients with coronavirus disease 2019 (COVID-19). Objectives To develop a deep learning-based clinical decision support system for automatic diagnosis of COVID-19 on chest CT scans. Secondarily, to develop a complementary segmentation tool to assess the extent of lung involvement and measure disease severity. Methods The Imaging COVID-19 AI initiative was formed to conduct a retrospective multicentre cohort study including 20 institutions from seven different European countries. Patients with suspected or known COVID-19 who underwent a chest CT were included. The dataset was split on the institution-level to allow external evaluation. Data annotation was performed by 34 radiologists/radiology residents and included quality control measures. A multi-class classification model was created using a custom 3D convo...