Search

Limitations of the chest X-ray (CXR) have resulted in attempts to create machine learning systems to assist clinicians and improve interpretation accuracy. An understanding of the capabilities and limitations of modern machine learning systems is necessary for clinicians as these tools begin to permeate practice. This systematic review aimed to provide an overview of machine learning applications designed to facilitate CXR interpretation. A systematic search strategy was executed to identify research into machine learning algorithms capable of detecting >2 radiographic findings on CXRs published between January 2020 and September 2022. Model details and study characteristics, including risk of bias and quality, were summarized. Initially, 2248 articles were retrieved, with 46 included in the final review. Published models demonstrated strong standalone performance and were typically as accurate, or more accurate, than radiologists or non-radiologist clinicians. Multiple studies demonstrated an improvement in the clinical finding classification performance of clinicians when models acted as a diagnostic assistance device. Device performance was compared with that of clinicians in 30% of studies, while effects on clinical perception and diagnosis were evaluated in 19%. Only one study was prospectively run. On average, 128,662 images were used to train and validate models. Most classified less than eight clinical findings, while the three most comprehensive models classified 54, 72, and 124 findings. This review suggests that machine learning devices designed to facilitate CXR interpretation perform strongly, improve the detection performance of clinicians, and improve the efficiency of radiology workflow. Several limitations were identified, and clinician involvement and expertise will be key to driving the safe implementation of quality CXR machine learning systems.

Brain computed tomography (CTB) scans are widely used to evaluate intracranial pathology. The implementation and adoption of CTB has led to clinical improvements. However, interpretation errors occur and may have substantial morbidity and mortality implications for patients. Deep learning has shown promise for facilitating improved diagnostic accuracy and triage. This research charts the potential of deep learning applied to the analysis of CTB scans. It draws on the experience of practicing clinicians and technologists involved in development and implementation of deep learning-based clinical decision support systems. We consider the past, present and future of the CTB, along with limitations of existing systems as well as untapped beneficial use cases. Implementing deep learning CTB interpretation systems and effectively navigating development and implementation risks can deliver many benefits to clinicians and patients, ultimately improving efficiency and safety in healthcare.

Background and Purpose: Distal medium vessel occlusions (DMVOs) are increasingly considered for endovascular thrombectomy but are difficult to detect on computed tomography angiography (CTA). We aimed to determine whether time-to-maximum of tissue residue function (Tmax) maps, derived from CT perfusion, can be used as a triage screening tool to accurately and rapidly identify patients with DMVOs. Method(s): Consecutive code stroke patients who underwent multimodal CT were screened retrospectively. Two experienced readers evaluated all patients' Tmax maps in consensus for presence of delay in an arterial territory (territorial Tmax delay). The diagnostic accuracy of this surrogate for identifying DMVOs was determined using receiver-operating characteristic analysis. CTA, interpreted by 2 experienced neuroradiologists with access to all imaging data, served as the reference standard. Diagnostic performance of 4 other readers with different levels of experience for identifying DMVOs on Tmax versus CTA was also assessed. These readers independently assessed patients' Tmax maps and CTAs in 2 separate timed sessions, and areas under the receiver-operating characteristic curves were compared using the DeLong algorithm. The Wilcoxon signed-rank test was used to comparatively assess diagnostic speed. Result(s): Three hundred seventy-three code stroke patients (median age, 70 years; 56% male, 70 with a DMVO) were included. Territorial Tmax delay had a sensitivity of 100% (CI95, 94.9%-100%) and specificity of 87.8% (CI95, 83.6%-91.3%) for presence of a DMVO, yielding an area under the receiver-operating characteristic curves of 0.939 (CI95, 0.920-0.957). All 4 readers achieved sensitivity >95% and specificity >84% for detecting DMVOs using Tmax maps, with diagnostic accuracy (area under the receiver-operating characteristic curves) and speed that were significantly (P<0.001) higher than on CTA. Conclusion(s): Territorial Tmax delay had perfect sensitivity and high specificity

BACKGROUND AND PURPOSE: Detecting intracranial distal arterial occlusions on CTA is challenging but increasingly relevant to clinical decision-making. Our purpose was to determine whether the use of CTP-derived time-to-maximum of the tissue residue function maps improves diagnostic performance for detecting these occlusions. MATERIALS AND METHODS: Seventy consecutive patients with a distal arterial occlusion and 70 randomly selected controls who underwent multimodal CT with CTA and CTP for a suspected acute ischemic stroke were included in this retrospective study. Four readers with different levels of experience independently read the CTAs in 2 separate sessions, with and without time-to-maximum of the tissue residue function maps, recording the presence or absence of an occlusion, diagnostic confidence, and interpretation time. Accuracy for detecting distal occlusions was assessed using receiver operating characteristic analysis, and areas under curves were compared to assess whether accuracy improved with use of time-to-maximum of the tissue residue function. Changes in diagnostic confidence and interpretation time were assessed using the Wilcoxon signed rank test. RESULT(S): Mean sensitivity for detecting occlusions on CTA increased from 70.7% to 90.4% with use of time-to-maximum of the tissue residue function maps. Diagnostic accuracy improved significantly for the 4 readers (P, .001), with areas under the receiver operating characteristic curves increasing by 0.186, 0.136, 0.114, and 0.121, respectively. Diagnostic confidence and speed also significantly increased. CONCLUSION(S): All assessed metrics of diagnostic performance for detecting distal arterial occlusions improved with the use of time-to-maximum of the tissue residue function maps, encouraging their use to aid in interpretation of CTA by both experienced and inexperienced readers. These findings show the added diagnostic value of including CTP in the acute stroke imaging protocol.Copyright © 2021 Am

INTRODUCTION: This study aims to evaluate deep learning (DL)-based artificial intelligence (AI) techniques for detecting the presence of breast cancer on a digital mammogram image. METHODS: We evaluated several DL-based AI techniques that employ different approaches and backbone DL models and tested the effect on performance of using different data-processing strategies on a set of digital mammographic images with annotations of pathologically proven breast cancer. RESULTS: Our evaluation uses the area under curve (AUC) and accuracy (ACC) for performance measurement. The best evaluation result, based on 349 test cases (930 test images), was an AUC of 0.8979 [95% confidence interval (CI) 0.873, 0.923] and ACC of 0.8178 [95% CI 0.785, 0.850]. This was achieved by an AI technique that utilises a certain family of DL models, namely ResNet, as its backbone, combines the global features extracted from the whole mammogram and the local features extracted from the automatically detected cancer and non-cancer local regions in the whole image, and leverages background cropping and text removal, contrast adjustment and more training data. CONCLUSION: DL-based AI techniques have shown promising results in retrospective studies for many medical image analysis applications. Our study demonstrates a significant opportunity to boost the performance of such techniques applied to breast cancer detection by exploring different types of approaches, backbone DL models and data-processing strategies. The promising results we have obtained suggest further development of AI reading services could transform breast cancer screening in the future.

BACKGROUND: Chest x-rays are widely used in clinical practice; however, interpretation can be hindered by human error and a lack of experienced thoracic radiologists. Deep learning has the potential to improve the accuracy of chest x-ray interpretation. We therefore aimed to assess the accuracy of radiologists with and without the assistance of a deep-learning model. METHODS: In this retrospective study, a deep-learning model was trained on 821 681 images (284 649 patients) from five data sets from Australia, Europe, and the USA. 2568 enriched chest x-ray cases from adult patients (≥16 years) who had at least one frontal chest x-ray were included in the test dataset; cases were representative of inpatient, outpatient, and emergency settings. 20 radiologists reviewed cases with and without the assistance of the deep-learning model with a 3-month washout period. We assessed the change in accuracy of chest x-ray interpretation across 127 clinical findings when the deep-learning model was used as a decision support by calculating area under the receiver operating characteristic curve (AUC) for each radiologist with and without the deep-learning model. We also compared AUCs for the model alone with those of unassisted radiologists. If the lower bound of the adjusted 95% CI of the difference in AUC between the model and the unassisted radiologists was more than -0·05, the model was considered to be non-inferior for that finding. If the lower bound exceeded 0, the model was considered to be superior. FINDINGS: Unassisted radiologists had a macroaveraged AUC of 0·713 (95% CI 0·645-0·785) across the 127 clinical findings, compared with 0·808 (0·763-0·839) when assisted by the model. The deep-learning model statistically significantly improved the classification accuracy of radiologists for 102 (80%) of 127 clinical findings, was statistically non-inferior for 19 (15%) findings, and no findings showed a decrease in accuracy when radiologists used the deep-learning model. Unas

OBJECTIVES: To evaluate the ability of a commercially available comprehensive chest radiography deep convolutional neural network (DCNN) to detect simple and tension pneumothorax, as stratified by the following subgroups: the presence of an intercostal drain; rib, clavicular, scapular or humeral fractures or rib resections; subcutaneous emphysema and erect versus non-erect positioning. The hypothesis was that performance would not differ significantly in each of these subgroups when compared with the overall test dataset. DESIGN: A retrospective case-control study was undertaken. SETTING: Community radiology clinics and hospitals in Australia and the USA. PARTICIPANTS: A test dataset of 2557 chest radiography studies was ground-truthed by three subspecialty thoracic radiologists for the presence of simple or tension pneumothorax as well as each subgroup other than positioning. Radiograph positioning was derived from radiographer annotations on the images. OUTCOME MEASURES: DCNN performance for detecting simple and tension pneumothorax was evaluated over the entire test set, as well as within each subgroup, using the area under the receiver operating characteristic curve (AUC). A difference in AUC of more than 0.05 was considered clinically significant. RESULTS: When compared with the overall test set, performance of the DCNN for detecting simple and tension pneumothorax was statistically non-inferior in all subgroups. The DCNN had an AUC of 0.981 (0.976-0.986) for detecting simple pneumothorax and 0.997 (0.995-0.999) for detecting tension pneumothorax. CONCLUSIONS: Hidden stratification has significant implications for potential failures of deep learning when applied in clinical practice. This study demonstrated that a comprehensively trained DCNN can be resilient to hidden stratification in several clinically meaningful subgroups in detecting pneumothorax.

Prostate cancer (PCa) is the second most frequent type of cancer found in men worldwide, with around one in nine men being diagnosed with PCa within their lifetime. PCa often shows no symptoms in its early stages and its diagnosis techniques are either invasive, resource intensive, or has low efficacy, making widespread early detection onerous. Inspired by the recent success of deep convolutional neural networks (CNN) in computer aided detection (CADe), we propose a new CNN based framework for incidental detection of clinically significant prostate cancer (csPCa) in patients who had a CT scan of the abdomen/pelvis for other reasons. While CT is generally considered insufficient to diagnose PCa due to its inferior soft tissue characterisation, our evaluations on a relatively large dataset consisting of 139 clinically significant PCa patients and 432 controls show that the proposed deep neural network pipeline can detect csPCa patients at a level that is suitable for incidental detection. The proposed pipeline achieved an area under the receiver operating characteristic curve (ROC-AUC) of 0.88 (95% Confidence Interval: 0.86-0.90) at patient level csPCa detection on CT, significantly higher than the AUCs achieved by two radiologists (0.61 and 0.70) on the same task.