Computer-aided Detection Research Articles

Computer-aided detection of retinopathy of prematurity severity assessment via vessel tortuosity measurement in preterm infants' fundus images.

To develop a computer-aided diagnostic system for retinopathy of prematurity (ROP) disease using retinal vessel morphological features. A total of 200 fundus images from 136 preterm infants with stage 1 to 3 ROP were analysed. Two methods were developed to measure vessel tortuosity: the peak-and-valley method and the polynomial curve fitting method. Correlations between temporal artery tortuosity (TAT) and temporal vein tortuosity (TVT) with ROP severity were investigated, and vessel tortuosity relationships with vessel angles (TAA and TVA) and vessel widths (TAW and TVW). A separate dataset from Japan containing 126 images from 97 preterm patients was used for verification. Both methods identified similar tortuosity in images without ROP and mild ROP cases. However, the polynomial curve fit method demonstrated enhanced tortuosity detection in stages 2 and 3 ROP compared to the peak and valley method. A strong positive correlation was revealed between ROP severity and increased arterial and venous tortuosity (P < 0.0001). A significant negative correlation between TAA and TAT (r = -0.485, P < 0.0001) and TVA and TVT (r = -0.281, P < 0.0001), and a significant positive correlation between TAW and TAT (r = 0.204, P value = 0.0040) were identified. Similar results were found in the test dataset from Japan. ROP severity was associated with increased retinal tortuosity and retinal vessel width while displaying a decrease in retinal vascular angle. This quantitative analysis of retinal vessels provides crucial insights for advancing ROP diagnosis and understanding its progression.

Effect of artificial intelligence implementation to the latest generation 4K colonoscopy.

&lt;b&gt;Indroduction:&lt;/b&gt; Colonoscopy is an acclaimed screening test to detect colorectal cancer (CRC). The most important quality indicators for colonoscopy are adenoma detection rate (ADR), cecal intubation rate (CIR), withdrawal time (WT), and bowel preparation (Boston Bowel Preparation Scale; BBPS). In modern endoscopy practice, the human eye is enhanced by highdefinition white-light visualization and advanced imaging technology. The main limitation of this procedure is the detection rate of suspicious lesions. The next generation of endoscopes with 4K resolution and computer-aided detection (CADe) based on artificial intelligence (AI) may be the next step to improve the quality of tests performed.&lt;b&gt;Aim:&lt;/b&gt; The aim was to assess the effect of CADe implementation in the environment of the latest generation of endoscopes and 4K visualization in retrospective analysis.&lt;b&gt;Methods:&lt;/b&gt; The study included 2,000 patients over 18 years old who underwent colonoscopy for various indications. Olympus Endo-Aid CADe AI system was used, together with the latest X1 series endoscope set using LED lighting and 4K ultra high-resolution technology. Group I consisted of 1,000 consecutive tests performed using Endo-Aid CADe, and group II the first 1,000 consecutive tests without the CADe system. ADR, Advanced adenoma detection rate (AADR), polyp detection rate (PDR), and mean polyp per patient score (MPP) were assessed in each group&lt;b&gt;Results:&lt;/b&gt; A total of 2,000 participants were included in the analysis, divided into two groups regarding CADe implementation. The overall PDR was similar in the analyzed groups (AI: 46.7% &lt;i&gt;vs.&lt;/i&gt; non-AI: 44.9%, P = 0.419). Both ADR (29.7 &lt;i&gt;vs.&lt;/i&gt; 28.9%, P = 0.694) and AADR (6.9 &lt;i&gt;vs.&lt;/i&gt; 7.1%, P = 0.861) changed unremarkably. However, a significant elevation in MPP was noted. The MPP rose from 0.85 in the non-AI group to 1.26 in the AI group (P&lt;0.001). The comparative analysis conducted separately for each segment of the bowel revealed that PDR remarkably increased in the left colon (29.3 &lt;i&gt;vs.&lt;/i&gt; 18.0%, P&lt;0.001), with no difference for other segments and other parameters. Investigating the MPP separately in each segment showed a significant difference for the right colon (0.33 &lt;i&gt;vs.&lt;/i&gt; 0.23, P = 0.032) and the left colon (0.47 &lt;i&gt;vs.&lt;/i&gt; 0.28, P&lt;0.001). When adjusted to bowel preparation the PDR and MPP were constantly higher in the AI group (29.3 &lt;i&gt;vs.&lt;/i&gt; 19.0%, P&lt;0.001, and 0.48 &lt;i&gt;vs.&lt;/i&gt; 0.30, P&lt;0.001, respectively). In addition, the significant impact of AI implementation on MPP faded in the right colon (0.33 &lt;i&gt;vs.&lt;/i&gt; 0.24, P = 0.051) when compared with the overall analysis.&lt;b&gt;Conclusions:&lt;/b&gt; Although recently published evidence is optimistic regarding AI efficiency in improving the quality of colonoscopy, the provided results widen the overall perspective. Prospective randomized controlled trials (RCTs) including procedures performed with newest generation scopes should elucidate the role of AI in high-resolution colonoscopy.

Deep learning fusion framework for automated coronary artery disease detection using raw heart sound signals

One of the most common cardiovascular diseases is coronary artery disease (CAD). Thus, it is crucial for early CAD diagnosis to control disease progression. Computer-aided CAD detection often converts heart sounds into graphics for analysis. However, this method relies heavily on the subjective experience of experts. Therefore, in this study, we proposed a method for CAD detection using raw heart sound signals by constructing a fusion framework with two CAD detection models: a multidomain feature model and a medical multidomain feature fusion model. We collected heart sound signal datasets from 400 participants, extracting 206 multidomain features and 126 medical multidomain features. The designed framework fused the same one-dimensional deep learning features with different multidomain features for CAD detection. The experimental results showed that the multidomain feature model and the medical multidomain feature fusion model achieved areas under the curve (AUC) of 94.7 % and 92.7 %, respectively, demonstrating the effectiveness of the fusion framework in integrating one-dimensional and cross-domain heart sound features through deep learning algorithms, providing an effective solution for noninvasive CAD detection.

S2VQ-VAE: Semi-Supervised Vector Quantised-Variational AutoEncoder for Automatic Evaluation of Trail Making Test.

Computer-aided detection of cognitive impairment garnered increasing attention, offering older adults in the community access to more objective, ecologically valid, and convenient cognitive assessments using multimodal sensing technology on digital devices. In this study, we aimed to develop an automated method for screening cognitive impairment, building on paper- and electronic TMTs. We proposed a novel deep representation learning approach named Semi-Supervised Vector Quantised-Variational AutoEncoder (S2VQ-VAE). Within S2VQ-VAE, we incorporated intra- and inter-class correlation losses to disentangle class-related factors. These factors were then combined with various real-time obtainable features (including demographic, time-related, pressure-related, and jerk-related features) to create a robust feature engineering block. Finally, we identified the light gradient boosting machine as the optimal classifier. The experiments were conducted on a dataset collected from older adults in the community. The experimental results showed that the proposed multi-type feature fusion method outperformed the conventional method used in paper-based TMTs and the existing VAE-based feature extraction in terms of screening performance. In conclusion, the proposed deep representation learning method significantly enhances the cognitive diagnosis capabilities of behavior-based TMTs and streamlines large-scale community-based cognitive impairment screening while reducing the workload of professional healthcare staff.

A Hessian-Based Technique for Specular Reflection Detection and Inpainting in Colonoscopy Images.

In the field of Computer-Aided Detection (CADx), the use of AI-based algorithms for disease detection in endoscopy images, especially colonoscopy images, is on the rise. However, these algorithms often encounter performance issues due to obstructions like specular reflection, resulting in false positives. This paper presents a novel algorithm specifically designed to tackle the challenges posed by high specular reflection regions in colonoscopy images. The proposed algorithm identifies these regions and applies precise inpainting for restoration. The process entails converting the input image from RGB to HSV color space and focusing on the Saturation (S) component in convex regions detected using a Hessian-based method. This step creates a binary mask that pinpoints areas of specular reflection. The inpainting function then uses this mask to guide the restoration of these identified regions and their borders. To ensure a seamless blend of the restored regions with the background and adjacent pixels, a feathering process is applied to the repaired regions. This enhances both the accuracy and aesthetic coherence of the inpainted images. The performance of our algorithm was rigorously tested on five unique colonoscopy datasets and various endoscopy images from the Kvasir dataset, using an extensive set of evaluation metrics and a comparative analysis with existing methods consistently highlighted the superior performance of our algorithm.

Comparative Analysis of the Diagnostic Value of S-Detect Technology in Different Planes Versus the BI-RADS Classification for Breast Lesions

Rationale and ObjectivesS-Detect, a deep learning-based Computer-Aided Detection system, is recognized as an important tool for diagnosing breast lesions using ultrasound imaging.However,it may exhibit inconsistent findings across multiple imaging planes. This study aims to evaluate the diagnostic performance of S-Detect in different planes and identify factors contributing to these inconsistencies. Materials and MethodsA retrospective cohort study was conducted on 711 patients with 756 breast lesions between January 2019 and January 2022. S-Detect was utilized to assess lesions in radial and anti-radial planes. BI-RADS classifications were employed for comparative analysis.The diagnostic performance was compared within each group, and p-values were computed for intergroup comparisons. Univariable and multivariable analyses were conducted to identify factors contributing to diagnostic inconsistency in S-Detect across planes. ResultsAmong 756 breast lesions, 668 (88.4%) exhibited consistent S-Detect outcomes across planes while 88 (11.6%) were inconsistent. In the consistent group, the diagnostic accuracy and area under the curve (AUC) of S-Detect were significantly higher than those of BI-RADS (accuracy: 91.2% vs. 84.9%, p = 0.045; AUC: 0.916 vs. 0.859, p = 0.036). In the inconsistent group, the diagnostic accuracy and AUC of S-Detect in radial and anti-radial planes were lower than those of BI-RADS (accuracy: 47.7% for radial, 52.2% for anti-radial vs. 69.3% for BI-RADS, p = 0.014, p-anti = 0.039; AUC: 0.503 for radial, 0.497 for anti-radial vs. 0.739 for BI-RADS, p = 0.042, p-anti < 0.001). Diagnostic inconsistency in S-Detect across planes was significantly associated with lesion size, indistinct or angular margins, and enhancement posterior acoustic features(p< 0.05). ConclusionS-Detect has outperformed BI-RADS in diagnostic precision under conditions of inter-planar concordance. However, its diagnostic efficacy is compromised in scenarios of inter-planar discordance. Under these circumstances, the results of S-Detect should be carefully referenced.

Endoscopic Artificial Intelligence for Image Analysis in Gastrointestinal Neoplasms.

Artificial intelligence (AI) using deep learning systems has recently been utilized in various medical fields. In the field of gastroenterology, AI is primarily implemented in image recognition and utilized in the realm of gastrointestinal (GI) endoscopy. In GI endoscopy, computer-aided detection/diagnosis (CAD) systems assist endoscopists in GI neoplasm detection or differentiation of cancerous or noncancerous lesions. Several AI systems for colorectal polyps have already been applied in colonoscopy clinical practices. In esophagogastroduodenoscopy, a few CAD systems for upper GI neoplasms have been launched in Asian countries. The usefulness of these CAD systems in GI endoscopy has been gradually elucidated. In this review, we outline recent articles on several studies of endoscopic AI systems for GI neoplasms, focusing on esophageal squamous cell carcinoma (ESCC), esophageal adenocarcinoma (EAC), gastric cancer (GC), and colorectal polyps. In ESCC and EAC, computer-aided detection (CADe) systems were mainly developed, and a recent meta-analysis study showed sensitivities of 91.2% and 93.1% and specificities of 80% and 86.9%, respectively. In GC, a recent meta-analysis study on CADe systems demonstrated that their sensitivity and specificity were as high as 90%. A randomized controlled trial (RCT) also showed that the use of the CADe system reduced the miss rate. Regarding computer-aided diagnosis (CADx) systems for GC, although RCTs have not yet been conducted, most studies have demonstrated expert-level performance. In colorectal polyps, multiple RCTs have shown the usefulness of the CADe system for improving the polyp detection rate, and several CADx systems have been shown to have high accuracy in colorectal polyp differentiation. Most analyses of endoscopic AI systems suggested that their performance was better than that of nonexpert endoscopists and equivalent to that of expert endoscopists. Thus, endoscopic AI systems may be useful for reducing the risk of overlooking lesions and improving the diagnostic ability of endoscopists.

Investigation of distributed learning for automated lesion detection in head MR images

In this study, we investigated the application of distributed learning, including federated learning and cyclical weight transfer, in the development of computer-aided detection (CADe) software for (1) cerebral aneurysm detection in magnetic resonance (MR) angiography images and (2) brain metastasis detection in brain contrast-enhanced MR images. We used datasets collected from various institutions, scanner vendors, and magnetic field strengths for each target CADe software. We compared the performance of multiple strategies, including a centralized strategy, in which software development is conducted at a development institution after collecting de-identified data from multiple institutions. Our results showed that the performance of CADe software trained through distributed learning was equal to or better than that trained through the centralized strategy. However, the distributed learning strategies that achieved the highest performance depend on the target CADe software. Hence, distributed learning can become one of the strategies for CADe software development using data collected from multiple institutions.

Validation of a commercially available CAD-system for lung nodule detection and characterization using CT-scans.

This study aims to externally validate a commercially available Computer-Aided Detection (CAD)-system for the automatic detection and characterization of solid, part-solid, and ground-glass lung nodules (LN) on CT scans. This retrospective study encompasses 263 chest CT scans performed between January 2020 and December 2021 at a Dutch university hospital. All scans were read by a radiologist (R1) and compared with the initial radiology report. Conflicting scans were assessed by an adjudicating radiologist (R2). All scans were also processed by CAD. The standalone performance of CAD in terms of sensitivity and false-positive (FP)-rate for detection was calculated together with the sensitivity for characterization, including texture, calcification, speculation, and location. The R1's detection sensitivity was also assessed. A total of 183 true nodules were identified in 121 nodule-containing scans (142 non-nodule-containing scans), of which R1 identified 165/183 (90.2%). CAD detected 149 nodules, of which 12 were not identified by R1, achieving a sensitivity of 149/183 (81.4%) with an FP-rate of 49/121 (0.405). CAD's detection sensitivity for solid, part-solid, and ground-glass LNs was 82/94 (87.2%), 42/47 (89.4%), and 25/42 (59.5%), respectively. The classification accuracy for solid, part-solid, and ground-glass LNs was 81/82 (98.8%), 16/42 (38.1%), and 18/25 (72.0%), respectively. Additionally, CAD demonstrated overall classification accuracies of 137/149 (91.9%), 123/149 (82.6%), and 141/149 (94.6%) for calcification, spiculation, and location, respectively. Although the overall detection rate of this system slightly lags behind that of a radiologist, CAD is capable of detecting different LNs and thereby has the potential to enhance a reader's detection rate. While promising characterization performances are obtained, the tool's performance in terms of texture classification remains a subject of concern. Numerous lung nodule computer-aided detection-systems are commercially available, with some of them solely being externally validated based on their detection performance on solid nodules. We encourage researchers to assess performances by incorporating all relevant characteristics, including part-solid and ground-glass nodules. Few computer-aided detection (CAD) systems are externally validated for automatic detection and characterization of lung nodules. A detection sensitivity of 81.4% and an overall texture classification sensitivity of 77.2% were measured utilizing CAD. CAD has the potential to increase single reader detection rate, however, improvement in texture classification is required.

Multi-class Breast Cancer Classification Using CNN Features Hybridization

Breast cancer has become the leading cause of cancer mortality among women worldwide. The timely diagnosis of such cancer is always in demand among researchers. This research pours light on improving the design of computer-aided detection (CAD) for earlier breast cancer classification. Meanwhile, the design of CAD tools using deep learning is becoming popular and robust in biomedical classification systems. However, deep learning gives inadequate performance when used for multilabel classification problems, especially if the dataset has an uneven distribution of output targets. And this problem is prevalent in publicly available breast cancer datasets. To overcome this, the paper integrates the learning and discrimination ability of multiple convolution neural networks such as VGG16, VGG19, ResNet50, and DenseNet121 architectures for breast cancer classification. Accordingly, the approach of fusion of hybrid deep features (FHDF) is proposed to capture more potential information and attain improved classification performance. This way, the research utilizes digital mammogram images for earlier breast tumor detection. The proposed approach is evaluated on three public breast cancer datasets: mammographic image analysis society (MIAS), curated breast imaging subset of digital database for screening mammography (CBIS-DDSM), and INbreast databases. The attained results are then compared with base convolutional neural networks (CNN) architectures and the late fusion approach. For MIAS, CBIS-DDSM, and INbreast datasets, the proposed FHDF approach provides maximum performance of 98.706%, 97.734%, and 98.834% of accuracy in classifying three classes of breast cancer severities.

Identification of Glaucoma from Retinal Fundus Images using Deep Learning Model, MobileNet

Glaucoma is one of the leading causes of permanent vision impairment and blindness everywhere in the world due to high intraocular stress inside the eyes. So, early and accurate detection is crucial for preventing irreversible vision loss. Manual recognition of Glaucoma is a difficult task that requires proficiency and a highly experienced person. Computer Aided Detection (CAD) techniques assist ophthalmologists in the detection of such ophthalmologic diseases by analyzing the retinal fundus images. Deep learning(DL) algorithms have accomplished exceptionally in various computer vision applications by giving them an apparent advantage over more traditional techniques by analyzing the retinal fundus images. In this paper, a pre-trained Convolutional Neural Network, MobileNet, is used to detect Glaucoma in retinal fundus images by automatically extracting the features rather than manually classifying fundus images. Due to efficiency, speed of execution, accuracy, customizability, transfer learning, real-time applications and size of the architecture, MobileNet is proposed here. The DrishtiGS, EyePACS AIROGS-Light, BEH, REFUGE, sjchoi86- HRF, CRFO-v4, G1020, FIVES, and PAPILA datasets were utilized in this study. The suggested model is evaluated by significant factors such as accuracy, precision, sensitivity, specificity, F1 score, and Confusion Matrix to examine the model's efficacy. These studies reveal the capability of the DL approach to classify Glaucoma from retinal fundus images and recommend that the suggested approach can assist ophthalmologists in a quick, correct, and dependable diagnosis of Glaucoma.

An artificial intelligence-assisted system versus white light endoscopy alone for adenoma detection in individuals with Lynch syndrome (TIMELY): an international, multicentre, randomised controlled trial

Computer-aided detection (CADe) systems for colonoscopy have been shown to increase small polyp detection during colonoscopy in the general population. People with Lynch syndrome represent an ideal target population for CADe-assisted colonoscopy because adenomas, the primary cancer precursor lesions, are characterised by their small size and higher likelihood of showing advanced histology. We aimed to evaluate the performance of CADe-assisted colonoscopy in detecting adenomas in individuals with Lynch syndrome. TIMELY was an international, multicentre, parallel, randomised controlled trial done in 11 academic centres and six community centres in Belgium, Germany, Italy, and Spain. We enrolled individuals aged 18 years or older with pathogenic or likely pathogenic MLH1, MSH2, MSH6, or EPCAM variants. Participants were consecutively randomly assigned (1:1) to either CADe (GI Genius) assisted white light endoscopy (WLE) or WLE alone. A centre-stratified randomisation sequence was generated through a computer-generated system with a separate randomisation list for each centre according to block-permuted randomisation (block size 26 patients per centre). Allocation was automatically provided by the online AEG-REDCap database. Participants were masked to the random assignment but endoscopists were not. The primary outcome was the mean number of adenomas per colonoscopy, calculated by dividing the total number of adenomas detected by the total number of colonoscopies and assessed in the intention-to-treat population. This trial is registered with ClinicalTrials.gov, NCT04909671. Between Sept 13, 2021, and April 6, 2023, 456 participants were screened for eligibility, 430 of whom were randomly assigned to receive CADe-assisted colonoscopy (n=214) or WLE (n=216). 256 (60%) participants were female and 174 (40%) were male. In the intention-to-treat analysis, the mean number of adenomas per colonoscopy was 0·64 (SD 1·57) in the CADe group and 0·64 (1·17) in the WLE group (adjusted rate ratio 1·03 [95% CI 0·72-1·47); p=0·87). No adverse events were reported during the trial. In this multicentre international trial, CADe did not improve the detection of adenomas in individuals with Lynch syndrome. High-quality procedures and thorough inspection and exposure of the colonic mucosa remain the cornerstone in surveillance of Lynch syndrome. Spanish Gastroenterology Association, Spanish Society of Digestive Endoscopy, European Society of Gastrointestinal Endoscopy, Societat Catalana de Digestologia, Instituto Carlos III, Beca de la Marato de TV3 2020. Co-funded by the European Union.

Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software

Computer-aided detection (CAD) can help identify people with active tuberculosis left undetected. However, few studies have compared the performance of commercially available CAD products for screening in high tuberculosis and high HIV settings, and there is poor understanding of threshold selection across products in different populations. We aimed to compare CAD products' performance, with further analyses on subgroup performance and threshold selection. We evaluated 12 CAD products on a case-control sample of participants from a South African tuberculosis prevalence survey. Only those with microbiological test results were eligible. The primary outcome was comparing products' accuracy using the area under the receiver operating characteristic curve (AUC) against microbiological evidence. Threshold analyses were performed based on pre-defined criteria and across all thresholds. We conducted subgroup analyses including age, gender, HIV status, previous tuberculosis history, symptoms presence, and current smoking status. Of the 774 people included, 516 were bacteriologically negative and 258 were bacteriologically positive. Diverse accuracy was noted: Lunit and Nexus had AUCs near 0·9, followed by qXR, JF CXR-2, InferRead, Xvision, and ChestEye (AUCs 0·8-0·9). XrayAME, RADIFY, and TiSepX-TB had AUC under 0·8. Thresholds varied notably across these products and different versions of the same products. Certain products (Lunit, Nexus, JF CXR-2, and qXR) maintained high sensitivity (>90%) across a wide threshold range while reducing the number of individuals requiring confirmatory diagnostic testing. All products generally performed worst in older individuals, people with previous tuberculosis, and people with HIV. Variations in thresholds, sensitivity, and specificity existed across groups and settings. Several previously unevaluated products performed similarly to those evaluated by WHO. Thresholds differed across products and demographic subgroups. The rapid emergence of products and versions necessitates a global strategy to validate new versions and software to support CAD product and threshold selections. Government of Canada.

Mass detection in automated three dimensional breast ultrasound using cascaded convolutional neural networks

PurposeEarly detection of breast cancer has a significant effect on reducing its mortality rate. For this purpose, automated three-dimensional breast ultrasound (3-D ABUS) has been recently used alongside mammography. The 3-D volume produced in this imaging system includes many slices. The radiologist must review all the slices to find the mass, a time-consuming task with a high probability of mistakes. Therefore, many computer-aided detection (CADe) systems have been developed to assist radiologists in this task. In this paper, we propose a novel CADe system for mass detection in 3-D ABUS images. MethodsThe proposed system includes two cascaded convolutional neural networks. The goal of the first network is to achieve the highest possible sensitivity, and the second network’s goal is to reduce false positives while maintaining high sensitivity. In both networks, an improved version of 3-D U-Net architecture is utilized in which two types of modified Inception modules are used in the encoder section. In the second network, new attention units are also added to the skip connections that receive the results of the first network as saliency maps. ResultsThe system was evaluated on a dataset containing 60 3-D ABUS volumes from 43 patients and 55 masses. A sensitivity of 91.48% and a mean false positive of 8.85 per patient were achieved. ConclusionsThe suggested mass detection system is fully automatic without any user interaction. The results indicate that the sensitivity and the mean FP per patient of the CADe system outperform competing techniques.

Prior tuberculosis, radiographic lung abnormalities and prevalent diabetes in rural South Africa

BackgroundGrowing evidence suggests that chronic inflammation caused by tuberculosis (TB) may increase the incidence of diabetes. However, the relationship between post-TB pulmonary abnormalities and diabetes has not been well characterized.MethodsWe analyzed data from a cross-sectional study in KwaZulu-Natal, South Africa, of people 15 years and older who underwent chest X-ray and diabetes screening with hemoglobin A1c testing. The analytic sample was restricted to persons with prior TB, defined by either (1) a self-reported history of TB treatment, (2) radiologist-confirmed prior TB on chest radiography, and (3) a negative sputum culture and GeneXpert. Chest X-rays of all participants were evaluated by the study radiologist to determine the presence of TB lung abnormalities. To assess the relationships between our outcome of interest, prevalent diabetes (HBA1c ≥6.5%), and our exposure of interest, chest X-ray abnormalities, we fitted logistic regression models adjusted for potential clinical and demographic confounders. In secondary analyses, we used the computer-aided detection system CAD4TB, which scores X-rays from 10 to 100 for detection of TB disease, as our exposure interest, and repeated analyses with a comparator group that had no history of TB disease.ResultsIn the analytic cohort of people with prior TB (n = 3,276), approximately two-thirds (64.9%) were women, and the average age was 50.8 years (SD 17.4). The prevalence of diabetes was 10.9%, and 53.0% of people were living with HIV. In univariate analyses, there was no association between diabetes prevalence and radiologist chest X-ray abnormalities (OR 1.23, 95%CI 0.95–1.58). In multivariate analyses, the presence of pulmonary abnormalities was associated with an 29% reduction in the odds of prevalent diabetes (aOR 0.71, 95%CI 0.53–0.97, p = 0.030). A similar inverse relationship was observed for diabetes with each 10-unit increase in the CAD4TB chest X-ray scores among people with prior TB (aOR 0.92, 95%CI 0.87–0.97; p = 0.002), but this relationship was less pronounced in the no TB comparator group (aOR 0.96, 95%CI 0.94–0.99).ConclusionsAmong people with prior TB, pulmonary abnormalities on digital chest X-ray are inversely associated with prevalent diabetes. The severity of radiographic post-TB lung disease does not appear to be a determinant of diabetes in this South African population.

Greater benefits of deep learning-based computer-aided detection systems for finding small signals in 3D volumetric medical images.

Radiologists are tasked with visually scrutinizing large amounts of data produced by 3D volumetric imaging modalities. Small signals can go unnoticed during the 3D search because they are hard to detect in the visual periphery. Recent advances in machine learning and computer vision have led to effective computer-aided detection (CADe) support systems with the potential to mitigate perceptual errors. Sixteen nonexpert observers searched through digital breast tomosynthesis (DBT) phantoms and single cross-sectional slices of the DBT phantoms. The 3D/2D searches occurred with and without a convolutional neural network (CNN)-based CADe support system. The model provided observers with bounding boxes superimposed on the image stimuli while they looked for a small microcalcification signal and a large mass signal. Eye gaze positions were recorded and correlated with changes in the area under the ROC curve (AUC). The CNN-CADe improved the 3D search for the small microcalcification signal ( , ) and the 2D search for the large mass signal ( , ). The CNN-CADe benefit in 3D for the small signal was markedly greater than in 2D ( , ). Analysis of individual differences suggests that those who explored the least with eye movements benefited the most from the CNN-CADe ( , ). However, for the large signal, the 2D benefit was not significantly greater than the 3D benefit ( , ). The CNN-CADe brings unique performance benefits to the 3D (versus 2D) search of small signals by reducing errors caused by the underexploration of the volumetric data.

Deep Learning-Based Localization and Detection of Malpositioned Nasogastric Tubes on Portable Supine Chest X-Rays in Intensive Care and Emergency Medicine: A Multi-center Retrospective Study.

Malposition of a nasogastric tube (NGT) can lead to severe complications. We aimed to develop a computer-aided detection (CAD) system to localize NGTs and detect NGT malposition on portable chest X-rays (CXRs). A total of 7378 portable CXRs were retrospectively retrieved from two hospitals between 2015 and 2020. All CXRs were annotated with pixel-level labels for NGT localization and image-level labels for NGT presence and malposition. In the CAD system, DeepLabv3 + with backbone ResNeSt50 and DenseNet121 served as the model architecture for segmentation and classification models, respectively. The CAD system was tested on images from chronologically different datasets (National Taiwan University Hospital (National Taiwan University Hospital)-20), geographically different datasets (National Taiwan University Hospital-Yunlin Branch (YB)), and the public CLiP dataset. For the segmentation model, the Dice coefficients indicated accurate delineation of the NGT course (National Taiwan University Hospital-20: 0.665, 95% confidence interval (CI) 0.630-0.696; National Taiwan University Hospital-Yunlin Branch: 0.646, 95% CI 0.614-0.678). The distance between the predicted and ground-truth NGT tips suggested accurate tip localization (National Taiwan University Hospital-20: 1.64 cm, 95% CI 0.99-2.41; National Taiwan University Hospital-Yunlin Branch: 2.83 cm, 95% CI 1.94-3.76). For the classification model, NGT presence was detected with high accuracy (area under the receiver operating characteristic curve (AUC): National Taiwan University Hospital-20: 0.998, 95% CI 0.995-1.000; National Taiwan University Hospital-Yunlin Branch: 0.998, 95% CI 0.995-1.000; CLiP dataset: 0.991, 95% CI 0.990-0.992). The CAD system also detected NGT malposition with high accuracy (AUC: National Taiwan University Hospital-20: 0.964, 95% CI 0.917-1.000; National Taiwan University Hospital-Yunlin Branch: 0.991, 95% CI 0.970-1.000) and detected abnormal nasoenteric tube positions with favorable performance (AUC: 0.839, 95% CI 0.807-0.869). The CAD system accurately localized NGTs and detected NGT malposition, demonstrating excellent potential for external generalizability.

Pulmonary nodule detection in low dose computed tomography using a medical-to-medical transfer learning approach.

Lung cancer is the second most common cancer and the leading cause of cancer death globally. Low dose computed tomography (LDCT) is the recommended imaging screening tool for the early detection of lung cancer. A fully automated computer-aided detection method for LDCT will greatly improve the existing clinical workflow. Most of the existing methods for lung detection are designed for high-dose CTs (HDCTs), and those methods cannot be directly applied to LDCTs due to domain shifts and inferior quality of LDCT images. In this work, we describe a semi-automated transfer learning-based approach for the early detection of lung nodules using LDCTs. In this work, we developed an algorithm based on the object detection model, you only look once (YOLO) to detect lung nodules. The YOLO model was first trained on CTs, and the pre-trained weights were used as initial weights during the retraining of the model on LDCTs using a medical-to-medical transfer learning approach. The dataset for this study was from a screening trial consisting of LDCTs acquired from 50 biopsy-confirmed lung cancer patients obtained over 3 consecutive years (T1, T2, and T3). About 60 lung cancer patients' HDCTs were obtained from a public dataset. The developed model was evaluated using a hold-out test set comprising 15 patient cases (93 slices with cancerous nodules) using precision, specificity, recall, and F1-score. The evaluation metrics were reported patient-wise on a per-year basis and averaged for 3 years. For comparative analysis, the proposed detection model was trained using pre-trained weights from the COCO dataset as the initial weights. A paired t-test and chi-squared test with an alpha value of 0.05 were used for statistical significance testing. The results were reported by comparing the proposed model developed using HDCT pre-trained weights with COCO pre-trained weights. The former approach versus the latter approach obtained a precision of 0.982 versus 0.93 in detecting cancerous nodules, specificity of 0.923 versus 0.849 in identifying slices with no cancerous nodules, recall of 0.87 versus 0.886, and F1-score of 0.924 versus 0.903. As the nodule progressed, the former approach achieved a precision of 1, specificity of 0.92, and sensitivity of 0.930. The statistical analysis performed in the comparative study resulted in a -value of 0.0054 for precision and a -value of 0.00034 for specificity. In this study, a semi-automated method was developed to detect lung nodules in LDCTs using HDCT pre-trained weights as the initial weights and retraining the model. Further, the results were compared by replacing HDCT pre-trained weights in the above approach with COCO pre-trained weights. The proposed method may identify early lung nodules during the screening program, reduce overdiagnosis and follow-ups due to misdiagnosis in LDCTs, start treatment options in the affected patients, and lower the mortality rate.

Utilizing Deep Feature Fusion for Automatic Leukemia Classification: An Internet of Medical Things-Enabled Deep Learning Framework.

Acute lymphoblastic leukemia, commonly referred to as ALL, is a type of cancer that can affect both the blood and the bone marrow. The process of diagnosis is a difficult one since it often calls for specialist testing, such as blood tests, bone marrow aspiration, and biopsy, all of which are highly time-consuming and expensive. It is essential to obtain an early diagnosis of ALL in order to start therapy in a timely and suitable manner. In recent medical diagnostics, substantial progress has been achieved through the integration of artificial intelligence (AI) and Internet of Things (IoT) devices. Our proposal introduces a new AI-based Internet of Medical Things (IoMT) framework designed to automatically identify leukemia from peripheral blood smear (PBS) images. In this study, we present a novel deep learning-based fusion model to detect ALL types of leukemia. The system seamlessly delivers the diagnostic reports to the centralized database, inclusive of patient-specific devices. After collecting blood samples from the hospital, the PBS images are transmitted to the cloud server through a WiFi-enabled microscopic device. In the cloud server, a new fusion model that is capable of classifying ALL from PBS images is configured. The fusion model is trained using a dataset including 6512 original and segmented images from 89 individuals. Two input channels are used for the purpose of feature extraction in the fusion model. These channels include both the original and the segmented images. VGG16 is responsible for extracting features from the original images, whereas DenseNet-121 is responsible for extracting features from the segmented images. The two output features are merged together, and dense layers are used for the categorization of leukemia. The fusion model that has been suggested obtains an accuracy of 99.89%, a precision of 99.80%, and a recall of 99.72%, which places it in an excellent position for the categorization of leukemia. The proposed model outperformed several state-of-the-art Convolutional Neural Network (CNN) models in terms of performance. Consequently, this proposed model has the potential to save lives and effort. For a more comprehensive simulation of the entire methodology, a web application (Beta Version) has been developed in this study. This application is designed to determine the presence or absence of leukemia in individuals. The findings of this study hold significant potential for application in biomedical research, particularly in enhancing the accuracy of computer-aided leukemia detection.

Patient and procedural factors associated with true histology rates in patients undergoing colonoscopy with computer-aided detection of polyps

Computer-aided detection (CADe) devices have been shown to increase adenoma detection rates and adenomas per colonoscopy compared to standard colonoscopies. Questions remain about whether CADe colonoscopies are mainly increasing the detection of small, nonneoplastic lesions or if they are detecting more pathologically meaningful polyps. In this analysis, we compare the true histology rate (defined as polyps with confirmation of clinically relevant histopathology) of CADe-identified polyps with polyps identified during standard colonoscopies. Using data from the SKOUT trial, we compared the true histology rate (THR) between CADe and standard colonoscopies. We also conducted a subgroup analysis by patient, procedural, and endoscopist factors. To account for multiple testing of comparisons, we used the false discovery rate. A total of 1423 participants were included (CADe, n= 714; standard, n= 709). Overall, THR was similar between the CADe and standard colonoscopy arms for adenomas, sessile serrated lesions, and large hyperplastic polyps. Higher THR with CADe colonoscopy was observed in some subgroups for adenomas. Endoscopists with 11 to 20 years of experience and procedures occurring after 12 pm had significantly higher adenoma THRs in the CADe cohort. Patients younger than 65 years, male patients, and procedures with a withdrawal time of≥8 minutes had borderline significance in the CADe device adenoma THR subgroup. CADe colonoscopies may hold the key to improving endoscopic quality measures, provided that the polyps identified by the CADe device are those of clinical relevance. Although the benefit and significance in the CADe group were demonstrated in this analysis, further research is warranted to ensure that the true histology is maintained when applied in real-world applications.