AI-enabled POCUS for breast cancer risk stratification in a resource-limited tertiary clinic

BackgroundDiffusion-weighted imaging (DWI) can increase breast MRI diagnostic specificity due to the tendency of malignancies to restrict diffusion. Diffusion tensor imaging (DTI) provides further information over conventional DWI regarding diffusion directionality and anisotropy. Our study evaluates DTI features of suspicious breast lesions detected on MRI to determine the added diagnostic value of DTI for breast imaging.MethodsWith IRB approval, we prospectively enrolled patients over a 3-year period who had suspicious (BI-RADS category 4 or 5) MRI-detected breast lesions with histopathological results. Patients underwent multiparametric 3 T MRI with dynamic contrast-enhanced (DCE) and DTI sequences. Clinical factors (age, menopausal status, breast density, clinical indication, background parenchymal enhancement) and DCE-MRI lesion parameters (size, type, presence of washout, BI-RADS category) were recorded prospectively by interpreting radiologists. DTI parameters (apparent diffusion coefficient [ADC], fractional anisotropy [FA], axial diffusivity [λ1], radial diffusivity [(λ2 + λ3)/2], and empirical difference [λ1 − λ3]) were measured retrospectively. Generalized estimating equations (GEE) and least absolute shrinkage and selection operator (LASSO) methods were used for univariate and multivariate logistic regression, respectively. Diagnostic performance was internally validated using the area under the curve (AUC) with bootstrap adjustment.ResultsThe study included 238 suspicious breast lesions (95 malignant, 143 benign) in 194 women. In univariate analysis, lower ADC, axial diffusivity, and radial diffusivity were associated with malignancy (OR = 0.37–0.42 per 1-SD increase, p < 0.001 for each), as was higher FA (OR = 1.45, p = 0.007). In multivariate analysis, LASSO selected only ADC (OR = 0.41) as a predictor for a DTI-only model, while both ADC (OR = 0.41) and FA (OR = 0.88) were selected for a model combining clinical and imaging parameters. Post-hoc analysis revealed varying association of FA with malignancy depending on the lesion type. The combined model (AUC = 0.81) had a significantly better performance than Clinical/DCE-MRI-only (AUC = 0.76, p < 0.001) and DTI-only (AUC = 0.75, p = 0.002) models.ConclusionsDTI significantly improves diagnostic performance in multivariate modeling. ADC is the most important diffusion parameter for distinguishing benign and malignant breast lesions, while anisotropy measures may help further characterize tumor microstructure and microenvironment.

Time-dependent diffusion MRI and kinetic heterogeneity as potential imaging biomarkers for diagnosing suspicious breast lesions with 3.0-T breast MRI.

Background: Chest imaging, including chest X-ray (CXR) and computed tomography (CT), can be a helpful adjunct to nucleic acid test (NAT) in the diagnosis and management of Coronavirus Disease 2019 (COVID-19). Lung point of care ultrasound (POCUS), particularly with handheld devices, is an imaging alternative that is rapid, highly portable, and more accessible in low-resource settings. A standardized POCUS scanning protocol has been proposed to assess the severity of COVID-19 pneumonia, but it has not been sufficiently validated to assess diagnostic accuracy for COVID-19 pneumonia. Purpose: To assess the diagnostic performance of a standardized lung POCUS protocol using a handheld POCUS device to detect patients with either a positive NAT or a COVID-19-typical pattern on CT scan. Methods: Adult inpatients with confirmed or suspected COVID-19 and a recent CT were recruited from April to July 2020. Twelve lung zones were scanned with a handheld POCUS machine. Images were reviewed independently by blinded experts and scored according to the proposed protocol. Patients were divided into low, intermediate, and high suspicion based on their POCUS score. Results: Of 79 subjects, 26.6% had a positive NAT and 31.6% had a typical CT pattern. The receiver operator curve for POCUS had an area under the curve (AUC) of 0.787 for positive NAT and 0.820 for a typical CT. Using a two-point cutoff system, POCUS had a sensitivity of 0.90 and 1.00 compared to NAT and typical CT pattern, respectively, at the lower cutoff; it had a specificity of 0.90 and 0.89 compared to NAT and typical CT pattern at the higher cutoff, respectively. Conclusions: The proposed lung POCUS protocol with a handheld device showed reasonable diagnostic performance to detect inpatients with a positive NAT or typical CT pattern for COVID-19. Particularly in low-resource settings, POCUS with handheld devices may serve as a helpful adjunct for persons under investigation for COVID-19 pneumonia.

Impact of Sarcopenia Diagnosed by Point-of-Care Ultrasound on Geriatric Rehabilitation Outcomes: A Prospective Cohort Study.

ObjectiveTo analyze primary angle closure suspect (PACS) patients’ anatomical characteristics of anterior chamber configuration, and to establish artificial intelligence (AI)-aided diagnostic system for PACS screening.MethodsA total of 1668 scans of 839 patients were included in this cross-sectional study. The subjects were divided into two groups: PACS group and normal group. With anterior segment optical coherence tomography scans, the anatomical diversity between two groups was compared, and anterior segment structure features of PACS were extracted. Then, AI-aided diagnostic system was constructed, which based different algorithms such as classification and regression tree (CART), random forest (RF), logistic regression (LR), VGG-16 and Alexnet. Then the diagnostic efficiencies of different algorithms were evaluated, and compared with junior physicians and experienced ophthalmologists.ResultsRF [sensitivity (Se) = 0.84; specificity (Sp) = 0.92; positive predict value (PPV) = 0.82; negative predict value (NPV) = 0.95; area under the curve (AUC) = 0.90] and CART (Se = 0.76, Sp = 0.93, PPV = 0.85, NPV = 0.92, AUC = 0.90) showed better performance than LR (Se = 0.68, Sp = 0.91, PPV = 0.79, NPV = 0.90, AUC = 0.86). In convolutional neural networks (CNN), Alexnet (Se = 0.83, Sp = 0.95, PPV = 0.92, NPV = 0.87, AUC = 0.85) was better than VGG-16 (Se = 0.84, Sp = 0.90, PPV = 0.85, NPV = 0.90, AUC = 0.79). The performance of 2 CNN algorithms was better than 5 junior physicians, and the mean value of diagnostic indicators of 2 CNN algorithm was similar to experienced ophthalmologists.ConclusionPACS patients have distinct anatomical characteristics compared with health controls. AI models for PACS screening are reliable and powerful, equivalent to experienced ophthalmologists.

Hip fractures are among the most morbid acute orthopaedic injuries often due to accompanying patient frailty. The purpose of this study was to determine the reliability of assessing surgical risk after hip fracture through machine learning (ML) algorithms. The American College of Surgeons National Surgical Quality Improvement Program was queried from 2011 to 2018 and the American College of Surgeons National Surgical Quality Improvement Program hip fracture-targeted data set was queried from 2016 to 2018 for all patients undergoing surgical fixation for a diagnosis of an acute primary hip fracture. The data set was randomly split into training (80%) and testing (20%) sets. 3 ML algorithms were used to train models in the prediction of extended hospital length of stay (LOS) >13 days, death, readmissions, home discharge, transfusion, and any medical complication. Testing sets were assessed by receiver operating characteristic, positive predictive value (PPV), and negative predictive value (NPV) and were compared with models constructed from legacy comorbidity indices such as American Society of Anesthesiologists (ASA) score, modified Charlson Comorbidity Index, frailty index, and Nottingham Hip Fracture Score. Following inclusion/exclusion criteria, 95,745 cases were available in the overall data set and 22,344 in the targeted data set. ML models outperformed comorbidity indices for each complication by area under the curve (AUC) analysis ( P < 0.01 for each): medical complications (AUC=0.65, PPV=67.5, NPV=71.7), death (AUC=0.80, PPV=46.7, NPV=94.9), extended LOS (AUC=0.69, PPV=71.4, NPV=94.1), transfusion (AUC=0.79, PPV=64.2, NPV=77.4), readmissions (AUC=0.63, PPV=0, NPV=96.8), and home discharge (AUC=0.74, PPV=65.9, NPV=76.7). In comparison, the best performing legacy index for each complication was medical complication (ASA: AUC=0.60), death (NHFS: AUC=0.70), extended LOS (ASA: AUC=0.62), transfusion (ASA: AUC=0.57), readmissions (CCI: AUC=0.58), and home discharge (ASA: AUC=0.61). ML algorithms offer an improved method to holistically calculate preoperative risk of patient morbidity, mortality, and discharge destination. Through continued validation, risk calculators using these algorithms may inform medical decision making to providers and payers.

Study question What is CHLOE’s (Fairtility) efficacy of prediction of blastulation (at 30hpi), pregnancy and ongoing clinical pregnancy following single embryo transfer (SET)? Summary answer CHLOE(Fairtility) algorithms are effective predictors of blastulation, ploidy, pregnancy, implantation and ongoing clinical pregnancy What is known already Time-lapse incubators have increased the amount of information available to the embryologist to help determine the fate of embryos. This has led to differences in clinical practice between clinics in how this information is prioritised. Moreover, inter-operator inconsistencies and the time-consuming nature of manually annotating time-lapse videos are challenges currently experienced by time-lapse users that can be relieved with Artificial Intelligence(AI) tools, such as CHLOE(Fairtility). CHLOE levergaes AI-based predictors to predict blastulation and implantation, whilst providing transparency to which biological characteristics have led to that determination. There is a need to validate AI tools before their incorporation into clinical practice. Study design, size, duration This was a single centre study that took place between 2017-2020, at Istanbul Memorial Sisli Hospital in Turkey, ART and Center. This was a retrospective cohort analysis that reviewed 6748 time-lapse videos containing 5392 cleaved embryos, 3763 blastocysts, 877 single embryo transfers(SET) with known ongoing pregnancy outcome (KOPO), 306 euploid SETs and 25 mosaic embryo SETs with KOPO. CHLOE blastocyst and implantation score efficacy of prediction of clinical outcomes was quantified using the metric AUC. Participants/materials, setting, methods Time-lapse videos were assessed using CHLOE(Fairtility), an AI based tool, to quantify quantitative and qualitative morphokinetics (including automated annotations of tPNa,tPNf,t2,t3,t4,t5,t6,t7,t8,t9,tM,tSB,tB,tEB), CHLOE implantation score and CHLOE blastocyst score (calculated at 30hpi) relative to laboratory (ploidy results, blastulation) and clinical outcomes (biochemical, clinical and ongoing pregnancy) following overall SET. Binary logistic regression was used to calculate area under the curve (AUC) as a measure of prediction efficacy. Main results and the role of chance Blastulation score assessment of cleaved embryos was predictive of blastulation (AUC=0.96, baseline=70% n = 5392, p &amp;lt; 0.001). Following PGT-A, implantation score was predictive of euploids (AUC=0.61, baseline=34%, n = 1456, p &amp;lt; 0.001), but not of embryos classified as mosaics (AUC=0.5, baseline=19%, n = 1456, p &amp;gt; 0.05). Following SET, implantation score was predictive of biochemical (AUC=0.71, baseline=49%, n = 866, p &amp;lt; 0.001), clinical and ongoing pregnancy rate (AUC=0.69, baseline=37%, n = 866, p &amp;lt; 0.001). Following SET of non-PGT-A embryos, implantation score decreased with increasing patient age (p &amp;lt; 0.001). The type of aneuploidy (such as monosomy, trisomy, segmental) did not affect implantation score or blastulation score (p &amp;gt; 0.05). Implantation score prediction of outcome was higher for non-PGT-A transfers than overall transfers for biochemical (Non-PGTA: AUC=0.73, baseline=33%, n = 535, p &amp;lt; 0.001; OVERALL: AUC=0.71, baseline=49%, n = 866, p &amp;lt; 0.001), clinical and ongoing pregnancy (Non-PGTA: AUC=0.76, baseline=24%, n = 535, p &amp;lt; 0.001; OVERALL: AUC=0.69, baseline=37%, n = 866, p &amp;lt; 0.001), despite lower baselines. Limitations, reasons for caution This is a single centre study, using retrospective data where embryos were selected for transfer by human embryologists. Despite the data has heterogeneity in terms of clinical features, the study is part of a larger framework for responsible incorporation of AI into clinical practice through robust validation. Wider implications of the findings AI-based tools have the potential of increasing consistency, efficiency and efficacy of embryo selection. The additional information on quantitative and qualitative morphokinetics that AI tools such as CHLOE provide, bring transparency to the prediction, allowing for improvement in personalisation of care down to each individual embryo. Trial registration number None

Introduction: In Canada, family physicians (FPs) provide the majority of early pregnancy care. To receive a same day US, most patients will be sent to the emergency department (ED). FPs are starting to use point of care ultrasound (POCUS) for a variety of indications. The FaMOUS course was modeled after the Canadian Emergency Ultrasound Society (CEUS) ED Echo (EDE) curriculum and adapted with permission for FPs. The objective of this study was to assess the indications for POCUS use in early pregnancy and determine the diagnostic accuracy of POCUS performed by FPs following FaMOUS certification to detect intrauterine pregnancy (IUP) and fetal cardiac activity (FCA). Methods: This was a prospective, observational study conducted in 3 FP clinics from November 2015 to June 2016. Pregnant women &amp;lt;20 weeks gestational age who underwent a focused, transabdominal POCUS by a FaMOUS-certified FP using a handheld GE VScan were enrolled. FPs documented the presence or absence of IUP and FCA. The reference standard was radiologist-interpreted US performed after the FP POCUS. FPs were surveyed to assess provider confidence using POCUS and perceived impact on clinical decision-making. Results: Of 253 eligible patients, 56 (22.1%) underwent POCUS. Of these, 50 (89.3%) had a radiologist-interpreted US following the office-based FP visit. POCUS was used for the following indications: 11 (19.6%) had vaginal bleeding, 5 (8.9%) had abdominal pain, 7 (12.5%) had both vaginal bleeding and abdominal pain, and the indication for 33 (58.9%) patients was unclear. All patients had a documented IUP, resulting in a sensitivity of 94.0% (95% CI: 83.5%, 98.5%) and 100% positive predictive value. FCA resulted in sensitivity of 82.9% (95% CI: 69.2, 92.4%) and specificity of 100% (95% CI: 29.2%, 100.0%). When surveyed, 100% of FPs were confident performing POCUS and reported POCUS had an overall positive impact on clinical practice. 75% agreed the use of POCUS decreased the need for urgent radiologist-interpreted US. Conclusion: Following a certification process modeled after the CEUS EDE curriculum, FPs used POCUS for both CEUS-defined indications and indications that were unclear. FPs trained in early pregnancy POCUS demonstrated excellent diagnostic accuracy identifying IUP and FCA. Future study should assess the clinical impact of office-based POCUS, including whether its use results in decreased ED visits for this patient population.

PurposeTo compare the mammographic malignant architectural distortion (AD) detection performance of radiologists who read mammographic examinations unaided versus those who read these examinations with the support of artificial intelligence (AI) systems.Material and MethodsThis retrospective case-control study was based on a double-reading of clinical mammograms between January 2011 and December 2016 at a large tertiary academic medical center. The study included 177 malignant and 90 benign architectural distortion (AD) patients. The model was built based on the ResNeXt-50 network. Algorithms used deep learning convolutional neural networks, feature classifiers, image analysis algorithms to depict AD and output a score that translated to malignant. The accuracy for malignant AD detection was evaluated using area under the curve (AUC).ResultsThe overall AUC was 0.733 (95% CI, 0.673-0.792) for Reader First-1, 0.652 (95% CI, 0.586-0.717) for Reader First-2, and 0.655 (95% CI, 0.590-0.719) for Reader First-3. and the overall AUCs for Reader Second-1, 2, 3 were 0.875 (95% CI, 0.830-0.919), 0.882 (95% CI, 0.839-0.926), 0.884 (95% CI, 0.841-0.927),respectively. The AUCs for all the reader-second radiologists were significantly higher than those for all the reader-first radiologists (Reader First-1 vs. Reader Second-1, P= 0.004). The overall AUC was 0.792 (95% CI, 0.660-0.925) for AI algorithms. The combination assessment of AI algorithms and Reader First-1 achieved an AUC of 0.880 (95% CI, 0.793-0.968), increased than the Reader First-1 alone and AI algorithms alone. AI algorithms alone achieved a specificity of 61.1% and a sensitivity of 80.6%. The specificity for Reader First-1 was 55.5%, and the sensitivity was 86.1%. The results of the combined assessment of AI and Reader First-1 showed a specificity of 72.7% and sensitivity of 91.7%. The performance showed significant improvements compared with AI alone (p<0.001) as well as the reader first-1 alone (p=0.006).ConclusionWhile the single AI algorithm did not outperform radiologists, an ensemble of AI algorithms combined with junior radiologist assessments were found to improve the overall accuracy. This study underscores the potential of using machine learning methods to enhance mammography interpretation, especially in remote areas and primary hospitals.

Artificial Intelligence-related Literature in Transplantation: A Practical Guide.

<b>Introduction:</b> On chest X-ray pneumothorax (pnx) recognition variability among readers is high. By using artificial intelligence (AI), both the success and rapidity of diagnosis can be increased. However, one of the most critical problems with AI is generalizability. Since AI can only learn the features of the data set it is trained on, it’s still not widely used today. In this study, we evaluated the model’s success trained with a single center dataset in detecting pnx in data from another center, and the effect of interventions to improve its performance. <b>Methods:</b> Deep learning based pneumothorax detection algorithm (PDA)-alfa was trained and validated on a set of 1450 chest X-rays from Center-1, including 800 pnx and 650 non-pnx pathologies. PDA-alfa was assessed with internal (Center-1) and external (Center-2) test dataset (both include 50 pnx and 200 non-pnx x-rays), respectively. After PDA-beta was validated with an additional 50 pnx chest x-rays, obtained from Center-2, assessed with the external (Center-2) test dataset. <b>Results:</b> PDA-alfa internal results were accuracy %98.3, recall %98.3, F1 score 98.5 and area under the curve (AUC) %99.5. PDA-alfa external results were accuracy %96.4, recall %88, F1 score 90.7 and AUC %98.9. PDA-beta external results were accuracy %98.8, recall %98, F1 score 97 and AUC %99.3. <b>Conclusion:</b> PDA can be used as a successful early warning system in hospitals after its performance is strengthened by the validation of a small number of X-ray data from those centers. Further multicenter studies can solve the generalizability problem by determining the amount of data for external validation.&nbsp;AI can be transformed from experiment to product.

Anxiety-driven clinical interventions have been queried due to the nondeterminacy of pure ground-glass nodules (pGGNs). Although radiomics and radiogenomics aid diagnosis, standardization and reproducibility challenges persist. We aimed to assess a risk score system for invasive adenocarcinoma in pGGNs. In a retrospective, multi-center study, 772 pGGNs from 707 individuals in The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital were grouped into training (509 patients with 558 observations) and validation (198 patients with 214 observations) sets consecutively from January 2017 to November 2021. An additional test set of 143 observations in Hainan Cancer Hospital was analyzed in the same period. Computed tomography (CT) signs and clinical features were manually collected, and the quantitative parameters were achieved by artificial intelligence (AI). The positive cutoff score was ≥3. Risk scores system 3 combined carcinoma history, chronic obstructive pulmonary disease (COPD), maximum diameters, nodule volume, mean CT values, type II or III vascular supply signs, and other radiographic characteristics. The evaluation included the area under the curves (AUCs), accuracy, sensitivity, specificity, positive predictive values (PPV), and negative predictive values (NPV) for both the risk score systems 1, 2, 3 and the AI model. The risk score system 3 [AUC, 0.840; 95% confidence interval (CI): 0.789-0.890] outperformed the AI model (AUC, 0.553; 95% CI: 0.487-0.619), risk score system 1 (AUC, 0.802; 95% CI: 0.754-0.851), and risk score system 2 (AUC, 0.816; 95% CI: 0.766-0.867), with 88.0% (0.850-0.904) accuracy, 95.6% (0.932-0.972) PPV, 0.620 (0.535-0.702) NPV, 89.6% (0.864-0.920) sensitivity, and 80.6% (0.717-0.872) specificity in the training sets. In the validation and test sets, risk score system 3 performed best with AUCs of 0.769 (0.678-0.860) and 0.801 (0.669-0.933). An AI-based risk scoring system using quantitative image parameters, clinical features, and radiographic characteristics effectively predicts invasive adenocarcinoma in pulmonary pGGNs.

BackgroundBreast cancer (BC) is the most common malignancy in women and the second cause of cancer death. In recent years, there has been a strong development in artificial intelligence (AI) applications in medical imaging for several tasks. Our aim was to evaluate the potential of transfer learning with convolutional neural networks (CNNs) in discriminating suspicious breast lesions on ultrasound images.MethodsTransfer learning performances of five different CNNs (Inception V3, Xception, Densenet121, VGG 16, and ResNet50) were evaluated on a public and on an institutional dataset (526 and 392 images, respectively), customizing the top layers for the specific task. Institutional images were contoured by an expert radiologist and processed to feed the CNNs for training and testing. Postimaging biopsies were used as a reference standard for classification. The area under the receiver operating curve (AUROC) was used to assess diagnostic performance.ResultsNetworks performed very well on the public dataset (AUROC 0.938–0.996). The direct generalization to the institutional dataset resulted in lower performances (max AUROC 0.676); however, when tested on BI-RADS 3 and BI-RADS 5 only, results were improved (max AUROC 0.792). Good results were achieved on the institutional dataset (AUROC 0.759–0.818) and, when selecting a threshold of 2% for classification, a sensitivity of 0.983 was obtained for three of five CNNs, with the potential to spare biopsy in 15.3%–18.6% of patients.ConclusionIn conclusion, transfer learning with CNNs may achieve high sensitivity and might be used as a support tool in managing suspicious breast lesions on ultrasound images.Relevance statementTransfer learning is a powerful technique to exploit the performances of well-trained CNNs for image classification. In a clinical scenario, it might be useful for the management of suspicious breast lesions on breast ultrasound, potentially sparing biopsy in a non-negligible number of patients.Key PointsProperly trained CNNs with transfer learning are highly effective in differentiating benign and malignant lesions on breast ultrasound.Setting clinical thresholds increased sensitivity.CNNs might be useful as support tools in managing suspicious lesions on breast ultrasound.Graphical

Evaluation of a filter system to harvest plasma for identification of failure of passive transfer in newborn calves

ARTIFICIAL INTELLIGENCE ASSESSMENT OF LEFT VENTRICULAR VOLUMES AND FUNCTION ON POCUS IMAGING