-
Mashup Score: 2AI-integrated Screening to Replace Double Reading of Mammograms: A Population-wide Accuracy and Feasibility Study | Radiology: Artificial Intelligence - 1 month(s) ago
Mammography screening supported by deep learning–based artificial intelligence (AI) solutions can potentially reduce workload without compromising breast cancer detection accuracy, but the site of deployment in the workflow might be crucial. This retrospective study compared three simulated AI-integrated screening scenarios with standard double reading with arbitration in a sample of 249 402 mammograms from a representative screening population. A commercial AI system replaced the first reader (scenario 1: integrated AIfirst), the second reader (scenario 2: integrated AIsecond), or both readers for triaging of low- and high-risk cases (scenario 3: integrated AItriage). AI threshold values were chosen based partly on previous validation and setting the screen-read volume reduction at approximately 50% across scenarios. Detection accuracy measures were calculated. Compared with standard double reading, integrated AIfirst showed no evidence of a difference in accuracy metrics except for a
Source: pubs.rsna.orgCategories: General Medicine News, Future of MedicineTweet
-
Mashup Score: 1Digital profiling of gene expression from histology images with linearized attention - 1 month(s) ago
Nature Communications – Predicting gene alterations and expression from whole-slide images (WSIs) can be a cost-efficient solution for cancer profiling. Here, the authors develop SEQUOIA, a…
Source: www.nature.comCategories: General Medicine News, Hem/OncsTweet-
SCI member @ogevaert & others show how transformer-based #DeepLearning models, combining algorithmic advances with biological analysis, can predict high-dimensional gene expression from whole-slide histology images. https://t.co/chk7H57dnX https://t.co/RtpEjniVk0
-
-
Mashup Score: 4Unleashing the strengths of unlabelled data in deep learning-assisted pan-cancer abdominal organ quantification: the FLARE22 challenge - 2 month(s) ago
Deep learning has shown great potential to automate abdominal organ segmentation and quantification. However, most existing algorithms rely on expert annotations and do not have comprehensive evaluations in real-world multinational settings. To address these limitations, we organised the FLARE 2022 challenge to benchmark fast, low-resource, and accurate abdominal organ segmentation algorithms. We first constructed an intercontinental abdomen CT dataset from more than 50 clinical research groups.
Source: www.thelancet.comCategories: General Medicine News, Future of MedicineTweet-
NEW Resource: "Unleashing the strengths of unlabelled data in #DeepLearning-assisted pan-cancer abdominal organ quantification: the FLARE22 challenge". @JunMa_11 @BoWang87 Read it here: https://t.co/P51O9kB0aS https://t.co/ZcKyuwLnso
-
-
Mashup Score: 1Computed Tomography Study Examines Potential of Automated Coronary Artery Calcium Scoring with Deep Learning - 2 month(s) ago
For segment-level coronary artery calcium (CAC) scoring, a deep learning model had an accuracy rate of 73 percent for assigning calcifications to coronary artery segments and achieved a micro-average specificity of 97.8 percent.
Source: www.diagnosticimaging.comCategories: General Medicine News, CardiologistsTweet-
RT @Dx_imaging: CT Study Examines Potential of Automated Coronary Artery Calcium Scoring with #DeepLearning https://t.co/YV2h9Ub6sn @ACRRFS…
-
-
Mashup Score: 90
Advanced machine learning enables rapid and precise analysis of complex MA-XRF datasets in painting analysis.
Source: www.science.orgCategories: General Medicine News, Future of MedicineTweet-
A new #DeepLearning neural network can process macro x-ray fluorescence data from historic paintings automatically—offering a fast, accurate, and user-friendly alternative to classical deconvolution methods that require extensive training and expertise. https://t.co/O8fGSJ5Nfp… https://t.co/FcftfuAfkJ https://t.co/4HPlgjbozO
-
-
Mashup Score: 5
Assessment of senescence-associated nuclear morphologies with deep learning allows prediction of future cancer risk from normal breast biopsy samples. The combination of multiple models improved prediction of future breast cancer compared with the current clinical benchmark, the Gail model. Our results suggest an important role for microscope image-based deep learning models in predicting future cancer development. Such models could be incorporated into current breast cancer risk assessment and screening protocols.
Source: www.thelancet.comCategories: General Medicine News, Future of MedicineTweet-
NEW Research: #DeepLearning assessment of senescence-associated nuclear morphologies in mammary tissue from healthy female donors to predict future risk of breast cancer: a retrospective cohort study. @ScheibyeKnudsen Read it here: https://t.co/ikCIGcKoHR https://t.co/MG3U72IiLs
-
-
Mashup Score: 94
Force-torque sensors enable an intrinsic sense of touch without tactile skins for physical human-robot interaction.
Source: www.science.orgCategories: General Medicine News, Future of MedicineTweet-
A new @SciRobotics study describes how a robot can recognize and interpret symbols or letters handwritten on its body by using its force-torque sensors with #DeepLearning algorithms. https://t.co/zYYkYiR0Gk https://t.co/aeWk5N45pk
-
-
Mashup Score: 1
Purpose To develop and evaluate a publicly available deep learning model for segmenting and classifying cardiac implantable electronic devices (CIEDs) on Digital Imaging and Communications in Medicine (DICOM) and smartphone-based chest radiographs. Materials and Methods This institutional review board–approved retrospective study included patients with implantable pacemakers, cardioverter defibrillators, cardiac resynchronization therapy devices, and cardiac monitors who underwent chest radiography between January 2012 and January 2022. A U-Net model with a ResNet-50 backbone was created to classify CIEDs on DICOM and smartphone images. Using 2321 chest radiographs in 897 patients (median age, 76 years [range, 18–96 years]; 625 male, 272 female), CIEDs were categorized into four manufacturers, 27 models, and one “other” category. Five smartphones were used to acquire 11 072 images. Performance was reported using the Dice coefficient on the validation set for segmentation or balanced ac
Source: pubs.rsna.orgCategories: General Medicine News, Future of MedicineTweet-
RT @Radiology_AI: #DeepLearning model highly accurate at classifying cardiac implants chest xrays https://t.co/5ui0dd8irz @escardio #ESCCon…
-
-
Mashup Score: 51Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data - 6 month(s) ago
A deep learning model trained on genomic data from routine clinical sequencing accurately classifies 38 distinct tumor types, enabling guided treatment decisions for patients with cancers of unknown or uncertain origin.
Source: aacrjournals.orgCategories: General Medicine News, Oncologists1Tweet-
New from the June issue— #DeepLearning Model for Tumor Type Prediction using Targeted Clinical Genomic Sequencing Data, by @mmdarmofal, @MFBerger1, @quaidmorris et al. https://t.co/KPMQ5EW160 @MSKCancerCenter https://t.co/K7Vuvf7zU7
-
-
Mashup Score: 25Advancing high-resolution ultrasound imaging with deep learning - 8 month(s) ago
Researchers at the Beckman Institute for Advanced Science and Technology have developed a new technique to make ultrasound localization microscopy, an emerging diagnostic tool used for high-resolution …
Source: medicalxpress.comCategories: General Medicine News, General HCPsTweet-
Advancing high-resolution ultrasound imaging with #deepLearning @beckmaninst @NatureComms https://t.co/1MCOU1Prud
-
RT @Radiology_AI: Can #DeepLearning substitute for a 2nd-reader radiologist? https://t.co/1ndup1a5NJ @OUHhospital @UniSouthDenmark @uni_cop…