It has been shown that AI models can learn race on medical images, leading to algorithmic bias. Our aim in this study was to enhance the fairness of medical image models by eliminating bias related to...
This study included 44,953 patients who identified as Asian, Black, or White (mean age, 60.68 years ±18.21; 23,499 women) for a total of 194,359 chest X-rays (CXRs) from MIMIC-CXR database. The includ...
In the detection of radiological findings, training a model using augmented CXR images was shown to reduce disparities in error rate among racial groups (-5.45%), age groups (-13.94%), and sex (-22.22...
The model trained using the augmented images was less likely to be influenced by demographic information in detecting image labels. These results demonstrate that the proposed augmentation scheme coul...
National Science and Technology Council (Taiwan), National Institutes of Health....
Investigations on plant-pathogen interactions require quantitative, accurate, and rapid phenotyping of crop diseases. However, visual assessment of disease symptoms is preferred over available numeric...
We developed an image analysis script in Python, called SeptoSympto. This script uses deep learning models based on the U-Net and YOLO architectures to quantify necrosis and pycnidia on detached, flat...
SeptoSympto takes the same amount of time as a visual assessment to evaluate STB symptoms. However, unlike visual assessments, it allows for data to be stored and evaluated by experts and non-experts ...
To evaluate the diagnostic performance of CT-like MR images reconstructed with an algorithm combining compressed sense (CS) with deep learning (DL) in patients with suspected osseous shoulder injury c...
Thirty-two patients (12 women, mean age 46 ± 14.9 years) with suspected traumatic shoulder injury were prospectively enrolled into the study. All patients received MR imaging of the shoulder, includin...
Compared to CT, all acute fractures (n = 23) and osseous pathologies were detected accurately on the CS only and CS DL images with almost perfect agreement between the CS DL and CS only images (κ 0.95...
Evaluation of traumatic shoulder pathologies is feasible using a DL-based algorithm for reconstruction of high-resolution CT-like MR imaging....
To explore the differences between low kiloelectron volt (keV) virtual monoenergetic images (VMIs) using IQon spectral CT and conventional CT (120 kVp) in the diagnosis of osteoporosis....
This retrospective study included 317 patients who underwent IQon spectral CT and dual-energy X-ray absorptiometry (DXA) examination. Commercial deep learning-based software was used for the fully aut...
Random forest-based prediction model obtained good overall performance among all classifiers, and macro/micro average AUC values of 0.820/840, 0.834/853, and 0.831/852 were obtained based on 40/70 keV...
The performance of the osteoporosis diagnosis model using IQon spectral CT simulating the low tube voltage scanning condition (less than 120 kVp) was also satisfactory. Bone density screening evaluati...
To evaluate the association of intracranial non-stenotic atherosclerotic plaque with cerebral small vessel disease (CSVD) imaging markers in a CSVD population using 3.0 T high-resolution magnetic reso...
We aimed to compare the image quality and focal lesion detection ability of hepatobiliary phase (HBP) images obtained using compressed sensing (CS) and controlled aliasing in parallel imaging results ...
We retrospectively included 244 gadoxetic acid-enhanced liver MRI from 244 patients with cirrhosis obtained by two HBP images using CS and CAIPIRINHA from July 2020 to December 2020. The optimized res...
CS-HBP showed comparable overall image quality (3.7 ± 0.9 vs. 3.6 ± 0.8, p = 0.680), superior liver edge sharpness (3.9 ± 0.6 vs. 3.6 ± 0.5, p < 0.001), and fewer respiratory motion artifacts (4.0 ± 0...
CS-HBP showed better focal lesion detection ability, comparable overall image quality, and fewer respiratory motion artifacts, but higher non-respiratory artifacts and noise compared to CAIPIRINHA-HBP...
Thin-slice CS-HBP may be useful for detecting sub-centimeter hepatocellular carcinoma in cirrhotic patients with Child-Pugh classification A while maintaining comparable subjective image quality....
• Compared with controlled aliasing in parallel imaging results in higher acceleration, compressed sensing hepatobiliary phase yielded thinner slices and shorter scan time at a higher accelerating fac...
A content-based image retrieval system, as an Indonesian traditional woven fabric knowledge base, can be useful for artisans and trade promotions. However, creating an effective and efficient retrieva...
The collection and annotation of medical images are hindered by data scarcity, privacy, and ethical reasons or limited resources, negatively affecting deep learning approaches. Data augmentation is of...
We propose the novel use of statistical shape and intensity models (SSIM) to generate augmented images with variety in both shape and intensity of imaged structures and surroundings. The SSIM uses seg...
In a fivefold cross-validation, the SSIM augmentation improved segmentation robustness and accuracy. In particular, the combination of basic and SSIM augmentation outperformed trained models not using...
We proposed a novel augmentation varying both the shape and appearance of structures in generated images. Tested on bone segmentation, our approach is generalizable to other structures or tasks such a...
Our data augmentation approach produces realistic shape and appearance variations of structures in generated images, which supports the clinical adoption of AI in radiology by alleviating the collecti...
• Data augmentation generally improves the accuracy and generalization of deep learning models. • Traditional data augmentation does not consider the appearance of imaged structures. • Statistical sha...
