1 July 2021 in Medical Image Analysis
7 September 2023 in Medical Image Analysis
17 May 2019 in Biomedical Optics Express
Speckle artifacts degrade image quality in virtually all modalities that utilize coherent energy, including optical coherence tomography, reflectance confocal microscopy, ultrasound, and widefield imaging with laser illumination. We present an adversarial deep learning framework for laser speckle reduction, called DeepLSR (https://durr.jhu.edu/DeepLSR), that transforms images from a source domain of coherent illumination to a target domain of speckle-free, incoherent illumination. We apply this method to widefield images of objects and tissues illuminated with a multi-wavelength laser, using light emitting diode-illuminated images as ground truth. In images of gastrointestinal tissues, DeepLSR reduces laser speckle noise by 6.4 dB, compared to a 2.9 dB reduction from optimized non-local means processing, a 3.0 dB reduction from BM3D, and a 3.7 dB reduction from an optical speckle reducer utilizing an oscillating diffuser. Further, DeepLSR can be combined with optical speckle reduction to reduce speckle noise by 9.4 dB. This dramatic reduction in speckle noise may enable the use of coherent light sources in applications that require small illumination sources and high-quality imaging, including medical endoscopy.
7 May 2024 in IEEE Journal of Biomedical and Health Informatics
A major challenge in applying deep learning to medical imaging is the paucity of annotated data. This study explores the use of synthetic images for data augmentation to address the challenge of limited annotated data in colonoscopy lesion classification. We demonstrate that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training data to improve polyp classification performance by deep learning models. We invert pairs of images with the same label to a semantically rich and disentangled latent space and manipulate latent representations to produce new synthetic images. These synthetic images maintain the same label as the input pairs. We perform image modality translation (style transfer) between white light and narrow-band imaging (NBI). We also generate realistic synthetic lesion images by interpolating between original training images to increase the variety of lesion shapes in the training dataset. Our experiments show that GAN inversion can produce multiple colonoscopy data augmentations that improve the downstream polyp classification performance by 2.7% in F1-score and 4.9% in sensitivity over other methods, including state-of-the-art data augmentation. Testing on unseen out-of-domain data also showcased an improvement of 2.9% in F1-score and 2.7% in sensitivity. This approach outperforms other colonoscopy data augmentation techniques and does not require re-training multiple generative models. It also effectively uses information from diverse public datasets, even those not specifically designed for the targeted downstream task, resulting in strong domain generalizability. Project code and model: https://github.com/DurrLab/GAN-Inversion .
1 January 2025 in Journal of Biomedical Optics
Laparoscopy is a minimally invasive surgical technique that has become the standard of care for many procedures, such as prostatectomies and appendectomies.1 Compared with traditional open surgery, laparoscopy results in faster recovery times, reduced scarring, and lower medical costs.2 However, laparoscopy presents challenges in visualization due to limited field of view (FOV) and poor contrast, which can make it difficult to accurately identify critical anatomical structures, assess tissue perfusion, and determine cancerous tissue margins.3 These limitations can lead to subjective decision-making reliant on the surgeon’s experience,4 leading to wide variability in clinical outcomes.5 This has spurred the development of optical technologies for surgical guidance, including fluorescence contrast6,7 and endogenous contrast.8 – 10 However, fluorescence imaging using an exogenous dye requires pre- or peri-operative administration of an optical contrast agent, which increases intraoperative workflow complexity. In addition, many of these techniques are qualitative, leading to user subjectivity, which limits their practical clinical value and generalization to downstream tasks employing artificial intelligence. Recent research studies have demonstrated that tissue optical properties can be used to identify tissue types with high sensitivity and specificity,10,11 underscoring the potential impact of laparoscopic techniques enabling quantitative mapping of optical properties.
18 December 2020 in Journal of Medical Devices
Transarterial embolization (TAE) is a standard-of-care treatment for tumors in which embolic particles are locally injected via a catheter to occlude blood flow and induce ischemia in the target tissue. Physicians currently rely on subjective visual cues from fluoroscopy in order to determine the procedural endpoint relative to the injection site. This contributes to highly variable treatment outcomes, including the accumulation of embolic particles in healthy tissue, called off-target embolization. To address this concern, we describe a novel, multilumen catheter that 1) measures real-time pressure upstream of the tumor site during TAE injection; and 2) associates that measurement with the volume of embolic particles injected. Using an in vitro silicon vascular model, we characterize the relationship between blood flow, intravascular pressure, and injection pressure. Furthermore, we identify a predictive pressure curve based on the volume of embolic particles injected. This approach has the potential to standardize and optimize TAE, reducing the likelihood of incomplete or off-target embolization, and improving patient outcomes.