Core Needle Biopsy Guidance Based on Tissue Morphology Assessment with AI-OCT Imaging

Maguluri, Gopi; Grimble, John; Caron, Aliana; Zhu, Guangxi; Krishnamurthy, Savitri; McWatters, Amanda; Beamer, Gillian; Lee, Seung-Yi; Iftimia, Nicusor

doi:10.3390/diagnostics13132276

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OCT probe: A specially designed OCT probe, suitable for tissue investigation through the bore of the biopsy needle, was used in this study. The design of this probe was recently reported [ 26 ]. In short, the probe consists of four major parts: probe main body, plunger, encoder, and needle containing the OCT fiber optic catheter (see Figure 3 ).…”

Section: Methodsmentioning

confidence: 99%

Assessing Lung Fibrosis with ML-Assisted Minimally Invasive OCT Imaging

Steinberg,

Meehan,

Tavrow

et al. 2024

Diagnostics

View full text Add to dashboard Cite

This paper presents a combined optical coherence tomography (OCT) imaging/machine learning (ML) technique for real-time analysis of lung tissue morphology to determine the presence and level of invasiveness of idiopathic lung fibrosis (ILF). This is an important clinical problem as misdiagnosis is common, resulting in patient exposure to costly and invasive procedures and substantial use of healthcare resources. Therefore, biopsy is needed to confirm or rule out radiological findings. Videoscopic-assisted thoracoscopic wedge biopsy (VATS) under general anesthesia is typically necessary to obtain enough tissue to make an accurate diagnosis. This kind of biopsy involves the placement of several tubes through the chest wall, one of which is used to cut off a piece of lung to send for evaluation. The removed tissue is examined histopathologically by microscopy to confirm the presence and the pattern of fibrosis. However, VATS pulmonary biopsy can have multiple side effects, including inflammation, tissue morbidity, and severe bleeding, which further degrade the quality of life for the patient. Furthermore, the results are not immediately available, requiring tissue processing and analysis. Here, we report an initial attempt of using ML-assisted polarization sensitive OCT (PS-OCT) imaging for lung fibrosis assessment. This approach has been preliminarily tested on a rat model of lung fibrosis. Our preliminary results show that ML-assisted PS-OCT imaging can detect the presence of ILF with an average of 77% accuracy and 89% specificity.

show abstract

Section: Methodsmentioning

confidence: 99%

Assessing Lung Fibrosis with ML-Assisted Minimally Invasive OCT Imaging

Steinberg,

Meehan,

Tavrow

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…for Cervix, 599 for Kidney, 252 for Ovary, 599 for the Prostate, 588 for Testis, 234 for Uterus and 272 for Vagina. Several factors, such as staining protocols, tissue quality, section thickness, tissue folding, and the amount of tissue on the slide, could negatively impact the efficiency of GAN model in generating high quality data [32]. To account for this, we conducted pre-processing normalization of the images.…”

Section: Data Sharingmentioning

confidence: 99%

Synthetic Genitourinary Image Synthesis via Generative Adversarial Networks: Enhancing AI Diagnostic Precision

Van Booven,

Chen,

Malpani

et al. 2024

Preprint

View full text Add to dashboard Cite

In the realm of computational pathology, the scarcity and restricted diversity of genitourinary (GU) tissue datasets pose significant challenges for training robust diagnostic models. This study explores the potential of Generative Adversarial Networks (GANs) to mitigate these limitations by generating high-quality synthetic images of rare or underrepresented GU tissues. We hypothesized that augmenting the training data of computational pathology models with these GAN-generated images, validated through pathologist evaluation and quantitative similarity measures, would significantly enhance model performance in tasks such as tissue classification, segmentation, and disease detection. To test this hypothesis, we employed a GAN model to produce synthetic images of eight different GU tissues. The quality of these images was rigorously assessed using a Relative Inception Score (RIS) of 17.2 and a Frechet Inception Distance (FID) that stabilized at 120, metrics that reflect the visual and statistical fidelity of the generated images to real histopathological images. Additionally, the synthetic images received an 80% approval rating from board-certified pathologists, further validating their realism and diagnostic utility. We used an alternative Spatial Heterogeneous Recurrence Quantification Analysis (SHRQA) to assess quality in prostate tissue. This allowed us to make a comparison between original and synthetic data in the context of features, which were further validated by the pathologist's evaluation. Future work will focus on implementing a deep learning model to evaluate the performance of the augmented datasets in tasks such as tissue classification, segmentation, and disease detection. This will provide a more comprehensive understanding of the utility of GAN-generated synthetic images in enhancing computational pathology workflows. This study not only confirms the feasibility of using GANs for data augmentation in medical image analysis but also highlights the critical role of synthetic data in addressing the challenges of dataset scarcity and imbalance. Future work will focus on refining the generative models to produce even more diverse and complex tissue representations, potentially transforming the landscape of medical diagnostics with AI-driven solutions.

show abstract

Core Needle Biopsy Guidance Based on Tissue Morphology Assessment with AI-OCT Imaging

Cited by 2 publications

References 38 publications

Assessing Lung Fibrosis with ML-Assisted Minimally Invasive OCT Imaging

Assessing Lung Fibrosis with ML-Assisted Minimally Invasive OCT Imaging

Synthetic Genitourinary Image Synthesis via Generative Adversarial Networks: Enhancing AI Diagnostic Precision

Contact Info

Product

Resources

About