Publications by authors named "Caleb O'Connor"
Article Synopsis
- The study addresses the challenges faced in liver surgeries due to the complex anatomy of liver blood vessels and the limitations of traditional 2D ultrasound imaging, which is often affected by noise and artifacts.
- Researchers developed an AI-based "2D-weighted U-Net model" to improve intraoperative ultrasonography by enhancing the real-time detection and segmentation of key liver blood vessels.
- The deep learning model demonstrated high accuracy in identifying various vessels, achieving Dice scores between 0.84 and 0.96, with plans to extend its use for more comprehensive liver vascular mapping in future surgeries.
Identification of A0 minimum ablative margins for colorectal liver metastases: multicentre, retrospective study using deformable CT registration and artificial intelligence-based autosegmentation.
Iwan Paolucci Jessica Albuquerque Marques Silva Yuan-Mao Lin Gregor Laimer Valentina Cignini Caleb O'Connor
Br J Surg
August 2024
Article Synopsis
- Several new software methods have been developed to assess the minimum ablative margin during thermal ablation of colorectal liver metastases, aiming to enhance patient outcomes in a multi-institutional context.
- This retrospective study analyzed 400 cases of thermal ablation over 13 years, focusing on minimum ablative margins and their correlation with local disease progression rates.
- Results showed that a minimum ablative margin of 5 mm or more significantly reduces the risk of local tumor progression, confirming the importance of this margin across various institutions.
Article Synopsis
- * By utilizing contrast-enhanced CT images from three patients, the researchers simulated temperature distribution during MWA, aiming to predict effective ablation zones for better treatment planning.
- * Results showed a strong correlation between predicted and actual ablation zones, with Dice scores ranging from 0.73 to 0.86, demonstrating that these 3D models can enhance accuracy in MWA strategies and treatment outcomes.
Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text].
View Article and Find Full Text PDFArticle Synopsis
- CT hepatic arteriography (CTHA) is very effective at detecting colorectal liver metastases (CLMs) but struggles with specificity for small, incidental lesions due to pseudolesions and ambiguous imaging signatures.
- A study involving 22 patients highlighted the identification of incidental ring-hyperenhancing liver micronodules (RHLMs) during CTHA, revealing that 41.7% of CTHA images contained these nodules, with many subsequently confirmed as CLMs.
- The research suggests that RHLMs detected in CTHA may serve as an early indicator for small CLMs, which could help in improving the accuracy of liver ablation procedures.
Article Synopsis
- The study aimed to evaluate how effectively two different image registration methods—deformable (DIR) and rigid (RIR)—can quantify minimal ablative margins (MAM) in patients undergoing thermal ablation for colorectal liver metastasis (CLM).
- Out of 72 patients analyzed, DIR showed better registration accuracy (0.96-0.98) compared to RIR (0.67-0.98), along with a higher predictive capability for local tumor outcomes, evidenced by a higher AUC (0.89 vs. 0.72).
- The results suggest that DIR is a superior method for quantifying MAM during intraprocedural CT imaging, thus improving the prediction of local tumor outcomes after thermal
Objectives: The aim of this study was to investigate the prognostic value of 3-dimensional minimal ablative margin (MAM) quantified by intraprocedural versus initial follow-up computed tomography (CT) in predicting local tumor progression (LTP) after colorectal liver metastasis (CLM) thermal ablation.
Materials And Methods: This single-institution, patient-clustered, tumor-based retrospective study included patients undergoing microwave and radiofrequency ablation between 2016 and 2021. Patients without intraprocedural and initial follow-up contrast-enhanced CT, residual tumors, or with follow-up less than 1 year without LTP were excluded.
Article Synopsis
- Researchers studied how effective a new imaging technique is for assessing the completeness of tumor ablation in patients with colorectal liver metastasis (CLM).
- The method involves using biomechanical deformable image registration (DIR) and AI to measure the minimal ablative margin (MAM) on CT scans and track local disease progression after treatment.
- Results showed that a smaller MAM (particularly 0 mm) was linked to a higher rate of local disease recurrence, while a margin of 5 mm or more was associated with no progression, highlighting the importance of adequate ablation margins.
Article Synopsis
- The study evaluates a new ablation confirmation method using AI and biomechanical image registration to improve tumor treatment outcomes by ensuring better coverage with minimal ablative margins (MAM).
- It is a randomized trial involving 100 patients with liver tumors, comparing the new method to standard visual inspection techniques in assessing tumor coverage during ablation procedures.
- The trial aims to provide insights into the effectiveness of this innovative approach, potentially enhancing liver cancer treatment and patient outcomes in terms of survival and quality of life.