Radiomics features may predict outcome in diffuse large B-cell lymphoma (DLBCL). Currently, multiple segmentation methods are used to calculate metabolic tumor volume (MTV). We assessed the influence of segmentation method on the discriminative power of radiomics features in DLBCL at the patient level and for the largest lesion. Fifty baseline F-FDG PET/CT scans of DLBCL patients with progression or relapse within 2 years after diagnosis were matched on uptake time and reconstruction method with 50 baseline PET/CT scans of DLBCL patients without progression. Scans were analyzed using 6 semiautomatic segmentation methods (SUV threshold of 4.0 [SUV4.0], SUV threshold of 2.5, 41% of SUV, 50% of SUV, a majority vote segmenting voxels detected by ≥2 methods, and a majority vote segmenting voxels detected by ≥3 methods). On the basis of these segmentations, 490 radiomics features were extracted at the patient level, and 486 features were extracted for the largest lesion. To quantify the agreement between features extracted from different segmentation methods, the intraclass correlation (ICC) agreement was calculated for each method compared with SUV4.0. The feature space was reduced by deleting features that had high Pearson correlations (≥0.7) with the previously established predictors MTV or SUV Model performance was assessed using stratified repeated cross validation with 5 folds and 2,000 repeats, yielding the mean receiver-operating-characteristics curve integral for all segmentation methods using logistic regression with backward feature selection. The percentage of features yielding an ICC of at least 0.75, compared with the SUV4.0 segmentation, was lowest for 50% of SUV both at the patient level and for the largest lesion, with 77.3% and 66.7% of the features yielding an ICC of at least 0.75, respectively. Features did not correlate strongly with MTV, with at least 435 features at the patient level and 409 features for the largest lesion for all segmentation methods having a correlation coefficient of less than 0.7. Features correlated strongly with SUV (at least 190 at patient level and 134 for the largest lesion were uncorrelated to SUV, respectively). Receiver-operating-characteristics curve integrals ranged between 0.69 ± 0.11 and 0.84 ± 0.09 at the patient level and between 0.69 ± 0.11 and 0.73 ± 0.10 at the lesion level. Even though there are differences in the actual radiomics feature values derived and selected features among segmentation methods, there is no substantial difference in the discriminative power of radiomics features among segmentation methods.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8978204PMC
http://dx.doi.org/10.2967/jnumed.121.262117DOI Listing

Publication Analysis

Top Keywords

segmentation methods
28
patient level
24
radiomics features
20
largest lesion
20
features
15
features extracted
12
segmentation
10
methods
9
diffuse large
8
large b-cell
8

Similar Publications

Purpose: Current technologies to define the zone of acute peripheral nerve injury intraoperatively are limited by surgical experience, time, cumbersome electrodiagnostic equipment, and interpreter reliability. In this pilot study, we evaluated a real-time, label-free optical technique for intraoperative nerve injury imaging. We hypothesize that fluorescence lifetime imaging (FLIm) will detect a difference between the time-resolved fluorescence signatures for acute crush injuries versus uninjured segments of peripheral nerves in sheep.

View Article and Find Full Text PDF

Left-lateral decubitus jackknife position for laparoscopic resection of right posterior liver tumors: A safe and effective approach.

Langenbecks Arch Surg

January 2025

Department of Hepatobiliary Surgery, Shandong Provincial Hospital, Shandong First Medical University, 324 Jingwuweiqi Road, Jinan, 250021, China.

Purpose: To compare outcomes of LLR in VI/VII of the liver in Left-lateral Decubitus Jackknife Position (LDJP) and traditional Supine Position (SP). We used propensity score matching (PSM) to analyze clinical outcomes.

Patients & Methods: This study retrospectively analyzed patients undergoing LLR for liver tumors in segments VI and/or VII at Shandong Provincial Hospital from 2018 to 2023.

View Article and Find Full Text PDF

Purpose: During endovascular revascularization interventions for peripheral arterial disease, the standard modality of X-ray fluoroscopy (XRF) used for image guidance is limited in visualizing distal segments of infrapopliteal vessels. To enhance visualization of arteries, an image registration technique was developed to align pre-acquired computed tomography (CT) angiography images and to create fusion images highlighting arteries of interest.

Methods: X-ray image metadata capturing the position of the X-ray gantry initializes a multiscale iterative optimization process, which uses a local-variance masked normalized cross-correlation loss to rigidly align a digitally reconstructed radiograph (DRR) of the CT dataset with the target X-ray, using the edges of the fibula and tibia as the basis for alignment.

View Article and Find Full Text PDF

Modeling and analysis of explicit dynamics of foot landing.

Med Biol Eng Comput

January 2025

School of Medical Engineering, Department of Cardiology of The First Affiliated Hospital of Xinxiang Medical University, Xinxiang Medical University, Xinxiang, 453003, Henan, China.

The research aims to investigate the mechanical response of footfalls at different velocities to understand the mechanism of heel injury and provide a scientific basis for the prevention and treatment of heel fractures. A three-dimensional solid model of foot drop was constructed using anatomical structures segmented from medical CT scans, including bone, cartilage, ligaments, plantar fascia, and soft tissues, and the impact velocities of the foot were set to be 2 m/s, 4 m/s, 6 m/s, 8 m/s, and 10 m/s. Explicit kinetic analysis methods were used to investigate the mechanical response of the foot landing with different speeds to explore the damage mechanism of heel bone at different impact velocities.

View Article and Find Full Text PDF

In this study, we explore an enhancement to the U-Net architecture by integrating SK-ResNeXt as the encoder for Land Cover Classification (LCC) tasks using Multispectral Imaging (MSI). SK-ResNeXt introduces cardinality and adaptive kernel sizes, allowing U-Net to better capture multi-scale features and adjust more effectively to variations in spatial resolution, thereby enhancing the model's ability to segment complex land cover types. We evaluate this approach using the Five-Billion-Pixels dataset, composed of 150 large-scale RGB-NIR images and over 5 billion labeled pixels across 24 categories.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!