Purpose: To present an objective automated method to determine time trends in prostatic edema resulting from iodine-125 brachytherapy.

Methods And Materials: We followed 20 patients, implanted with stranded seeds, with seven consecutive CT scans to establish a time trend in prostate edema. Seed positions were obtained automatically from the CT series. The change in seed positions was used as surrogate for edema. Two approaches were applied to model changes in volume. (1) A cylindrical model: seeds from the compared distribution were linked to the reference distribution of Day 28. After alignment, the compared distribution was scaled in cylindrical coordinates, leading to the changes in radial and craniocaudal directions. The volume changes were calculated using these scaling factors. (2) A spherical model: distances of seeds to the center of gravity of all seeds were used as a measure to model volume changes.

Results: With Day 28 as reference, the observed volume changes were smaller than 18% ± 6% (1 standard deviation) for the cylindrical model and 12% ± 7% for the spherical model. One day after implantation, the implanted prostate was less than 10% larger than in the reference scan for both models. Apart from Day 0, both models showed similar volume changes.

Conclusions: We present an objective automated method to determine changes in the implanted prostate volume, eliminating the influence of an observer in the assessment of the prostate size. The implanted volume change was less than 18% ± 7% for the studied group of 20 patients. Edema was 9% ± 5% from 1 day after implantation onward.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.brachy.2011.06.003DOI Listing

Publication Analysis

Top Keywords

objective automated
12
time trends
8
prostate edema
8
automated method
8
method determine
8
seed positions
8
cylindrical model
8
compared distribution
8
volume changes
8
spherical model
8

Similar Publications

The technical development of implant-supported fixed dental prostheses (iFDP) initially concentrated on the computer-aided manufacturing of prosthetic restorations (CAM). Advances in information technologies have shifted the focus for optimizing digital workflows to AI-based processes for design (CAD). This pre-clinical pilot trial investigated the feasibility of the automatic design of three-unit iFDPs using CAD software (Dental Manger 2021, 3Shape; DentalCAD 3.

View Article and Find Full Text PDF

: Attaining adequate oxygenation in critically ill patients undergoing invasive ventilation necessitates intense monitoring through pulse oximetry (SpO) and frequent manual adjustments of ventilator settings like the fraction of inspired oxygen (FiO) and the level of positive end-expiratory pressure (PEEP). Our aim was to compare the quality of oxygenation with the use of automated ventilation provided by INTELLiVENT-Adaptive Support Ventilation (ASV) vs. ventilation that is not automated, i.

View Article and Find Full Text PDF

Assessing the Diagnostic Performance of Automated Pituitary Gland Volume Measurement for Idiopathic Central Precocious Puberty.

J Clin Med

December 2024

Departments of Radiology, Eulji University Hospital, Eulji University College of Medicine, 95 Dunsanseo-ro, Seo-gu, Daejeon 35233, Republic of Korea.

It is known that the pituitary gland volume (PV) in idiopathic central precocious puberty (IPP) is significantly higher than in healthy children. However, most PV measurements rely on manual quantitative methods, which are time-consuming and labor-intensive. This study aimed to automatically measure the PV of patients with IPP using artificial intelligence to accurately quantify the correlation between IPP and PV, and to improve the efficiency of diagnosing IPP.

View Article and Find Full Text PDF

This study presents a comprehensive workflow for developing and deploying Multi-Layer Perceptron (MLP)-based soft sensors on embedded FPGAs, addressing diverse deployment objectives. The proposed workflow extends our prior research by introducing greater model adaptability. It supports various configurations-spanning layer counts, neuron counts, and quantization bitwidths-to accommodate the constraints and capabilities of different FPGA platforms.

View Article and Find Full Text PDF

Advanced Brain Tumor Classification in MR Images Using Transfer Learning and Pre-Trained Deep CNN Models.

Cancers (Basel)

January 2025

Department of Computer Science, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology, 2815 Gjøvik, Norway.

Background/objectives: Brain tumor classification is a crucial task in medical diagnostics, as early and accurate detection can significantly improve patient outcomes. This study investigates the effectiveness of pre-trained deep learning models in classifying brain MRI images into four categories: Glioma, Meningioma, Pituitary, and No Tumor, aiming to enhance the diagnostic process through automation.

Methods: A publicly available Brain Tumor MRI dataset containing 7023 images was used in this research.

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!