AI Article Synopsis
- This study assesses the effectiveness of three AI algorithms for segmenting prostate regions in MRI scans of patients with complex medical backgrounds and varied anatomical features.
- The researchers analyzed data from 683 MRI scans, ensuring that they included criteria such as previous treatments and different scanner qualities, and compared the AI’s segmentation against expert radiologist assessments.
- Results showed that deep learning models significantly outperformed other methods, especially in cases with smaller prostate volumes and better image quality, highlighting the challenges presented by variances in anatomy and scan conditions.
Article Abstract
Objective: Automated methods for prostate segmentation on MRI are typically developed under ideal scanning and anatomical conditions. This study evaluates three different prostate segmentation AI algorithms in a challenging population of patients with prior treatments, variable anatomic characteristics, complex clinical history, or atypical MRI acquisition parameters.
Materials And Methods: A single institution retrospective database was queried for the following conditions at prostate MRI: prior prostate-specific oncologic treatment, transurethral resection of the prostate (TURP), abdominal perineal resection (APR), hip prosthesis (HP), diversity of prostate volumes (large ≥ 150 cc, small ≤ 25 cc), whole gland tumor burden, magnet strength, noted poor quality, and various scanners (outside/vendors). Final inclusion criteria required availability of axial T2-weighted (T2W) sequence and corresponding prostate organ segmentation from an expert radiologist. Three previously developed algorithms were evaluated: (1) deep learning (DL)-based model, (2) commercially available shape-based model, and (3) federated DL-based model. Dice Similarity Coefficient (DSC) was calculated compared to expert. DSC by model and scan factors were evaluated with Wilcox signed-rank test and linear mixed effects (LMER) model.
Results: 683 scans (651 patients) met inclusion criteria (mean prostate volume 60.1 cc [9.05-329 cc]). Overall DSC scores for models 1, 2, and 3 were 0.916 (0.707-0.971), 0.873 (0-0.997), and 0.894 (0.025-0.961), respectively, with DL-based models demonstrating significantly higher performance (p < 0.01). In sub-group analysis by factors, Model 1 outperformed Model 2 (all p < 0.05) and Model 3 (all p < 0.001). Performance of all models was negatively impacted by prostate volume and poor signal quality (p < 0.01). Shape-based factors influenced DL models (p < 0.001) while signal factors influenced all (p < 0.001).
Conclusion: Factors affecting anatomical and signal conditions of the prostate gland can adversely impact both DL and non-deep learning-based segmentation models.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00261-024-04242-7 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
An Automatic Deep-Radiomics Framework for Prostate Cancer Diagnosis and Stratification in Patients with Serum Prostate-Specific Antigen of 4.0-10.0 ng/mL: A Multicenter Retrospective Study.
Acad Radiol
January 2025
Department of Urology, Nanfang Hospital, Southern Medical University, Guangzhou, Guangdong 510515, China (B.Z., F.M., X.S., S.L., Q.W.); Department of Urology, Guangdong Provincial People's Hospital, Southern Medical University, Guangzhou, Guangdong 510080, China (Q.W.). Electronic address:
Rationale And Objectives: To develop an automatic deep-radiomics framework that diagnoses and stratifies prostate cancer in patients with prostate-specific antigen (PSA) levels between 4 and 10 ng/mL.
Materials And Methods: A total of 1124 patients with histological results and PSA levels between 4 and 10 ng/mL were enrolled from one public dataset and two local institutions. An nnUNet was trained for prostate masks, and a feature extraction module identified suspicious lesion masks.
Sensory innervation in the prostate and a role for calcitonin gene-related peptide in prostatic epithelial proliferation.
Front Mol Neurosci
December 2024
Department of Pharmacology and Toxicology, Indiana University School of Medicine, Indianapolis, IN, United States.
Introduction: The prostate is densely innervated like many visceral organs and glands. However, studies to date have focused on sympathetic and parasympathetic nerves and little attention has been given to the presence or function of sensory nerves in the prostate. Recent studies have highlighted a role for sensory nerves beyond perception of noxious stimuli, as anterograde release of neuropeptides from sensory nerves can affect vascular tone and local immune responses.
View Article and Find Full Text PDFRadiomics based Machine Learning Models for Classification of Prostate Cancer Grade Groups from Multi Parametric MRI Images.
J Med Signals Sens
December 2024
Department of Radiation Sciences, School of Allied Medicine, Iran University of Medical Sciences, Tehran, Iran.
Article Synopsis
- This study explored how well machine learning models using mpMRI radiomic features can classify Gleason grade groups (GG) in prostate cancer.
- It involved analyzing data from 203 patients who had pre-biopsy mpMRI scans, using various feature selection methods and machine learning classifiers to assess model performance.
- The best-performing model achieved impressive accuracy and sensitivity (97.0% and 98.0% respectively) for classifying prostate cancer into five GG categories, demonstrating the effectiveness of this non-invasive approach.
Interpretable machine learning model for predicting clinically significant prostate cancer: integrating intratumoral and peritumoral radiomics with clinical and metabolic features.
BMC Med Imaging
December 2024
Department of MRI, Xinxiang Central Hospital (The Fourth Clinical College of Xinxiang Medical University), 56 Jinsui Road, Xinxiang, Henan, 453000, China.
Background: To develop and validate an interpretable machine learning model based on intratumoral and peritumoral radiomics combined with clinicoradiological features and metabolic information from magnetic resonance spectroscopy (MRS), to predict clinically significant prostate cancer (csPCa, Gleason score ≥ 3 + 4) and avoid unnecessary biopsies.
Methods: This study retrospectively analyzed 350 patients with suspicious prostate lesions from our institution who underwent 3.0 Tesla multiparametric magnetic resonance imaging (mpMRI) prior to biopsy (training set, n = 191, testing set, n = 83, and a temporal validation set, n = 76).
Dynamic domain generalization for medical image segmentation.
Neural Netw
December 2024
School of Cyberspace, Hangzhou Dianzi University, Hangzhou, 310018, China; Suzhou Research Institute of Shandong University, Suzhou, 215123, China. Electronic address:
Domain Generalization-based Medical Image Segmentation (DGMIS) aims to enhance the robustness of segmentation models on unseen target domains by learning from fully annotated data across multiple source domains. Despite the progress made by traditional DGMIS methods, they still face several challenges. First, most DGMIS approaches rely on static models to perform inference on unseen target domains, lacking the ability to dynamically adapt to samples from different target domains.
View Article and Find Full Text PDFWant 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!