Publications by authors named "Madhuri Rudolph"
Article Synopsis
- The study addresses challenges in organizing and retrieving large volumes of medical imaging data, focusing on developing a CNN that classifies images based on voxel data without relying on traditional naming and metadata.
- A 3D CNN was trained on over 31,000 prostate MRI volumes using patient-based cross-validation, demonstrating high accuracy (99.88%) even when trained with a reduced dataset (10%).
- The CNN's capabilities in automatic sequence identification of prostate MRIs could improve the management of medical imaging data and support more efficient clinical workflows using AI.
Background Clinically significant prostate cancer (PCa) diagnosis at MRI requires accurate and efficient radiologic interpretation. Although artificial intelligence may assist in this task, lack of transparency has limited clinical translation. Purpose To develop an explainable artificial intelligence (XAI) model for clinically significant PCa diagnosis at biparametric MRI using Prostate Imaging Reporting and Data System (PI-RADS) features for classification justification.
View Article and Find Full Text PDFMRI-targeted biopsy cores from prostate index lesions: assessment and prediction of the number needed.
Prostate Cancer Prostatic Dis
September 2023
Article Synopsis
- MRI is crucial for detecting prostate lesions before a targeted biopsy, but it's still unclear how many biopsy cores from the lesion are necessary for an accurate diagnosis.
- A study analyzed data from 451 patients who underwent MRI-targeted biopsies, focusing on the number of cores needed and developing a prediction model for diagnosis accuracy.
- The findings revealed that 97% of relevant diagnoses were made after obtaining three biopsy cores, while a prediction model achieved an accuracy of 79%, suggesting that collecting at least three cores is essential for effective identification of significant lesions.
Article Synopsis
- The study investigates the differences in inter-reader variability when using the PI-RADS v2 and v2.1 for classifying prostate lesions through multiparametric MRI.
- Results show that PI-RADS v2.1 has better agreement among radiologists in the peripheral zone but lower in the transition zone.
- Combining scores 1 and 2 in PI-RADS v2.1 led to nearly perfect agreement in the peripheral zone and substantial agreement in the transition zone, suggesting a need for clearer definitions in these scoring categories.
The purpose of this study is to compare diagnostic performance of Prostate Imaging Reporting and Data System (PI-RADS) version (v) 2.1 and 2.0 for detection of Gleason Score (GS) ≥ 7 prostate cancer on MRI.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to evaluate if MRI size cut-offs can effectively identify clinically significant prostate cancer (csPCA), focusing on improving existing criteria in PI-RADS.
- MRIs from 293 patients were analyzed, with tumors measured from different zones and correlated with their Gleason grades; 309 lesions were examined.
- Results indicated that lesion size has a stronger association with clinically significant cancer in the peripheral zone (PZ) than in the transition zone (TZ), suggesting size cut-offs of 14 mm for PZ and 21 mm for TZ to better differentiate between cancer severities.
Objectives: To assess the discriminatory power of lexicon terms used in PI-RADS version 2 to describe MRI features of prostate lesions.
Methods: Four hundred fifty-four patients were included in this retrospective, institutional review board-approved study. Patients received multiparametric (mp) MRI and subsequent prostate biopsy including MRI/transrectal ultrasound fusion biopsy and 10-core systematic biopsy.