홈 › Papers

Anatomy-informed Data Augmentation for Enhanced Prostate Cancer Detection

2023-09-07 · Balint Kovacs, Nils Netzer, Michael Baumgartner, Carolin Eith, Dimitrios Bounias, Clara Meinzer, Paul F. Jaeger, Kevin S. Zhang, Ralf Floca, Adrian Schrader, Fabian Isensee, Regula Gnirs, Magdalena Goertz, Viktoria Schuetz, Albrecht Stenzinger, Markus Hohenfellner, Heinz-Peter Schlemmer, Ivo Wolf, David Bonekamp, Klaus H. Maier-Hein

Data augmentation (DA) is a key factor in medical image analysis, such as in prostate cancer (PCa) detection on magnetic resonance images. State-of-the-art computer-aided diagnosis systems still rely on simplistic spatial transformations to preserve the pathological label post transformation. However, such augmentations do not substantially increase the organ as well as tumor shape variability in the training set, limiting the model's ability to generalize to unseen cases with more diverse localized soft-tissue deformations. We propose a new anatomy-informed transformation that leverages information from adjacent organs to simulate typical physiological deformations of the prostate and generates unique lesion shapes without altering their label. Due to its lightweight computational requirements, it can be easily integrated into common DA frameworks. We demonstrate the effectiveness of our augmentation on a dataset of 774 biopsy-confirmed examinations, by evaluating a state-of-the-art method for PCa detection with different augmentation settings.

📄 PDF Abstract BibTeX arXiv:2309.03652

Code (2)

MIC-DKFZ/batchgenerators 공식 구현 pytorch

mic-dkfz/anatomy_informed_da 공식 구현 pytorch

Tasks

Anatomy Data AugmentationMedical Image Analysis

Learning Prostate Anatomy at Test Time for Cancer Detection in Micro-Ultrasound

2026-08-20 · Obed Korshie Dzikunu, Mohammad Mahdi Abootorabi, Mohamed Harmanani, Paul F. R. Wilson 외 arxiv

Domain shift across clinical centers using different imaging hardware or acquisition protocols remains a fundamental barrier to deploying deep learning models for prostate cancer (PCa) detection. Existing test-time adapt…

Test-time Adaptation

Autoencoders for Multi-Label Prostate MR Segmentation

2018-06-09 · Ard de Gelder, Henkjan Huisman

Organ image segmentation can be improved by implementing prior knowledge about the anatomy. One way of doing this is by training an autoencoder to learn a lowdimensional representation of the segmentation. In this paper,…

Anatomy Image Segmentation Segmentation Semantic Segmentation

Anatomical and Diagnostic Bayesian Segmentation in Prostate MRI $-$Should Different Clinical Objectives Mandate Different Loss Functions?

2021-10-25 · Anindo Saha, Joeran Bosma, Jasper Linmans, Matin Hosseinzadeh 외

We hypothesize that probabilistic voxel-level classification of anatomy and malignancy in prostate MRI, although typically posed as near-identical segmentation tasks via U-Nets, require different loss functions for optim…

Anatomy Diagnostic Lesion Detection Panoptic Segmentation+2

Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations

2026-04-28 · Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim, Kundan Thind 외 arxiv

Learning-based fluence map prediction offers a fast alternative to iterative inverse planning in intensity-modulated radiation therapy (IMRT), but its robustness under realistic distribution shifts remains unclear. We st…

Anatomy-Aware Measurement of Segmentation Accuracy

2016-04-16 · Hamid. R. Tizhoosh, Ahmed A. Othman

Quantifying the accuracy of segmentation and manual delineation of organs, tissue types and tumors in medical images is a necessary measurement that suffers from multiple problems. One major shortcoming of all accuracy m…

Anatomy Segmentation