Author name cluster

Dorit Merhof

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

NeurIPS Conference 2024 Conference Paper

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

Pedro R. Bassi
Wenxuan Li
Yucheng Tang
Fabian Isensee
Zifu Wang
Jieneng Chen
Yu-Cheng Chou
Saikat Roy

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5, 195 training CT scans from 76 hospitals around the world and 5, 903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks---which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

PDF Details DOI

YNICL Journal 2023 Journal Article

Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies

Santiago Aja-Fernández
Carmen Martín-Martín
Álvaro Planchuelo-Gómez
Abrar Faiyaz
Md Nasir Uddin
Giovanni Schifitto
Abhishek Tiwari
Saurabh J. Shigwan

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.

Details DOI

YNIMG Journal 2020 Journal Article

Cross-scanner and cross-protocol multi-shell diffusion MRI data harmonization: Algorithms and results

Lipeng Ning
Elisenda Bonet-Carne
Francesco Grussu
Farshid Sepehrband
Enrico Kaden
Jelle Veraart
Stefano B. Blumberg
Can Son Khoo

Cross-scanner and cross-protocol variability of diffusion magnetic resonance imaging (dMRI) data are known to be major obstacles in multi-site clinical studies since they limit the ability to aggregate dMRI data and derived measures. Computational algorithms that harmonize the data and minimize such variability are critical to reliably combine datasets acquired from different scanners and/or protocols, thus improving the statistical power and sensitivity of multi-site studies. Different computational approaches have been proposed to harmonize diffusion MRI data or remove scanner-specific differences. To date, these methods have mostly been developed for or evaluated on single b-value diffusion MRI data. In this work, we present the evaluation results of 19 algorithms that are developed to harmonize the cross-scanner and cross-protocol variability of multi-shell diffusion MRI using a benchmark database. The proposed algorithms rely on various signal representation approaches and computational tools, such as rotational invariant spherical harmonics, deep neural networks and hybrid biophysical and statistical approaches. The benchmark database consists of data acquired from the same subjects on two scanners with different maximum gradient strength (80 and 300 mT/m) and with two protocols. We evaluated the performance of these algorithms for mapping multi-shell diffusion MRI data across scanners and across protocols using several state-of-the-art imaging measures. The results show that data harmonization algorithms can reduce the cross-scanner and cross-protocol variabilities to a similar level as scan-rescan variability using the same scanner and protocol. In particular, the LinearRISH algorithm based on adaptive linear mapping of rotational invariant spherical harmonics features yields the lowest variability for our data in predicting the fractional anisotropy (FA), mean diffusivity (MD), mean kurtosis (MK) and the rotationally invariant spherical harmonic (RISH) features. But other algorithms, such as DIAMOND, SHResNet, DIQT, CMResNet show further improvement in harmonizing the return-to-origin probability (RTOP). The performance of different approaches provides useful guidelines on data harmonization in future multi-site studies.

Details DOI

YNIMG Journal 2019 Journal Article

Cross-scanner and cross-protocol diffusion MRI data harmonisation: A benchmark database and evaluation of algorithms

Chantal MW. Tax
Francesco Grussu
Enrico Kaden
Lipeng Ning
Umesh Rudrapatna
C. John Evans
Samuel St-Jean
Alexander Leemans

Diffusion MRI is being used increasingly in studies of the brain and other parts of the body for its ability to provide quantitative measures that are sensitive to changes in tissue microstructure. However, inter-scanner and inter-protocol differences are known to induce significant measurement variability, which in turn jeopardises the ability to obtain ‘truly quantitative measures’ and challenges the reliable combination of different datasets. Combining datasets from different scanners and/or acquired at different time points could dramatically increase the statistical power of clinical studies, and facilitate multi-centre research. Even though careful harmonisation of acquisition parameters can reduce variability, inter-protocol differences become almost inevitable with improvements in hardware and sequence design over time, even within a site. In this work, we present a benchmark diffusion MRI database of the same subjects acquired on three distinct scanners with different maximum gradient strength (40, 80, and 300 mT/m), and with ‘standard’ and ‘state-of-the-art’ protocols, where the latter have higher spatial and angular resolution. The dataset serves as a useful testbed for method development in cross-scanner/cross-protocol diffusion MRI harmonisation and quality enhancement. Using the database, we compare the performance of five different methods for estimating mappings between the scanners and protocols. The results show that cross-scanner harmonisation of single-shell diffusion data sets can reduce the variability between scanners, and highlight the promises and shortcomings of today's data harmonisation techniques.

Details DOI

YNIMG Journal 2011 Journal Article

Novel Fast Marching for Automated Segmentation of the Hippocampus (FMASH): Method and validation on clinical data

Courtney A. Bishop
Mark Jenkinson
Jesper Andersson
Jerome Declerck
Dorit Merhof

With hippocampal atrophy both a clinical biomarker for early Alzheimer's Disease (AD) and implicated in many other neurological and psychiatric diseases, there is much interest in the accurate, reproducible delineation of this region of interest (ROI) in structural MR images. Here we present Fast Marching for Automated Segmentation of the Hippocampus (FMASH): a novel approach using the Sethian Fast Marching (FM) technique to grow a hippocampal ROI from an automatically-defined seed point. Segmentation performance is assessed on two separate clinical datasets, utilising expert manual labels as gold standard to quantify Dice coefficients, false positive rates (FPR) and false negative rates (FNR). The first clinical dataset (denoted CMA) contains normal controls (NC) and atrophied AD patients, whilst the second is a collection of NC and bipolar (BP) patients (denoted BPSA). An optimal and robust stopping criterion is established for the propagating FM front and the final FMASH segmentation estimates compared to two commonly-used methods: FIRST/FSL and Freesurfer (FS). Results show that FMASH outperforms both FIRST and FS on the BPSA data, with significantly higher Dice coefficients (0. 80±0. 01) and lower FPR. Despite some intrinsic bias for FIRST and FS on the CMA data, due to their training, FMASH performs comparably well on the CMA data, with an average bilateral Dice coefficient of 0. 82±0. 01. Furthermore, FMASH most accurately captures the hippocampal volume difference between NC and AD, and provides a more accurate estimation of the problematic hippocampus–amygdala border on both clinical datasets. The consistency in performance across the two datasets suggests that FMASH is applicable to a range of clinical data with differing image quality and demographics.

Details DOI

YNIMG Journal 2006 Journal Article

Intraoperative visualization of the pyramidal tract by diffusion-tensor-imaging-based fiber tracking

Christopher Nimsky
Oliver Ganslandt
Dorit Merhof
A. Gregory Sorensen
Rudolf Fahlbusch

Functional neuronavigation allows intraoperative visualization of cortical eloquent brain areas. Major white matter tracts, such as the pyramidal tract, can be delineated by diffusion-tensor-imaging based fiber tracking. These tractography data were integrated into 3-D datasets applied for neuronavigation by rigid registration of the diffusion images with standard anatomical image data so that their course could be superimposed onto the surgical field during resection of gliomas. Intraoperative high-field magnetic resonance imaging was used to compensate for the effects of brain shift, which amounted up to 8 mm. Despite image distortion of echo planar images, which was identified by non-linear registration techniques, navigation was reliable. In none of the 19 patients new postoperative neurological deficits were encountered. Intraoperative visualization of major white matter tracts allows save resection of gliomas near eloquent brain areas. A possible shifting of the pyramidal tract has to be taken into account after major tumor parts are resected.

Details DOI