The U-Net was presented in 2015. With its straight-forward and successful architecture it quickly evolved to a commonly used benchmark in medical image segmentation. The adaptation of the U-Net to novel problems, however, comprises several degrees of freedom regarding the exact architecture, pre-processing, training and inference. These choices are not independent of each other and substantially impact the overall performance. The present paper introduces the nnU-Net ("nonew-Net"), which refers to a robust and self-adapting framework on the basis of 2D and 3D vanilla U-Nets. We argue the strong case for taking away superfluous bells and whistles of many proposed network designs and instead focus on the remaining aspects that make out the performance and generalizability of a method. We evaluate the nnU-Net in the context of the Medical Segmentation Decathlon challenge, which measures segmentation performance in ten disciplines comprising distinct entities, image modalities, image geometries and dataset sizes, with no manual adjustments between datasets allowed. At the time of manuscript submission, nnU-Net achieves the highest mean dice scores across all classes and seven phase 1 tasks (except class 1 in BrainTumour) in the online leaderboard of the challenge.
Objectives: Disseminated bone marrow (BM) involvement is frequent in multiple myeloma (MM). Whole-body magnetic resonance imaging (wb-MRI) enables to evaluate the whole BM. Reading of such whole-body scans is time-consuming, and yet radiologists can transfer only a small fraction of the information of the imaging data set to the report. This limits the influence that imaging can have on clinical decision-making and in research toward precision oncology. The objective of this feasibility study was to implement a concept for automatic, comprehensive characterization of the BM from wb-MRI, by automatic BM segmentation and subsequent radiomics analysis of 30 different BM spaces (BMS). Materials and Methods: This retrospective multicentric pilot study used a total of 106 wb-MRI from 102 patients with (smoldering) MM from 8 centers. Fifty wb-MRI from center 1 were used for training of segmentation algorithms (nnU-Nets) and radiomics algorithms. Fifty-six wb-MRI from 8 centers, acquired with a variety of different MRI scanners and protocols, were used for independent testing. Manual segmentations of 2700 BMS from 90 wb-MRI were performed for training and testing of the segmentation algorithms. For each BMS, 296 radiomics features were calculated individually. Dice score was used to assess similarity between automatic segmentations and manual reference segmentations. Results: The "multilabel nnU-Net" segmentation algorithm, which performs segmentation of 30 BMS and labels them individually, reached mean dice scores of 0.88 ± 0.06/0.87 ± 0.06/0.83 ± 0.11 in independent test sets from center 1/center 2/center 3-8 (interrater variability between radiologists, 0.88 ± 0.01). The subset from the multicenter, multivendor test set (center 3-8) that was of high imaging quality was segmented with high precision (mean dice score, 0.87), comparable to the internal test data from center 1. The radiomic BM phenotype consisting of 8880 descriptive parameters per patient, which result from calculation of 296 radiomics features for each of the 30 BMS, was calculated for all patients.Exemplary cases demonstrated connections between typical BM patterns in MM and radiomic signatures of the respective BMS. In plausibility tests, predicted size and weight based on radiomics models of the radiomic BM phenotype significantly correlated with patients' actual size and weight (P = 0.002 and P = 0.003, respectively). Conclusions: This pilot study demonstrates the feasibility of automatic, objective, comprehensive BM characterization from wb-MRI in multicentric data sets. This concept allows the extraction of high-dimensional phenotypes to capture the complexity of disseminated BM disorders from imaging. Further studies need to assess the clinical potential of this method for automatic staging, therapy response assessment, or prediction of biopsy results.
A matrix is called a multiple resultant matrix associated to two matrix polynomials when it becomes singular if and only if the two matrix polynomials have at least one common eigenvalue. In this paper a new multiple resultant matrix is introduced. It concerns the Fisher information matrix (FIM) of a stationary vector autoregressive and moving average time series process (VARMA). The two matrix polynomials are the autoregressive and the moving average matrix polynomials of the VARMA process. In order to show that the FIM is a multiple resultant matrix two new representations of the FIM are derived. To construct such representations appropriate matrix differential rules are applied. The newly obtained representations are expressed in terms of the multiple Sylvester matrix and the tensor Sylvester matrix. The representation of the FIM expressed by the tensor Sylvester matrix is used to prove that the FIM becomes singular if and only if the autoregressive and moving average matrix polynomials have at least one common eigenvalue. It then follows that the FIM and the tensor Sylvester matrix have equivalent singularity conditions. In a simple numerical example it is shown however that the FIM fails to detect common eigenvalues due to some kind of numerical instability. Whereas the tensor Sylvester matrix reveals it clearly, proving the usefulness of the results derived in this paper.
Purpose Reduction and osteosynthesis of ankle fractures is a challenging surgical procedure when it comes to the verification of the reduction result. Evaluation is conducted using intra-operative imaging of the injured ankle and depends on the expertise of the surgeon. Studies suggest that intra-individual variance of the ankle bone shape and pose is considerably lower than the inter-individual variance. It stands to reason that the information gain from the healthy contralateral side can help to improve the evaluation. Method In this paper, an assistance system is proposed that provides a side-to-side view of the two ankle joints for visual comparison and instant evaluation using only one 3D C-arm image. Two convolutional neural networks (CNN) are employed to extract the relevant image regions and pose information of each ankle so that they can be aligned with each other. A first U-Net uses a sliding window to predict the location of each ankle. The standard plane estimation is formulated as segmentation problem so that a second U-Net predicts the three viewing planes for alignment. Results Experiments were conducted to assess the accuracy of the individual steps on 218 unilateral ankle datasets as well as the overall performance on 7 bilateral ankle datasets. The experiments on unilateral ankles yield a median position-to-plane error of $$0.73\pm 1.36$$ 0.73 ± 1.36 mm and a median angular error between 2.98$$^\circ $$ ∘ and 3.71$$^\circ $$ ∘ for the plane normals. Conclusion Standard plane estimation via segmentation outperforms direct pose regression. Furthermore, the complete pipeline was evaluated including ankle detection and subsequent plane estimation on bilateral datasets. The proposed pipeline enables a direct contralateral side comparison without additional radiation. This has the potential to ease and improve the intra-operative evaluation for the surgeons in the future and reduce the need for revision surgery.
Objectives: Despite the extensive number of publications in the field of radiomics, radiomics algorithms barely enter large-scale clinical application. Supposedly, the low external generalizability of radiomics models is one of the main reasons, which hinders the translation from research to clinical application. The objectives of this study were to investigate reproducibility of radiomics features (RFs) in vivo under variation of patient positioning, magnetic resonance imaging (MRI) sequence, and MRI scanners, and to identify a subgroup of RFs that shows acceptable reproducibility across all different acquisition scenarios.Materials and Methods: Between November 30, 2020 and February 16, 2021, 55 patients with monoclonal plasma cell disorders were included in this prospective, bi-institutional, single-vendor study. Participants underwent one reference scan at a 1.5 T MRI scanner and several retest scans: once after simple repositioning, once with a second MRI protocol, once at another 1.5 T scanner, and once at a 3 T scanner. Radiomics feature from the bone marrow of the left hip bone were extracted, both from original scans and after different image normalizations. Intraclass correlation coefficient (ICC) was used to assess RF repeatability and reproducibility. Results: Fifty-five participants (mean age, 59 ± 7 years; 36 men) were enrolled. For T1-weighted images after muscle normalization, in the simple test-retest experiment, 110 (37%) of 295 RFs showed an ICC ≥0.8: 54 (61%) of 89 first-order features (FOFs), 35 (95%) of 37 volume and shape features, and 21 (12%) of 169 texture features (TFs). When the retest was performed with different technical settings, even after muscle normalization, the number of FOF/TF with an ICC ≥0.8 declined to 58/13 for the second protocol, 29/7 for the second 1.5 T scanner, and 49/7 for the 3 T scanner, respectively. Twenty-five (28%) of the 89 FOFs and 6 (4%) of the 169 TFs from muscle-normalized T1-weighted images showed an ICC ≥0.8 throughout all repeatability and reproducibility experiments. Conclusions: In vivo, only few RFs are reproducible with different MRI sequences or different MRI scanners, even after application of a simple image normalization. Radiomics features selected by a repeatability experiment only are not necessarily suited to build radiomics models for multicenter clinical application. This study isolated a subset of RFs, which are robust to variations in MRI acquisition observed in scanners from 1 vendor, and therefore are candidates to build reproducible radiomics models for monoclonal plasma cell disorders for multicentric applications, at least when centers are equipped with scanners from this vendor.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.