Search

Your search keyword '"Kuipers, T.P."' showing total 3 results
Start Over Author "Kuipers, T.P."
3 results on '"Kuipers, T.P."'

1. ASO Visual Abstract: The Impact of Preoperative Breast MRI on Surgical Margin Status in Breast Cancer Patients Recalled at Biennial Screening Mammography: An Observational Cohort Study

Author

Gommers, J.J.J., Duijm, L. E. M., Bult, P., Strobbe, L.J.A., Kuipers, T.P., Hooijen, M.J.H., Mann, R.M., Voogd, A.C., Gommers, J.J.J., Duijm, L. E. M., Bult, P., Strobbe, L.J.A., Kuipers, T.P., Hooijen, M.J.H., Mann, R.M., and Voogd, A.C.

Abstract

Contains fulltext : 245149.pdf (Publisher’s version ) (Closed access)

Published
2021

2. The Impact of Preoperative Breast MRI on Surgical Margin Status in Breast Cancer Patients Recalled at Biennial Screening Mammography: An Observational Cohort Study

Author

Gommers, J.J.J., Duijm, L.E.M., Bult, P., Strobbe, L.J.A., Kuipers, T.P., Hooijen, M.J.H., Mann, R.M., Voogd, A.C., Gommers, J.J.J., Duijm, L.E.M., Bult, P., Strobbe, L.J.A., Kuipers, T.P., Hooijen, M.J.H., Mann, R.M., and Voogd, A.C.

Abstract

Contains fulltext : 238687.pdf (Publisher’s version ) (Open Access), BACKGROUND: This study aimed to examine the association between preoperative magnetic resonance imaging (MRI) and surgical margin involvement, as well as to determine the factors associated with positive resection margins in screen-detected breast cancer patients undergoing breast-conserving surgery (BCS). METHODS: Breast cancer patients eligible for BCS and diagnosed after biennial screening mammography in the south of The Netherlands (2008-2017) were retrospectively included. Missing values were imputed and multivariable regression analyses were performed to analyze whether preoperative MRI was related to margin involvement after BCS, as well as to examine what factors were associated with positive resection margins, defined as more than focally (>4 mm) involved. RESULTS: Overall, 2483 patients with invasive breast cancer were enrolled, of whom 123 (5.0%) had more than focally involved resection margins. In multivariable regression analyses, preoperative MRI was associated with a reduced risk of positive resection margins after BCS (adjusted odds ratio [OR] 0.56, 95% confidence interval [CI] 0.33-0.96). Lobular histology (adjusted OR 2.86, 95% CI 1.68-4.87), large tumor size (per millimeter increase, adjusted OR 1.05, 95% CI 1.03-1.07), high (>75%) mammographic density (adjusted OR 3.61, 95% CI 1.07-12.12), and the presence of microcalcifications (adjusted OR 4.45, 95% CI 2.69-7.37) and architectural distortions (adjusted OR 1.85, 95% CI 1.01-3.40) were independently associated with positive resection margins after BCS. CONCLUSIONS: Preoperative MRI was associated with lower risk of positive resection margins in patients with invasive breast cancer eligible for BCS using multivariable analysis. Furthermore, specific mammographic characteristics and tumor characteristics were independently associated with positive resection margins after BCS.

Published
2021

3. Hard Occlusions in Visual Object Tracking

Author

Kuipers, T.P., Arya, D., Gupta, D.K., Bartoli, A., Fusiello, A., and Intelligent Sensory Information Systems (IVI, FNWI)

Subjects
Training set, business.industry, Computer science, BitTorrent tracker, Bandwidth (signal processing), ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Tracking (particle physics), Video tracking, Benchmark (computing), Computer vision, Artificial intelligence, business, Focus (optics), Rotation (mathematics), ComputingMethodologies_COMPUTERGRAPHICS
Abstract

Visual object tracking is among the hardest problems in computer vision, as trackers have to deal with many challenging circumstances such as illumination changes, fast motion, occlusion, among others. A tracker is assessed to be good or not based on its performance on the recent tracking datasets, e.g., VOT2019, and LaSOT. We argue that while the recent datasets contain large sets of annotated videos that to some extent provide a large bandwidth for training data, the hard scenarios such as occlusion and in-plane rotation are still underrepresented. For trackers to be brought closer to the real-world scenarios and deployed in safety-critical devices, even the rarest hard scenarios must be properly addressed. In this paper, we particularly focus on hard occlusion cases and benchmark the performance of recent state-of-the-art trackers (SOTA) on them. We created a small-scale dataset (Dataset can be accessed at https://github.com/ThijsKuipers1995/HTB2020) containing different categories within hard occlusions, on which the selected trackers are evaluated. Results show that hard occlusions remain a very challenging problem for SOTA trackers. Furthermore, it is observed that tracker performance varies wildly between different categories of hard occlusions, where a top-performing tracker on one category performs significantly worse on a different category. The varying nature of tracker performance based on specific categories suggests that the common tracker rankings using averaged single performance scores are not adequate to gauge tracker performance in real-world scenarios.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results