Background: Sentinel lymph node (SLN) status is a clinically important prognostic biomarker in breast cancer and is used to guide therapy, especially for hormone receptor-positive, HER2-negative cases. However, invasive lymph node staging is increasingly omitted before therapy, and studies such as the randomised Intergroup Sentinel Mamma (INSEMA) trial address the potential for further de-escalation of axillary surgery. Therefore, it would be helpful to accurately predict the pretherapeutic sentinel status using medical images.
Methods: Using a ResNet 50 architecture pretrained on ImageNet and a previously successful strategy, we trained deep learning (DL)-based image analysis algorithms to predict sentinel status on hematoxylin/eosin-stained images of predominantly luminal, primary breast tumours from the INSEMA trial and three additional, independent cohorts (The Cancer Genome Atlas (TCGA) and cohorts from the University hospitals of Mannheim and Regensburg), and compared their performance with that of a logistic regression using clinical data only. Performance on an INSEMA hold-out set was investigated in a blinded manner.
Results: None of the generated image analysis algorithms yielded significantly better than random areas under the receiver operating characteristic curves on the test sets, including the hold-out test set from INSEMA. In contrast, the logistic regression fitted on the Mannheim cohort retained a better than random performance on INSEMA and Regensburg. Including the image analysis model output in the logistic regression did not improve performance further on INSEMA.
Conclusions: Employing DL-based image analysis on histological slides, we could not predict SLN status for unseen cases in the INSEMA trial and other predominantly luminal cohorts.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.ejca.2023.113390 | DOI Listing |
Magn Reson Med
December 2024
Center for Image Sciences, High Field MR Research Group, Department of Radiology, University Medical Centre Utrecht, Utrecht, The Netherlands.
Purpose: To implement a low-rank and subspace model-based reconstruction for 3D deuterium metabolic imaging (DMI) and compare its performance against Fourier transform-based (FFT) reconstruction in terms of spectral fitting reliability.
Methods: Both reconstruction methods were applied on simulated and experimental DMI data. Numerical simulations were performed to evaluate the effect of increasing acceleration factors.
Eur J Med Res
December 2024
Department of Neurosurgery, Neuromedicine Center, Beijing Shijitan Hospital, Capital Medical University, No. 10, Tieyi Road, Yangfangdian, Haidian District, Beijing, 100038, People's Republic of China.
Background: Full-endoscopic microvascular decompression (fE-MVD) is an emerging treatment option for trigeminal neuralgia (TN). However, the risk factors associated with postoperative recurrence of TN after fE-MVD procedure remain controversial. The aim of the present study was to summarize the surgical technique of fE-MVD for the treatment of TN and to develop a predictive model for recurrence at 1 year postoperatively based on independent risk factors.
View Article and Find Full Text PDFCereb Cortex
December 2024
Department of Neurology, Xuanwu Hospital of Capital Medical University, #45 Changchun Street, Xicheng District, Beijing 100053, China.
The asymmetric pattern of β-amyloid plaque distribution across Alzheimer's disease clinical progression stages remains unclear. In this study, 66 participants with normal cognition, 59 with subjective cognitive decline, 12 with mild cognitive impairment, and 11 with Alzheimer's disease dementia were included in the Sino Longitudinal Study on Cognitive Decline (SILCODE) cohort. A regional asymmetry index, denoting the left-right asymmetry of β-amyloid plaques, was derived for each region based on the Anatomical Automatic Labeling atlas.
View Article and Find Full Text PDFJ Struct Biol
December 2024
Program in Cellular and Molecular Medicine, Boston Children's Hospital, 200 Longwood Ave, Boston, MA 02115, USA; Department of Cell Biology, Harvard Medical School, 200 Longwood Ave, Boston, MA 02115, USA; Department of Pediatrics, Harvard Medical School, 200 Longwood Ave, Boston, MA 02115, USA. Electronic address:
Cryogenic electron tomography (cryo-ET) has rapidly advanced as a high-resolution imaging tool for visualizing subcellular structures in 3D with molecular detail. Direct image inspection remains challenging due to inherent low signal-to-noise ratios (SNR). We introduce CryoSamba, a self-supervised deep learning-based model designed for denoising cryo-ET images.
View Article and Find Full Text PDFRev Esp Med Nucl Imagen Mol (Engl Ed)
December 2024
Selcuk University Medical Faculty, Department of Nuclear Medicine, Konya, Turkey.
Introduction And Objectives: Tissue attenuation reduces the specificity of the myocardial perfusion imaging single photon emission tomography (SPECT), which leads reduced diagnostic accuracy. The aim of this study is to compare performances of non-attenuation corrected (NAC), computed tomography based-attenuation corrected (AC) and prone images for qualitative and semi-quantitative analysis of myocardial perfusion SPECT in diagnosis of coronary artery disease (CAD).
Materials And Methods: Eightysix patients in whom NAC, AC and prone images were obtained with SPECT at Selcuk University Faculty of Medicine, and whose coronary angiography/CT coronary angiography was completed within 3 months, were retrospectively studied.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!