Longitudinal interpretability of deep learning based breast cancer risk prediction DOI Creative Commons
Žan Klaneček, Yao‐Kuan Wang, Tobias Wagner

et al.

Physics in Medicine and Biology, Journal Year: 2024, Volume and Issue: 70(1), P. 015001 - 015001

Published: Dec. 11, 2024

Deep-learning-based models have achieved state-of-the-art breast cancer risk (BCR) prediction performance. However, these are highly complex, and the underlying mechanisms of BCR not fully understood. Key questions include whether can detect morphologic changes that lead to cancer. These findings would boost confidence in utilizing practice provide clinicians with new perspectives. In this work, we aimed determine when oncogenic processes sufficient signal for changes.

Language: Английский

Liquid biopsy and its significance in tumour – Detection in the field of pathology DOI

Upma Tomar,

Neeraj Grover, Sanjeev Tomar

et al.

Journal of Oral and Maxillofacial Pathology, Journal Year: 2023, Volume and Issue: 27(1), P. 195 - 200

Published: Jan. 1, 2023

The treatment of cancer has remarkably improved because increased knowledge the abnormalities at molecular level, which results in human growth. This initiated development ever more successful as well effective targeted therapies. Detection is diagnosed basically by performing routine biopsy/cytology, many drawbacks. Therefore, concept liquid biopsy been introduced to oncology, potential revolutionise management patients, eliminating invasive procedures needed obtain tissue samples and provide information. Liquid analysis tumour cells or cell products obtained from blood other body fluids, providing a broad range opportunities field pathology. Here, we focus on most prominent markers, circulating tumour-derived deoxyribonucleic acid (DNA), patients. In this review, discuss recent clinical studies these biomarkers for early detection prognostication cancer, helps management. Hence, with great promise personalised medicine its ability multiple non-invasive snapshots primary metastatic tumours.

Language: Английский

Citations

6

Longitudinal interpretability of deep learning based breast cancer risk prediction DOI Creative Commons
Žan Klaneček, Yao‐Kuan Wang, Tobias Wagner

et al.

Physics in Medicine and Biology, Journal Year: 2024, Volume and Issue: 70(1), P. 015001 - 015001

Published: Dec. 11, 2024

Deep-learning-based models have achieved state-of-the-art breast cancer risk (BCR) prediction performance. However, these are highly complex, and the underlying mechanisms of BCR not fully understood. Key questions include whether can detect morphologic changes that lead to cancer. These findings would boost confidence in utilizing practice provide clinicians with new perspectives. In this work, we aimed determine when oncogenic processes sufficient signal for changes.

Language: Английский

Citations

1