Computation of microdosimetric distributions for small sites

Chmelevsky, D.; Kellerer, Albrecht M.

doi:10.1007/bf01332148

Cited by 24 publications

(8 citation statements)

References 12 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lineal energy, unlike LET, is a stochastic quantity, meaning that distributions of occurrence are obtained for a given irradiation instead of deterministic values. Hence, y is capable of determining the volumetric patterns of energy deposition in microscopic structures [22], [23].…”

Section: Introductionmentioning

confidence: 99%

Experimental validation of an analytical microdosimetric model based on Geant4-DNA simulations by using a silicon-based microdosimeter

Bertolet

Grilj

Guardiola

et al. 2020

Radiation Physics and Chemistry

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Experimental validation of an analytical microdosimetric model based on Geant4-DNA simulations by using a silicon-based microdosimeter

Bertolet

Grilj

Guardiola

et al. 2020

Radiation Physics and Chemistry

View full text Add to dashboard Cite

“…The procedure for weighted sampling is required in numerical evaluations of simulated particle tracks [62,65]. It is also essential in considerations that lead to the proximity function and its applications, and it will be discussed in this context in Section VI,C.…”

Section: Formulas For Weighted Samplingmentioning

confidence: 99%

Fundamentals of Microdosimetry

Kellerer¹

1985

The Dosimetry of Ionizing Radiation

101

110

View full text Add to dashboard Cite

“…Due to the presence of this microdosimetric spread, individual target volumes such as cell nuclei do not necessarily receive the same amount of absorbed energy, when ionizing radiation traverses through the tissue. 6,7 The size distributions of cells and nuclei depend on various factors: the tissue type, cell cycle, and the malignancy, all of which also vary between patients. Tumor nuclei generally have more variability in size and shape compared to healthy nuclei.…”

Section: Introductionmentioning

confidence: 99%

Deep learning-based tumor segmentation on digital images of histopathology slides for microdosimetry applications

Weishaupt

Torres

Camilleri-Broët

et al. 2021

Preprint

View full text Add to dashboard Cite

The goal of this study was (i) to use artificial intelligence to automate the traditionally labor-intensive process of manual segmentation of tumor regions in pathology slides performed by a pathologist and (ii) to validate the use of a deep learning architecture. Automation will reduce the human error involved in the manual process, increase efficiency, and result in more accurate and reproducible segmentation. This advancement will alleviate the bottleneck in the workflow in clinical and research applications due to a lack of pathologist time. Our application is patient-specific microdosimetry and radiobiological modeling, which builds on the contoured pathology slides. A deep neural network named UNet was used to segment tumor regions in pathology core biopsies of lung tissue with adenocarcinoma stained using hematoxylin and eosin. A pathologist manually contoured the tumor regions in 56 images with binary masks for training. To overcome memory limitations overlapping and non-overlapping patch extraction with various patch sizes and image downsampling were investigated individually. Data augmentation was used to reduce overfitting and artificially create more data for training. Using this deep learning approach, the UNet achieved accuracy of 0.91±0.06, specificity of 0.90±0.08, sensitivity of 0.92±0.07, and precision of 0.8±0.1. The F1/DICE score was 0.85±0.07, with a segmentation time of 3.24±0.03 seconds per image, thus achieving a 370±3 times increased efficiency over manual segmentation, which took 20 minutes per image on average. In some cases, the neural network correctly delineated the tumor's stroma from its epithelial component in tumor regions that were classified as tumor by the pathologist. The UNet architecture can segment images with a level of efficiency and accuracy that makes it suitable for tumor segmentation of histopathological images in fields such as radiotherapy dosimetry, specifically in the subfields of microdosimetry.

show abstract

Computation of microdosimetric distributions for small sites

Cited by 24 publications

References 12 publications

Experimental validation of an analytical microdosimetric model based on Geant4-DNA simulations by using a silicon-based microdosimeter

Experimental validation of an analytical microdosimetric model based on Geant4-DNA simulations by using a silicon-based microdosimeter

Fundamentals of Microdosimetry

Deep learning-based tumor segmentation on digital images of histopathology slides for microdosimetry applications

Contact Info

Product

Resources

About