arXiv subjects

Patrick Martineau

Publications and source records attributed to Patrick Martineau.

9 recordsLinked to original sources

arXiv2026

Beyond the Tumor: Recurrence-Prone Radiomics for Prognostication in Negative PSMA PET/CT scans of Prostate Cancer

In patients with biochemical recurrence of prostate cancer and negative PSMA PET/CT, radiomics features extracted from recurrence-prone organs can predict clinical progression and progression-free survival. In a cohort of 132 patients, combining PET/CT radiomics with clinical variables significantly improved prognostic performance (C-index 0.74 vs. 0.65). Model performance was influenced by reader diagnostic certainty and remained robust on external validation. These findings suggest that radiomics from visually negative scans capture subclinical disease and provide added value for risk stratification.

physics.med-ph↗

arXiv2024

Semi-supervised learning towards automated segmentation of PET images with limited annotations: Application to lymphoma patients

The time-consuming task of manual segmentation challenges routine systematic quantification of disease burden. Convolutional neural networks (CNNs) hold significant promise to reliably identify locations and boundaries of tumors from PET scans. We aimed to leverage the need for annotated data via semi-supervised approaches, with application to PET images of diffuse large B-cell lymphoma (DLBCL) and primary mediastinal large B-cell lymphoma (PMBCL). We analyzed 18F-FDG PET images of 292 patients with PMBCL (n=104) and DLBCL (n=188) (n=232 for training and validation, and n=60 for external testing). We employed FCM and MS losses for training a 3D U-Net with different levels of supervision: i) fully supervised methods with labeled FCM (LFCM) as well as Unified focal and Dice loss functions, ii) unsupervised methods with Robust FCM (RFCM) and Mumford-Shah (MS) loss functions, and iii) Semi-supervised methods based on FCM (RFCM+LFCM), as well as MS loss in combination with supervised Dice loss (MS+Dice). Unified loss function yielded higher Dice score (mean +/- standard deviation (SD)) (0.73 +/- 0.03; 95% CI, 0.67-0.8) compared to Dice loss (p-value<0.01). Semi-supervised (RFCM+alpha*LFCM) with alpha=0.3 showed the best performance, with a Dice score of 0.69 +/- 0.03 (95% CI, 0.45-0.77) outperforming (MS+alpha*Dice) for any supervision level (any alpha) (p<0.01). The best performer among (MS+alpha*Dice) semi-supervised approaches with alpha=0.2 showed a Dice score of 0.60 +/- 0.08 (95% CI, 0.44-0.76) compared to another supervision level in this semi-supervised approach (p<0.01). Semi-supervised learning via FCM loss (RFCM+alpha*LFCM) showed improved performance compared to supervised approaches. Considering the time-consuming nature of expert manual delineations and intra-observer variabilities, semi-supervised approaches have significant potential for automated segmentation workflows.

physics.med-ph↗

arXiv2024

A cascaded deep network for automated tumor detection and segmentation in clinical PET imaging of diffuse large B-cell lymphoma

Accurate detection and segmentation of diffuse large B-cell lymphoma (DLBCL) from PET images has important implications for estimation of total metabolic tumor volume, radiomics analysis, surgical intervention and radiotherapy. Manual segmentation of tumors in whole-body PET images is time-consuming, labor-intensive and operator-dependent. In this work, we develop and validate a fast and efficient three-step cascaded deep learning model for automated detection and segmentation of DLBCL tumors from PET images. As compared to a single end-to-end network for segmentation of tumors in whole-body PET images, our three-step model is more effective (improves 3D Dice score from 58.9% to 78.1%) since each of its specialized modules, namely the slice classifier, the tumor detector and the tumor segmentor, can be trained independently to a high degree of skill to carry out a specific task, rather than a single network with suboptimal performance on overall segmentation.

eess.IV↗

arXiv2023

Comprehensive framework for evaluation of deep neural networks in detection and quantification of lymphoma from PET/CT images: clinical insights, pitfalls, and observer agreement analyses

This study addresses critical gaps in automated lymphoma segmentation from PET/CT images, focusing on issues often overlooked in existing literature. While deep learning has been applied for lymphoma lesion segmentation, few studies incorporate out-of-distribution testing, raising concerns about model generalizability across diverse imaging conditions and patient populations. We highlight the need to compare model performance with expert human annotators, including intra- and inter-observer variability, to understand task difficulty better. Most approaches focus on overall segmentation accuracy but overlook lesion-specific measures important for precise lesion detection and disease quantification. To address these gaps, we propose a clinically relevant framework for evaluating deep segmentation networks. Using this lesion measure-specific evaluation, we assess the performance of four deep networks (ResUNet, SegResNet, DynUNet, and SwinUNETR) across 611 cases from multi-institutional datasets, covering various lymphoma subtypes and lesion characteristics. Beyond standard metrics like the Dice similarity coefficient, we evaluate clinical lesion measures and their prediction errors. We also introduce detection criteria for lesion localization and propose a new detection Criterion 3 based on metabolic characteristics. We show that networks perform better on large, intense lesions with higher metabolic activity. Finally, we compare network performance to physicians via intra- and inter-observer variability analyses, demonstrating that network errors closely resemble those made by experts, i.e., the small and faint lesions remain challenging for both humans and networks. This study aims to improve automated lesion segmentation's clinical relevance, supporting better treatment decisions for lymphoma patients. The code is available at: https://github.com/microsoft/lymphoma-segmentation-dnn.

cs.CV↗

arXiv2022

Convolutional neural network with a hybrid loss function for fully automated segmentation of lymphoma lesions in FDG PET images

Segmentation of lymphoma lesions is challenging due to their varied sizes and locations in whole-body PET scans. This work presents a fully-automated segmentation technique using a multi-center dataset of diffuse large B-cell lymphoma (DLBCL) with heterogeneous characteristics. We utilized a dataset of [18F]FDG-PET scans (n=194) from two different imaging centers, including cases with primary mediastinal large B-cell lymphoma (PMBCL) (n=104). Automated brain and bladder removal approaches were utilized as preprocessing steps to tackle false positives caused by normal hypermetabolic uptake in these organs. Our segmentation model is a convolutional neural network (CNN) based on a 3D U-Net architecture that includes squeeze and excitation (SE) modules. Hybrid distribution, region, and boundary-based losses (Unified Focal and Mumford-Shah (MS)) were utilized that showed the best performance compared to other combinations (p<0.05). Cross-validation between different centers, DLBCL and PMBCL cases, and three random splits were applied on train/validation data. The ensemble of these six models achieved a Dice similarity coefficient (DSC) of 0.77 +- 0.08 and Hausdorff distance (HD) of 16.5 +-12.5. Our 3D U-net model with SE modules for segmentation with hybrid loss performed significantly better (p<0.05) as compared to the 3D U-Net (without SE modules) using the same loss function (Unified Focal and MS loss) (DSC= 0.64 +-0.21 and HD= 26.3 +- 18.7). Our model can facilitate a fully automated quantification pipeline in a multi-center context that opens the possibility for routine reporting of total metabolic tumor volume (TMTV) and other metrics shown useful for the management of lymphoma.

physics.med-ph↗

arXiv2021

Development of the Lymphatic System in the 4D XCAT Phantom

Purpose: The XCAT phantom allows for highly sophisticated multimodality imaging research. It includes a complete set of organs, muscle, bone, soft tissue, while also accounting for age, sex, and body mass index (BMI), which allows phantom studies to be performed at a population scale. At the same time, the XCAT phantom does not currently include the lymphatic system, critical for evaluating bulky nodal malignancies in lymphoma. We aimed to incorporate a full lymphatic system into the XCAT phantom and to generate realistic simulated images via guidance from lymphoma patient studies. Methods: A template lymphatic system was extended based on known anatomy was used to define 276 lymph nodes and corresponding vessels using non-uniform rational basis spline (NURBS) surfaces. Lymph node properties were modified using the Rhinoceros 3D viewing software. The XCAT general parameter script was used to input organ concentrations and generate binary files with uptake and attenuation information. Results: Lymph nodes can be scaled, stretched, and translated within the intuitive Rhinoceros interface, to allow for realistic simulation of different lymph node pathologies. Bulky, heterogeneous PMBCL tumours were generated in the mediastinum using expanded lymph nodes. Our results suggest that optimized thresholding provides better accuracy for determining total metabolic tumour volume (TMTV) of PMBCL tumours, while the gradient method was most accurate for total lesion glycolysis (TLG). Conclusions: An upgraded XCAT phantom with a fully simulated lymphatic system was created. Distributed to the research community, the XCAT phantom with the new lymphatic system has the potential of enabling studies to optimize image quality and quantitation, towards improved assessment of lymphoma including predictive modeling (e.g. improved TMTV and radiomics research).

physics.med-ph↗

arXiv2006

More on the Spectrum of Perturbations in String Gas Cosmology

String gas cosmology is rewritten in the Einstein frame. In an effective theory in which a gas of closed strings is coupled to a dilaton gravity background without any potential for the dilaton, the Hagedorn phase which is quasi-static in the string frame corresponds to an expanding, non-accelerating phase from the point of view of the Einstein frame. The Einstein frame curvature singularity which appears in this toy model is related to the blowing up of the dilaton in the string frame. However, for large values of the dilaton, the toy model clearly is inapplicable. Thus, there must be a new string phase which is likely to be static with frozen dilaton. With such a phase, the horizon problem can be successfully addressed in string gas cosmology. The generation of cosmological perturbations in the Hagedorn phase seeded by a gas of long strings in thermal equilibrium is reconsidered, both from the point of view of the string frame (in which it is easier to understand the generation of fluctuations) and the Einstein frame (in which the evolution equations are well known). It is shown that fixing the dilaton at some early stage is important in order to obtain a scale-invariant spectrum of cosmological fluctuations in string gas cosmology.

hep-th↗

arXiv2005

The Effects of Gravitational Back-Reaction on Cosmological Perturbations

Because of the non-linearity of the Einstein equations, the cosmological fluctuations which are generated during inflation on a wide range of wavelengths do not evolve independently. In particular, to second order in perturbation theory, the first order fluctuations back-react both on the background geometry and on the perturbations themselves. I this paper, the gravitational back-reaction of long wavelength (super-Hubble) scalar metric fluctuations on the perturbations themselves is investigated for a large class of inflationary models. Specifically, the equations describing the evolution of long wavelength cosmological metric and matter perturbations in an inflationary universe are solved to second order in both the amplitude of the perturbations and in the slow roll expansion parameter. Assuming that the linear fluctuations have random phases, we show that the fractional correction to the power spectrum due to the leading infrared back-reaction terms does not change the shape of the spectrum. The amplitude of the effect is suppressed by the product of the inflationary slow-roll parameter and the amplitude of the linear power spectrum. The non-gaussianity of the spectrum induced by back-reaction is commented upon.

astro-ph↗

arXiv2002

Reheating from Tachyon Condensation

We argue that it may be possible to reheat the universe after inflation driven by D-brane annihilation, due to the coupling of massless fields to the time-dependent tachyon condensate which describes the annihilation process. This mechanism can work if the original branes annihilate to a stable brane containing the standard model. Given reasonable assumptions about the shape of the tachyon background configuration and the size of the relevant extra dimension, the reheating can be efficient enough to overcome the problem of the universe being perpetually dominated by cold dark tachyon matter. In particular, reheating is most efficient when the final brane codimension is large, and when the derivatives of the tachyon background are large.

hep-th↗