Total metabolic tumor volume (TMTV), calculated from 18F-FDG PET/CT baseline studies, is a prognostic factor in diffuse large B-cell lymphoma (DLBCL) whose measurement requires the segmentation of all malignant foci throughout the body. No consensus currently exists regarding the most accurate approach for such segmentation. Further, all methods still require extensive manual input from an experienced reader. We examined whether an artificial intelligence-based method could estimate TMTV with a comparable prognostic value to TMTV measured by experts. Methods: Baseline 18F-FDG PET/CT scans of 301 DLBCL patients from the REMARC trial (NCT01122472) were retrospectively analyzed using a prototype software (PET Assisted Reporting System [PARS]). An automated whole-body high-uptake segmentation algorithm identified all 3-dimensional regions of interest (ROIs) with increased tracer uptake. The resulting ROIs were processed using a convolutional neural network trained on an independent cohort and classified as nonsuspicious or suspicious uptake. The PARS-based TMTV (TMTVPARS) was estimated as the sum of the volumes of ROIs classified as suspicious uptake. The reference TMTV (TMTVREF) was measured by 2 experienced readers using independent semiautomatic software. The TMTVPARS was compared with the TMTVREF in terms of prognostic value for progression-free survival (PFS) and overall survival (OS). Results: TMTVPARS was significantly correlated with the TMTVREF (ρ = 0.76; P < 0.001). Using PARS, an average of 24 regions per subject with increased tracer uptake was identified, and an average of 20 regions per subject was correctly identified as nonsuspicious or suspicious, yielding 85% classification accuracy, 80% sensitivity, and 88% specificity, compared with the TMTVREF region. Both TMTV results were predictive of PFS (hazard ratio, 2.3 and 2.6 for TMTVPARS and TMTVREF, respectively; P < 0.001) and OS (hazard ratio, 2.8 and 3.7 for TMTVPARS and TMTVREF, respectively; P < 0.001). Conclusion: TMTVPARS was consistent with that obtained by experts and displayed a significant prognostic value for PFS and OS in DLBCL patients. Classification of high-uptake regions using deep learning for rapidly discarding physiologic uptake may considerably simplify TMTV estimation, reduce observer variability, and facilitate the use of TMTV as a predictive factor in DLBCL patients.

https://jnm.snmjournals.org/content/jnumed/62/1/30.full.pdf

Deep-Learning 18F-FDG Uptake Classification Enables Total Metabolic Tumor Volume Estimation in Diffuse Large B-Cell Lymphoma

Ultrahigh-resolution NMR has recently attracted considerable attention in the field of complex samples analysis. Indeed, the implementation of broadband homonuclear decoupling techniques has allowed us to greatly simplify crowded 1H spectra, yielding singlets for almost every proton site from the analyzed molecules. Pure shift methods have notably shown to be particularly suitable for deciphering mixtures of metabolites in biological samples. Here, we have successfully implemented a new pure shift pulse sequence based on the PSYCHE method, which incorporates a block for solvent suppression that is suitable for metabolomics analysis. The resulting experiment allows us to record ultrahigh-resolution 1D NOESY 1H spectra of biofluids with suppression of the water signal, which is a crucial step for highlighting metabolite mixtures in an aqueous phase. We have successfully recorded pure shift spectra on extracellular media of diffuse large B-cell lymphoma (DLBCL) cells. Despite a lower sensitivity, the resolution of pure shift data was found to be better than that of the standard approach, which provides a more detailed vision of the exo-metabolome. The statistical analyses carried out on the resulting metabolic profiles allow us to successfully highlight several metabolic pathways affected by these drugs. Notably, we show that Kidrolase plays a major role in the metabolic pathways of this DLBCL cell line.

Ultrahigh-Resolution NMR with Water Signal Suppression for a Deeper Understanding of the Action of Antimetabolic Drugs on Diffuse Large B-Cell Lymphoma.

https://hal.archives-ouvertes.fr/hal-02155801/document

Shaping for PET image analysis

In the care of patients with cancer, knowledge of the disease spread and overall burden is a key factor in the clinical decision-making process. Medical imaging is routinely used as noninvasive method to aid diagnosis and staging as well as treatment selection, planning, and monitoring. In addition to qualitative image inspection by physicians, standardized categorical and quantitative variables are increasingly used for accurate and reproducible image evaluation. Nevertheless, the manual determination of detailed image-derived parameters can require laborious examination and maneuvering, thus being time-consuming, error-prone, and operator dependent. Conversely, automated image analysis methods can be employed to improve robustness and repeatability. Notably, deep learning techniques have demonstrated high accuracy in automating visual tasks and are promising for enabling image-derived biomarkers in oncology. This dissertation presents contributions to image analysis methods in positron emission tomography (PET) / computed tomography (CT) and their application in determining image-derived biomarkers in oncology. The first contribution consists in a deep learning method for automated classification of elevated tracer uptake regions, trained for multiple radiotracers. PET/CT image regions are classified as uptake suspicious or nonsuspicious for cancer. Additionally, high-uptake regions are classified with respect to their anatomical location. Results indicate that a convolutional neural network can classify high uptake sites in good agreement with the visual assessment by a physician. The second contribution consists in the application of automated uptake classification in Prostate Specific Membrane Antigen (PSMA)-ligand PET/CT to assess prostate cancer stage. Results indicate that the proposed method can be used to determine the image-based nodal and metastatic stage according to a standardized reporting framework in concordance with expert reader evaluation. The third contribution consists in the application of automated uptake classification in 18F-Fluorodeoxyglucose (FDG) PET/CT images to estimate total metabolic tumor volume (TMTV) in lymphoma patients. Results show that in the examined cohort the proposed method determined an estimation of baseline TMTV significantly correlated and having comparable prognostic value with the TMTV estimation obtained semi-automatically by clinicians. The presented methods for automated analysis of PET/CT images using deep learning show promising results for supporting physicians in evaluating cancer stage and overall burden. Moreover, the investigated methods could potentially allow clinicians to identify novel biomarkers based on the rich information extracted from whole-body tumor assessment in PET/CT images. In conclusion, deep learning algorithms may aid the evaluation of informative and actionable image-derived cancer biomarkers and, together with diligent validation in multicenter trials, drive their establishment in the clinical routine.

Radiotracer uptake classification using deep learning for evaluation of image-derived cancer biomarkers in PET/CT

followed by autologous stem cell transplant (CT+ASCT) (group 1a). Among biopsy-negative cases (group 1b), 4/10 were observed and 6/10 received radiotherapy (RT) consolidation. Among the nonbiopsied cases (group 2), 10/18 were observed (group 2a), 7/18 received RT (group 2b), and 1/18 underwent CT+ASCT (group 2c). Patients of group 2a had a repeat PET scan after a median time of 13 weeks (range 4-35) and then only 7/10 showed persistent FDG uptake or progression disease. 6/6 biopsies performed at this time were positive and all cases received CT+ASCT. No biopsy was done in 1/7 case considered to be thymic rebound. Among patients of group 1a, 2a and 2c receiving CT-ASCT, complete remission (CR) was obtained in 11/16 (69%); 8/13 (61%) patients from group 1b or 2b receiving consolidative RT remained in CR; 2/4 cases observed after a negative biopsy subsequently progressed; 3/10 cases of group 2a converted to PET negativity and remained in CR. (Fig 1) With a median follow up of 38.4 months, no survival difference between groups 1 and 2 was observed. On radiological review of 34/37 patients at the end of therapy, Deauville scores (DS) of the PET images were as follows: 3 cases DS2, 4 DS3, 12 DS4, 12 DS5, 3 thymic rebound (DSX). The rate of relapse was 1/3 (33%) for DS2, 1/4 (25%) for DS3, 4/12 (33%) for DS4, 10/12 (83%) for DS5 and 1/3 (33%) for DSX. Conclusions: Within the limitations of this small retrospective cohort, biopsy of post-treatment persistent mediastinal PET-positivity in cHL patients is positive in less than half the cases and DS was relatively unhelpful in selecting patients with potentially refractory disease. We conclude that adopting a “wait-and-see” strategy with a repeat PET scan reassessment 8-12 weeks later increases the likelihood that the subsequent biopsy will be positive without compromising the outcome and may be the preferred approach.

High total metabolic tumor volume at baseline allows to discriminate for survival patients in response after r‐chop: an ancillary analysis of the remarc study

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

H. Gonzalez

Author Tools

Chat about Author

Papers

High total metabolic tumor volume at baseline allows to discriminate for survival patients in response after r‐chop: an ancillary analysis of the remarc study