Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography

Pinochet, Pierre; Eude, Florian; Becker, Stéphanie; Shah, Vijay; Sibille, Ludovic; Toledano, Mathieu Nessim; Modzelewski, Romain; Véra, Pierre; Decazes, Pierre

doi:10.3389/fmed.2021.628179

Cited by 23 publications

(16 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This sensitive threshold [ 24 , 25 ] was chosen to include all potential tumor lesions in our evaluation. Different segmentation thresholds were used by other authors: fixed thresholds of an SUV of 2.5 [ 12 , 16 ], 3.0 [ 23 ] or 4.0 [ 26 ], or adaptive thresholds of 41%/42% of the SUVmax [ 11 , 16 , 26 , 27 ] or background-related thresholds [ 12 , 16 , 21 ].…”

Section: Discussionmentioning

confidence: 99%

“…Fourth, volumes below a size of 2.0 ml were not considered for classification. This approach was also applied by other authors and reduced the number of artifact-related lesions, prone to misclassification [ 12 , 21 ]. Moreover, a lower threshold on volume size was also used for staging assessment in lymphoma trials [ 18 , 28 ].…”

Section: Discussionmentioning

confidence: 99%

“…Several authors used convolutional neural networks (CNN) for automatic segmentation [ 11 , 21 ] and/or classification [ 12 , 27 ] of lymphoma lesions. Capobianco et al [ 12 ] and Sibille et al [ 27 ] presented a sensitivity and specificity of 80% and 88%, and of 75% and 96% for lymphoma classification.…”

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

et al. 2022

View full text Add to dashboard Cite

Introduction The automatic classification of lymphoma lesions in PET is a main topic of ongoing research. An automatic algorithm would enable the swift evaluation of PET parameters, like texture and heterogeneity markers, concerning their prognostic value for patients outcome in large datasets. Moreover, the determination of the metabolic tumor volume would be facilitated. The aim of our study was the development and evaluation of an automatic algorithm for segmentation and classification of lymphoma lesions in PET. Methods Pre-treatment PET scans from 60 Hodgkin lymphoma patients from the EuroNet-PHL-C1 trial were evaluated. A watershed algorithm was used for segmentation. For standardization of the scan length, an automatic cropping algorithm was developed. All segmented volumes were manually classified into one of 14 categories. The random forest method and a nested cross-validation was used for automatic classification and evaluation. Results Overall, 853 volumes were segmented and classified. 203/246 tumor lesions and 554/607 non-tumor volumes were classified correctly by the automatic algorithm, corresponding to a sensitivity, a specificity, a positive and a negative predictive value of 83%, 91%, 79% and 93%. In 44/60 (73%) patients, all tumor lesions were correctly classified. In ten out of the 16 patients with misclassified tumor lesions, only one false-negative tumor lesion occurred. The automatic classification of focal gastrointestinal uptake, brown fat tissue and composed volumes consisting of more than one tissue was challenging. Conclusion Our algorithm, trained on a small number of patients and on PET information only, showed a good performance and is suitable for automatic lymphoma classification.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

et al. 2022

View full text Add to dashboard Cite

show abstract

“…A follow up study evaluated the usefulness and performance of the above CNN in research and clinical routine [207]. Automatically segmented total metabolic tumor volumes of diffuse large B cell lymphoma lesions were predictive for clinical endpoints such as disease-free survival and overall survival.…”

Section: Whole-body Imagingmentioning

confidence: 99%

Artificial intelligence with deep learning in nuclear medicine and radiology

et al. 2021

View full text Add to dashboard Cite

The use of deep learning in medical imaging has increased rapidly over the past few years, finding applications throughout the entire radiology pipeline, from improved scanner performance to automatic disease detection and diagnosis. These advancements have resulted in a wide variety of deep learning approaches being developed, solving unique challenges for various imaging modalities. This paper provides a review on these developments from a technical point of view, categorizing the different methodologies and summarizing their implementation. We provide an introduction to the design of neural networks and their training procedure, after which we take an extended look at their uses in medical imaging. We cover the different sections of the radiology pipeline, highlighting some influential works and discussing the merits and limitations of deep learning approaches compared to other traditional methods. As such, this review is intended to provide a broad yet concise overview for the interested reader, facilitating adoption and interdisciplinary research of deep learning in the field of medical imaging.

show abstract

“…The tool presented by Sibille et al is incorporated in a research prototype called the PET-assisted reporting system (PARS), which is available for research purposes. The same research group has been involved in two studies evaluating PARS (Capobianco et al, 2021;Pinochet et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Automated classification of PET‐CT lesions in lung cancer: An independent validation study

Borrelli

Góngora

Kaboteh

et al. 2022

Clin Physio Funct Imaging

View full text Add to dashboard Cite

Introduction Recently, a tool called the positron emission tomography (PET)‐assisted reporting system (PARS) was developed and presented to classify lesions in PET/computed tomography (CT) studies in patients with lung cancer or lymphoma. The aim of this study was to validate PARS with an independent group of lung‐cancer patients using manual lesion segmentations as a reference standard, as well as to evaluate the association between PARS‐based measurements and overall survival (OS). Methods This study retrospectively included 115 patients who had undergone clinically indicated (18F)‐fluorodeoxyglucose (FDG) PET/CT due to suspected or known lung cancer. The patients had a median age of 66 years (interquartile range [IQR]: 61–72 years). Segmentations were made manually by visual inspection in a consensus reading by two nuclear medicine specialists and used as a reference. The research prototype PARS was used to automatically analyse all the PET/CT studies. The PET foci classified as suspicious by PARS were compared with the manual segmentations. No manual corrections were applied. Total lesion glycolysis (TLG) was calculated based on the manual and PARS‐based lung‐tumour segmentations. Associations between TLG and OS were investigated using Cox analysis. Results PARS showed sensitivities for lung tumours of 55.6% per lesion and 80.2% per patient. Both manual and PARS TLG were significantly associated with OS. Conclusion Automatically calculated TLG by PARS contains prognostic information comparable to manually measured TLG in patients with known or suspected lung cancer. The low sensitivity at both the lesion and patient levels makes the present version of PARS less useful to support clinical reading, reporting and staging.

show abstract

Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography

Cited by 23 publications

References 35 publications

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

Automatic classification of lymphoma lesions in FDG-PET–Differentiation between tumor and non-tumor uptake

Artificial intelligence with deep learning in nuclear medicine and radiology

Automated classification of PET‐CT lesions in lung cancer: An independent validation study

Contact Info

Product

Resources

About