UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images

Valeri, Federico; Bartolucci, Maurizio; Cantoni, E.; Carpi, Roberto; Cisbani, E.; Cupparo, Ilaria; Doria, Sandra; Gori, C.; Grigioni, Mauro; Lasagni, Lorenzo; Marconi, A.; Mazzoni, Lorenzo Nicola; Miele, Vittorio; Pradella, Silvia; Risaliti, G.; Sanguineti, Valentina; Sona, Diego; Vannucchi, L; Taddeucci, A.

doi:10.1117/1.jmi.10.s1.s11904

Cited by 4 publications

(1 citation statement)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the handling of false positive (FP) predictions made by human observers can better be incorporated into the statistical analysis in future studies. The U-Net architecture has been successfully applied as a model observer in studies like (Lorente et al 2020) and (Valeri et al 2023) to localize a single low-contrast object in CT-scan images. However, our method diverges by predicting visibility probabilities for multiple objects simultaneously, thereby yielding the probability of a random observer detecting each object.…”

Section: Introductionmentioning

confidence: 99%

Probabilistic U-Net model observer for the DDC method in CT scan protocol optimization

Stocker,

Sommer,

Gueng

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Optimizing complex imaging procedures within Computed Tomography,considering both dose and image quality, presents significant challenges amidst rapidtechnological advancements and the adoption of Machine Learning (ML) methods.A crucial metric in this context is the Difference-Detailed Curve, which relies onhuman observer studies. However, these studies are labor-intensive and prone toboth inter- and intra-observer variability. To tackle these issues, a ML-based modelobserver utilizing the U-Net architecture and a Bayesian methodology is proposed. Inorder to train a model observer unaffected by the spatial arrangement of low-contrastobjects, the image preprocessing incorporates a Gaussian Process-based noise model.Additionally, Gradient-weighted Class Activation Mapping is utilized to gain insightsinto the model observer’s decision-making process. By training on data from adiverse group of observers, well-calibrated probabilistic predictions that quantifyobserver variability are achieved. Leveraging the principles of Beta regression,the Bayesian methodology is used to derive a model observer performance metric,effectively gauging the model observer’s strength in terms of an ’effective number ofobservers’. Ultimately, this framework enables to predict the DDC distribution byapplying thresholds to the inferred probabilities.

show abstract

Section: Introductionmentioning

confidence: 99%

Probabilistic U-Net model observer for the DDC method in CT scan protocol optimization

Stocker,

Sommer,

Gueng

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

A deep learning anthropomorphic model observer for a detection task in PET

Shao,

Byrd,

Mitra

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundLesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task‐based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET.PurposeThe goal of the study is to investigate whether DLMOs can predict HOs better than conventional MOs such as CHO in a two‐alternative forced‐choice (2AFC) detection task using PET images with real anatomical variability.MethodsTwo types of DLMOs were implemented: (1) CNN DLMO, and (2) CNN‐SwinT DLMO that combines CNN and Swin Transformer (SwinT) encoders. Lesion‐absent PET images were reconstructed from clinical data, and lesion‐present images were reconstructed with adding simulated lesion sinogram data. Lesion‐present and lesion‐absent PET image pairs were labeled by eight HOs consisting of four radiologists and four image scientists in a 2AFC detection task. In total, 2268 pairs of lesion‐present and lesion‐absent images were used for training, 324 pairs for validation, and 324 pairs for test. CNN DLMO, CNN‐SwinT DLMO, CHO with internal noise, and non‐prewhitening matched filter (NPWMF) were compared in the same train‐test paradigm. For comparison, six quantitative metrics including prediction accuracy, mean squared errors (MSEs) and correlation coefficients, which measure how well a MO predicts HOs, were calculated in a 9‐fold cross‐validation experiment.ResultsIn terms of the accuracy and MSE metrics, CNN DLMO and CNN‐SwinT DLMO showed better performance than CHO and NPWMF, and CNN‐SwinT DLMO showed the best performance among the MOs evaluated.ConclusionsDLMO can predict HOs more accurately than conventional MOs such as CHO in PET lesion detection. Combining SwinT and CNN encoders can improve the DLMO prediction performance compared to using CNN only.

show abstract

Harmonizing Unets: Attention Fusion module in cascaded-Unets for low-quality OCT image fluid segmentation

Wu,

Fang

et al. 2024

Computers in Biology and Medicine

View full text Add to dashboard Cite

UNet and MobileNet CNN-based model observers for CT protocol optimization: comparative performance evaluation by means of phantom CT images

Cited by 4 publications

References 71 publications

Probabilistic U-Net model observer for the DDC method in CT scan protocol optimization

Probabilistic U-Net model observer for the DDC method in CT scan protocol optimization

A deep learning anthropomorphic model observer for a detection task in PET

Harmonizing Unets: Attention Fusion module in cascaded-Unets for low-quality OCT image fluid segmentation

Contact Info

Product

Resources

About