Purpose: The purpose of this study was to evaluate and explore the difference between an atlas-based and deep learning (DL)-based auto-segmentation scheme for organs at risk (OARs) of nasopharyngeal carcinoma cases to provide valuable help for clinical practice.

Methods: 120 nasopharyngeal carcinoma cases were established in the MIM Maestro (atlas) database and trained by a DL-based model (AccuContour), and another 20 nasopharyngeal carcinoma cases were randomly selected outside the atlas database. The experienced physicians contoured 14 OARs from 20 patients based on the published consensus guidelines, and these were defined as the reference volumes (V). Meanwhile, these OARs were auto-contoured using an atlas-based model, a pre-built DL-based model, and an on-site trained DL-based model. These volumes were named V, V, and V, respectively. The similarities between V, V, V, and V were assessed using the Dice similarity coefficient (DSC), Jaccard coefficient (JAC), maximum Hausdorff distance (HD), and deviation of centroid (DC) methods. A one-way ANOVA test was carried out to show the differences (between each two of them).

Results: The results of the three methods were almost similar for the brainstem and eyes. For inner ears and temporomandibular joints, the results of the pre-built DL-based model are the worst, as well as the results of atlas-based auto-segmentation for the lens. For the segmentation of optic nerves, the trained DL-based model shows the best performance (p < 0.05). For the contouring of the oral cavity, the DSC value of V is the smallest, and V is the most significant (p < 0.05). For the parotid glands, the DSC of V is the minimum (about 0.80 or so), and V and V are slightly larger (about 0.82 or so). In addition to the oral cavity, parotid glands, and the brainstem, the maximum Hausdorff distances of the other organs are below 0.5 cm using the trained DL-based segmentation model. The trained DL-based segmentation method behaves well in the contouring of all the organs that the maximum average deviation of the centroid is no more than 0.3 cm.

Conclusion: The trained DL-based segmentation performs significantly better than atlas-based segmentation for nasopharyngeal carcinoma, especially for the OARs with small volumes. Although some delineation results still need further modification, auto-segmentation methods improve the work efficiency and provide a level of help for clinical work.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9008357PMC
http://dx.doi.org/10.3389/fonc.2022.833816DOI Listing

Publication Analysis

Top Keywords

trained dl-based
24
nasopharyngeal carcinoma
20
dl-based model
20
carcinoma cases
12
dl-based segmentation
12
dl-based
9
atlas-based deep
8
help clinical
8
atlas database
8
pre-built dl-based
8

Similar Publications

In recent years, the deep learning (DL) technique has rapidly developed and shown great success in scoring the protein-ligand binding affinities. The protein-ligand conformation optimization based on DL-derived scoring functions holds broad application prospects, for instance, drug design and enzyme engineering. In this study, we evaluated the robustness of a DL-based ligand conformation optimization protocol (DeepRMSD+Vina) for optimizing structures with input perturbations by examining the predicted ligand binding poses and scoring.

View Article and Find Full Text PDF

ConoDL: a deep learning framework for rapid generation and prediction of conotoxins.

J Comput Aided Mol Des

December 2024

Chongqing Key Laboratory of Natural Product Synthesis and Drug Research, School of Pharmaceutical Sciences, Chongqing University, Chongqing, 401331, China.

Conotoxins, being small disulfide-rich and bioactive peptides, manifest notable pharmacological potential and find extensive applications. However, the exploration of conotoxins' vast molecular space using traditional methods is severely limited, necessitating the urgent need of developing novel approaches. Recently, deep learning (DL)-based methods have advanced to the molecular generation of proteins and peptides.

View Article and Find Full Text PDF

Cell type annotation is a critical step in analyzing single-cell RNA sequencing (scRNA-seq) data. A large number of deep learning (DL)-based methods have been proposed to annotate cell types of scRNA-seq data and have achieved impressive results. However, there are several limitations to these methods.

View Article and Find Full Text PDF

Deep learning-based intratumoral and peritumoral features for differentiating ocular adnexal lymphoma and idiopathic orbital inflammation.

Eur Radiol

December 2024

Xi'an Key Lab of Radiomics and Intelligent Perception, School of Information Science and Technology, Northwest University, Xi'an, China.

Objectives: To evaluate the value of deep-learning-based intratumoral and peritumoral features for differentiating ocular adnexal lymphoma (OAL) and idiopathic orbital inflammation (IOI).

Methods: Nighty-seven patients with histopathologically confirmed OAL (n = 43) and IOI (n = 54) were randomly divided into training (n = 79) and test (n = 18) groups. DL-based intratumoral and peritumoral features were extracted to characterize the differences in heterogeneity and tissue invasion between different lesions, respectively.

View Article and Find Full Text PDF

Passive acoustic monitoring (PAM) is an increasingly popular tool to study vocalising species. The amount of data generated by PAM studies calls for robust automatic classifiers. Deep learning (DL) techniques have been proven effective in identifying acoustic signals in challenging datasets, but due to their black-box nature their underlying biases are hard to quantify.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!