[Segmentation of organs at risk in nasopharyngeal cancer for radiotherapy using a self-adaptive Unet network]

Application of FGD-BCEL loss function in segmenting temporal lobes on localized CT images for radiotherapy

Objectives

The aim of this study was to find a new loss function to automatically segment temporal lobes on localized CT images for radiotherapy with more accuracy and a solution to dealing with the classification of class-imbalanced samples in temporal lobe segmentation.

Methods

Localized CT images for radiotherapy of 70 patients with nasopharyngeal carcinoma were selected. Radiation oncologists sketched mask maps. The dataset was randomly divided into the training set (n = 49), the validation set (n = 7), and the test set (n = 14). The training set was expanded by rotation, flipping, zooming, and shearing, and the models were evaluated using Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), positive predictive value (PPV), sensitivity (SE), and Hausdorff distance (HD). This study presented an improved loss function, focal generalized Dice-binary cross-entropy loss (FGD-BCEL), and compared it with four other loss functions, Dice loss (DL), generalized Dice loss (GDL), Tversky loss (TL), and focal Tversky loss (FTL), using the U-Net model framework.

Results

With the U-Net model based on FGD-BCEL, the DSC, JSC, PPV, SE, and HD were 0.87 ± 0.11, 0.78 ± 0.11, 0.90 ± 0.10, 0.87 ± 0.13, and 4.11 ± 0.75, respectively. Except for the SE, all the other evaluation metric values of the temporal lobes segmented by the FGD-BCEL-based U-Net model were improved compared to the DL, GDL, TL, and FTL loss function-based U-Net models. Moreover, the FGD-BCEL-based U-Net model was morphologically more similar to the mask maps. The over- and under-segmentation was lessened, and it effectively segmented the tiny structures in the upper and lower poles of the temporal lobe with a limited number of samples.

Conclusions

For the segmentation of the temporal lobe on localized CT images for radiotherapy, the U-Net model based on the FGD-BCEL can meet the basic clinical requirements and effectively reduce the over- and under-segmentation compared with the U-Net models based on the other four loss functions. However, there still exists some over- and under-segmentation in the results, and further improvement is needed.

Application of Multi-Scale Fusion Attention U-Net to Segment the Thyroid Gland on Localized Computed Tomography Images for Radiotherapy

Objective

To explore the performance of Multi-scale Fusion Attention U-Net (MSFA-U-Net) in thyroid gland segmentation on localized computed tomography (CT) images for radiotherapy.

Methods

We selected localized radiotherapeutic CT images from 80 patients with breast cancer or head and neck tumors; label images were manually delineated by experienced radiologists. The data set was randomly divided into the training set (n = 60), the validation set (n = 10), and the test set (n = 10). We expanded the data in the training set and evaluated the performance of the MSFA-U-Net model using the evaluation indices Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), positive predictive value (PPV), sensitivity (SE), and Hausdorff distance (HD).

Results

For the MSFA-U-Net model, the DSC, JSC, PPV, SE, and HD values of the segmented thyroid gland in the test set were 0.90 ± 0.09, 0.82± 0.11, 0.91 ± 0.09, 0.90 ± 0.11, and 2.39 ± 0.54, respectively. Compared with U-Net, HRNet, and Attention U-Net, MSFA-U-Net increased DSC by 0.04, 0.06, and 0.04, respectively; increased JSC by 0.05, 0.08, and 0.04, respectively; increased SE by 0.04, 0.11, and 0.09, respectively; and reduced HD by 0.21, 0.20, and 0.06, respectively. The test set image results showed that the thyroid edges segmented by the MSFA-U-Net model were closer to the standard thyroid edges delineated by the experts than were those segmented by the other three models. Moreover, the edges were smoother, over-anti-noise interference was stronger, and oversegmentation and undersegmentation were reduced.

Conclusion

The MSFA-U-Net model could meet basic clinical requirements and improve the efficiency of physicians' clinical work.

Application of Artificial Intelligence for Nasopharyngeal Carcinoma Management - A Systematic Review

INTRODUCTION

Nasopharyngeal carcinoma (NPC) is endemic to Eastern and South-Eastern Asia, and, in 2020, 77% of global cases were diagnosed in these regions. Apart from its distinct epidemiology, the natural behavior, treatment, and prognosis are different from other head and neck cancers. With the growing trend of artificial intelligence (AI), especially deep learning (DL), in head and neck cancer care, we sought to explore the unique clinical application and implementation direction of AI in the management of NPC.

METHODS

The search protocol was performed to collect publications using AI, machine learning (ML) and DL in NPC management from PubMed, Scopus and Embase. The articles were filtered using inclusion and exclusion criteria, and the quality of the papers was assessed. Data were extracted from the finalized articles.

RESULTS

A total of 78 articles were reviewed after removing duplicates and papers that did not meet the inclusion and exclusion criteria. After quality assessment, 60 papers were included in the current study. There were four main types of applications, which were auto-contouring, diagnosis, prognosis, and miscellaneous applications (especially on radiotherapy planning). The different forms of convolutional neural networks (CNNs) accounted for the majority of DL algorithms used, while the artificial neural network (ANN) was the most frequent ML model implemented.

CONCLUSION

There is an overall positive impact identified from AI implementation in the management of NPC. With improving AI algorithms, we envisage AI will be available as a routine application in a clinical setting soon.

[Regional classification-guided wavelet Y-Net network for hard exudate segmentation in fundus images]

OBJECTIVE

We propose an hard exudate(EX)segmentation algorithm based on regional classification-guided wavelet Y-Net network to eliminate the influence of optic disc on EX segmentation process.

METHODS

The wavelet Y-Net network was an end-to-end fundus image EX segmentation network, which combined the regional detection of optic disc and hard exudates segmentation by regional classification-guided EX segmentation to effectively reduce the interference of optic disc in EX segmentation.To avoid failure of small EX region segmentation caused by information loss due to down-sampling operation, discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT) were introduced to replace the traditional pooling down-sampling and up-sampling operations.Meanwhile, the inception module based on residual connection was used to obtain the multi-scale features.The proposed algorithm was trained and tested on the IDRiD and e-ophtha EX datasets and evaluated at the pixel level.

RESULTS

For IDRiD and e-ophtha EX datasets, the proposed algorithm achieved accuracy rates of 0.9858 and 0.9938 with AUC values of 0.9880 and 0.9986, respectively.

CONCLUSION

The proposed method can effectively avoid the influence of the optic disc, retain the image details, and improve the effect of EX segmentation.