Deep Learning Networks for Automatic Retroperitoneal Sarcoma Segmentation in Computerized Tomography

Salvaggio, Giuseppe; Cutaia, Giuseppe; Greco, Antonio; Pace, Mario; Salvaggio, L; Vernuccio, Federica; Cannella, Roberto; Algeri, Laura; Incorvaia, Lorena; Stefano, Alessandro; Gallucci, M.; Badalamenti, Giuseppe; Comelli, Albert

doi:10.3390/app12031665

Cited by 11 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the research in this paper, continue to improve our method to make this method applicable to bone tumors in more sites. (3) Giuseppe Salvaggio et al 24,25 proposed a fully automated deep learning network called Efficient Neural Network (ENet) for segmenting prostates with mesial hyperplasia. Since then, ENet has been used for many small sample segmentation tasks.…”

Section: Discussionmentioning

confidence: 99%

A semiautomatic segmentation method framework for pelvic bone tumors based on CT‐MR multimodal images

Xia

Yan

et al. 2023

Numer Methods Biomed Eng

View full text Add to dashboard Cite

The pelvic structure is complex and the tumor is poorly defined from the surrounding tissues. Finding the exact tumor resection margin based on the surgeon's clinical experience alone is a time‐consuming and difficult task, which is a major factor leading to surgical failure. An accurate method for segmenting pelvic bone tumors is needed. In this paper, a semiautomatic segmentation method for pelvic bone tumors based on CT‐MR multimodal images is presented. The method combines multiple medical prior knowledge and image segmentation algorithms. Finally, the segmentation results are visualized in three dimensions. We tested the proposed method on a collection of 10 cases (97 tumor MR images in total). The segmentation results were compared with the manual annotation of the physicians. On average, our method has an accuracy of 0.9358, a recall of 0.9278, an IOU value of 0.8697, a Dice value of 0.9280, and an AUC value of 0.9632. The average error of the 3D model was within the allowable range of the surgery. The proposed algorithm can accurately segment bone tumors in pelvic MR images regardless of tumor location, size, and other factors. It provides the possibility to assist pelvic bone tumor preservation surgery.

show abstract

Section: Discussionmentioning

confidence: 99%

A semiautomatic segmentation method framework for pelvic bone tumors based on CT‐MR multimodal images

Xia

Yan

et al. 2023

Numer Methods Biomed Eng

View full text Add to dashboard Cite

show abstract

“…ENet has an order of magnitude fewer parameters than U‐Net, and the segmentation speed is faster than U‐Net. Salvaggio et al 31 used ENet to segment CT images of retroperitoneal sarcoma and obtained a higher Dice similarity coefficient, indicating that ENet achieved a higher segmentation accuracy and had a higher similarity with manual segmentation.…”

Section: Related Workmentioning

confidence: 99%

Brain tumor image segmentation based on prior knowledge via transformer

Li,

Liu,

Nie

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Many researchers use AI to improve the accuracy of early diagnostic techniques. However, as a result of the tumor's uneven shape, fuzzy borders and too few data, existing tumor segmentation methods do not propose accurate segmentation results. We innovative introduces the prior knowledge learned to filter the noise information and guide the final network to generate a more accurate segmentation model. First, we introduce a classification network with an attention block to highlight the potential location of the brain tumor and also obtain the rough diagnosis result as the prior knowledge. Second, we provide a novel image fusion network consisting of a transformer with cross attention to merge tumor localization information with brain MRI images. Third, we propose a novel multilayer transformer experience information fusion network to combine the classic U‐Net network to handle the guiding of prior knowledge. The higher performance of the suggested method is demonstrated by comparison with contemporary methods.

show abstract

“…The ENet (Efficient Neural Network) proposed by Adam Paszke et al 54 for real-time semantic segmentation is utilized in various recent biomedical researches for medical image segmentation. Salvaggio et al 55 designed an ENet-based structure for automatic retroperitoneal sarcoma segmentation and generated optimum results superior to UNet. We hope that this study might be used for head and neck segmentation in the future.…”

Section: Future Scopementioning

confidence: 99%

SABOS‐Net: Self‐supervised attention based network for automatic organ segmentation of head and neck CT images

Francis

Pooloth

Singam

et al. 2022

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The segmentation of Organs At Risk (OAR) in Computed Tomography (CT) images is an essential part of the planning phase of radiation treatment to avoid the adverse effects of cancer radiotherapy treatment. Accurate segmentation is a tedious task in the head and neck region due to a large number of small and sensitive organs and the low contrast of CT images. Deep learningbased automatic contouring algorithms can ease this task even when the organs have irregular shapes and size variations. This paper proposes a fully automatic deep learning-based self-supervised 3D Residual UNet architecture with CBAM(Convolution Block Attention Mechanism) for the organ segmentation in head and neck CT images. The Model Genesis structure and image context restoration techniques are used for self-supervision, which can help the network learn image features from unlabeled data, hence solving the annotated medical data scarcity problem in deep networks. A new loss function is applied for training by integrating Focal loss, Tversky loss, and Cross-entropy loss. The proposed model outperforms the state-of-the-art methods in terms of dice similarity coefficient in segmenting the organs. Our self-supervised model could achieve a 4% increase in the dice score of Chiasm, which is a small organ that is present only in a very few CT slices. The proposed model exhibited better accuracy for 5 out of 7 OARs than the recent state-of-the-art models. The proposed model could simultaneously segment all seven organs in an average time of 0.

show abstract

Deep Learning Networks for Automatic Retroperitoneal Sarcoma Segmentation in Computerized Tomography

Cited by 11 publications

References 41 publications

A semiautomatic segmentation method framework for pelvic bone tumors based on CT‐MR multimodal images

A semiautomatic segmentation method framework for pelvic bone tumors based on CT‐MR multimodal images

Brain tumor image segmentation based on prior knowledge via transformer

SABOS‐Net: Self‐supervised attention based network for automatic organ segmentation of head and neck CT images

Contact Info

Product

Resources

About