1
|
Isaksson LJ, Summers P, Mastroleo F, Marvaso G, Corrao G, Vincini MG, Zaffaroni M, Ceci F, Petralia G, Orecchia R, Jereczek-Fossa BA. Automatic Segmentation with Deep Learning in Radiotherapy. Cancers (Basel) 2023; 15:4389. [PMID: 37686665 PMCID: PMC10486603 DOI: 10.3390/cancers15174389] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Revised: 08/28/2023] [Accepted: 08/30/2023] [Indexed: 09/10/2023] Open
Abstract
This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, trends, and methods, and identify areas where more research might be needed. Moreover, we analyzed the corpus by posing explicit questions aimed at providing high-quality and actionable insights, including: "What should researchers think about when starting a segmentation study?", "How can research practices in medical image segmentation be improved?", "What is missing from the current corpus?", and more. This allowed us to provide practical guidelines on how to conduct a good segmentation study in today's competitive environment that will be useful for future research within the field, regardless of the specific radiotherapeutic subfield. To aid in our analysis, we used the large language model ChatGPT to condense information.
Collapse
Affiliation(s)
- Lars Johannes Isaksson
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
- Department of Oncology and Hemato-Oncology, University of Milan, 20141 Milan, Italy; (F.C.); (G.P.)
| | - Paul Summers
- Division of Radiology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy;
| | - Federico Mastroleo
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
- Department of Translational Medicine, University of Piemonte Orientale (UPO), 20188 Novara, Italy
| | - Giulia Marvaso
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
| | - Giulia Corrao
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
| | - Maria Giulia Vincini
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
| | - Mattia Zaffaroni
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
| | - Francesco Ceci
- Department of Oncology and Hemato-Oncology, University of Milan, 20141 Milan, Italy; (F.C.); (G.P.)
- Division of Nuclear Medicine, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy
| | - Giuseppe Petralia
- Department of Oncology and Hemato-Oncology, University of Milan, 20141 Milan, Italy; (F.C.); (G.P.)
- Precision Imaging and Research Unit, Department of Medical Imaging and Radiation Sciences, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy
| | - Roberto Orecchia
- Scientific Directorate, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy;
| | - Barbara Alicja Jereczek-Fossa
- Division of Radiation Oncology, IEO European Institute of Oncology IRCCS, 20141 Milan, Italy; (L.J.I.); (F.M.); (G.C.); (M.G.V.); (M.Z.); (B.A.J.-F.)
- Department of Oncology and Hemato-Oncology, University of Milan, 20141 Milan, Italy; (F.C.); (G.P.)
| |
Collapse
|
2
|
Luján MÁ, Sotos JM, Santos JL, Borja AL. Accurate neural network classification model for schizophrenia disease based on electroencephalogram data. INT J MACH LEARN CYB 2022. [DOI: 10.1007/s13042-022-01668-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/06/2022]
|
3
|
Wang X, Hao Y, Sun H, Chen C. MRI Imaging Omics and Risk Factors Analysis of PWMD in Premature Infants Based on Fuzzy Clustering Algorithm. CONTRAST MEDIA & MOLECULAR IMAGING 2022; 2022:8624617. [PMID: 36247847 PMCID: PMC9536967 DOI: 10.1155/2022/8624617] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/02/2022] [Revised: 08/09/2022] [Accepted: 08/18/2022] [Indexed: 01/26/2023]
Abstract
The magnetic resonance imaging (MRI) characteristics of periventricular white matter damage (PWMD) in premature infants using the fuzzy c-means clustering algorithm (FCM) is explored, and the influencing factors are further clarified. A total of 100 premature infants admitted to the neonatal department of our hospital from February 2020 to February 2022 are selected for in-depth investigation. According to the occurrence of PWMD, they are divided into the PWMD group and the simple premature delivery group, with 50 cases in each group. All preterm infants are examined by MRI and the changes in image characteristics and apparent diffusion coefficient (ADC) values are analyzed. Clinical information of the subjects is collected and the influencing factors of PWMD in preterm infants are analyzed by multivariate regression analysis. In the first magnetic resonance imaging (MRI) examination, the cases of punctured, clustered, and linear lesions are 28 cases, 12 cases, and 10 cases, respectively. The experimental results showed that PWMD of preterm infants presented punctate, clustered, and high linear T1 signal MRI manifestations, which caused a downward trend of ADC value, and caused respiratory distress, low birth weight, premature rupture of membranes, respiratory tract infection, and other risk symptoms.
Collapse
Affiliation(s)
- Xiaofei Wang
- Department of Radiology, Xi'an Children's Hospital, Xi'an 710003, China
| | - Yuewen Hao
- Department of Radiology, Xi'an Children's Hospital, Xi'an 710003, China
| | - Huan Sun
- NICU, Xi'an Children's Hospital, Xi'an 710003, China
| | - Chao Chen
- Department of Radiology, Xi'an Children's Hospital, Xi'an 710003, China
| |
Collapse
|
4
|
Magnetic Resonance Features of Acquired Immune Deficiency Syndrome Involving Central Nervous System Diseases by Intelligent Fuzzy C-Means Clustering (FCM) Algorithm. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:4955555. [PMID: 35836918 PMCID: PMC9276516 DOI: 10.1155/2022/4955555] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/05/2022] [Revised: 06/09/2022] [Accepted: 06/12/2022] [Indexed: 11/23/2022]
Abstract
This study was aimed to explore the application of fuzzy C-means (FCM) algorithm in MR images of acquired immune deficiency syndrome (AIDS) patients. Sixty AIDS patients with central nervous disease were selected as the research object. A method of brain MR image segmentation based on FCM clustering optimization was proposed, and FCM was optimized based on the neighborhood pixel correlation of gray difference. The correlation was introduced into the objective function to obtain more accurate pixel membership and segmentation features of the image. The segmented image can retain the original image information. The proposed algorithm can clearly distinguish gray matter from white matter in images. The average time of image segmentation was 0.142 s, the longest time of level set algorithm was 2.887 s, and the running time of multithreshold algorithm was 1.708 s. FCM algorithm had the shortest running time, and the average time was significantly better than other algorithms (P < 0.05). FCM image segmentation efficiency was above 90%, and patients can clearly display the location of lesions after MRI imaging examination. In summary, FCM algorithm can effectively combine the spatial neighborhood information of the brain image, segment the BRAIN MR image, analyze the characteristics of AIDS patients from different directions, and provide effective treatment for patients.
Collapse
|
5
|
Arabic Hate Speech Detection Using Deep Recurrent Neural Networks. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12126010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
With the vast number of comments posted daily on social media and other platforms, manually monitoring internet activity for possible national security risks or cyberbullying is an impossible task. However, with recent advances in machine learning (ML), the automatic monitoring of such posts for possible national security risks and cyberbullying becomes feasible. There is still the issue of privacy on the internet; however, in this study, only the technical aspects of designing an automated system that could monitor and detect hate speech in the Arabic language were targeted, which many companies, such as Facebook, Twitter, and others, could use to prevent hate speech and cyberbullying. For this task, a unique dataset consisting of 4203 comments classified into seven categories, including content against religion, racist content, content against gender equality, violent content, offensive content, insulting/bullying content, normal positive comments, and normal negative comments, was designed. The dataset was extensively preprocessed and labeled, and its features were extracted. In addition, the use of deep recurrent neural networks (RNNs) was proposed for the classification and detection of hate speech. The proposed RNN architecture, called DRNN-2, consisted of 10 layers with 32 batch sizes and 50 iterations for the classification task. Another model consisting of five hidden layers, called DRNN-1, was used only for binary classification. Using the proposed models, a recognition rate of 99.73% was achieved for binary classification, 95.38% for the three classes of Arabic comments, and 84.14% for the seven classes of Arabic comments. This accuracy was high for the classification of a complex language, such as Arabic, into seven different classes. The achieved accuracy was higher than that of similar methods reported in the recent literature, whether for binary classification, three-class classification, or seven-class classification, as discussed in the literature review section.
Collapse
|
6
|
He X, Xu W, Yang J, Mao J, Chen S, Wang Z. Deep Convolutional Neural Network With a Multi-Scale Attention Feature Fusion Module for Segmentation of Multimodal Brain Tumor. Front Neurosci 2021; 15:782968. [PMID: 34899175 PMCID: PMC8662724 DOI: 10.3389/fnins.2021.782968] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2021] [Accepted: 11/02/2021] [Indexed: 12/21/2022] Open
Abstract
As a non-invasive, low-cost medical imaging technology, magnetic resonance imaging (MRI) has become an important tool for brain tumor diagnosis. Many scholars have carried out some related researches on MRI brain tumor segmentation based on deep convolutional neural networks, and have achieved good performance. However, due to the large spatial and structural variability of brain tumors and low image contrast, the segmentation of MRI brain tumors is challenging. Deep convolutional neural networks often lead to the loss of low-level details as the network structure deepens, and they cannot effectively utilize the multi-scale feature information. Therefore, a deep convolutional neural network with a multi-scale attention feature fusion module (MAFF-ResUNet) is proposed to address them. The MAFF-ResUNet consists of a U-Net with residual connections and a MAFF module. The combination of residual connections and skip connections fully retain low-level detailed information and improve the global feature extraction capability of the encoding block. Besides, the MAFF module selectively extracts useful information from the multi-scale hybrid feature map based on the attention mechanism to optimize the features of each layer and makes full use of the complementary feature information of different scales. The experimental results on the BraTs 2019 MRI dataset show that the MAFF-ResUNet can learn the edge structure of brain tumors better and achieve high accuracy.
Collapse
Affiliation(s)
- Xueqin He
- School of Informatics, Xiamen University, Xiamen, China
| | - Wenjie Xu
- School of Informatics, Xiamen University, Xiamen, China
| | - Jane Yang
- Department of Cognitive Science, University of California, San Diego, San Diego, CA, United States
| | - Jianyao Mao
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen, China
| | - Sifang Chen
- Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen, China
| | - Zhanxiang Wang
- Xiamen Key Laboratory of Brain Center, Department of Neurosurgery, The First Affiliated Hospital of Xiamen University, Xiamen, China.,Department of Neuroscience, School of Medicine, Institute of Neurosurgery, Xiamen University, Xiamen, China
| |
Collapse
|