1
|
Lian Z, Lu Q, Lin B, Chen L, Gong J, Hu Q, Wang H, Feng Y. A fully automatic parenchyma extraction method for MRI T2* relaxometry of iron loaded liver in transfusion-dependent patients. Magn Reson Imaging 2024; 109:18-26. [PMID: 38430975 DOI: 10.1016/j.mri.2024.02.017] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2023] [Revised: 02/28/2024] [Accepted: 02/28/2024] [Indexed: 03/05/2024]
Abstract
PURPOSE To develop a fully automatic parenchyma extraction method for the T2* relaxometry of iron overload liver. METHODS A retrospective multicenter collection of liver MR examinations from 177 transfusion-dependent patients was conducted. The proposed method extended a semiautomatic parenchyma extraction algorithm to a fully automatic approach by introducing a modified TransUNet on the R2* (1/T2*) map for liver segmentation. Axial liver slices from 129 patients at 1.5 T were allocated to training (85%) and internal test (15%) sets. Two external test sets separately included 1.5 T data from 20 patients and 3.0 T data from 28 patients. The final T2* measurement was obtained by fitting the average signal of the extracted liver parenchyma. The agreement between T2* measurements using fully and semiautomatic parenchyma extraction methods was assessed using coefficient of variation (CoV) and Bland-Altman plots. RESULTS Dice of the deep network-based liver segmentation was 0.970 ± 0.019 on the internal dataset, 0.960 ± 0.035 on the external 1.5 T dataset, and 0.958 ± 0.014 on the external 3.0 T dataset. The mean difference bias between T2* measurements of the fully and semiautomatic methods were separately 0.12 (95% CI: -0.37, 0.61) ms, 0.04 (95% CI: -1.0, 1.1) ms, and 0.01 (95% CI: -0.25, 0.23) ms on the three test datasets. The CoVs between the two methods were 4.2%, 4.8% and 2.0% on the internal test set and two external test sets. CONCLUSIONS The developed fully automatic parenchyma extraction approach provides an efficient and operator-independent T2* measurement for assessing hepatic iron content in clinical practice.
Collapse
Affiliation(s)
- Zifeng Lian
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China; Guangdong Provincial Key Laboratory of Medical Image Processing & Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, China; Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence & Key Laboratory of Mental Health of the Ministry of Education & Guangdong-Hong Kong Joint Laboratory for Psychiatric Disorders, Southern Medical University, Guangzhou, China
| | - Qiqi Lu
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China; Guangdong Provincial Key Laboratory of Medical Image Processing & Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, China; Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence & Key Laboratory of Mental Health of the Ministry of Education & Guangdong-Hong Kong Joint Laboratory for Psychiatric Disorders, Southern Medical University, Guangzhou, China
| | - Bingquan Lin
- Department of Medical Imaging Center, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Lingjian Chen
- Department of Radiology, Shunde Hospital, Southern Medical University (The First People's Hospital of Shunde, Foshan), Foshan, China
| | - Jian Gong
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - Qiugen Hu
- Department of Radiology, Shunde Hospital, Southern Medical University (The First People's Hospital of Shunde, Foshan), Foshan, China
| | - Huafeng Wang
- Department of Radiology, Shunde Hospital, Southern Medical University (The First People's Hospital of Shunde, Foshan), Foshan, China
| | - Yanqiu Feng
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China; Guangdong Provincial Key Laboratory of Medical Image Processing & Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou, China; Guangdong-Hong Kong-Macao Greater Bay Area Center for Brain Science and Brain-Inspired Intelligence & Key Laboratory of Mental Health of the Ministry of Education & Guangdong-Hong Kong Joint Laboratory for Psychiatric Disorders, Southern Medical University, Guangzhou, China; Department of Radiology, Shunde Hospital, Southern Medical University (The First People's Hospital of Shunde, Foshan), Foshan, China.
| |
Collapse
|
2
|
Li S, Li XG, Zhou F, Zhang Y, Bie Z, Cheng L, Peng J, Li B. Automated segmentation of liver and hepatic vessels on portal venous phase computed tomography images using a deep learning algorithm. J Appl Clin Med Phys 2024:e14397. [PMID: 38773719 DOI: 10.1002/acm2.14397] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2024] [Revised: 04/20/2024] [Accepted: 04/29/2024] [Indexed: 05/24/2024] Open
Abstract
BACKGROUND CT-image segmentation for liver and hepatic vessels can facilitate liver surgical planning. However, time-consuming process and inter-observer variations of manual segmentation have limited wider application in clinical practice. PURPOSE Our study aimed to propose an automated deep learning (DL) segmentation algorithm for liver and hepatic vessels on portal venous phase CT images. METHODS This retrospective study was performed to develop a coarse-to-fine DL-based algorithm that was trained, validated, and tested using private 413, 52, and 50 portal venous phase CT images, respectively. Additionally, the performance of the DL algorithm was extensively evaluated and compared with manual segmentation using an independent clinical dataset of preoperative contrast-enhanced CT images from 44 patients with hepatic focal lesions. The accuracy of DL-based segmentation was quantitatively evaluated using the Dice Similarity Coefficient (DSC) and complementary metrics [Normalized Surface Dice (NSD) and Hausdorff distance_95 (HD95) for liver segmentation, Recall and Precision for hepatic vessel segmentation]. The processing time for DL and manual segmentation was also compared. RESULTS Our DL algorithm achieved accurate liver segmentation with DSC of 0.98, NSD of 0.92, and HD95 of 1.52 mm. DL-segmentation of hepatic veins, portal veins, and inferior vena cava attained DSC of 0.86, 0.89, and 0.94, respectively. Compared with the manual approach, the DL algorithm significantly outperformed with better segmentation results for both liver and hepatic vessels, with higher accuracy of liver and hepatic vessel segmentation (all p < 0.001) in independent 44 clinical data. In addition, the DL method significantly reduced the manual processing time of clinical postprocessing (p < 0.001). CONCLUSIONS The proposed DL algorithm potentially enabled accurate and rapid segmentation for liver and hepatic vessels using portal venous phase contrast CT images.
Collapse
Affiliation(s)
- Shengwei Li
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Xiao-Guang Li
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Fanyu Zhou
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Yumeng Zhang
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Zhixin Bie
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Lin Cheng
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Jinzhao Peng
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| | - Bin Li
- Minimally Invasive Tumor Therapy Center, Beijing Hospital, Peking Union Medical College, Beijing, China
| |
Collapse
|
3
|
Gross M, Huber S, Arora S, Ze'evi T, Haider SP, Kucukkaya AS, Iseke S, Kuhn TN, Gebauer B, Michallek F, Dewey M, Vilgrain V, Sartoris R, Ronot M, Jaffe A, Strazzabosco M, Chapiro J, Onofrey JA. Automated MRI liver segmentation for anatomical segmentation, liver volumetry, and the extraction of radiomics. Eur Radiol 2024:10.1007/s00330-023-10495-5. [PMID: 38217704 PMCID: PMC11245591 DOI: 10.1007/s00330-023-10495-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2023] [Revised: 09/20/2023] [Accepted: 10/29/2023] [Indexed: 01/15/2024]
Abstract
OBJECTIVES To develop and evaluate a deep convolutional neural network (DCNN) for automated liver segmentation, volumetry, and radiomic feature extraction on contrast-enhanced portal venous phase magnetic resonance imaging (MRI). MATERIALS AND METHODS This retrospective study included hepatocellular carcinoma patients from an institutional database with portal venous MRI. After manual segmentation, the data was randomly split into independent training, validation, and internal testing sets. From a collaborating institution, de-identified scans were used for external testing. The public LiverHccSeg dataset was used for further external validation. A 3D DCNN was trained to automatically segment the liver. Segmentation accuracy was quantified by the Dice similarity coefficient (DSC) with respect to manual segmentation. A Mann-Whitney U test was used to compare the internal and external test sets. Agreement of volumetry and radiomic features was assessed using the intraclass correlation coefficient (ICC). RESULTS In total, 470 patients met the inclusion criteria (63.9±8.2 years; 376 males) and 20 patients were used for external validation (41±12 years; 13 males). DSC segmentation accuracy of the DCNN was similarly high between the internal (0.97±0.01) and external (0.96±0.03) test sets (p=0.28) and demonstrated robust segmentation performance on public testing (0.93±0.03). Agreement of liver volumetry was satisfactory in the internal (ICC, 0.99), external (ICC, 0.97), and public (ICC, 0.85) test sets. Radiomic features demonstrated excellent agreement in the internal (mean ICC, 0.98±0.04), external (mean ICC, 0.94±0.10), and public (mean ICC, 0.91±0.09) datasets. CONCLUSION Automated liver segmentation yields robust and generalizable segmentation performance on MRI data and can be used for volumetry and radiomic feature extraction. CLINICAL RELEVANCE STATEMENT Liver volumetry, anatomic localization, and extraction of quantitative imaging biomarkers require accurate segmentation, but manual segmentation is time-consuming. A deep convolutional neural network demonstrates fast and accurate segmentation performance on T1-weighted portal venous MRI. KEY POINTS • This deep convolutional neural network yields robust and generalizable liver segmentation performance on internal, external, and public testing data. • Automated liver volumetry demonstrated excellent agreement with manual volumetry. • Automated liver segmentations can be used for robust and reproducible radiomic feature extraction.
Collapse
Affiliation(s)
- Moritz Gross
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA.
- Charité Center for Diagnostic and Interventional Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany.
| | - Steffen Huber
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
| | - Sandeep Arora
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
| | - Tal Ze'evi
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - Stefan P Haider
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Munich, Germany
| | - Ahmet S Kucukkaya
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
- Charité Center for Diagnostic and Interventional Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Simon Iseke
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
- Department of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany
| | - Tom Niklas Kuhn
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
- Department of Diagnostic and Interventional Radiology, University Duesseldorf, Duesseldorf, Germany
| | - Bernhard Gebauer
- Charité Center for Diagnostic and Interventional Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Florian Michallek
- Charité Center for Diagnostic and Interventional Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Marc Dewey
- Charité Center for Diagnostic and Interventional Radiology, Charité - Universitätsmedizin Berlin, Berlin, Germany
| | - Valérie Vilgrain
- Université Paris Cité, Île-de-France, Paris, France
- Department of Radiology, Hôpital Beaujon, AP-HP.Nord, Department of Radiology, Île-de-France, Clichy, France
| | - Riccardo Sartoris
- Université Paris Cité, Île-de-France, Paris, France
- Department of Radiology, Hôpital Beaujon, AP-HP.Nord, Department of Radiology, Île-de-France, Clichy, France
| | - Maxime Ronot
- Université Paris Cité, Île-de-France, Paris, France
- Department of Radiology, Hôpital Beaujon, AP-HP.Nord, Department of Radiology, Île-de-France, Clichy, France
| | - Ariel Jaffe
- Department of Internal Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Mario Strazzabosco
- Department of Internal Medicine, Yale University School of Medicine, New Haven, CT, USA
| | - Julius Chapiro
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA
| | - John A Onofrey
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, USA.
- Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
- Department of Urology, Yale University School of Medicine, New Haven, CT, USA.
| |
Collapse
|
4
|
Nashwan AJ, Alkhawaldeh IM, Shaheen N, Albalkhi I, Serag I, Sarhan K, Abujaber AA, Abd-Alrazaq A, Yassin MA. Using artificial intelligence to improve body iron quantification: A scoping review. Blood Rev 2023; 62:101133. [PMID: 37748945 DOI: 10.1016/j.blre.2023.101133] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 09/13/2023] [Accepted: 09/14/2023] [Indexed: 09/27/2023]
Abstract
This scoping review explores the potential of artificial intelligence (AI) in enhancing the screening, diagnosis, and monitoring of disorders related to body iron levels. A systematic search was performed to identify studies that utilize machine learning in iron-related disorders. The search revealed a wide range of machine learning algorithms used by different studies. Notably, most studies used a single data type. The studies varied in terms of sample sizes, participant ages, and geographical locations. AI's role in quantifying iron concentration is still in its early stages, yet its potential is significant. The question is whether AI-based diagnostic biomarkers can offer innovative approaches for screening, diagnosing, and monitoring of iron overload and anemia.
Collapse
Affiliation(s)
- Abdulqadir J Nashwan
- Department of Nursing, Hazm Mebaireek General Hospital, Hamad Medical Corporation, Doha, Qatar; Department of Public Health, College of Health Sciences, QU Health, Qatar University, Doha, Qatar.
| | | | - Nour Shaheen
- Faculty of Medicine, Alexandria University, Alexandria, Egypt
| | - Ibrahem Albalkhi
- College of Medicine, Alfaisal University, Riyadh, Saudi Arabia; Department of Neuroradiology, Great Ormond Street Hospital NHS Foundation Trust, Great Ormond St, London WC1N 3JH, United Kingdom.
| | - Ibrahim Serag
- Faculty of Medicine, Mansoura University, Mansoura, Egypt
| | - Khalid Sarhan
- Faculty of Medicine, Mansoura University, Mansoura, Egypt
| | - Ahmad A Abujaber
- Department of Nursing, Hazm Mebaireek General Hospital, Hamad Medical Corporation, Doha, Qatar.
| | - Alaa Abd-Alrazaq
- AI Center for Precision Health, Weill Cornell Medicine-Qatar, Doha, Qatar.
| | - Mohamed A Yassin
- Hematology and Oncology, Hamad General Hospital, Hamad Medical Corporation, Doha, Qatar.
| |
Collapse
|
5
|
Chen C, Zhou K, Wang Z, Zhang Q, Xiao R. All answers are in the images: A review of deep learning for cerebrovascular segmentation. Comput Med Imaging Graph 2023; 107:102229. [PMID: 37043879 DOI: 10.1016/j.compmedimag.2023.102229] [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: 10/24/2022] [Revised: 03/03/2023] [Accepted: 04/03/2023] [Indexed: 04/14/2023]
Abstract
Cerebrovascular imaging is a common examination. Its accurate cerebrovascular segmentation become an important auxiliary method for the diagnosis and treatment of cerebrovascular diseases, which has received extensive attention from researchers. Deep learning is a heuristic method that encourages researchers to derive answers from the images by driving datasets. With the continuous development of datasets and deep learning theory, it has achieved important success for cerebrovascular segmentation. Detailed survey is an important reference for researchers. To comprehensively analyze the newest cerebrovascular segmentation, we have organized and discussed researches centered on deep learning. This survey comprehensively reviews deep learning for cerebrovascular segmentation since 2015, it mainly includes sliding window based models, U-Net based models, other CNNs based models, small-sample based models, semi-supervised or unsupervised models, fusion based models, Transformer based models, and graphics based models. We organize the structures, improvement, and important parameters of these models, as well as analyze development trends and quantitative assessment. Finally, we have discussed the challenges and opportunities of possible research directions, hoping that our survey can provide researchers with convenient reference.
Collapse
Affiliation(s)
- Cheng Chen
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Kangneng Zhou
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Zhiliang Wang
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China
| | - Qian Zhang
- Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, Beijing 100070, China; China National Clinical Research Center for Neurological Diseases, Beijing 100070, China
| | - Ruoxiu Xiao
- School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing 100083, China; Shunde Innovation School, University of Science and Technology Beijing, Foshan 100024, China.
| |
Collapse
|
6
|
Shen J, Lu S, Qu R, Zhao H, Zhang Y, Chang A, Zhang L, Fu W, Zhang Z. Measuring distance from lowest boundary of rectal tumor to anal verge on CT images using pyramid attention pooling transformer. Comput Biol Med 2023; 155:106675. [PMID: 36805228 DOI: 10.1016/j.compbiomed.2023.106675] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2022] [Revised: 01/23/2023] [Accepted: 02/11/2023] [Indexed: 02/16/2023]
Abstract
Accurately measuring the Distance from the lowest boundary of rectal tumor To the Anal Verge (DTAV) is critical for developing optimal surgical plans for treating patients with rectal cancer. DTAV was traditionally estimated by colonoscopy or manual measurement on computed tomography (CT) images. However, colonoscopy brings substantial pains to the patient. As for manual measurement on CT images, it is time-consuming and its accuracy depends on the surgeon's expertise. In this work, we present a novel method for automatically measuring DTAV from sagittal CT images. The success of our method is mainly credited to a pyramid attention pooling (PAP) transformer architecture, which naturally entangles global lesion localization and local boundary delineation. Our method automatically generates the rectum's centerline based on a segmented rectum and tumor image to simulate the manual measurement of DTAV. We conduct a comprehensive evaluation of the method with a newly collected rectum tumor CT image dataset. On a test dataset of 48 patients' CT images with rectal tumors, the mean absolute difference between our method and the gold standard is 1.74 cm, which is a significant improvement of 1.29 cm over that measured by a resident surgeon (P < 0.001). In addition, The results measured by the resident surgeon referring to our segmentation results improved by 1.46 cm compared to the results measured independently by the residents. As experimentally demonstrated, our method exhibits great application potential in clinical scenarios.
Collapse
Affiliation(s)
- Jianjun Shen
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Siyi Lu
- Department of General Surgery, Peking University Third Hospital, Beijing 100191, China; Cancer Center, Peking University Third Hospital, Beijing 100191, China
| | - Ruize Qu
- Department of General Surgery, Peking University Third Hospital, Beijing 100191, China; Cancer Center, Peking University Third Hospital, Beijing 100191, China
| | - Hao Zhao
- Intel Lab, Beijing 100190, China
| | - Yu Zhang
- School of Astronautics, Beihang University, Beijing 100191, China
| | - An Chang
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
| | - Li Zhang
- Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
| | - Wei Fu
- Department of General Surgery, Peking University Third Hospital, Beijing 100191, China; Cancer Center, Peking University Third Hospital, Beijing 100191, China.
| | - Zhipeng Zhang
- Department of General Surgery, Peking University Third Hospital, Beijing 100191, China; Cancer Center, Peking University Third Hospital, Beijing 100191, China.
| |
Collapse
|
7
|
Techniques and Algorithms for Hepatic Vessel Skeletonization in Medical Images: A Survey. ENTROPY 2022; 24:e24040465. [PMID: 35455128 PMCID: PMC9031516 DOI: 10.3390/e24040465] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Revised: 03/21/2022] [Accepted: 03/23/2022] [Indexed: 02/01/2023]
Abstract
Hepatic vessel skeletonization serves as an important means of hepatic vascular analysis and vessel segmentation. This paper presents a survey of techniques and algorithms for hepatic vessel skeletonization in medical images. We summarized the latest developments and classical approaches in this field. These methods are classified into five categories according to their methodological characteristics. The overview and brief assessment of each category are provided in the corresponding chapters, respectively. We provide a comprehensive summary among the cited publications, image modalities and datasets from various aspects, which hope to reveal the pros and cons of every method, summarize its achievements and discuss the challenges and future trends.
Collapse
|
8
|
Gross M, Spektor M, Jaffe A, Kucukkaya AS, Iseke S, Haider SP, Strazzabosco M, Chapiro J, Onofrey JA. Improved performance and consistency of deep learning 3D liver segmentation with heterogeneous cancer stages in magnetic resonance imaging. PLoS One 2021; 16:e0260630. [PMID: 34852007 PMCID: PMC8635384 DOI: 10.1371/journal.pone.0260630] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Accepted: 11/13/2021] [Indexed: 11/23/2022] Open
Abstract
PURPOSE Accurate liver segmentation is key for volumetry assessment to guide treatment decisions. Moreover, it is an important pre-processing step for cancer detection algorithms. Liver segmentation can be especially challenging in patients with cancer-related tissue changes and shape deformation. The aim of this study was to assess the ability of state-of-the-art deep learning 3D liver segmentation algorithms to generalize across all different Barcelona Clinic Liver Cancer (BCLC) liver cancer stages. METHODS This retrospective study, included patients from an institutional database that had arterial-phase T1-weighted magnetic resonance images with corresponding manual liver segmentations. The data was split into 70/15/15% for training/validation/testing each proportionally equal across BCLC stages. Two 3D convolutional neural networks were trained using identical U-net-derived architectures with equal sized training datasets: one spanning all BCLC stages ("All-Stage-Net": AS-Net), and one limited to early and intermediate BCLC stages ("Early-Intermediate-Stage-Net": EIS-Net). Segmentation accuracy was evaluated by the Dice Similarity Coefficient (DSC) on a dataset spanning all BCLC stages and a Wilcoxon signed-rank test was used for pairwise comparisons. RESULTS 219 subjects met the inclusion criteria (170 males, 49 females, 62.8±9.1 years) from all BCLC stages. Both networks were trained using 129 subjects: AS-Net training comprised 19, 74, 18, 8, and 10 BCLC 0, A, B, C, and D patients, respectively; EIS-Net training comprised 21, 86, and 22 BCLC 0, A, and B patients, respectively. DSCs (mean±SD) were 0.954±0.018 and 0.946±0.032 for AS-Net and EIS-Net (p<0.001), respectively. The AS-Net 0.956±0.014 significantly outperformed the EIS-Net 0.941±0.038 on advanced BCLC stages (p<0.001) and yielded similarly good segmentation performance on early and intermediate stages (AS-Net: 0.952±0.021; EIS-Net: 0.949±0.027; p = 0.107). CONCLUSION To ensure robust segmentation performance across cancer stages that is independent of liver shape deformation and tumor burden, it is critical to train deep learning models on heterogeneous imaging data spanning all BCLC stages.
Collapse
Affiliation(s)
- Moritz Gross
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Charité Center for Diagnostic and Interventional Radiology, Charité—Universitätsmedizin Berlin, Berlin, Germany
| | - Michael Spektor
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
| | - Ariel Jaffe
- Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut, United States of America
| | - Ahmet S. Kucukkaya
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Charité Center for Diagnostic and Interventional Radiology, Charité—Universitätsmedizin Berlin, Berlin, Germany
| | - Simon Iseke
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Department of Diagnostic and Interventional Radiology, Pediatric Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany
| | - Stefan P. Haider
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Department of Otorhinolaryngology, University Hospital of Ludwig Maximilians Universität München, Munich, Germany
| | - Mario Strazzabosco
- Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut, United States of America
| | - Julius Chapiro
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
| | - John A. Onofrey
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Department of Urology, Yale University School of Medicine, New Haven, Connecticut, United States of America
- Department of Biomedical Engineering, Yale University, New Haven, Connecticut, United States of America
| |
Collapse
|
9
|
Hill CE, Biasiolli L, Robson MD, Grau V, Pavlides M. Emerging artificial intelligence applications in liver magnetic resonance imaging. World J Gastroenterol 2021; 27:6825-6843. [PMID: 34790009 PMCID: PMC8567471 DOI: 10.3748/wjg.v27.i40.6825] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/06/2021] [Revised: 04/16/2021] [Accepted: 09/30/2021] [Indexed: 02/06/2023] Open
Abstract
Chronic liver diseases (CLDs) are becoming increasingly more prevalent in modern society. The use of imaging techniques for early detection, such as magnetic resonance imaging (MRI), is crucial in reducing the impact of these diseases on healthcare systems. Artificial intelligence (AI) algorithms have been shown over the past decade to excel at image-based analysis tasks such as detection and segmentation. When applied to liver MRI, they have the potential to improve clinical decision making, and increase throughput by automating analyses. With Liver diseases becoming more prevalent in society, the need to implement these techniques to utilize liver MRI to its full potential, is paramount. In this review, we report on the current methods and applications of AI methods in liver MRI, with a focus on machine learning and deep learning methods. We assess four main themes of segmentation, classification, image synthesis and artefact detection, and their respective potential in liver MRI and the wider clinic. We provide a brief explanation of some of the algorithms used and explore the current challenges affecting the field. Though there are many hurdles to overcome in implementing AI methods in the clinic, we conclude that AI methods have the potential to positively aid healthcare professionals for years to come.
Collapse
Affiliation(s)
- Charles E Hill
- Department of Engineering Science, University of Oxford, Oxford OX3 7DQ, United Kingdom
| | - Luca Biasiolli
- Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, United Kingdom
| | | | - Vicente Grau
- Department of Engineering, University of Oxford, Oxford OX3 7DQ, United Kingdom
| | - Michael Pavlides
- Oxford Centre for Clinical Magnetic Resonance Research, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, United Kingdom
- Translational Gastroenterology Unit, University of Oxford, Oxford OX3 9DU, United Kingdom
- Oxford NIHR Biomedical Research Centre, University of Oxford, Oxford OX3 9DU, United Kingdom
| |
Collapse
|
10
|
Wantanajittikul K, Saiviroonporn P, Saekho S, Krittayaphong R, Viprakasit V. An automated liver segmentation in liver iron concentration map using fuzzy c-means clustering combined with anatomical landmark data. BMC Med Imaging 2021; 21:138. [PMID: 34583631 PMCID: PMC8477544 DOI: 10.1186/s12880-021-00669-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2021] [Accepted: 09/15/2021] [Indexed: 11/14/2022] Open
Abstract
Background To estimate median liver iron concentration (LIC) calculated from magnetic resonance imaging, excluded vessels of the liver parenchyma region were defined manually. Previous works proposed the automated method for excluding vessels from the liver region. However, only user-defined liver region remained a manual process. Therefore, this work aimed to develop an automated liver region segmentation technique to automate the whole process of median LIC calculation. Methods 553 MR examinations from 471 thalassemia major patients were used in this study. LIC maps (in mg/g dry weight) were calculated and used as the input of segmentation procedures. Anatomical landmark data were detected and used to restrict ROI. After that, the liver region was segmented using fuzzy c-means clustering and reduced segmentation errors by morphological processes. According to the clinical application, erosion with a suitable size of the structuring element was applied to reduce the segmented liver region to avoid uncertainty around the edge of the liver. The segmentation results were evaluated by comparing with manual segmentation performed by a board-certified radiologist. Results The proposed method was able to produce a good grade output in approximately 81% of all data. Approximately 11% of all data required an easy modification step. The rest of the output, approximately 8%, was an unsuccessful grade and required manual intervention by a user. For the evaluation matrices, percent dice similarity coefficient (%DSC) was in the range 86–92, percent Jaccard index (%JC) was 78–86, and Hausdorff distance (H) was 14–28 mm, respectively. In this study, percent false positive (%FP) and percent false negative (%FN) were applied to evaluate under- and over-segmentation that other evaluation matrices could not handle. The average of operation times could be reduced from 10 s per case using traditional method, to 1.5 s per case using our proposed method. Conclusion The experimental results showed that the proposed method provided an effective automated liver segmentation technique, which can be applied clinically for automated median LIC calculation in thalassemia major patients.
Collapse
Affiliation(s)
- Kittichai Wantanajittikul
- Department of Radiologic Technology, Faculty of Associated Medical Sciences, Chiang Mai University, Chiang Mai, Thailand
| | - Pairash Saiviroonporn
- Division of Diagnostic Radiology, Department of Radiology, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok, 10700, Thailand.
| | - Suwit Saekho
- Department of Radiologic Technology, Faculty of Associated Medical Sciences, Chiang Mai University, Chiang Mai, Thailand
| | - Rungroj Krittayaphong
- Division of Cardiology, Department of Medicine, Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Vip Viprakasit
- Haematology/Oncology Division, Department of Pediatrics and Thalassemia Center, Siriraj Hospital, Mahidol University, Bangkok, Thailand
| |
Collapse
|
11
|
Xin M, Wen J, Wang Y, Yu W, Fang B, Hu J, Xu Y, Linghu C. Blood Vessel Segmentation Based on the 3D Residual U-Net. INT J PATTERN RECOGN 2021. [DOI: 10.1142/s021800142157007x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
In this paper, we propose blood vessel segmentation based on the 3D residual U-Net method. First, we integrate the residual block structure into the 3D U-Net. By exploring the influence of adding residual blocks at different positions in the 3D U-Net, we establish a novel and effective 3D residual U-Net. In addition, to address the challenges of pixel imbalance, vessel boundary segmentation, and small vessel segmentation, we develop a new weighted Dice loss function with a better effect than the weighted cross-entropy loss function. When training the model, we adopted a two-stage method from coarse-to-fine. In the fine stage, a local segmentation method of 3D sliding window is added. In the model testing phase, we used the 3D fixed-point method. Furthermore, we employ the 3D morphological closed operation to smooth the surfaces of vessels and volume analysis to remove noise blocks. To verify the accuracy and stability of our method, we compare our method with FCN, 3D DenseNet, and 3D U-Net. The experimental results indicate that our method has higher accuracy and better stability than the other studied methods and that the average Dice coefficients for hepatic veins and portal veins reach 71.7% and 76.5% in the coarse stage and 72.5% and 77.2% in the fine stage, respectively. In order to verify the robustness of the model, we conducted the same comparative experiment on the brain vessel datasets, and the average Dice coefficient reached 87.2%.
Collapse
Affiliation(s)
- Mulin Xin
- College of Computer Science, Chongqing University, Chongqing 401331, P. R. China
| | - Jing Wen
- College of Computer Science, Chongqing University, Chongqing 401331, P. R. China
| | - Yi Wang
- College of Computer Science, Chongqing University, Chongqing 401331, P. R. China
| | - Wei Yu
- College of Computer Science, Chongqing University, Chongqing 401331, P. R. China
| | - Bin Fang
- College of Computer Science, Chongqing University, Chongqing 401331, P. R. China
| | - Jun Hu
- Southwest Hospital, Army Military Medical University, Chongqing 401331, P. R. China
| | - Yongmei Xu
- Southwest Hospital, Army Military Medical University, Chongqing 401331, P. R. China
| | - Chunhong Linghu
- Southwest Hospital, Army Military Medical University, Chongqing 401331, P. R. China
| |
Collapse
|
12
|
Ivashchenko OV, Smit JN, Nijkamp J, Ter Beek LC, Rijkhorst EJ, Kok NFM, Ruers TJM, Kuhlmann KFD. Clinical Implementation of In-House Developed MR-Based Patient-Specific 3D Models of Liver Anatomy. Eur Surg Res 2021; 61:143-152. [PMID: 33508828 DOI: 10.1159/000513335] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2020] [Accepted: 11/20/2020] [Indexed: 11/19/2022]
Abstract
Knowledge of patient-specific liver anatomy is key to patient safety during major hepatobiliary surgery. Three-dimensional (3D) models of patient-specific liver anatomy based on diagnostic MRI images can provide essential vascular and biliary anatomical insight during surgery. However, a method for generating these is not yet publicly available. This paper describes how these 3D models of the liver can be generated using open source software, and then subsequently integrated into a sterile surgical environment. The most common image quality aspects that degrade the quality of the 3D models as well possible ways of eliminating these are also discussed. Per patient, a single diagnostic multiphase MRI scan with hepatospecific contrast agent was used for automated segmentation of liver contour, arterial, portal, and venous anatomy, and the biliary tree. Subsequently, lesions were delineated manually. The resulting interactive 3D model could be accessed during surgery on a sterile covered tablet. Up to now, such models have been used in 335 surgical procedures. Their use simplified the surgical treatment of patients with a high number of liver metastases and contributed to the localization of vanished lesions in cases of a radiological complete response to neoadjuvant treatment. They facilitated perioperative verification of the relationship of tumors and the surrounding vascular and biliary anatomy, and eased decision-making before and during surgery.
Collapse
Affiliation(s)
- Oleksandra V Ivashchenko
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands, .,Department of Radiology, Leiden University Medical Center, Medical Physics Group, Leiden, The Netherlands,
| | - Jasper N Smit
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| | - Jasper Nijkamp
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| | - Leon C Ter Beek
- Department of Medical Physics and Technology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| | - Erik-Jan Rijkhorst
- Department of Medical Physics and Technology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| | - Niels F M Kok
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| | - Theo J M Ruers
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands.,Faculty of Science and Technology (TNW), Nanobiophysics Group (NBP), University of Twente, Enschede, The Netherlands
| | - Koert F D Kuhlmann
- Department of Surgical Oncology, The Netherlands Cancer Institute - Antoni van Leeuwenhoek Hospital, Amsterdam, The Netherlands
| |
Collapse
|