1
|
Qi H, Wang Z, Qi X, Shi Y, Xie T. Ultrasound image segmentation of renal tumors based on UNet++ with fusion of multiscale residuals and dual attention. Phys Med Biol 2024; 69:075002. [PMID: 38412532 DOI: 10.1088/1361-6560/ad2d7f] [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: 09/29/2023] [Accepted: 02/27/2024] [Indexed: 02/29/2024]
Abstract
Objective. Laparoscopic renal unit-preserving resection is a routine and effective means of treating renal tumors. Image segmentation is an essential part before tumor resection. The current segmentation method mainly relies on doctors manual delineation, which is time-consuming, labor-intensive, and influenced by their personal experience and ability. And the image quality of segmentation is low, with problems such as blurred edges, unclear size and shape, which are not conducive to clinical diagnosis.Approach. To address these problems, we propose an automated segmentation method, i.e. the UNet++ algorithm fusing multiscale residuals and dual attention (MRDA_UNet++). It replaces two consecutive 3 × 3 convolutions in UNet++ with the 'MultiRes block' module, which incorporates coordinate attention to fuse features from different scales and suppress the impact of background noise. Furthermore, an attention gate is also added at the short connections to enhance the ability of the network to extract features from the target area.Main results. The experimental results show that MRDA_UNet++ achieves 93.18%, 92.87%, 93.66%, and 92.09% on the real-world dataset for MIoU, Dice, Precision, and Recall, respectively. Compared to the baseline model UNet++ on three public datasets, the MIoU, Dice, and Recall metrics improved by 6.00%, 7.90% and 18.09% respectively for BUSI, 0.39%, 0.27% and 1.03% for Dataset C, and 1.37%, 1.75% and 1.30% for DDTI.Significance. The proposed MRDA_UNet++ exhibits obvious advantages in feature extraction, which can not only significantly reduce the workload of doctors, but also further decrease the risk of misdiagnosis. It is of great value to assist doctors diagnosis in the clinic.
Collapse
Affiliation(s)
- Hui Qi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Zhen Wang
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Xiaobo Qi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Ying Shi
- School of Computer Science and Technology, Taiyuan Normal University, Shanxi 030619, People's Republic of China
| | - Tianwu Xie
- Institute of Radiation Medicine, Fudan University, Shanghai 200032, People's Republic of China
| |
Collapse
|
2
|
Cellina M, Cè M, Rossini N, Cacioppa LM, Ascenti V, Carrafiello G, Floridi C. Computed Tomography Urography: State of the Art and Beyond. Tomography 2023; 9:909-930. [PMID: 37218935 PMCID: PMC10204399 DOI: 10.3390/tomography9030075] [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: 02/15/2023] [Revised: 04/26/2023] [Accepted: 04/27/2023] [Indexed: 05/24/2023] Open
Abstract
Computed Tomography Urography (CTU) is a multiphase CT examination optimized for imaging kidneys, ureters, and bladder, complemented by post-contrast excretory phase imaging. Different protocols are available for contrast administration and image acquisition and timing, with different strengths and limits, mainly related to kidney enhancement, ureters distension and opacification, and radiation exposure. The availability of new reconstruction algorithms, such as iterative and deep-learning-based reconstruction has dramatically improved the image quality and reducing radiation exposure at the same time. Dual-Energy Computed Tomography also has an important role in this type of examination, with the possibility of renal stone characterization, the availability of synthetic unenhanced phases to reduce radiation dose, and the availability of iodine maps for a better interpretation of renal masses. We also describe the new artificial intelligence applications for CTU, focusing on radiomics to predict tumor grading and patients' outcome for a personalized therapeutic approach. In this narrative review, we provide a comprehensive overview of CTU from the traditional to the newest acquisition techniques and reconstruction algorithms, and the possibility of advanced imaging interpretation to provide an up-to-date guide for radiologists who want to better comprehend this technique.
Collapse
Affiliation(s)
- Michaela Cellina
- Radiology Department, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Piazza Principessa Clotilde 3, 20121 Milan, Italy
| | - Maurizio Cè
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy
| | - Nicolo’ Rossini
- Department of Clinical, Special and Dental Sciences, University Politecnica delle Marche, 60126 Ancona, Italy
| | - Laura Maria Cacioppa
- Division of Interventional Radiology, Department of Radiological Sciences, University Politecnica delle Marche, 60126 Ancona, Italy
| | - Velio Ascenti
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy
| | - Gianpaolo Carrafiello
- Radiology Department, Policlinico di Milano Ospedale Maggiore|Fondazione IRCCS Ca’ Granda, Via Francesco Sforza 35, 20122 Milan, Italy
| | - Chiara Floridi
- Division of Interventional Radiology, Department of Radiological Sciences, University Politecnica delle Marche, 60126 Ancona, Italy
- Division of Special and Pediatric Radiology, Department of Radiology, University Hospital “Umberto I-Lancisi-Salesi”, 60126 Ancona, Italy
| |
Collapse
|
3
|
Reponen J, Niinimäki J. Emergence of teleradiology, PACS, and other radiology IT solutions in Acta Radiologica. Acta Radiol 2021; 62:1525-1533. [PMID: 34637341 DOI: 10.1177/02841851211051003] [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] [Indexed: 11/15/2022]
Abstract
For this historical review, we searched a database containing all the articles published in Acta Radiologica during its 100-year history to find those on the use of information technology (IT) in radiology. After reading the full texts, we selected the presented articles according to major radiology IT domains such as teleradiology, picture archiving and communication systems, image processing, image analysis, and computer-aided diagnostics in order to describe the development as it appeared in the journal. Publications generally follow IT megatrends, but because the contents of Acta Radiologica are mainly clinically oriented, some technology achievements appear later than they do in journals discussing mainly imaging informatics topics.
Collapse
Affiliation(s)
- Jarmo Reponen
- Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland
- Medical Research Center Oulu, Oulu University Hospital and University of Oulu, Oulu, Finland
| | - Jaakko Niinimäki
- Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland
- Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland
| |
Collapse
|
4
|
Baghdadi A, Aldhaam NA, Elsayed AS, Hussein AA, Cavuoto LA, Kauffman E, Guru KA. Automated differentiation of benign renal oncocytoma and chromophobe renal cell carcinoma on computed tomography using deep learning. BJU Int 2020; 125:553-560. [PMID: 31901213 DOI: 10.1111/bju.14985] [Citation(s) in RCA: 33] [Impact Index Per Article: 8.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022]
Abstract
OBJECTIVES To develop and evaluate the feasibility of an objective method using artificial intelligence (AI) and image processing in a semi-automated fashion for tumour-to-cortex peak early-phase enhancement ratio (PEER) in order to differentiate CD117(+) oncocytoma from the chromophobe subtype of renal cell carcinoma (ChRCC) using convolutional neural networks (CNNs) on computed tomography imaging. METHODS The CNN was trained and validated to identify the kidney + tumour areas in images from 192 patients. The tumour type was differentiated through automated measurement of PEER after manual segmentation of tumours. The performance of this diagnostic model was compared with that of manual expert identification and tumour pathology with regard to accuracy, sensitivity and specificity, along with the root-mean-square error (RMSE), for the remaining 20 patients with CD117(+) oncocytoma or ChRCC. RESULTS The mean ± sd Dice similarity score for segmentation was 0.66 ± 0.14 for the CNN model to identify the kidney + tumour areas. PEER evaluation achieved accuracy of 95% in tumour type classification (100% sensitivity and 89% specificity) compared with the final pathology results (RMSE of 0.15 for PEER ratio). CONCLUSIONS We have shown that deep learning could help to produce reliable discrimination of CD117(+) benign oncocytoma and malignant ChRCC through PEER measurements obtained by computer vision.
Collapse
Affiliation(s)
- Amir Baghdadi
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA.,Department of Industrial and Systems Engineering, University at Buffalo, Buffalo, NY, USA
| | - Naif A Aldhaam
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Ahmed S Elsayed
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Ahmed A Hussein
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Lora A Cavuoto
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA.,Department of Industrial and Systems Engineering, University at Buffalo, Buffalo, NY, USA
| | - Eric Kauffman
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| | - Khurshid A Guru
- Department of Urology, Roswell Park Comprehensive Cancer Center, Buffalo, NY, USA
| |
Collapse
|
5
|
Detection of Renal Calculi in Ultrasound Image Using Meta-Heuristic Support Vector Machine. J Med Syst 2019; 43:300. [DOI: 10.1007/s10916-019-1407-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2019] [Accepted: 06/26/2019] [Indexed: 10/26/2022]
|
6
|
Yu Q, Shi Y, Sun J, Gao Y, Zhu J, Dai Y. Crossbar-Net: A Novel Convolutional Neural Network for Kidney Tumor Segmentation in CT Images. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2019; 28:4060-4074. [PMID: 30892206 DOI: 10.1109/tip.2019.2905537] [Citation(s) in RCA: 34] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
Due to the unpredictable location, fuzzy texture and diverse shape, accurate segmentation of the kidney tumor in CT images is an important yet challenging task. To this end, we in this paper present a cascaded trainable segmentation model termed as Crossbar-Net. Our method combines two novel schemes: (1) we originally proposed the crossbar patches, which consists of two orthogonal non-squared patches (i.e., the vertical patch and horizontal patch). The crossbar patches are able to capture both the global and local appearance information of the kidney tumors from both the vertical and horizontal directions simultaneously. (2) With the obtained crossbar patches, we iteratively train two sub-models (i.e., horizontal sub-model and vertical sub-model) in a cascaded training manner. During the training, the trained sub-models are encouraged to become more focus on the difficult parts of the tumor automatically (i.e., mis-segmented regions). Specifically, the vertical (horizontal) sub-model is required to help segment the mis-segmented regions for the horizontal (vertical) sub-model. Thus, the two sub-models could complement each other to achieve the self-improvement until convergence. In the experiment, we evaluate our method on a real CT kidney tumor dataset which is collected from 94 different patients including 3,500 CT slices. Compared with the state-of-the-art segmentation methods, the results demonstrate the superior performance of our method on the Dice similarity coefficient, true positive fraction, centroid distance and Hausdorff distance. Moreover, to exploit the generalization to other segmentation tasks, we also extend our Crossbar-Net to two related segmentation tasks: (1) cardiac segmentation in MR images and (2) breast mass segmentation in X-ray images, showing the promising results for these two tasks. Our implementation is released at https: //github.com/Qianyu1226/Crossbar-Net.
Collapse
|
7
|
Quantitative computer-aided diagnostic algorithm for automated detection of peak lesion attenuation in differentiating clear cell from papillary and chromophobe renal cell carcinoma, oncocytoma, and fat-poor angiomyolipoma on multiphasic multidetector computed tomography. Abdom Radiol (NY) 2017; 42:1919-1928. [PMID: 28280876 DOI: 10.1007/s00261-017-1095-6] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/19/2022]
Abstract
OBJECTIVE To evaluate the performance of a novel, quantitative computer-aided diagnostic (CAD) algorithm on four-phase multidetector computed tomography (MDCT) to detect peak lesion attenuation to enable differentiation of clear cell renal cell carcinoma (ccRCC) from chromophobe RCC (chRCC), papillary RCC (pRCC), oncocytoma, and fat-poor angiomyolipoma (fp-AML). MATERIALS AND METHODS We queried our clinical databases to obtain a cohort of histologically proven renal masses with preoperative MDCT with four phases [unenhanced (U), corticomedullary (CM), nephrographic (NP), and excretory (E)]. A whole lesion 3D contour was obtained in all four phases. The CAD algorithm determined a region of interest (ROI) of peak lesion attenuation within the 3D lesion contour. For comparison, a manual ROI was separately placed in the most enhancing portion of the lesion by visual inspection for a reference standard, and in uninvolved renal cortex. Relative lesion attenuation for both CAD and manual methods was obtained by normalizing the CAD peak lesion attenuation ROI (and the reference standard manually placed ROI) to uninvolved renal cortex with the formula [(peak lesion attenuation ROI - cortex ROI)/cortex ROI] × 100%. ROC analysis and area under the curve (AUC) were used to assess diagnostic performance. Bland-Altman analysis was used to compare peak ROI between CAD and manual method. RESULTS The study cohort comprised 200 patients with 200 unique renal masses: 106 (53%) ccRCC, 32 (16%) oncocytomas, 18 (9%) chRCCs, 34 (17%) pRCCs, and 10 (5%) fp-AMLs. In the CM phase, CAD-derived ROI enabled characterization of ccRCC from chRCC, pRCC, oncocytoma, and fp-AML with AUCs of 0.850 (95% CI 0.732-0.968), 0.959 (95% CI 0.930-0.989), 0.792 (95% CI 0.716-0.869), and 0.825 (95% CI 0.703-0.948), respectively. On Bland-Altman analysis, there was excellent agreement of CAD and manual methods with mean differences between 14 and 26 HU in each phase. CONCLUSION A novel, quantitative CAD algorithm enabled robust peak HU lesion detection and discrimination of ccRCC from other renal lesions with similar performance compared to the manual method.
Collapse
|
8
|
Diagnostic accuracy of contrast-enhanced computed tomography and contrast-enhanced magnetic resonance imaging of small renal masses in real practice: sensitivity and specificity according to subjective radiologic interpretation. World J Surg Oncol 2016; 14:260. [PMID: 27729042 PMCID: PMC5059933 DOI: 10.1186/s12957-016-1017-z] [Citation(s) in RCA: 29] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/17/2015] [Accepted: 10/04/2016] [Indexed: 12/26/2022] Open
Abstract
Background The aim of this study was to investigate the diagnostic accuracy of contrast-enhanced computed tomography (CT) and contrast-enhanced magnetic resonance imaging (MRI) of small renal masses in real practice. Methods Contrast-enhanced CT and MRI were performed between February 2008 and February 2013 on 68 patients who had suspected small (≤4 cm) renal cell carcinoma (RCC) based on ultrasonographic measurements. CT and MRI radiographs were reviewed, and the findings of small renal masses were re-categorized into five dichotomized scales by the same two radiologists who had interpreted the original images. Receiver operating characteristics curve analysis was performed, and sensitivity and specificity were determined. Results Among the 68 patients, 60 (88.2 %) had RCC and eight had benign disease. The diagnostic accuracy rates of contrast-enhanced CT and MRI were 79.41 and 88.23 %, respectively. Diagnostic accuracy was greater when using contrast-enhanced MRI because too many masses (67.6 %) were characterized as “4 (probably solid cancer) or 5 (definitely solid cancer).” The sensitivity of contrast-enhanced CT and MRI for predicting RCC were 79.7 and 88.1 %, respectively. The specificities of contrast-enhanced CT and MRI for predicting RCC were 44.4 and 33.3 %, respectively. Fourteen diagnoses (20.5 %) were missed or inconsistent compared with the final pathological diagnoses. One appropriate nephroureterectomy and five unnecessary percutaneous biopsies were performed for RCC. Seven unnecessary partial nephrectomies were performed for benign disease. Conclusions Although contrast-enhanced CT and MRI showed high sensitivity for detecting small renal masses, specificity remained low.
Collapse
|
9
|
Gloger O, Tönnies K, Mensel B, Völzke H. Fully automatized renal parenchyma volumetry using a support vector machine based recognition system for subject-specific probability map generation in native MR volume data. Phys Med Biol 2015; 60:8675-93. [DOI: 10.1088/0031-9155/60/22/8675] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
|
10
|
Gloger O, Tönnies K, Laqua R, Völzke H. Fully Automated Renal Tissue Volumetry in MR Volume Data Using Prior-Shape-Based Segmentation in Subject-Specific Probability Maps. IEEE Trans Biomed Eng 2015; 62:2338-51. [DOI: 10.1109/tbme.2015.2425935] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
|
11
|
Mitra S, Uma Shankar B. Medical image analysis for cancer management in natural computing framework. Inf Sci (N Y) 2015. [DOI: 10.1016/j.ins.2015.02.015] [Citation(s) in RCA: 46] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
12
|
Liu J, Wang S, Linguraru MG, Yao J, Summers RM. Computer-aided detection of exophytic renal lesions on non-contrast CT images. Med Image Anal 2014; 19:15-29. [PMID: 25189363 DOI: 10.1016/j.media.2014.07.005] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2013] [Revised: 07/18/2014] [Accepted: 07/24/2014] [Indexed: 12/11/2022]
Abstract
Renal lesions are important extracolonic findings on computed tomographic colonography (CTC). They are difficult to detect on non-contrast CTC images due to low image contrast with surrounding objects. In this paper, we developed a novel computer-aided diagnosis system to detect a subset of renal lesions, exophytic lesions, by (1) exploiting efficient belief propagation to segment kidneys, (2) establishing an intrinsic manifold diffusion on kidney surface, (3) searching for potential lesion-caused protrusions with local maximum diffusion response, and (4) exploring novel shape descriptors, including multi-scale diffusion response, with machine learning to classify exophytic renal lesions. Experimental results on the validation dataset with 167 patients revealed that manifold diffusion significantly outperformed conventional shape features (p<1e-3) and resulted in 95% sensitivity with 15 false positives per patient for detecting exophytic renal lesions. Fivefold cross-validation also demonstrated that our method could stably detect exophytic renal lesions. These encouraging results demonstrated that manifold diffusion is a key means to enable accurate computer-aided diagnosis of renal lesions.
Collapse
Affiliation(s)
- Jianfei Liu
- Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Shijun Wang
- Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Marius George Linguraru
- Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Medical Center, Washington, DC, USA; Departments of Radiology and Pediatrics, School of Medicine and Health Sciences, George Washington University, Washington DC, USA
| | - Jianhua Yao
- Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Ronald M Summers
- Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA.
| |
Collapse
|
13
|
Kim JH, Bae JH, Lee KW, Kim ME, Park SJ, Park JY. Predicting the histology of small renal masses using preoperative dynamic contrast-enhanced magnetic resonance imaging. Urology 2012; 80:872-6. [PMID: 22854134 DOI: 10.1016/j.urology.2012.06.001] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2012] [Revised: 05/22/2012] [Accepted: 06/01/2012] [Indexed: 10/28/2022]
Abstract
OBJECTIVE To study whether magnetic resonance imaging can predict the histologic type of small renal cell carcinoma. METHODS Dynamic contrast-enhanced magnetic resonance imaging was performed in 63 patients with computed tomography- or ultrasonography-suspected small (≤ 4 cm) renal cell carcinoma from February 2008 to February 2010. Percentage signal intensity change, tumor-to-cortex enhancement index during precontrast phase, corticomedullary phase, and nephrogenic phase were investigated. RESULTS Among the 60 patients, 42 were proven to have clear cell renal cell carcinoma and 18 patients were proven to have non-clear cell renal cell carcinoma (10 patients with papillary renal cell carcinoma, 8 patients with chromophobe renal cell carcinoma). The percentage signal intensity change in the clear cell type was higher only in the corticomedullary phase (P = .002). The tumor-to-cortex enhancement index in the clear cell type was higher in the corticomedullary and nephrogenic phases (P = .007 and P = .041, respectively). The most valuable marker was percentage signal intensity change in the corticomedullary phase (area under the receiver operating characteristic curve 0.85). The cut-off value of percentage signal intensity change in the corticomedullary phase was 173%, and the sensitivity and specificity were 81% and 87.5%, respectively. CONCLUSION Dynamic contrast-enhanced magnetic resonance imaging could be useful for discriminating the clear cell type from non-clear cell type in small renal cell carcinoma with high sensitivity and specificity.
Collapse
Affiliation(s)
- Jae Heon Kim
- Department of Urology, Soonchunhyang University Hospital, Seoul, Korea
| | | | | | | | | | | |
Collapse
|
14
|
Gloger O, Tönies KD, Liebscher V, Kugelmann B, Laqua R, Völzke H. Prior shape level set segmentation on multistep generated probability maps of MR datasets for fully automatic kidney parenchyma volumetry. IEEE TRANSACTIONS ON MEDICAL IMAGING 2012; 31:312-325. [PMID: 21937343 DOI: 10.1109/tmi.2011.2168609] [Citation(s) in RCA: 20] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/31/2023]
Abstract
Fully automatic 3-D segmentation techniques for clinical applications or epidemiological studies have proven to be a very challenging task in the domain of medical image analysis. 3-D organ segmentation on magnetic resonance (MR) datasets requires a well-designed segmentation strategy due to imaging artifacts, partial volume effects, and similar tissue properties of adjacent tissues. We developed a 3-D segmentation framework for fully automatic kidney parenchyma volumetry that uses Bayesian concepts for probability map generation. The probability map quality is improved in a multistep refinement approach. An extended prior shape level set segmentation method is then applied on the refined probability maps. The segmentation quality is improved by incorporating an exterior cortex edge alignment technique using cortex probability maps. In contrast to previous approaches, we combine several relevant kidney parenchyma features in a sequence of segmentation techniques for successful parenchyma delineation on native MR datasets. Furthermore, the proposed method is able to recognize and exclude parenchymal cysts from the parenchymal volume. We analyzed four different quality measures showing better results for right parenchymal tissue than for left parenchymal tissue due to an incorporated liver part removal in the segmentation framework. The results show that the outer cortex edge alignment approach successfully improves the quality measures.
Collapse
Affiliation(s)
- Oliver Gloger
- Institute for Community Medicine, Ernst Moritz Arndt University of Greifswald, 17475 Greifswald, Germany.
| | | | | | | | | | | |
Collapse
|
15
|
Linguraru MG, Wang S, Shah F, Gautam R, Peterson J, Linehan WM, Summers RM. Automated noninvasive classification of renal cancer on multiphase CT. Med Phys 2011; 38:5738-46. [PMID: 21992388 PMCID: PMC3203128 DOI: 10.1118/1.3633898] [Citation(s) in RCA: 25] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2011] [Revised: 07/30/2011] [Accepted: 08/09/2011] [Indexed: 11/07/2022] Open
Abstract
PURPOSE To explore the added value of the shape of renal lesions for classifying renal neoplasms. To investigate the potential of computer-aided analysis of contrast-enhanced computed-tomography (CT) to quantify and classify renal lesions. METHODS A computer-aided clinical tool based on adaptive level sets was employed to analyze 125 renal lesions from contrast-enhanced abdominal CT studies of 43 patients. There were 47 cysts and 78 neoplasms: 22 Von Hippel-Lindau (VHL), 16 Birt-Hogg-Dube (BHD), 19 hereditary papillary renal carcinomas (HPRC), and 21 hereditary leiomyomatosis and renal cell cancers (HLRCC). The technique quantified the three-dimensional size and enhancement of lesions. Intrapatient and interphase registration facilitated the study of lesion serial enhancement. The histograms of curvature-related features were used to classify the lesion types. The areas under the curve (AUC) were calculated for receiver operating characteristic curves. RESULTS Tumors were robustly segmented with 0.80 overlap (0.98 correlation) between manual and semi-automated quantifications. The method further identified morphological discrepancies between the types of lesions. The classification based on lesion appearance, enhancement and morphology between cysts and cancers showed AUC = 0.98; for BHD + VHL (solid cancers) vs. HPRC + HLRCC AUC = 0.99; for VHL vs. BHD AUC = 0.82; and for HPRC vs. HLRCC AUC = 0.84. All semi-automated classifications were statistically significant (p < 0.05) and superior to the analyses based solely on serial enhancement. CONCLUSIONS The computer-aided clinical tool allowed the accurate quantification of cystic, solid, and mixed renal tumors. Cancer types were classified into four categories using their shape and enhancement. Comprehensive imaging biomarkers of renal neoplasms on abdominal CT may facilitate their noninvasive classification, guide clinical management, and monitor responses to drugs or interventions.
Collapse
|
16
|
A new computerized measurement approach of carotid artery stenosis on tomographic image sequence. Acad Radiol 2010; 17:1498-505. [PMID: 20920858 DOI: 10.1016/j.acra.2010.08.015] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2010] [Revised: 07/15/2010] [Accepted: 08/03/2010] [Indexed: 11/21/2022]
Abstract
RATIONALE AND OBJECTIVES The stenosis degree of carotid artery (CA) can be a critical factor for treatment of cerebrovascular disease and for determining candidate of carotid endarterectomy. Currently, three different measuring methods are applied only on projectional cervical images. These measurement methods introduce several demerits such as a thromboembolic event, and three reference positions provide the different measurement results even on same subject. In addition, projection image could not provide the most severe stenosis position by nature; and the manual measurements also provide the inter-observer and intra-observer variability. Therefore, a computerized measuring scheme is necessary to overcome these drawbacks. MATERIALS AND METHODS By applying local adaptive thresholding technique on cervical magnetic resonance angiogram image sequence, CA objects are initially identified. These are used to determine the three-dimensional central axis of CA by using circumscribed quadrangle. The oblique slices are reformatted into two-dimensional image planes, which are perpendicular to the central axis of CA, to provide the circular shape of blood vessel provided that the artery runs horizontally across the scanning axis. After that, region growing technique is applied on obliquely reformatted image sequence followed by geometrically restoration of segmented CA objects. RESULTS The percentage of stenosis can be defined by the area ratio of segmented CA to restored CA object. The stenosis grading of is [(A-B)/A]×100%, where A represents area measure of restored object, B represents area measure of segmented CA object. Experiments have been conducted on both phantom that simulated the mild (30%), moderate (50%), and severe (70%) stenosis degree for validation of proposed measurement approach and 86 carotid arteries from 43 clinical data sets (including 5 occlusion cases). CONCLUSIONS The automated approach is recommended to measure the carotid stenosis by using axial image sequence. This technique is not only accurate as possible but also robust, simple to handle, and less time consuming as compared to manual measurements. In addition, a computerized carotid stenosis measuring method is necessary to overcome the drawbacks introduced by using the projectional image and measurement variability of inter-observer, intra-observer.
Collapse
|
17
|
Farmaki C, Marias K, Sakkalis V, Graf N. Spatially adaptive active contours: a semi-automatic tumor segmentation framework. Int J Comput Assist Radiol Surg 2010; 5:369-84. [PMID: 20473782 DOI: 10.1007/s11548-010-0477-9] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/25/2009] [Accepted: 04/22/2010] [Indexed: 10/19/2022]
Abstract
PURPOSE Tumor segmentation constitutes a crucial step in simulating cancer growth and response to therapy. Incorporation of imaging data individualizes the simulation and assists clinical correlation with the predicted outcome. We adapted snakes to improve tumor segmentation including difficult cases with inherently inhomogeneous structure and poorly defined margins. METHODS Snakes are flexible curves, based on the parameter-controlled deformation of an initial user-defined contour toward the boundary of the desired object, through the minimization of a suitable energy function. Although parameter-adjustment can yield fairly good results in homogeneous regions, traditional snakes often fail to provide an accurate segmentation result when both rigid and very elastic behavior is needed simultaneously to delineate the true outline of the tumor. We developed and tested a spatially adaptive active contour technique by introducing local snake bending, to improve traditional snakes performance for segmenting tumors. The key point of our method is the use of adaptable snake parameters, instead of constant ones, to adjust the bending of the curve according to the local edge characteristics. Our algorithm discriminates image regions according to underlying image features, such as gradient magnitude and corner strength. More specifically, it assigns each region a different "localized" set of parameters, one corresponding to a very flexible snake, and the other corresponding to a very rigid one, according to the local image characteristics. RESULTS Qualitative results on more than 150 real MR images, as well as quantitative validation based on agreement with an expert clinician's annotations of the true tumor boundaries, demonstrate our approach is highly efficient compared to traditional active contours and region growing. Due to the use of adaptable parameters in the snake evolution process, our approach outperforms the other two methods, and consistently follows an expert's annotations. Statistical tests indicated significant difference between the results produced by our approach and two other algorithms traditional snakes and region growing, while multiple comparison showed that our method consistently outperformed those algorithms, with an average overlap of 89%, over the entire data set, while traditional snakes were at 82.5% and region growing at 59.2%. Furthermore, we performed several tests that demonstrate our method's stability to different initial contours, as well as, to lower resolution images. CONCLUSION Our adaptive snake algorithm can spatially adapt to diverse image characteristics, producing outlines that mimic the true tumor boundaries. Results in MR datasets are very close to an expert clinician's intuition about the tumor boundaries.
Collapse
Affiliation(s)
- Cristina Farmaki
- Institute of Computer Science, Hellas, Heraklion, Crete, Greece.
| | | | | | | |
Collapse
|
18
|
Linguraru MG, Wang S, Shah F, Gautam R, Peterson J, Linehan W, Summers RM. Computer-aided renal cancer quantification and classification from contrast-enhanced CT via histograms of curvature-related features. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2010; 2009:6679-82. [PMID: 19964705 DOI: 10.1109/iembs.2009.5334012] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
In clinical practice, renal cancer diagnosis is performed by manual quantifications of tumor size and enhancement, which are time consuming and show high variability. We propose a computer-assisted clinical tool to assess and classify renal tumors in contrast-enhanced CT for the management and classification of kidney tumors. The quantification of lesions used level-sets and a statistical refinement step to adapt to the shape of the lesions. Intra-patient and inter-phase registration facilitated the study of lesion enhancement. From the segmented lesions, the histograms of curvature-related features were used to classify the lesion types via random sampling. The clinical tool allows the accurate quantification and classification of cysts and cancer from clinical data. Cancer types are further classified into four categories. Computer-assisted image analysis shows great potential for tumor diagnosis and monitoring.
Collapse
Affiliation(s)
- Marius George Linguraru
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD 20892, USA.
| | | | | | | | | | | | | |
Collapse
|
19
|
Rangayyan RM, Banik S, Boag GS. Landmarking and segmentation of computed tomographic images of pediatric patients with neuroblastoma. Int J Comput Assist Radiol Surg 2009; 4:245-62. [PMID: 20033591 DOI: 10.1007/s11548-009-0289-y] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2008] [Accepted: 02/01/2009] [Indexed: 11/28/2022]
Abstract
OBJECTIVES Segmentation and landmarking of computed tomographic (CT) images of pediatric patients are important and useful in computer-aided diagnosis, treatment planning, and objective analysis of normal as well as pathological regions. Identification and segmentation of organs and tissues in the presence of tumors is difficult. Automatic segmentation of the primary tumor mass in neuroblastoma could facilitate reproducible and objective analysis of the tumor's tissue composition, shape, and volume. However, due to the heterogeneous tissue composition of the neuroblastic tumor, ranging from low-attenuation necrosis to high-attenuation calcification, segmentation of the tumor mass is a challenging problem. In this context, we explore methods for identification and segmentation of several abdominal and thoracic landmarks to assist in the segmentation of neuroblastic tumors in pediatric CT images. MATERIALS AND METHODS Methods are proposed to identify and segment automatically peripheral artifacts and tissues, the rib structure, the vertebral column, the spinal canal, the diaphragm, and the pelvic surface. The results of segmentation of the vertebral column, the spinal canal, the diaphragm and the pelvic girdle are quantitatively evaluated by comparing with the results of independent manual segmentation performed by a radiologist. RESULTS AND CONCLUSION The use of the landmarks and removal of several tissues and organs assisted in limiting the scope of the tumor segmentation process to the abdomen, and resulted in the reduction of the false-positive error rates by 22.4%, on the average, over ten CT exams of four patients, and improved the result of segmentation of neuroblastic tumors.
Collapse
Affiliation(s)
- Rangaraj M Rangayyan
- Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB T2N 1N4, Canada.
| | | | | |
Collapse
|
20
|
Linguraru MG, Yao J, Gautam R, Peterson J, Li Z, Linehan WM, Summers RM. Renal Tumor Quantification and Classification in Contrast-Enhanced Abdominal CT. PATTERN RECOGNITION 2009; 42:1149-1161. [PMID: 19492069 PMCID: PMC2658597 DOI: 10.1016/j.patcog.2008.09.018] [Citation(s) in RCA: 21] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/27/2023]
Abstract
Kidney cancer occurs in both a hereditary (inherited) and sporadic (non-inherited) form. It is estimated that almost a quarter of a million people in the USA are living with kidney cancer and their number increases with 51,000 diagnosed with the disease every year. In clinical practice, the response to treatment is monitored by manual measurements of tumor size, which are 2D, do not reflect the 3D geometry and enhancement of tumors, and show high intra- and inter-operator variability. We propose a computer-assisted radiology tool to assess renal tumors in contrast-enhanced CT for the management of tumor diagnoses and responses to new treatments. The algorithm employs anisotropic diffusion (for smoothing), a combination of fast-marching and geodesic level-sets (for segmentation), and a novel statistical refinement step to adapt to the shape of the lesions. It also quantifies the 3D size, volume and enhancement of the lesion and allows serial management over time. Tumors are robustly segmented and the comparison between manual and semi-automated quantifications shows disparity within the limits of inter-observer variability. The analysis of lesion enhancement for tumor classification shows great separation between cysts, von Hippel-Lindau syndrome lesions and hereditary papillary renal carcinomas (HPRC) with p-values inferior to 0.004. The results on temporal evaluation of tumors from serial scans illustrate the potential of the method to become an important tool for disease monitoring, drug trials and noninvasive clinical surveillance.
Collapse
Affiliation(s)
- Marius George Linguraru
- Diagnostic Radiology Department, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | | | | | | | | | | | | |
Collapse
|
21
|
Linguraru MG, Gautam R, Peterson J, Yao J, Linehan WM, Summers RM. RENAL TUMOR QUANTIFICATION AND CLASSIFICATION IN TRIPLE-PHASE CONTRAST-ENHANCED ABDOMINAL CT. PROCEEDINGS. IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING 2009; 2009:1310-1313. [PMID: 20383290 DOI: 10.1109/isbi.2009.5193305] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
It is estimated that a quarter of a million people in the USA are living with kidney cancer. In clinical practice, the response to treatment is monitored by manual measurements of tumor size, which are time consuming and show high intra- and inter-operator variability. We propose a computer-assisted radiology tool to assess renal tumors in contrast-enhanced CT for the management of tumor diagnoses and treatments. The algorithm employs anisotropic diffusion, a combination of fast-marching and geodesic level-sets, and a novel statistical refinement step to adapt to the shape of the lesions. It also quantifies the 3D size, volume and enhancement of the lesion and allows serial management of tumors. The comparison between manual and semi-automated quantifications shows disparity within the limits of inter-observer variability. The automated tumor classification shows great separation between cysts, von Hippel-Lindau syndrome (VHL) lesions and hereditary papillary renal carcinomas (HPRC) (p < 0.004).
Collapse
Affiliation(s)
- Marius George Linguraru
- Radiology and Imaging Sciences, Clinical Center, National Institutes of Health, Bethesda, MD, USA
| | | | | | | | | | | |
Collapse
|
22
|
|
23
|
Cai W, Holalkere NS, Harris G, Sahani D, Yoshida H. Dynamic-threshold level set method for volumetry of porcine kidney in CT images in vivo and ex vivo assessment of the accuracy of volume measurement. Acad Radiol 2007; 14:890-6. [PMID: 17574138 DOI: 10.1016/j.acra.2007.03.005] [Citation(s) in RCA: 23] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/26/2006] [Revised: 03/06/2007] [Accepted: 03/08/2007] [Indexed: 01/05/2023]
Abstract
RATIONALE AND OBJECTIVE We sought to assess the accuracy of a novel computerized volumetry method, called dynamic-thresholding (DT) level set, in determining the renal volume of pigs in CT images on the basis of in vivo and ex vivo reference standards. METHODS AND MATERIALS Eight Yorkshire breed anesthetized pigs (weight range 45-50 kg) were scanned on a 64-slice multidetector CT scanner (Sensation 64; Siemens) after injection of an iodinated (300 mg I/ml) contrast agent through an IV cannula. The kidneys of the pigs were then surgically resected and scanned by CT in the same manner. Both in vivo and ex vivo CT images were subjected to our computerized volumetry using DT level set method. The resulting volumes of the kidneys were compared with in vivo and ex vivo reference standards: the former was established by manual contouring of the kidneys on the CT images by an experienced radiologist, and the latter was established as the water displacement volume of the resected kidney. RESULTS The comparisons of the in vivo and ex vivo measurements by our volumetric scheme with the associated reference standards yielded a mean difference of 1.73 +/- 1.24% and 3.38 +/- 2.51%, respectively. The correlation coefficients were 0.981 and 0.973 for in vivo and ex vivo comparisons, respectively. The mean difference between in vivo and ex vivo reference standards was 5.79 +/- 4.26%, and the correlation coefficient between the two standards was 0.760. CONCLUSION Our computerized volumetry using the DT level set method can provide accurate in vivo and ex vivo measurements of kidney volume, despite a large difference between the two reference standards. This technique can be employed in human subjects for the determination of renal volume for preoperative surgical planning and assessment of oncology treatment.
Collapse
Affiliation(s)
- Wenli Cai
- Department of Radiology, Massachusetts General Hospital/Harvard Medical School, 25 New Chardon Street 400C, Boston, MA 02114, USA.
| | | | | | | | | |
Collapse
|
24
|
Raj GV, Bach AM, Iasonos A, Korets R, Blitstein J, Hann L, Russo P. Predicting the Histology of Renal Masses Using Preoperative Doppler Ultrasonography. J Urol 2007; 177:53-8. [PMID: 17161999 DOI: 10.1016/j.juro.2006.08.067] [Citation(s) in RCA: 32] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2006] [Indexed: 11/29/2022]
Abstract
PURPOSE Traditional imaging techniques cannot differentiate among benign, indolent and malignant renal neoplasms. Since conventional clear cell carcinomas are highly vascular, we used preoperative color and/or power Doppler ultrasonography to evaluate the association between vascular flow in a renal mass and surgical pathology. MATERIALS AND METHODS Nephrectomies performed at our institution between January 2001 and December 2004 were retrospectively evaluated. Any detection of flow in the renal mass on color Doppler ultrasonography was defined as vascular flow. A prospective validation study was then performed from January 2005 to October 2005 and a nomogram was constructed to predict clear cell histology. RESULTS Of 299 renal lesions in the retrospective cohort 210 (70%) had evidence of vascular flow, including 156 of 169 conventional clear cell carcinomas (92%) (p <0.0001). On logistic regression analysis vascular flow was associated with conventional clear cell histology (OR 16.9, 95% CI 8.7-32.8; p <0.0001). This finding was validated prospectively in 97 patients. Vascular flow was detected in 54 of 65 renal masses (83%) with conventional clear cell histology (p <0.0001), which was associated with an OR of 10.8 (95% CI 4.0-29.0; p <0.0001). A nomogram incorporating vascular flow along with clinical variables (clinical size, patient sex and age) to predict conventional clear cell histology was constructed on the retrospective cohort and validated on the prospective data set (concordance index 0.82 and 0.76, respectively). CONCLUSIONS Vascular flow detected by color Doppler ultrasonography is strongly associated with conventional clear cell histology. A nomogram incorporating vascular flow on color Doppler ultrasonography and clinical parameters may aid in the preoperative characterization of renal lesions.
Collapse
Affiliation(s)
- Ganesh V Raj
- Memorial Sloan-Kettering Cancer Center, New York, New York 10021, USA
| | | | | | | | | | | | | |
Collapse
|
25
|
Kim DY, Chung SM, Park JW. Automatic navigation path generation based on two-phase adaptive region-growing algorithm for virtual angioscopy. Med Eng Phys 2005; 28:339-47. [PMID: 16112889 DOI: 10.1016/j.medengphy.2005.07.011] [Citation(s) in RCA: 10] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/21/2004] [Revised: 07/12/2005] [Accepted: 07/12/2005] [Indexed: 10/25/2022]
Abstract
In this paper, we propose a fast and automated navigation path generation algorithm to visualize inside of carotid artery using MR angiography images. The carotid artery is one of the body regions not accessible by real optical probe but can be visualized with virtual endoscopy. By applying two-phase adaptive region-growing algorithm, the carotid artery segmentation is started at the initial seed, which is located on the initially thresholded binary image. This segmentation algorithm automatically detects the branch position with stack feature. Combining with a priori knowledge of anatomic structure of carotid artery, the detected branch position is used to separate the carotid artery into internal carotid artery and external carotid artery. A fly-through path is determined to automatically move the virtual camera based on the intersecting coordinates of two bisectors on the circumscribed quadrangle of segmented carotid artery. In consideration of the interactive rendering speed and the usability of standard graphic hardware, endoscopic view of carotid artery is generated by using surface rendering algorithm with perspective projection method. In addition, the endoscopic view is provided with ray casting algorithm for off-line navigation of carotid artery. Experiments have been conducted on both mathematical phantom and clinical data sets. This algorithm is more effective than key-framing and topological thinning method in terms of automated features and computing time. This algorithm is also applicable to generate the centerline of renal artery, coronary artery, and airway tree which has tree-like cylinder shape of organ structures in the medical imagery.
Collapse
Affiliation(s)
- Do-Yeon Kim
- Department of Information and Communication Engineering, Chungnam National University, 220 Gung-Dong, Yuseong-Gu, Taejon 305-764, Republic of Korea.
| | | | | |
Collapse
|