1
|
Di Stefano C, Salvatori E, Savino L, Forte V, Paoletti S, Ricciardi F, Floris R, Garaci F. Colo-colic intussusception in an adult caused by lipoma: Case report of a rare condition. Radiol Case Rep 2024; 19:665-670. [PMID: 38111559 PMCID: PMC10726323 DOI: 10.1016/j.radcr.2023.10.080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Revised: 10/27/2023] [Accepted: 10/30/2023] [Indexed: 12/20/2023] Open
Abstract
This report describes the case of a 56-year-old woman who presented at the emergency room with a 3-week history of severe, intermittent abdominal pain. A CT scan revealed colo-colic intussusception caused by a large, substenosing mass with predominant adipose density. Subsequent endoscopic examination with biopsy revealed a necrotic tissue covering the mass, without definitive histological characterization. A second biopsy led to the extremely rare diagnosis of colo-colic lipoma. While intussusception is rare in adults, it's important to consider it as a differential diagnosis, especially when presenting with abdominal pain and signs of bowel obstruction. Timely diagnosis and appropriate treatment are essential to prevent complications.
Collapse
Affiliation(s)
- Carla Di Stefano
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Eva Salvatori
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Luca Savino
- Institute of Anatomic Pathology, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Valentina Forte
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Stefano Paoletti
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Federica Ricciardi
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Roberto Floris
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| | - Francesco Garaci
- Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, Via Montpellier 1, Rome, 00133, Italy
| |
Collapse
|
2
|
Biswas A, Wong OY, Aygun B, Gore S, Mankad K. Extraocular Orbital and Peri-Orbital Masses. Neuroimaging Clin N Am 2023; 33:643-659. [PMID: 37741663 DOI: 10.1016/j.nic.2023.05.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 09/25/2023]
Abstract
In this article, we will describe relevant anatomy and imaging findings of extraocular and orbital rim pathologic conditions. We will highlight important clinical and imaging pearls that help in differentiating these lesions from one another, and provide a few practical tips for challenging cases.
Collapse
Affiliation(s)
- Asthik Biswas
- Department of Neuroradiology, Great Ormond Street Hospital for Children NHS Foundation Trust, Great Ormond Street, London WC1N 3JH, UK.
| | - Oi Yean Wong
- Department of Neuroradiology, Great Ormond Street Hospital for Children NHS Foundation Trust, Great Ormond Street, London WC1N 3JH, UK
| | - Berna Aygun
- Department of Neuroradiology, UK Kings College Hospital NHS Foundation Trust, Denmark Hill, London SE5 9RS, UK
| | - Sri Gore
- Department of Ophthalmology, Great Ormond Street Hospital for Children NHS Foundation Trust, London, UK
| | - Kshitij Mankad
- Department of Neuroradiology, Great Ormond Street Hospital for Children NHS Foundation Trust, Great Ormond Street, London WC1N 3JH, UK; UCL GOS Institute of Child Health, 30 Guilford Street, London WC1N 1EH, UK
| |
Collapse
|
3
|
de l'Escalopier N, Mathieu L, Anract P, Biau D. Management of musculoskeletal tumours of the extremity in low-resource settings. Int Orthop 2021. [PMID: 34494133 DOI: 10.1007/s00264-021-05207-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/24/2021] [Accepted: 08/31/2021] [Indexed: 10/20/2022]
Abstract
BACKGROUND Management of extremity tumor is particularly challenging in low-resource settings where patients are often referred with late presentations. First, diagnostic means are limited, with CT scan, MRI, and pathology usually not being available. Limitations are also related to therapeutic means, as the absence of adjuvant therapy (chemotherapy and radiotherapy) may preclude any improvement in overall survival despite a curative surgical treatment. OBJECTIVE The authors suggest a kind of "toolbox" combining a diagnostic guide, based on clinical examination and X-rays, and therapeutic advice adapted to this context of care. The objective is to help the surgeon to better categorize the tumor to decide whether or not to operate or act in a relevant way. CONCLUSION The authors do not aim to provide recommendations but rather an inventory of what the isolated surgeon should know to decide on the best treatment strategy which, however, can only be symptomatic.
Collapse
|
4
|
Bussani R, Castrichini M, Restivo L, Fabris E, Porcari A, Ferro F, Pivetta A, Korcova R, Cappelletto C, Manca P, Nuzzi V, Bessi R, Pagura L, Massa L, Sinagra G. Cardiac Tumors: Diagnosis, Prognosis, and Treatment. Curr Cardiol Rep 2020; 22:169. [PMID: 33040219 DOI: 10.1007/s11886-020-01420-z] [Citation(s) in RCA: 59] [Impact Index Per Article: 14.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 09/09/2020] [Indexed: 01/07/2023]
Abstract
Purpose of Review Cardiac masses frequently present significant diagnostic and therapeutic clinical challenges and encompass a broad set of lesions that can be either neoplastic or non-neoplastic. We sought to provide an overview of cardiac tumors using a cardiac chamber prevalence approach and providing epidemiology, imaging, histopathology, diagnostic workup, treatment, and prognoses of cardiac tumors. Recent Findings Cardiac tumors are rare but remain an important component of cardio-oncology practice. Over the past decade, the advances in imaging techniques have enabled a noninvasive diagnosis in many cases. Indeed, imaging modalities such as cardiac magnetic resonance, computed tomography, and positron emission tomography are important tools for diagnosing and characterizing the lesions. Although an epidemiological and multimodality imaging approach is useful, the definite diagnosis requires histologic examination in challenging scenarios, and histopathological characterization remains the diagnostic gold standard. Summary A comprehensive clinical and multimodality imaging evaluation of cardiac tumors is fundamental to obtain a proper differential diagnosis, but histopathology is necessary to reach the final diagnosis and subsequent clinical management.
Collapse
|
5
|
Abstract
Testicular cancer is responsible for approximately 0.1% of all cancer deaths in the USA, and seminoma is the most common type of testicular tumor. Ultrasonography is the primary imaging modality for accessing testicular and extratesticular lesions, while magnetic resonance imaging can be used for problem solving in lesion characterization in certain cases. CT imaging is usually performed for retroperitoneal staging of testicular cancer metastasis and follow-up after treatment. Extratesticular masses are common, yet rarely malignant. Imaging plays an important role in primary diagnosis of testicular cancer and differentiating it from common non-neoplastic findings. The purpose of this article is to review various imaging findings in testicular and extratesticular masses.
Collapse
|
6
|
Hadjipanteli A, Elangovan P, Mackenzie A, Wells K, Dance DR, Young KC. The threshold detectable mass diameter for 2D-mammography and digital breast tomosynthesis. Phys Med 2019; 57:25-32. [PMID: 30738528 DOI: 10.1016/j.ejmp.2018.11.014] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/28/2018] [Revised: 10/18/2018] [Accepted: 11/21/2018] [Indexed: 11/19/2022] Open
Abstract
Digital breast tomosynthesis (DBT) is currently under consideration for replacement of, or combined use with 2D-mammography in national breast screening programmes. To investigate the potential benefits that DBT can bring to screening, the threshold detectable lesion diameters were measured for different forms of DBT in comparison to 2D-mammography. The aim of this study was to compare the threshold detectable mass diameters obtained with narrow angle (15°/15 projections) and wide angle (50°/25 projections) DBT in comparison to 2D-mammography. Simulated images of 60 mm thick compressed breasts were produced with and without masses using a set of validated image modelling tools for 2D-mammography and DBT. Image processing and reconstruction were performed using commercial software. A series of 4-alternative forced choice (4AFC) experiments was conducted for signal detection with the masses as targets. The threshold detectable mass diameter was found for each imaging modality with a mean glandular dose of 2.5 mGy. The resulting values of the threshold diameter for 2D-mammography (10.2 ± 1.4 mm) were found to be larger (p < 0.001) than those for narrow angle DBT (6.0 ± 1.1 mm) and wide angle DBT (5.6 ± 1.2 mm). There was no significant difference between the threshold diameters for wide and narrow angle DBT. Implications for the introduction of DBT alone or in combination with 2D-mammography in breast cancer screening are discussed.
Collapse
Affiliation(s)
- Andria Hadjipanteli
- National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, Guildford, Surrey, UK; Medical School, University of Cyprus, Nicosia, Cyprus.
| | - Premkumar Elangovan
- National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, Guildford, Surrey, UK
| | - Alistair Mackenzie
- National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, Guildford, Surrey, UK
| | - Kevin Wells
- Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, UK
| | - David R Dance
- National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, Guildford, Surrey, UK; Department of Physics, University of Surrey, Guildford, UK
| | - Kenneth C Young
- National Coordinating Centre for the Physics of Mammography, Royal Surrey County Hospital, Guildford, Surrey, UK; Department of Physics, University of Surrey, Guildford, UK
| |
Collapse
|
7
|
Yousefi M, Krzyżak A, Suen CY. Mass detection in digital breast tomosynthesis data using convolutional neural networks and multiple instance learning. Comput Biol Med 2018; 96:283-293. [PMID: 29665537 DOI: 10.1016/j.compbiomed.2018.04.004] [Citation(s) in RCA: 33] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2018] [Revised: 04/05/2018] [Accepted: 04/06/2018] [Indexed: 10/17/2022]
Abstract
Digital breast tomosynthesis (DBT) was developed in the field of breast cancer screening as a new tomographic technique to minimize the limitations of conventional digital mammography breast screening methods. A computer-aided detection (CAD) framework for mass detection in DBT has been developed and is described in this paper. The proposed framework operates on a set of two-dimensional (2D) slices. With plane-to-plane analysis on corresponding 2D slices from each DBT, it automatically learns complex patterns of 2D slices through a deep convolutional neural network (DCNN). It then applies multiple instance learning (MIL) with a randomized trees approach to classify DBT images based on extracted information from 2D slices. This CAD framework was developed and evaluated using 5040 2D image slices derived from 87 DBT volumes. The empirical results demonstrate that this proposed CAD framework achieves much better performance than CAD systems that use hand-crafted features and deep cardinality-restricted Bolzmann machines to detect masses in DBTs.
Collapse
Affiliation(s)
- Mina Yousefi
- Department of Computer Science and Software Engineering Concordia University, 1455 De Maisonneuve Blvd. W, Montreal, Quebec H3G 1M8, Canada.
| | - Adam Krzyżak
- Department of Computer Science and Software Engineering Concordia University, 1455 De Maisonneuve Blvd. W, Montreal, Quebec H3G 1M8, Canada
| | - Ching Y Suen
- Department of Computer Science and Software Engineering Concordia University, 1455 De Maisonneuve Blvd. W, Montreal, Quebec H3G 1M8, Canada
| |
Collapse
|
8
|
Abstract
Pericardial tumors are rare lesions that include a range of neoplastic conditions that may arise within the pericardium or metastasize to involve it secondarily. Understanding the spectrum of lesions that are included in the differential diagnosis of a pericardial mass-lesion is critical to making timely, accurate diagnoses and getting the appropriate therapy should one be necessary. This review summarizes the radiologic and pathologic findings of the most commonly encountered of these entities.
Collapse
Affiliation(s)
- Joseph J Maleszewski
- Department of Laboratory Medicine and Pathology, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA; Department of Cardiovascular Diseases, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA; Department of Clinical Genomics, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA.
| | - Nandan S Anavekar
- Department of Cardiovascular Diseases, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA; Division of Cardiac Radiology, Department of Radiology, Mayo Clinic, 200 First Street Southwest, Rochester, MN 55905, USA
| |
Collapse
|
9
|
Eriksson M, Czene K, Pawitan Y, Leifland K, Darabi H, Hall P. A clinical model for identifying the short-term risk of breast cancer. Breast Cancer Res 2017; 19:29. [PMID: 28288659 PMCID: PMC5348894 DOI: 10.1186/s13058-017-0820-y] [Citation(s) in RCA: 69] [Impact Index Per Article: 9.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2016] [Accepted: 03/01/2017] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Most mammography screening programs are not individualized. To efficiently screen for breast cancer, the individual risk of the disease should be determined. We describe a model that could be used at most mammography screening units without adding substantial cost. METHODS The study was based on the Karma cohort, which included 70,877 participants. Mammograms were collected up to 3 years following the baseline mammogram. A prediction protocol was developed using mammographic density, computer-aided detection of microcalcifications and masses, use of hormone replacement therapy (HRT), family history of breast cancer, menopausal status, age, and body mass index. Relative risks were calculated using conditional logistic regression. Absolute risks were calculated using the iCARE protocol. RESULTS Comparing women at highest and lowest mammographic density yielded a fivefold higher risk of breast cancer for women at highest density. When adding microcalcifications and masses to the model, high-risk women had a nearly ninefold higher risk of breast cancer than those at lowest risk. In the full model, taking HRT use, family history of breast cancer, and menopausal status into consideration, the AUC reached 0.71. CONCLUSIONS Measures of mammographic features and information on HRT use, family history of breast cancer, and menopausal status enabled early identification of women within the mammography screening program at such a high risk of breast cancer that additional examinations are warranted. In contrast, women at low risk could probably be screened less intensively.
Collapse
Affiliation(s)
- Mikael Eriksson
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Box 281, Stockholm, 171 77, Sweden.
| | - Kamila Czene
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Box 281, Stockholm, 171 77, Sweden
| | - Yudi Pawitan
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Box 281, Stockholm, 171 77, Sweden
| | - Karin Leifland
- Department of Radiology, South General Hospital, 118 83, Stockholm, Sweden
| | - Hatef Darabi
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Box 281, Stockholm, 171 77, Sweden
| | - Per Hall
- Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Box 281, Stockholm, 171 77, Sweden.,Department of Oncology, South General Hospital, 118 83, Stockholm, Sweden
| |
Collapse
|
10
|
Dhungel N, Carneiro G, Bradley AP. A deep learning approach for the analysis of masses in mammograms with minimal user intervention. Med Image Anal 2017; 37:114-28. [PMID: 28171807 DOI: 10.1016/j.media.2017.01.009] [Citation(s) in RCA: 131] [Impact Index Per Article: 18.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2016] [Revised: 11/30/2016] [Accepted: 01/24/2017] [Indexed: 12/31/2022]
Abstract
We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-to-noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre-trained with a regression to hand-crafted feature values and fine-tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state-of-the-art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7.
Collapse
|
11
|
Sangster GP, Migliaro M, Heldmann MG, Bhargava P, Hamidian Jahromi A, Thomas-Ogunniyi J. The gamut of primary retroperitoneal masses: multimodality evaluation with pathologic correlation. Abdom Radiol (NY) 2016; 41:1411-30. [PMID: 27271217 DOI: 10.1007/s00261-016-0735-6] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
The retroperitoneum is a large space where primary and metastatic tumors grow silently before clinical signs appear. Neoplastic retroperitoneal diseases may be solid or cystic, primary or secondary and range from benign to aggressive in behavior. Retroperitoneal neoplasms are notable for their widely disparate histologies. The solid primary retroperitoneal neoplasms are extremely uncommon and can be classified based on their tissue of origin into three main categories: mesodermal tumors, neurogenic tumors, and extragonadal germ cell tumors. These tumors can grow to a large size before clinical symptoms occur or become palpable. When symptoms do occur, they are nonspecific. The majority of these masses are malignant and imaging plays a pivotal role in the detection, staging, and pre-operative planning. Benign and malignant masses should be distinguished whenever possible to avoid unnecessary surgical procedures. Macroscopic fat, calcification, necrosis, vascularity, and neural foraminal widening are common imaging features helping for tumor differentiation. Meticulous cross-sectional imaging can triage the patient to the most appropriate therapy. Tumor morphology dictates imaging character, and biologic activity is reflected by positron emission tomography (PET). Complete surgical excision with tumor free margins is essential for long-term survival. Biopsy should be performed in consultation with surgical oncology to avoid complicating curative surgery. This pictorial essay illustrates the spectrum of multidetector computed tomography (MDCT) imaging findings in common and uncommon primary retroperitoneal masses, with an emphasis on cross-sectional imaging features for an adequate tumor characterization and staging.
Collapse
|
12
|
Bianchi D, Vespasiani G, Bove P. Acute kidney injury due to bilateral ureteral obstruction in children. World J Nephrol 2014; 3:182-192. [PMID: 25374811 PMCID: PMC4220350 DOI: 10.5527/wjn.v3.i4.182] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/29/2014] [Revised: 07/28/2014] [Accepted: 09/10/2014] [Indexed: 02/06/2023] Open
Abstract
Bilateral ureteral obstruction in children is a rare condition arising from several medical or surgical pictures. It needs to be promptly suspected in order to attempt a quick renal function recovery. In this paper we concentrated on uncommon causes of obstruction, with the aim of giving a summary of such multiple, rare and heterogeneous conditions joint together by the common denominator of sudden bilateral ureteral obstruction, difficult to be suspected at times. Conversely, typical and well-known diseases have been just run over. We considered pediatric cases of ureteral obstruction presenting as bilateral, along with some cases which truly appeared as single-sided, because of their potential bilateral presentation. We performed a review of the literature by a search on PubMed, CrossRef Metadata Search, internet and reference lists of single articles updated to May 2014, with no time limits in the past. Given that we deal with rare conditions, we decided to include also papers in non-English languages, published with an English abstract. For the sake of clearness, we divided our research results into 8 categories: (1) urolithiasis; (2) congenital urinary tract malformations; (3) immuno-rheumatologic causes of ureteral obstruction; (4) ureteral localization of infections; (5) other systemic infective causes of ureteral obstructions; (6) neoplastic intrinsic ureteral obstructions; (7) extrinsic ureteral obstructions; and (8) iatrogenic trigonal obstruction or inflammation. Of course, different pathogenic mechanisms underlay those clinical pictures, partly well-known and partly not completely understood.
Collapse
|
13
|
Abstract
This article addresses the current technique and protocols for magnetic resonance (MR) enterography, with a primary focus on inflammatory bowel disease (IBD) and a secondary detailed discussion of other diseases of the small bowel beyond IBD. A brief discussion of MR imaging for appendicitis is included, but the evaluation of appendicitis does not require an enterographic protocol. The focused key points and approach presented in this article are intended to enhance the reader's understanding to help improve patient compliance with the MR enterographic studies, overcome challenges, and improve interpretation.
Collapse
|
14
|
Abstract
Advances in medical imaging with current cross-section modalities enable non-invasive characterization of adrenal lesions. Computed tomography (CT) provides characterization with its non-contrast and wash-out features. Magnetic resonance imaging (MRI) is helpful in further characterization using chemical shift imaging (CSI) and MR spectroscopy. For differentiating between benign and malignant masses, positron emission tomography (PET) imaging is useful with its qualitative analysis, as well as its ability to detect the presence of extra-adrenal metastases in cancer patients. The work-up for an indeterminate adrenal mass includes evaluation with a non-contrast CT. If a lesion is less than 10 Hounsfield Units on a non-contrast CT, it is a benign lipid-rich adenoma and no further work-up is required. For the indeterminate adrenal masses, a lipid-poor adenoma can be differentiated from a metastasis utilizing CT wash-out features. Also, MRI is beneficial with CSI and MR spectroscopy. If a mass remains indeterminate, PET imaging may be of use, in which benign lesions demonstrate low or no fluorodeoxyglucose activity. In the few cases in which adrenal lesions remain indeterminate, surgical sampling such as percutaneous biopsy can be performed.
Collapse
|
15
|
Mohd Khuzi A, Besar R, Wan Zaki W, Ahmad N. Identification of masses in digital mammogram using gray level co-occurrence matrices. Biomed Imaging Interv J 2009; 5:e17. [PMID: 21611053 DOI: 10.2349/biij.5.3.e17] [Citation(s) in RCA: 34] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/01/2009] [Revised: 05/24/2009] [Accepted: 06/03/2009] [Indexed: 11/24/2022] Open
Abstract
Digital mammogram has become the most effective technique for early breast cancer detection modality. Digital mammogram takes an electronic image of the breast and stores it directly in a computer. The aim of this study is to develop an automated system for assisting the analysis of digital mammograms. Computer image processing techniques will be applied to enhance images and this is followed by segmentation of the region of interest (ROI). Subsequently, the textural features will be extracted from the ROI. The texture features will be used to classify the ROIs as either masses or non-masses. In this study normal breast images and breast image with masses used as the standard input to the proposed system are taken from Mammographic Image Analysis Society (MIAS) digital mammogram database. In MIAS database, masses are grouped into either spiculated, circumscribed or ill-defined. Additional information includes location of masses centres and radius of masses. The extraction of the textural features of ROIs is done by using gray level co-occurrence matrices (GLCM) which is constructed at four different directions for each ROI. The results show that the GLCM at 0º, 45º, 90º and 135º with a block size of 8X8 give significant texture information to identify between masses and non-masses tissues. Analysis of GLCM properties i.e. contrast, energy and homogeneity resulted in receiver operating characteristics (ROC) curve area of Az = 0.84 for Otsu’s method, 0.82 for thresholding method and Az = 0.7 for K-mean clustering. ROC curve area of 0.8-0.9 is rated as good results. The authors’ proposed method contains no complicated algorithm. The detection is based on a decision tree with five criterions to be analysed. This simplicity leads to less computational time. Thus, this approach is suitable for automated real-time breast cancer diagnosis system.
Collapse
|