Adrenal incidentaloma: machine learning-based quantitative texture analysis of unenhanced CT can effectively differentiate sPHEO from lipid-poor adrenal adenoma

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Objective: To evaluate the feasibility and accuracy of machine learning based texture analysis of unenhanced CT images in differentiating subclinical pheochromocytoma (sPHEO) from lipid-poor adenoma (LPA) in adrenal incidentaloma (AI).

Methods: Seventy-nine patients with 80 LPA and 29 patients with 30 sPHEO were included in the study. Texture parameters were derived using imaging software (MaZda). Thirty texture features were selected and LPA was performed for the features selected. The number of positive features was used to predict results. Logistic multiple regression analysis was performed on the 30 texture features, and a predictive equation was created based on the coefficients obtained.

Results: LPA yielded a misclassification rate of 19.39% in differentiating sPHEO from LPA. Our predictive model had an accuracy rate of 94.4% (102/108), with a sensitivity of 86.2% (25/29) and a specificity of 97.5% (77/79) for differentiation. When the number of positive features was greater than 8, the accuracy of prediction was 85.2% (92/108), with a sensitivity of 96.6% (28/29) and a specificity of 81% (64/79).

Conclusions: Machine learning-based quantitative texture analysis of unenhanced CT may be a reliable quantitative method in differentiating sPHEO from LPA when AI is present.

Related collections

Most cited references 19

Record: found
Abstract: found
Article: not found

MaZda--a software package for image texture analysis.

Piotr M Szczypiński, Michał Strzelecki, Andrzej Materka … (2009)

MaZda, a software package for 2D and 3D image texture analysis is presented. It provides a complete path for quantitative analysis of image textures, including computation of texture features, procedures for feature selection and extraction, algorithms for data classification, various data visualization and image segmentation tools. Initially, MaZda was aimed at analysis of magnetic resonance image textures. However, it revealed its effectiveness in analysis of other types of textured images, including X-ray and camera images. The software was utilized by numerous researchers in diverse applications. It was proven to be an efficient and reliable tool for quantitative image analysis, even in more accurate and objective medical diagnosis. MaZda was also successfully used in food industry to assess food product quality. MaZda can be downloaded for public use from the Institute of Electronics, Technical University of Lodz webpage.

0 comments Cited 168 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

The clinically inapparent adrenal mass: update in diagnosis and management.

Michael Rothberg, Joseph Lau, Y. Miyachi … (2004)

Clinically inapparent adrenal masses are incidentally detected after imaging studies conducted for reasons other than the evaluation of the adrenal glands. They have frequently been referred to as adrenal incidentalomas. In preparation for a National Institutes of Health State-of-the-Science Conference on this topic, extensive literature research, including Medline, BIOSIS, and Embase between 1966 and July 2002, as well as references of published metaanalyses and selected review articles identified more than 5400 citations. Based on 699 articles that were retrieved for further examination, we provide a comprehensive update of the diagnostic and therapeutic approaches focusing on endocrine and radiological features as well as surgical options. In addition, we present recent developments in the discovery of tumor markers, endocrine testing for subclinical disease including autonomous glucocorticoid hypersecretion and silent pheochromocytoma, novel imaging techniques, and minimally invasive surgery. Based on the statements of the conference, the available literature, and ongoing studies, our aim is to provide practical recommendations for the management of this common entity and to highlight areas for future studies and research.

0 comments Cited 161 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

A survey on adrenal incidentaloma in Italy. Study Group on Adrenal Tumors of the Italian Society of Endocrinology.

F Mantero, M Terzolo, G Arnaldi … (2000)

The aim of this study was to perform a national survey on occasionally discovered adrenal masses [adrenal incidentalomas (AI)] under the auspices of the Italian Society of Endocrinology. This multicentric and retrospective evaluation of patients with AI includes 1096 cases collected in 26 centers between 1980 and 1995. Relevant information was obtained by means of a specifically tailored questionnaire. Of the 1096 forms received, 1004 were retained for final analysis. Patients were 420 males and 584 females, aged between 15-86 yr (median, 58 yr). Mass size (computed tomography measurement) ranged from 0.5-25 cm (median, 3.0 cm). Hormonal work-up demonstrated that 85% of the masses were nonhypersecretory, 9.2% were defined as subclinical Cushing's syndrome, 4.2% were pheochromocytomas, and 1.6% were aldosteronomas. Adrenalectomy was performed in 380 patients with removal of 198 cortical adenomas (52%), 47 cortical carcinomas (12%), 42 pheochromocytomas (11%), and other less frequent tumor types. Patients with carcinoma were significantly younger than patients with adenoma (median, 46; range, 17-84; vs. 57, 16-83 yr; P = 0.05). Adenomas were significantly smaller than carcinomas (3.5, 1-15 vs. 7.5, 2.6-25 cm; P < 0.001), and a cut-off at 4.0 cm had the highest sensitivity (93%) in differentiating between benign and malignant tumors. Hormonal work-up of patients with subclinical Cushing's syndrome showed low baseline ACTH in 79%, cortisol unsuppressibility after 1 mg dexamethasone in 73%, above normal urinary free cortisol in 75%, disturbed cortisol rhythm in 43%, and blunted ACTH response to CRH in 55%. Only 43% of patients with pheochromocytoma were hypertensive, and 86% showed elevated urinary catecholamines. All patients with aldosteronoma were hypertensive and had suppressed upright PRA. These results indicate that mass size is the most reliable variable in separating benign from malignant AI. Adrenalectomy should be recommended for AI greater than 4.0 cm because of the increased risk of malignancy, especially in young patients. Endocrine evaluation should be performed in all patients to identify silent states of hormone excess.

0 comments Cited 114 times – based on 0 reviews      Review now

Bookmark

All references

Author and article information

Journal

Journal ID (nlm-ta): J Cancer

Journal ID (iso-abbrev): J Cancer

Journal ID (publisher-id): jca

Title: Journal of Cancer

Publisher: Ivyspring International Publisher (Sydney )

ISSN (Electronic): 1837-9664

Publication date Collection: 2018

Publication date (Electronic): 8 September 2018

Volume: 9

Issue: 19

Pages: 3577-3582

Affiliations

[1 ]Department of Radiology, Xiangya Hospital, Central South University, Changsha, Hunan province, P.R.China;

[2 ]Postdoctoral Research Workstation of Pathology and Pathophysiology, Basic Medical Sciences, Xiangya Hospital, Central South University, P. R, China;

[3 ]Department of Urology, Xiangya Hospital, Central South University, Changsha, Hunan province, P.R.China;

[4 ]Department of Radiology, ZhuZhou 331 Hospital, Changsha Medical University, Changsha, Hunan province, P.R.China;

[5 ]Department of Diagnostic Radiology, City of Hope National Medical Center, Duarte, California, U. S. A;

[6 ]Department of Radiology, Keck Medical Center of USC, Los Angeles, CA.

Author notes

✉ Corresponding authors: Xueying Long, Department of Radiology, Xiangya Hospital, Central South University, No.87 Xiangya Road, Changsha, Hunan province, P.R.China. Tel: +86-731-84327448; Fax: +86-731-84327448; Email: longxueying@ 123456csu.edu.cn and Longfei Liu, Department of Urology, Xiangya Hospital, Central South University, No.87 Xiangya Road, Changsha, Hunan province, P.R. China; Tel: +86-15874869636; Fax: +86-731-89753011; Email: longfei_liu@ 123456163.com

^# Xiaoping Yi, Xiao Guan, and Chen Chen contributed equally to this work.

Competing Interests: The authors have declared that no competing interest exists.

Article

Publisher ID: jcav09p3577

DOI: 10.7150/jca.26356

PMC ID: 6171020

PubMed ID: 30310515

SO-VID: 59b592e6-ec1a-4fee-83ef-3e9968d6c153

License:

This is an open access article distributed under the terms of the Creative Commons Attribution (CC BY-NC) license ( https://creativecommons.org/licenses/by-nc/4.0/). See http://ivyspring.com/terms for full terms and conditions.

Adrenal incidentaloma: machine learning-based quantitative texture analysis of unenhanced CT can effectively differentiate sPHEO from lipid-poor adrenal adenoma

Read this article at

Abstract

Related collections

Karger: Oncology

Most cited references 19

MaZda--a software package for image texture analysis.

The clinically inapparent adrenal mass: update in diagnosis and management.

A survey on adrenal incidentaloma in Italy. Study Group on Adrenal Tumors of the Italian Society of Endocrinology.

Author and article information

Journal

Affiliations

Author notes

Article

History

Categories

Comments

Comment on this article

Similar content 204

Cited by 27

Most referenced authors 371