A Set of Image Processing Algorithms for Computer-Aided Diagnosis in Nuclear Medicine Whole Body Bone Scan Images

Huang, Jia-Yann; Kao, Pan-Fu; Chen, Yung‐Sheng

doi:10.1109/tns.2007.897830

Cited by 30 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yin et al [8] proposed a lesion extraction algorithm using the characteristic point-based fuzzy inference system. Huang et al [9] presented a bone scintigram segmentation algorithm followed by lesion extraction using adaptive thresholding with different cut-offs in different segmented regions. An alternative approach for lesion extraction was proposed by Shiraishi et al [10], who presented a temporal subtraction-based interval change detection algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…It should be noted that the aforementioned studies [8][9][10][11][12][13][14] conducted hot spot detection and bone scan classification but did not assess BSI. One of the possible reasons for this might be low accuracy in the automated skeleton segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…One of the possible reasons for this might be low accuracy in the automated skeleton segmentation. For example, previous studies [8,9] outputted polygonal regions, which roughly approximated bone regions. Although the skeleton segmentation performance in the previous study [12] was improved [13] by the use of ASM, it was found to be sensitive to the initial position of the model and image noise.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated measurement of bone scan index from a whole-body bone scintigram

et al. 2019

View full text Add to dashboard Cite

Purpose We propose a deep learning-based image interpretation system for skeleton segmentation and extraction of hot spots of bone metastatic lesion from a whole-body bone scintigram followed by automated measurement of a bone scan index (BSI), which will be clinically useful. Methods The proposed system employs butterfly-type networks (BtrflyNets) for skeleton segmentation and extraction of hot spots of bone metastatic lesions, in which a pair of anterior and posterior images are processed simultaneously. BSI is then measured using the segmented bones and extracted hot spots. To further improve the networks, deep supervision (DSV) and residual learning technologies were introduced. Results We evaluated the performance of the proposed system using 246 bone scintigrams of prostate cancer in terms of accuracy of skeleton segmentation, hot spot extraction, and BSI measurement, as well as computational cost. In a threefold cross-validation experiment, the best performance was achieved by BtrflyNet with DSV for skeleton segmentation and BtrflyNet with residual blocks. The cross-correlation between the measured and true BSI was 0.9337, and the computational time for a case was 112.0 s. Conclusion We proposed a deep learning-based BSI measurement system for a whole-body bone scintigram and proved its effectiveness by threefold cross-validation study using 246 whole-body bone scintigrams. The automatically measured BSI and computational time for a case are deemed clinically acceptable and reliable.Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated measurement of bone scan index from a whole-body bone scintigram

et al. 2019

View full text Add to dashboard Cite

show abstract

“…A few of the segmentation techniques were based on the Fuzzy Set Theory (Huang et al, 2007;Pietka et al, 2010), thresholding Gomathi and Thangaraj, 2010) and models (Mumcuoglu et al, 2011;Schilham et al, 2006). Detection approaches were based on the use of classifiers, such as artificial neural networks (Ashwin et al, 2012;Bevilacqua, 2013;García-Orellana et al, 2008;Itai et al, 2009;Kumar et al, 2011;Li et al, 2009;López et al, 2011;Mironică et al, 2011;Sasaki et al, 2010), k-nearest neighbor (AlAbsi et al, 2012;Li et al, 2009;Mironică et al, 2011;Sanchez et al, 2011;Schilham et al, 2006), support vectors machine (Grana et al, 2011;Li et al, 2009;Martinez-Murcia et al, 2014;Mironică et al, 2011;Miyaki et al, 2013;Segovia et al, 2012;Shilaskar and Ghatol, 2013;Wang et al, 2009) and probabilistic classifiers (Li et al, 2012;Liu et al, 2013;Mironică et al, 2011;Ramírez et al, 2009;Vertan et al, 2011).…”

Section: Tasks For Computer-aided Diagnosis Systemsmentioning

confidence: 99%

A systematic review on the evaluation and characteristics of computer-aided diagnosis systems

Gonçalves

Delamaro

Nunes

2014

Rev. Bras. Eng. Bioméd.

View full text Add to dashboard Cite

Introduction: One of the challenges in developing Computer-Aided Diagnosis (CAD) systems is their accurate and comprehensive assessment. This paper presents the conduction and results of a systematic review (SR) that aims to verify the state of the art regarding the assessment of CAD systems. This survey provides a general analysis of the current status of the design, development and assessment of such systems and includes discussions on the most used metrics and approaches that could be utilized to obtain more objective evaluation methods. Methods: The SR was conducted using the scientifi c databases, ACM Digital Library, IEEE Xplore Digital Library, ScienceDirect and Web of Science. Inclusion and exclusion criteria were defi ned and applied to each retrieved work to select those of interest. From 156 studies retrieved, 100 studies were included. Results: There is a number of abnormalities that have been used for the development of CAD systems. Images from computed tomographies and mammographies are the most encountered types of medical images. Additionally, a number of studies used public databases for CAD evaluations. The main evaluation metrics and methods applied to CAD systems include sensitivity, accuracy, specifi city and receiver operating characteristic (ROC) analyses. In the assessed CAD systems that used the segmentation method, 30.0% applied the overlap measure. Discussion: There remain several topics to explore for the assessment of CAD schemes. While some evaluation metrics are traditionally used, they require a prior knowledge of case characteristics to test CAD systems. We were not able to identify articles that use software testing to evaluate CAD systems. Thus, we realize that there is a gap between CAD assessments and traditional practices of software engineering. However, the scope of this research is limited to scientifi c and academic works and excludes commercial interests. Finally, we discuss potential research studies within this scope to create a more objective and effi cient evaluation of CAD systems.

show abstract

“…However, this approach could not detect areas with high symmetry and high uptake such as joints and vertebrae. Huang et al proposed a CAD system for using a hybrid method of bone division to analyze planar whole-body bone images [10]. Fuzzy set histogram thresholding technique was used to differentiate bones from soft tissues.…”

Section: Introductionmentioning

confidence: 99%

Automatic Vertebral Column Extraction by Whole-Body Bone SPECT Scan

Huang

Chao

Kao

et al. 2013

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

Bone extraction and division can enhance the accuracy of diagnoses based on whole-body bone SPECT data. This study developed a method for using conventional SPECT for automatic recognition of the vertebral column. A novel feature of the proposed approach is a novel “bone graph" image description method that represents the connectivity between these image regions to facilitate manipulation of morphological relationships in the skeleton before surgery. By tracking the paths shown on the bone graph, skeletal structures can be identified by performing morphological operations. The performance of the method was evaluated quantitatively and qualitatively by two experienced nuclear medicine physicians. Datasets for whole-body bone SPECT scans in 46 lung cancer patients with bone metastasis were obtained with Tc-99m MDP. The algorithm successfully segmented vertebrae in the thoracolumbar spine. The quantitative assessment shows that the segmentation method achieved an average TP, FP, and FN rates of 95.1%, 9.1%, and 4.9%. The qualitative evaluation shows an average acceptance rate of 83%, where the data for the acceptable and unacceptable groups had a Cronbach's alpha value of 0.718, which indicated reasonable internal consistency and reliability.

show abstract

A Set of Image Processing Algorithms for Computer-Aided Diagnosis in Nuclear Medicine Whole Body Bone Scan Images

Cited by 30 publications

References 6 publications

Automated measurement of bone scan index from a whole-body bone scintigram

Automated measurement of bone scan index from a whole-body bone scintigram

A systematic review on the evaluation and characteristics of computer-aided diagnosis systems

Automatic Vertebral Column Extraction by Whole-Body Bone SPECT Scan

Contact Info

Product

Resources

About