Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images
Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be help...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2018
|
| Subjects: |
| _version_ | 1825721603110993920 |
|---|---|
| author | Raghavendra, U. Gudigar, Anjan Maithri, Mangalore Gertych, Arkadiusz Meiburger, Kristen Mariko Yeong, Chai Hong Madla, Chakri Kongmebhol, Pailin Molinari, Filippo Ng, Kwan Hoong Acharya, U. Rajendra |
| author_facet | Raghavendra, U. Gudigar, Anjan Maithri, Mangalore Gertych, Arkadiusz Meiburger, Kristen Mariko Yeong, Chai Hong Madla, Chakri Kongmebhol, Pailin Molinari, Filippo Ng, Kwan Hoong Acharya, U. Rajendra |
| author_sort | Raghavendra, U. |
| collection | UM |
| description | Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings. |
| first_indexed | 2024-03-06T05:52:51Z |
| format | Article |
| id | um.eprints-20993 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:52:51Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | um.eprints-209932020-01-03T04:12:56Z http://eprints.um.edu.my/20993/ Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images Raghavendra, U. Gudigar, Anjan Maithri, Mangalore Gertych, Arkadiusz Meiburger, Kristen Mariko Yeong, Chai Hong Madla, Chakri Kongmebhol, Pailin Molinari, Filippo Ng, Kwan Hoong Acharya, U. Rajendra R Medicine Ultrasound imaging is one of the most common visualizing tools used by radiologists to identify the location of thyroid nodules. However, visual assessment of nodules is difficult and often affected by inter- and intra-observer variabilities. Thus, a computer-aided diagnosis (CAD) system can be helpful to cross-verify the severity of nodules. This paper proposes a new CAD system to characterize thyroid nodules using optimized multi-level elongated quinary patterns. In this study, higher order spectral (HOS) entropy features extracted from these patterns appropriately distinguished benign and malignant nodules under particle swarm optimization (PSO) and support vector machine (SVM) frameworks. Our CAD algorithm achieved a maximum accuracy of 97.71% and 97.01% in private and public datasets respectively. The evaluation of this CAD system on both private and public datasets confirmed its effectiveness as a secondary tool in assisting radiological findings. Elsevier 2018 Article PeerReviewed Raghavendra, U. and Gudigar, Anjan and Maithri, Mangalore and Gertych, Arkadiusz and Meiburger, Kristen Mariko and Yeong, Chai Hong and Madla, Chakri and Kongmebhol, Pailin and Molinari, Filippo and Ng, Kwan Hoong and Acharya, U. Rajendra (2018) Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images. Computers in Biology and Medicine, 95. pp. 55-62. ISSN 0010-4825, DOI https://doi.org/10.1016/j.compbiomed.2018.02.002 <https://doi.org/10.1016/j.compbiomed.2018.02.002>. https://doi.org/10.1016/j.compbiomed.2018.02.002 doi:10.1016/j.compbiomed.2018.02.002 |
| spellingShingle | R Medicine Raghavendra, U. Gudigar, Anjan Maithri, Mangalore Gertych, Arkadiusz Meiburger, Kristen Mariko Yeong, Chai Hong Madla, Chakri Kongmebhol, Pailin Molinari, Filippo Ng, Kwan Hoong Acharya, U. Rajendra Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title | Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title_full | Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title_fullStr | Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title_full_unstemmed | Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title_short | Optimized multi-level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| title_sort | optimized multi level elongated quinary patterns for the assessment of thyroid nodules in ultrasound images |
| topic | R Medicine |
| work_keys_str_mv | AT raghavendrau optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT gudigaranjan optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT maithrimangalore optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT gertycharkadiusz optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT meiburgerkristenmariko optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT yeongchaihong optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT madlachakri optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT kongmebholpailin optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT molinarifilippo optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT ngkwanhoong optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages AT acharyaurajendra optimizedmultilevelelongatedquinarypatternsfortheassessmentofthyroidnodulesinultrasoundimages |