ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform
Using right equipment and well trained personnel, ultrasound of the neck can detect a large number of non-palpable thyroid nodules. However, this technique often suffers from subjective interpretations and poor accuracy in the differential diagnosis of malignant and benign thyroid lesions. Therefore...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Online Access: | https://hdl.handle.net/10356/97356 http://hdl.handle.net/10220/13145 |
| _version_ | 1811683860083113984 |
|---|---|
| author | Acharya, U. Rajendra Faust, Oliver Sree, Subbhuraam Vinitha Molinari, Filippo Suri, Jasjit S. |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Acharya, U. Rajendra Faust, Oliver Sree, Subbhuraam Vinitha Molinari, Filippo Suri, Jasjit S. |
| author_sort | Acharya, U. Rajendra |
| collection | NTU |
| description | Using right equipment and well trained personnel, ultrasound of the neck can detect a large number of non-palpable thyroid nodules. However, this technique often suffers from subjective interpretations and poor accuracy in the differential diagnosis of malignant and benign thyroid lesions. Therefore, we developed an automated identification system based on knowledge representation techniques for characterizing the intra-nodular vascularization of thyroid lesions. Twenty nodules (10 benign and 10 malignant), taken from 3-D high resolution ultrasound (HRUS) images were used for this work. Malignancy was confirmed using fine needle aspiration biopsy and subsequent histological studies. A combination of discrete wavelet transformation (DWT) and texture algorithms were used to extract relevant features from the thyroid images. These features were fed to different configurations of AdaBoost classifier. The performance of these configurations was compared using receiver operating characteristic (ROC) curves. Our results show that the combination of texture features and DWT features presented an accuracy value higher than that reported in the literature. Among the different classifier setups, the perceptron based AdaBoost yielded very good result and the area under the ROC curve was 1 and classification accuracy, sensitivity and specificity were 100%. Finally, we have composed an Integrated Index called thyroid malignancy index (TMI) made up of these DWT and texture features, to facilitate distinguishing and diagnosing benign or malignant nodules using just one index or number. This index would help the clinicians in more quantitative assessment of the thyroid nodules. |
| first_indexed | 2024-10-01T04:19:26Z |
| format | Journal Article |
| id | ntu-10356/97356 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:19:26Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/973562020-03-07T13:22:17Z ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform Acharya, U. Rajendra Faust, Oliver Sree, Subbhuraam Vinitha Molinari, Filippo Suri, Jasjit S. School of Mechanical and Aerospace Engineering Using right equipment and well trained personnel, ultrasound of the neck can detect a large number of non-palpable thyroid nodules. However, this technique often suffers from subjective interpretations and poor accuracy in the differential diagnosis of malignant and benign thyroid lesions. Therefore, we developed an automated identification system based on knowledge representation techniques for characterizing the intra-nodular vascularization of thyroid lesions. Twenty nodules (10 benign and 10 malignant), taken from 3-D high resolution ultrasound (HRUS) images were used for this work. Malignancy was confirmed using fine needle aspiration biopsy and subsequent histological studies. A combination of discrete wavelet transformation (DWT) and texture algorithms were used to extract relevant features from the thyroid images. These features were fed to different configurations of AdaBoost classifier. The performance of these configurations was compared using receiver operating characteristic (ROC) curves. Our results show that the combination of texture features and DWT features presented an accuracy value higher than that reported in the literature. Among the different classifier setups, the perceptron based AdaBoost yielded very good result and the area under the ROC curve was 1 and classification accuracy, sensitivity and specificity were 100%. Finally, we have composed an Integrated Index called thyroid malignancy index (TMI) made up of these DWT and texture features, to facilitate distinguishing and diagnosing benign or malignant nodules using just one index or number. This index would help the clinicians in more quantitative assessment of the thyroid nodules. 2013-08-16T03:34:03Z 2019-12-06T19:41:48Z 2013-08-16T03:34:03Z 2019-12-06T19:41:48Z 2012 2012 Journal Article Acharya, U. R., Faust, O., Sree, S. V., Molinari, F., & Suri, J. S. (2012). ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. Computer methods and programs in biomedicine, 107(2), 233-241. 0169-2607 https://hdl.handle.net/10356/97356 http://hdl.handle.net/10220/13145 10.1016/j.cmpb.2011.10.001 en Computer methods and programs in biomedicine |
| spellingShingle | Acharya, U. Rajendra Faust, Oliver Sree, Subbhuraam Vinitha Molinari, Filippo Suri, Jasjit S. ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title | ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title_full | ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title_fullStr | ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title_full_unstemmed | ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title_short | ThyroScreen system : high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| title_sort | thyroscreen system high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform |
| url | https://hdl.handle.net/10356/97356 http://hdl.handle.net/10220/13145 |
| work_keys_str_mv | AT acharyaurajendra thyroscreensystemhighresolutionultrasoundthyroidimagecharacterizationintobenignandmalignantclassesusingnovelcombinationoftextureanddiscretewavelettransform AT faustoliver thyroscreensystemhighresolutionultrasoundthyroidimagecharacterizationintobenignandmalignantclassesusingnovelcombinationoftextureanddiscretewavelettransform AT sreesubbhuraamvinitha thyroscreensystemhighresolutionultrasoundthyroidimagecharacterizationintobenignandmalignantclassesusingnovelcombinationoftextureanddiscretewavelettransform AT molinarifilippo thyroscreensystemhighresolutionultrasoundthyroidimagecharacterizationintobenignandmalignantclassesusingnovelcombinationoftextureanddiscretewavelettransform AT surijasjits thyroscreensystemhighresolutionultrasoundthyroidimagecharacterizationintobenignandmalignantclassesusingnovelcombinationoftextureanddiscretewavelettransform |