An Evaluation of the Effectiveness of Image-based Texture Features Extracted from Static B-mode Ultrasound Images in Distinguishing between Benign and Malignant Ovarian Masses

Abstract

Significant successes in machine learning approaches to image analysis for various applications have energized strong interest in automated diagnostic support systems for medical images. The evolving in-depth understanding of the way carcinogenesis changes the texture of cellular networks of a mass/tumor has been informing such diagnostics systems with use of more suitable image texture features and their extraction methods. Several texture features have been recently applied in discriminating malignant and benign ovarian masses by analysing B-mode images from ultrasound scan of the ovary with different levels of performance. However, comparative performance evaluation of these reported features using common sets of clinically approved images is lacking. This paper presents an empirical evaluation of seven commonly used texture features (histograms, moments of histogram, local binary patterns [256-bin and 59-bin], histograms of oriented gradients, fractal dimensions, and Gabor filter), using a collection of 242 ultrasound scan images of ovarian masses of various pathological characteristics. The evaluation examines not only the effectiveness of classification schemes based on the individual texture features but also the effectiveness of various combinations of these schemes using the simple majority-rule decision level fusion. Trained support vector machine classifiers on the individual texture features without any specific pre-processing, achieve levels of accuracy between 75% and 85% where the seven moments and the 256-bin LBP are at the lower end while the Gabor filter is at the upper end. Combining the classification results of the top k ( k = 3, 5, 7) best performing features further improve the overall accuracy to a level between 86% and 90%. These evaluation results demonstrate that each of the investigated image-based texture features provides informative support in distinguishing benign or malignant ovarian masses.

Artificial intelligence performance in image-based ovarian cancer identification: A systematic review and meta-analysis

“… 20 49.5 Acharya et al, 50 2012 a NR NR 20 49.5 Umar et al, 51 2012 NR NR 24 NR Acharya et al, 52 2012 a NR Patients with no anatomopathological evaluation. 20 49.5 Al-Karawi et al, 53 2021 a All ovarian tumors were given a histological diagnosis label. NR 232 NR Jian et al, 54 2021 Histologically proven EOC; MRI performed within 1 month prior to gynecological operation; all four axial MRI sequences obtained: fast spin-echo T2-weighted imaging with fat saturation(T2WI FS), echo-planar DWI with gradient b factors of 0 and 600, 800, or 1000 s/mm 2 , ADC map, and 2D volumetric interpolated breath hold examination (VIBE) contrast enhanced T1-weighted imaging with FS (CE-T1WI) in the late phase (150–190 s after the intravenous administration of contrast agent); absence of prior gynecological operation or chemotherapy prior to MRI scanning.…”

“… NR NR No Acharya et al, 52 2012 a Retrospective study, NR. 1800/200 NR No Al-Karawi et al, 53 2021 a Retrospective study, data from the IOTA research. 150/148 74/76 2005.11–2013.11 No Jian et al, 54 2021 Retrospective study, eight centers.…”

A systematic review on the use of artificial intelligence in gynecologic imaging – Background, state of the art, and future directions

“…Radiomics techniques varied greatly between studies. Al-karawi et al investigated common computer vision feature sets to classify ovarian tumors as benign or malignant, but examined only a small subset of typical radiomic feature sets [38]. They found Gabor filters to be the best performing individual feature set.…”

The Use of Artificial Intelligence in Automation in the Fields of Gynaecology and Obstetrics – an Assessment of the State of Play

“…In a recently published study, Al-Karawi et al used ML algorithms (support vector machine classification) to investigate seven differing familiar image texture parameters in ultrasound still images, which, according to the authors, can provide information about altered cellular composition in the process of carcinogenesis. By combining the features with the best test results, the researchers achieved an accuracy of 86 – 90% 39 .…”

“…Al-Karawi et al untersuchten im Rahmen einer aktuellen Arbeit mittels ML-Algorithmen (Support Vector Machine Classifier) 7 unterschiedliche bekannte Bildtexturparameter in US-Standbildern, die nach Vorstellung der Autoren Auskunft über die veränderte zelluläre Zusammensetzung i. R. d. Karzinogenese geben können. Durch Kombination der Merkmale mit den besten Testergebnissen war eine Genauigkeit von 86 – 90% beschrieben worden 39 .…”