Characterization Of Liver Lesions Research Articles

Comprehensive review of imaging modalities for diagnosis and characterization of focal liver lesions

Comprehensive review of imaging modalities for diagnosis and characterization of focal liver lesions

Quantitative time intensity curve analysis of contrast-enhanced ultrasound (CEUS) examinations for the assessment of focal liver lesions.

Contrast enhanced ultrasound (CEUS) is well-established for the characterization of focal liver lesions (FLLs). By using intravenous ultrasound contrast agents, followed by specific low mechanical index examinations, CEUS enables a high spatial and temporal resolution as well as a dynamic assessment of macro- and microvascularization down to the capillaries. Nevertheless, CEUS has the disadvantage of being examiner-dependent, so quantitative analysis of time-intensity curves in dynamic CEUS (D-CEUS) could provide further information. The aim of this article is to provide a general review of the current literature regarding the usefulness of D-CEUS in the assessment of FLLs.

Comments and illustrations of the WFUMB CEUS liver guidelines: Rare benign focal liver lesion, part I.

Improved detection and characterization of common focal liver lesions (FLL) are the main topics of the World Federation for Ultrasound in Medicine and Biology (WFUMB) guidelines on the use of contrast-enhanced ultrasound (CEUS). On stateof-the-art CEUS imaging, to create a library of rare FLL, especially concerning their atypical imaging characteristics, might be helpful for improving clinical diagnostic efficiency. In this review, we aim to summarize the ultrasound and CEUS features of rare benign FLL. Currently there are limited reports and images published.

Malignancy diagnosis of liver lesion in contrast enhanced ultrasound using an end-to-end method based on deep learning

BackgroundContrast-enhanced ultrasound (CEUS) is considered as an efficient tool for focal liver lesion characterization, given it allows real-time scanning and provides dynamic tissue perfusion information. An accurate diagnosis of liver lesions with CEUS requires a precise interpretation of CEUS images. However,it is a highly experience dependent task which requires amount of training and practice. To help improve the constrains, this study aims to develop an end-to-end method based on deep learning to make malignancy diagnosis of liver lesions using CEUS.MethodsA total of 420 focal liver lesions with 136 benign cases and 284 malignant cases were included. A deep learning model based on a two-dimensional convolution neural network, a long short-term memory (LSTM), and a linear classifier (with sigmoid) was developed to analyze the CEUS loops from different contrast imaging phases. For comparison, a 3D-CNN based method and a machine-learning (ML)-based time-intensity curve (TIC) method were also implemented for performance evaluation.ResultsResults of the 4-fold validation demonstrate that the mean AUC is 0.91, 0.88, and 0.78 for the proposed method, the 3D-CNN based method, and the ML-based TIC method, respectively.ConclusionsThe proposed CNN-LSTM method is promising in making malignancy diagnosis of liver lesions in CEUS without any additional manual features selection.

Feasibility of the application of deep learning-reconstructed ultra-fast respiratory-triggered T2-weighted imaging at 3 T in liver imaging

ObjectiveThe evaluate the feasibility of a novel deep learning-reconstructed ultra-fast respiratory-triggered T2WI sequence (DL-RT-T2WI) In liver imaging, compared with respiratory-triggered Arms-T2WI (Arms-RT-T2WI) and respiratory-triggered FSE-T2WI (FSE-RT-T2WI) sequences. Methods71 patients with liver lesions underwent 3-T MRI and were prospectively enrolled. Two readers independently analyzed images acquired with DL-RT-T2WI, Arms-RT-T2WI, and FSE-RT-T2WI. The qualitative evaluation indicators, including overall image quality (OIQ), sharpness, noise, artifacts, lesion detectability (LC), lesion characterization (LD), cardiacmotion–related signal loss (CSL), and diagnostic confidence (DC), were evaluated in two readers, and further statistically compared using paired Wilcoxon rank-sum test among three sequences. Results176 lesions were detected in DL-RT-T2W and Arms-RT-T2WI, and 175 were detected in FSE-RT-T2WI. The acquisition time of DL-RT-T2WI was improved by 4.8–7.9 folds compared to the other two sequences. The OIQ was scored highest for DL-RT-T2WI (R1, 4.61 ± 0.52 and R2, 4.62 ± 0.49), was significantly superior to Arms-RT-T2WI (R1, 4.30 ± 0.66 and R2, 4.34 ± 0.69) and FSE-RT-T2WI (R1, 3.65 ± 1.08 and R2, 3.75 ± 1.01). Artifacts and sharpness scored highest for DL-RT-T2WI, followed by Arms-RT-T2WI, and were lowest for FSE-RT-T2WI in both two readers. Noise and CSL for DL-RT-T2WI scored similar to Arms-RT-T2WI (P > 0.05) and were significantly superior to FSE-RT-T2WI (P < 0.001). Both LD and LC for DL-RT-T2WI were significantly superior to Arms-RT-T2WI and FSE-RT-T2WI in two readers (P < 0.001). DC for DL-RT-T2WI scored best, significantly superior to Arms-RT-T2WI (P < 0.010) and FSE-RT-T2WI (P < 0.001). ConclusionsThe novel ultra-fast DL-RT-T2WI is feasible for liver imaging and lesion characterization and diagnosis, not only offers a significant improvement in acquisition time but also outperforms Arms-RT-T2WI and FSE-RT-T2WI concerning image quality and DC.

Comments and illustrations of the WFUMB CEUS liver guidelines: Rare focal liver lesion - infectious parasitic, fungus.

In this series of papers on comments and illustrations of the World Federation for Medicine and Biology (WFUMB) guidelines on contrast enhanced ultrasound (CEUS) the topics of parasitic and fungus infections are discussed. Improved detection and characterization of common focal liver lesions (FLL) are the main topics of these guidelines but detailed and illustrating information is missing. The focus in this paper on infectious (parasitic and fungus) focal liver lesions is on their appearance on B-mode and Doppler ultrasound and CEUS features. Knowledge of these data should help to raise awareness of these rarer findings, to think of these clinical pictures in the corresponding clinical situation, to interpret the ultrasound images correctly and thus to initiate the appropriate diagnostic and therapeutic steps in time.

Application of Intravoxel Incoherent Motion in Clinical Liver Imaging: A Literature Review.

Intravoxel incoherent motion (IVIM) modeling is a widely used double-exponential model for describing diffusion-weighted imaging (DWI) signal, with a slow component related to pure molecular diffusion and a fast component associated with microcirculatory perfusion, which compensates for the limitations of traditional DWI. IVIM is a noninvasive technique for obtaining liver pathological information and characterizing liver lesions, and has potential applications in the initial diagnosis and treatment monitoring of liver diseases. Recent studies have demonstrated that IVIM-derived parameters are useful for evaluating liver lesions, including nonalcoholic fatty liver disease (NAFLD), liver fibrosis and liver tumors. However, the results are not stable. Therefore, it is necessary to summarize the current applications of IVIM in liver disease research, identify existing shortcomings, and point out the future development direction. In this review, we searched for studies related to hepatic IVIM-DWI applications over the past two decades in the PubMed database. We first introduce the fundamental principles and influential factors of IVIM, and then discuss its application in NAFLD, liver fibrosis, and focal hepatic lesions. It has been found that IVIM is still unstable in ensuring the robustness and reproducibility of measurements in the assessment of liver fibrosis grade and liver tumors differentiation, due to inconsistent and substantial overlap in the range of IVIM-derived parameters for different fibrotic stages. In the end, the future direction of IVIM-DWI in the assessment of liver diseases is discussed, emphasizing the need for further research on the stability of IVIM-derived parameters, particularly perfusion-related parameters, in order to promote the clinical practice of IVIM-DWI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 3.

MR Fingerprinting for Contrast Agent-free and Quantitative Characterization of Focal Liver Lesions.

Purpose To evaluate the feasibility of liver MR fingerprinting (MRF) for quantitative characterization and diagnosis of focal liver lesions. Materials and Methods This single-site, prospective study included 89 participants (mean age, 62 years ± 15 [SD]; 45 women, 44 men) with various focal liver lesions who underwent MRI between October 2021 and August 2022. The participants underwent routine clinical MRI, non-contrast-enhanced liver MRF, and reference quantitative MRI with a 1.5-T MRI scanner. The bias and repeatability of the MRF measurements were assessed using linear regression, Bland-Altman plots, and coefficients of variation. The diagnostic capability of MRF-derived T1, T2, T2*, proton density fat fraction (PDFF), and a combination of these metrics to distinguish benign from malignant lesions was analyzed according to the area under the receiver operating characteristic curve (AUC). Results Liver MRF measurements showed moderate to high agreement with reference measurements (intraclass correlation = 0.94, 0.77, 0.45, and 0.61 for T1, T2, T2*, and PDFF, respectively), with underestimation of T2 values (mean bias in lesion = -0.5%, -29%, 5.8%, and -8.2% for T1, T2, T2*, and PDFF, respectively). The median coefficients of variation for repeatability of T1, T2, and T2* values were 2.5% (IQR, 3.6%), 3.1% (IQR, 5.6%), and 6.6% (IQR, 13.9%), respectively. After considering multicollinearity, a combination of MRF measurements showed a high diagnostic performance in differentiating benign from malignant lesions (AUC = 0.92 [95% CI: 0.86, 0.98]). Conclusion Liver MRF enabled the quantitative characterization of various focal liver lesions in a single breath-hold acquisition. Keywords: MR Imaging, Abdomen/GI, Liver, Imaging Sequences, Technical Aspects, Tissue Characterization, Technology Assessment, Diagnosis, Liver Lesions, MR Fingerprinting, Quantitative Characterization Supplemental material is available for this article. © RSNA, 2023.

Comments and illustrations of the WFUMB CEUS liver guidelines: Rare focal liver lesions - infectious (bacterial).

In this series of papers on comments and illustrations of the World Federation for Medicine and Biology (WFUMB) guidelines on contrast enhanced ultrasound (CEUS) the topics of bacterial infections are discussed. Improved detection and characterization of common focal liver lesions (FLL) are the main topics of these guidelines but detailed and illustrating information is missing. The focus in this paper on infectious (bacterial) focal liver lesions is on their appearance on B-mode and Doppler ultrasound and CEUS features. Knowledge of these data should help to raise awareness of these rarer findings, to think of these clinical pictures in the corresponding clinical situation, to interpret the ultrasound images correctly and thus to initiate the appropriate diagnostic and therapeutic steps in time.

6,6'-2 H2 ] fructose as a deuterium metabolic imaging probe in liver cancer.

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related deaths. Imaging plays a crucial role in the early detection of HCC, although current methods are limited in their ability to characterize liver lesions. Most recently, deuterium metabolic imaging (DMI) has been demonstrated as a powerful technique for the imaging of metabolism in vivo. Here, we assess the metabolic flux of [6,6'-2 H2 ] fructose in cell cultures and in subcutaneous mouse models at 9.4 T. We compare these rates with the most widely used DMI probe, [6,6'-2 H2 ] glucose, exploring the possibility of developing 2 H fructose to overcome the limitations of glucose as a novel DMI probe for detecting liver tumors. Comparison of the in vitro metabolic rates implies their similar glycolytic metabolism in the TCA cycle due to comparable production rates of 2 H glutamate/glutamine (glx) for the two precursors, but overall higher glycolytic metabolism from 2 H glucose because of a higher production rate of 2 H lactate. In vivo kinetic studies suggest that HDO can serve as a robust reporter for the consumption of the precursors in liver tumors. As fructose is predominantly metabolized in the liver, deuterated water (HDO) produced from 2 H fructose is probably less contaminated from whole-body metabolism in comparison with glucose. Moreover, in studies of the normal liver, 2 H fructose is readily converted to 2 H glx, enabling the characterization of 2 H fructose kinetics. This overcomes a major limitation of previous 2 H glucose studies in the liver, which were unable to confidently discern metabolic flux due to overlapped signals of 2 H glucose and its metabolic product, 2 H glycogen. This suggests a unique role for 2 H fructose metabolism in HCC and the normal liver, making it a useful approach for assessing liver-related diseases and the progression to oncogenesis.

Current and Advanced Applications of Gadoxetic Acid–enhanced MRI in Hepatobiliary Disorders

Gadoxetic acid is an MRI contrast agent that has specific applications in the study of hepatobiliary disease. After being distributed in the vascular and extravascular spaces during the dynamic phase, gadoxetic acid is progressively taken up by hepatocytes and excreted to the bile ducts during the hepatobiliary phase. The information derived from the enhancement characteristics during dynamic and hepatobiliary phases is particularly relevant in the detection and characterization of focal liver lesions and in the evaluation of the structure and function of the liver and biliary system. The use of new MRI sequences and advanced imaging techniques (eg, relaxometry, multiparametric imaging, and analysis of heterogeneity), the introduction of artificial intelligence, and the development of biomarkers and radiomic and radiogenomic tools based on gadoxetic acid-enhanced MRI findings will play an important role in the future in assessing liver function, chronic liver disease, and focal liver lesions; in studying biliary pathologic conditions; and in predicting treatment responses and prognosis. © RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Characterization of Incidental Liver Lesions: Comparison of Multidetector CT versus Ultrasonography

Background: Due to recent advancements in imaging techniques, as well as the widespread use of routine medical exams and screenings, incidental LL are now more frequently discovered by US. Physicians must decide whether to simply follow up when incidental LL are discovered in the US or to order additional imaging tests for lesion classification. The goal of our study was to identify LL using MDCT and US. Methods and Results: A total of 50 participants were selected from a variety of male and female patients with abdominal pain and suspected liver diseases, and received a CT triphasic scan and US at the Royal Care International Hospital, Ibn Alhaitham Diagnostic Center, Alfaisal Specialized Hospital, and the Department of Diagnostic Radiology in the CT department of Sudan from April 2018 to May 2020. The results of the ultrasound scanning (liver lesions and related findings) performed on patients before the CT scanning indicated that ascites+ liver lesions was predominant (48.6%). The incidental liver lesions that take peripheral nodular enhancement by MDCT when contrast media is injected, were liver metastases (30%), hemangioma (14%), and HCC (10%). Liver cysts represent 10(20%) of the total cases of lesions that were non-enhanced by CT, with a few cases of liver cirrhosis (2%), hepatosplenomegaly (2%), and cyst + hepatitis (2%). We found a significant relationship between peripheral nodular enhancement for liver lesions by MDCT and non-enhancing liver lesions (P=0.001). Conclusion: The US and CT scan findings have a statistically significant relationship (P≤0.017). Contrast-enhanced CT performs better at diagnosing liver lesions than does standard US.

Characterization of Primary and Malignant Liver Lesions using Texture Analysis

Texture analysis can be used as a classification approach to describe microscopic changes in the liver. In our study, a total of 260 patients aged 4 to 90 underwent successful liver ultrasound examinations using a General Electric ultrasound machine (21045-87) with a 3.5MHz curve-linear transducer, typically used to scan the liver. The liver was scanned in multiple planes (transverse, sagittal, and oblique) to analyze the lesion based on shape, position, size, and echogenicity. Then the pictures were retrieved and classified into 5 categories: normal, a liver cyst, a hydatid cyst, hepatocellular carcinoma (HCC), and liver metastases. All pictures were 512 x512 pixels with 8-bit gray-level and were encoded in DICOM format; then three FOS features (mean, entropy, and energy, obtained from the intensity function of the images) were calculated for each ROI through all images using a 3x3 window size, and the data were processed for stepwise linear discriminant (SW-LD) analysis. The classification matrix of the original and predicted groups, using the discriminant function, presents the classification accuracy of each class in which 99.2% of normal liver was correctly classified and 75.6%, 81.4%, 100.0%, and 100.0% classification sensitivity for liver cyst, HCC, hydatid cyst, and liver metastases, respectively, with the highest predictive overall accuracy of 89.1%.

Role of textural analysis parameters derived from FDG PET/CT in differentiating hepatocellular carcinoma and hepatic metastases.

Texture and radiomic analysis characterize the tumor's phenotype and evaluate its microenvironment in quantitative terms. The aim of this study was to investigate the role of textural features of 18F-FDG PET/computed tomography (CT) images in differentiating hepatocellular carcinoma (HCC) and hepatic metastasis in patients with suspected liver tumors. This is a retrospective, single-center study of 30 patients who underwent FDG PET/CT for the characterization of liver lesions or for staging a suspected liver tumor. The histological diagnosis of either primary or metastatic tumor was obtained from CT-guided biopsy, ultrasound-guided biopsy, or surgical removal of a liver lesion. The PET/CT images were then processed in commercially available textural analysis software. Region of interest was drawn over the primary tumor with a 40% threshold and was processed further to derive 42 textural and radiomic parameters. These parameters were then compared between HCC group and hepatic metastases group. Receiver-operating characteristic (ROC) curves were used to identify cutoff values for textural features with a P value <0.05 for statistical significance. A retrospective study of 30 patients with suspected liver tumors was done. After undergoing PET/CT, the histological diagnosis of these lesions was confirmed. Among these 30 patients, 15 patients had HCC, and 15 patients had hepatic metastases from various primary sites. Seven textural analysis parameters were significant in differentiating HCC from liver metastasis. Cutoff values were calculated for these parameters according to the ROC curves, standardized uptake value (SUV) Skewness (0.705), SUV Kurtosis (3.65), SUV Excess Kurtosis (0.653), gray-level zone length matrix_long zone emphasis (349.2), gray-level zone length matrix_long zone low gray-level emphasis (1.6), gray-level run length matrix_long run emphasis (1.38) and gray-level co-occurrence matrix_Homogeneity (0.406). Textural analysis parameters could successfully differentiate HCC and hepatic metastasis non-invasively. Larger multi-center studies are needed for better clinical prognostication of these parameters.

Modified contrast-enhanced ultrasonography with the new high-resolution examination technique of high frame rate contrast-enhanced ultrasound (HiFR-CEUS) for characterization of liver lesions: First results.

To examine to what extent the high frame rate contrast-enhanced ultrasound (HiFR) diagnostic enables the conclusive diagnosis of liver changes with suspected malignancy. Ultrasound examinations were performed by an experienced examiner using a multifrequency probe (SC6-1) on a high-end ultrasound system (Resona 7, Mindray) to clarify liver changes that were unclear on the B-scan. A bolus of 1-2.4 ml of the Sulphur hexafluoride ultrasound microbubbles contrast agent SonoVue™ (Bracco SpA, Italy) was administered with DICOM storage of CEUS examinations from the early arterial phase (5-15 s) to the late phase (5-6 min). Based on the image files stored in the PACS, an independent reading was performed regarding image quality and finding-related diagnostic significance (0 not informative/non-diagnostic to 5 excellent image quality/confident diagnosis possible). References were clinical follow-up, if possible, comparison to promptly performed computed tomography or magnetic resonance imaging, in some cases also to histopathology. We examined 100 patients (42 women, 58 men, from 18 years to 90 years, mean 63±13 years) with different entities of focal and diffuse liver parenchymal changes, which could be detected in all cases with sufficient image quality with CEUS and with high image quality with HiFR-CEUS. Proportionally septate cysts were found in n = 19 cases, scars after hemihepatectomy with local reduced fat in n = 5 cases, scars after microwave ablation in n = 19 cases, hemangiomas in n = 9 cases, focal nodular hyperplasia in n = 8 cases, colorectal metastases in n = 15 cases, hepatocellular carcinoma (HCC) in n = 11 cases, Osler disease in n = 8 cases. The size of lesions ranged from 5 mm to 200 mm with a mean value of 33.1±27.8 mm. Conclusive diagnoses could be made by the experienced investigator in 97/100 cases with CEUS, confirmed by reference imaging, in parts by histopathology or follow-up. The image quality for HiFR CEUS was rated with a score of 3 to 5; 62 cases were assessed with an average of good (4 points), 27 cases with very good (5 points), and in 11 cases (3 points) still satisfactory despite aggravated acoustic conditions. The specificity of HIFR-CEUS was 97%, the sensitivity 97%, the positive predictive value 94%, the negative predictive value 99% and the accuracy 97%. HIFR-CEUS has demonstrated has demonstrated an improved image quality resulting in a high diagnostic accuracy. In the hands of an experienced investigator, HiFR-CEUS allows the assessment of focal and diffuse unclear liver parenchymal changes on B-scan and dynamic assessment of microcirculation in solid and vascular changes.

Sonographische Differenzialdiagnostik fokaler Leberläsionen

Rapid diagnostic assessment is crucial for the clinical management of focal liver lesions. In addition to standard B‑mode sonography, color-coded Doppler sonography and contrast-enhanced ultrasound are widely used for the classification of liver tumors. In gastroenterology, clinical sonography plays an important role in the detection of tumors, in the follow-up of oncological patients and for the screening for hepatocellular carcinoma. Thereby, correctly classifying focal liver lesions essentially requires the interpretation of ultrasound findings in the clinical context (e.g., incidental finding, known risk factors, history of liver cirrhosis or malignant disease). In this review, we summarize the available ultrasound techniques for the characterization of focal liver lesions and discuss their importance and relevance for the differential diagnosis and further diagnostic and therapeutic management.

Clinical Significance of Liver MR Imaging.

MRI is widely used in clinical practice for detecting liver diseases. Since the introduction of gadoxetic acid, MRI has become the most effective modality for the detection and characterization of focal liver lesions. According to previous meta-analyses, the area under the receiver operating characteristic curve (AUROC) was 0.97-0.99 for the diagnosis of small hepatocellular carcinoma (≥ 2 cm) by gadoxetic-acid-enhanced MRI. Moreover, the AUROC for the diagnosis of colorectal liver metastases was significantly high (0.98). Despite gadoxetic acid's drawbacks, its clinical utility outweighs them, making it the contrast agent of choice in routine liver MRIs. Moreover, clinically, liver MRI has become more prevalent for a quantitative assessment. Liver fibrosis can be evaluated using MR elastography; whereas, hepatic steatosis and iron overload can be evaluated using proton density fat fraction, with high accuracy and reproducibility. This article reviewed the usefulness of liver MRI, which can be a comprehensive imaging modality in clinical practice.

The added value of diffusion weighted MRI over standard dynamic liver MRI in characterization of focal liver lesions

The added value of diffusion weighted MRI over standard dynamic liver MRI in characterization of focal liver lesions

Fusion and CNN based classification of liver focal lesions using magnetic resonance imaging phases

The diagnosis and follow-up of focal liver lesions have an important place in radiology practice and in planning the treatment of patients. Lesions detected in the liver can be benign or malign. While benign lesions do not require any treatment, some treatments and surgical operations may be required for malign lesions. Magnetic resonance imaging provides some advantages over other imaging modalities in the detection and characterization of focal liver lesions with its superior soft tissue contrast. Additionally, different phases help make a clear diagnosis of different contrast agent retention properties in magnetic resonance imaging. This study aims to classify focal liver lesions based on convolutional neural networks by fusing magnetic resonance liver images obtained in pre-contrast, venous, arterial, and delayed phases. Magnetic resonance imaging data were obtained from Selcuk University, Faculty of Medicine, Department of Radiology in Turkey. The experiments were performed using 460 magnetic resonance images in four phases of 115 patients. Two experiments were conducted. Two-dimensional discrete wavelet transform was used to fuse the phases in both experiments. In the first experiment, the best model was determined using the original data, different number of convolution layers and different activation functions. In the second experiment, the best-found model was used. Additionally, the number of data was increased using data augmentation methods in this experiment. The results were compared with other state-of-the art methods and the superiority of the proposed method was proved. As a result of the classification, 96.66% accuracy, 86.67% sensitivity and 98.76% specificity rates were obtained. When the results are examined, CNN efficiency increases by fusing MR liver images taken in different phases.

Characterisation of focal liver lesions in multi-phase CT images using textural and pathological descriptors

ABSTRACT Characterisation of Focal Liver Lesions using imaging techniques is a low-risk approach to help physicians in diagnosis and treatment planning. State-of-the-art techniques chiefly rely on texture-based features of deep networks or conventional feature extractor techniques. However, these techniques do not sufficiently exploit the semantic attributes to improve the description of the tumour types. In this paper, we introduce pathologic descriptors to characterise the lesions in Computer Tomography images including, the quality of the tumour’s boundary, the tumour’s geometry, and the lesion’s enhancement. We propose a blurred edge model to characterise the quality of a tumour’s border. The irregularity or homogeneity of a tumour’s geometry is determined by the assessment of the central part and a rim around the lesion’s boundary. We compare the tumour’s appearance with the intensity of normal liver tissue and the blood pools to describe its enhancement behaviour. The proposed algorithm labelled 123 Computer Tomography data consisting of five lesion types and achieved an average accuracy of 92.7%. These results prove the superiority of pathology-based descriptors compared to textural features and their future potential for the discrimination of the lesions in the brain and lung. Moreover, the features from the ‘Non-Contrast’ phase do not improve classification results.