Liver fibrosis processing, multiclassification, and diagnosis based on hybrid machine learning approaches

The new coronavirus disease (2019) has spread quickly as an acute respiratory distress syndrome (ARDS) among millions of individuals worldwide. Furthermore, the number of COVID-19 checking obtainable in hospitals is very limited as compared to the rising number of infections every day. As an outcome, an automatic detection system must be implemented as a quick diagnostic tool for preventing or reducing the spread of COVID-19 among humans. The present paper aims to propose an automated system by means of a hybrid Deep Learning ("convolutional neural network"(CNN)) and "support vector machine (SVM)" approach for identifying COVID-19 pneumonia-infected patients on the basis of chest computed tomography (746 CT images of "COVID-19" and "non-COVID-19"). The proposed system is composed of three phases. The first, pre-processing phase begins with converting CT images into greyscale level CT images of equal size (256×256). The "contrast limited adaptive histogram equalization" technology is adopted to enhance the intensity levels, and demonstrate the feature of lung tissue. It is also necessary to normalize the division of the image elements by 255 to make the values between 0 and 1, as this will speed up the processing process. The second phase, the CNN (SimpNet model), was applied as a deep feature extraction technique to identify CT samples. The SVM classifier and SoftMax function are employed in the third phase to classify COVID-19 pneumonia-infected patients. Specificity, Sensitivity, "F-score", Accuracy, and "area under curve" are used as criteria to estimate the efficiency of the classification. The results showed a high accuracy rate of COVID-19 classification which reached (98%) and (99.1%) for CNN-SoftMax and CNN-SVM classifier, respectively in the tested dataset (225 CT images).

The new coronavirus disease (2019) has spread quickly as an acute respiratory distress syndrome (ARDS) among millions of individuals worldwide. Furthermore, the number of COVID-19 checking obtainable in hospitals is very limited as compared to the rising number of infections every day. As an outcome, an automatic detection system must be implemented as a quick diagnostic tool for preventing or reducing the spread of COVID-19 among humans. The present paper aims to propose an automated system by means of a hybrid Deep Learning ("convolutional neural network"(CNN)) and "support vector machine (SVM)" approach for identifying COVID-19 pneumonia-infected patients on the basis of chest computed tomography (746 CT images of "COVID-19" and "non-COVID-19"). The proposed system is composed of three phases. The first, pre-processing phase begins with converting CT images into greyscale level CT images of equal size (256×256). The "contrast limited adaptive histogram equalization" technology is adopted to enhance the intensity levels, and demonstrate the feature of lung tissue. It is also necessary to normalize the division of the image elements by 255 to make the values between 0 and 1, as this will speed up the processing process. The second phase, the CNN (SimpNet model), was applied as a deep feature extraction technique to identify CT samples. The SVM classifier and SoftMax function are employed in the third phase to classify COVID-19 pneumonia-infected patients. Specificity, Sensitivity, "F-score", Accuracy, and "area under curve" are used as criteria to estimate the efficiency of the classification. The results showed a high accuracy rate of COVID-19 classification which reached (98%) and (99.1%) for CNN-SoftMax and CNN-SVM classifier, respectively in the tested dataset (225 CT images).

Image Processing Pipeline for Liver Fibrosis Classification Using Ultrasound Shear Wave Elastography

To automatically detect and isolate areas of low and high stiffness temporal stability in shear wave elastography (SWE) image sequences and define their impact in chronic liver disease (CLD) diagnosis improvement by means of clinical examination study and deep learning algorithm employing convolutional neural networks (CNNs). Two hundred SWE image sequences from 88 healthy individuals (F0 fibrosis stage) and 112 CLD patients (46 with mild fibrosis (F1), 16 with significant fibrosis (F2), 22 with severe fibrosis (F3), and 28 with cirrhosis (F4)) were analyzed to detect temporal stiffness stability between frames. An inverse Red, Green, Blue (RGB) colormap-to-stiffness process was performed for each image sequence, followed by a wavelet transform and fuzzy c-means clustering algorithm. This resulted in a binary mask depicting areas of high and low stiffness temporal stability. The mask was then applied to the first image of the SWE sequence, and the derived, masked SWE image was used to estimate its impact in standard clinical examination and CNN classification. Regarding the impact of the masked SWE image in clinical examination, one measurement by two radiologists was performed in each SWE image and two in the corresponding masked image measuring areas with high and low stiffness temporal stability. Then, stiffness stability parameters, interobserver variability evaluation and diagnostic performance by means of ROC analysis were assessed. The masked and unmasked sets of SWE images were fed into a CNN scheme for comparison. The clinical impact evaluation study showed that the masked SWE images decreased the interobserver variability of the radiologists' measurements in the high stiffness temporal stability areas (interclass correlation coefficient (ICC)=0.92) compared to the corresponding unmasked ones (ICC=0.76). In terms of diagnostic accuracy, measurements in the high-stability areas of the masked SWE images (area-under-the-curve (AUC) ranging from 0.800 to 0.851) performed similarly to those in the unmasked SWE images (AUC ranging from 0.805 to 0.893). Regarding the measurements in the low stiffness temporal stability areas of the masked SWE images, results for interobserver variability (ICC=0.63) and diagnostic accuracy (AUC ranging from 0.622 to 0.791) were poor. Regarding the CNN classification, the masked SWE images showed improved accuracy (ranging from 82.5% to 95.5%) compared to the unmasked ones (ranging from 79.5% to 93.2%) for various CLD stage combinations. Our detection algorithm excludes unreliable areas in SWE images, reduces interobserver variability, and augments CNN's accuracy scores for many combinations of fibrosis stages.

Breast cancer is one of the most common malignancies affecting women worldwide, and an early diagnosis is critical for improving prognosis. The present study aimed to investigate the diagnostic value of mammography (MG) combined with ultrasound shear wave elastography (SWE) and magnetic resonance imaging (MRI) for the early screening of breast cancer. Patients with breast tumors who underwent lumpectomy at a single hospital between December 2021 and January 2023 were selected and categorized into a benign or malignant group based on pathological findings. All patients had undergone examinations with MG, SWE and MRI. Imaging parameters were subsequently compared between the two groups. A total of 93 patients with breast tumors were included in the study, comprising 37 individuals in the benign group and 56 in the malignant group. MG findings revealed that patients in the malignant group exhibited significantly higher incidences of high breast glandular density, irregular mass margins, unclear mass borders and axillary lymph node involvement compared with those in the benign group. SWE results indicated that the elasticity ratio of the lesion to fat, and the mean and maximum values of the elastic modulus were significantly lower in the benign group than in the malignant group. Additionally, MRI findings demonstrated that the MRI-measured maximum diameter was larger, and the prevalence of irregular lesion morphology, irregular mass margins, signal enhancement and type III time-signal intensity curves was greater in the malignant group compared with the benign group. The diagnostic sensitivity, specificity, positive predictive value and negative predictive value of MG + SWE + MRI were 94.6, 86.5, 91.4 and 91.4%, respectively. Furthermore, the diagnostic efficacy of this combination surpassed that of MG + SWE, MG + MRI and SWE + MRI (area under the curve, 0.906 vs. 0.767, 0.758 and 0.763, respectively). In conclusion, the combination of MG with SWE and MRI exhibits a superior performance in the early diagnosis of breast cancer, exhibiting higher diagnostic accuracy and reliability compared with pairwise combinations.

OBJECTIVE. Liver transplant patients are monitored for rejection and hepatic fibrosis and often undergo liver biopsies. The purpose of the present study is to determine whether noninvasive shear wave elastography (SWE) can quantify fibrosis in liver transplant recipients, with the aim of decreasing and possibly eliminating unnecessary biopsies for patients with suspected or progressive hepatic fibrosis. MATERIALS AND METHODS. Between May 1, 2015, and December 31, 2017, our prospective study evaluated 111 adult liver transplant patients (age range, 23-79 years) who underwent 147 ultrasound (US) SWE examinations of the right hepatic lobe followed by biopsies. SWE values were compared with the histologic fibrosis (Metavir) scores of the biopsy samples. SWE threshold values were determined using classification and regression tree analysis by anchoring to the degree of fibrosis. The sensitivity, specificity, positive predictive value, and negative predictive value (with 95% CIs) were calculated on the basis of the threshold value. Overall prediction accuracy was estimated using the AUC value from the ROC curve. RESULTS. From the 147 US SWE examinations and liver biopsies, consistent threshold values were identified for patients with no or minimal fibrosis (Metavir scores of F0 and F1, respectively) compared with significant fibrosis (Metavir scores of F2, F3, or F4). A median SWE value of 1.76 m/s or less denoted no or minimal fibrosis, whereas a value greater than 1.76 m/s denoted significant fibrosis. The sensitivity of US SWE examinations in classifying fibrosis was 0.77 (95% CI, 0.5-0.93). The specificity, positive predictive value, and negative predictive value were 0.79 (95% CI, 0.71-0.86), 0.33 (95% CI, 0.19-0.49), and 0.96 (95% CI, 0.91-0.99), respectively. CONCLUSION. Liver transplant patients may avoid liver biopsy if US SWE examination shows a median shear wave velocity of 1.76 or less, which corresponds to a Metavir score of F0 or F1, denoting no or minimal fibrosis.

A Machine-Learning Algorithm Toward Color Analysis for Chronic Liver Disease Classification, Employing Ultrasound Shear Wave Elastography

Noninvasive Staging of Liver Fibrosis with Dual-Energy CT: Close but No Cigar.

Diffuse liver disease is common, primarily driven by high prevalence of non-alcoholic fatty liver disease (NAFLD). It is currently assessed by liver biopsy to determine fibrosis, often staged as F0 (normal) - F4 (cirrhosis). A noninvasive assessment method will allow a broader population to be monitored longitudinally, facilitating risk stratification and treatment efficacy assessment. Ultrasound shear wave elastography (SWE) is a promising noninvasive technique for measuring tissue stiffness that has been shown to correlate with fibrosis stage. However, this approach has been limited by variability in stiffness measurements. In this work, we developed and evaluated an automated framework, called SWE-Assist, that checks SWE image quality, selects a region of interest (ROI), and classifies the ROI to determine whether the fibrosis stage is at or exceeds F2, which is important for clinical decisionmaking. Our database consists of 3,392 images from 328 cases. Several classifiers, including random forest, support vector machine, and convolutional neural network (CNN)) were evaluated. The best approach utilized a CNN and yielded an area under the receiver operating curve (AUROC) of 0.89, compared to the conventional stiffness only based AUROC of 0.74. Moreover, the new method is based on single image per decision, vs. 10 images per decision for the baseline. A larger dataset is needed to further validate this approach, which has the potential to improve the accuracy and efficiency of non-invasive liver fibrosis staging.

Objectives: To determine the prognostic significance of tissue stiffness measurement using transrectal ultrasound shear wave elastography in predicting biochemical recurrence following radical prostatectomy for clinically localized prostate cancer.Patients and Methods: Eligible male patients with clinically localized prostate cancer and extraperitoneal laparoscopic radical prostatectomy between November 2013 and August 2017 were retrospectively selected. Information of potential biochemical recurrence predictors, including imaging (ultrasound shear wave elastography and magnetic resonance imaging), clinicopathological characteristics, and preoperative prostate specific antigen (PSA) levels were obtained. Recurrence-free survival (Kaplan–Meier curve) and a multivariate model were constructed using Cox regression analysis to evaluate the impact of shear wave elastography as a prognostic marker for biochemical recurrence.Results: Patients experienced biochemical recurrence in an average of 26.3 ± 16.3 months during their follow-up. A cutoff of 144.85 kPa for tissue stiffness measurement was estimated for recurrence status at follow-up with a sensitivity of 74.4% and a specificity of 61.7%, respectively (p < 0.05). In univariate analysis, shear wave elastography performed well in all preoperative factors compared to biopsy Gleason Score, PSA and magnetic resonance imaging; in multivariate analysis with postoperative pathological factors, shear wave elastography was statistically significant in predicting postoperative biochemical recurrence, which improved the C-index of predictive nomogram significantly (0.74 vs. 0.70, p < 0.05).Conclusions: The study revealed that quantitative ultrasound shear wave elastography-measured tissue stiffness was a significant imaging marker that enhanced the predictive ability with other clinical and histopathological factors in prognosticating postoperative biochemical recurrence following radical prostatectomy for clinically localized prostate cancer.

Aims: To propose a deep learning algorithm for pothole detection and compare the performance of Sigmoid and Softmax activation functions in the creation of Convolutional Neural Network (CNN) algorithms. Methods: Three different datasets were used to justify the robustness of the CNN model in detecting dry and wet potholes. The CNN algorithms were created separately using the Sigmoid and Softmax activation functions. Results: The CNN algorithm using the Sigmoid function achieved higher accuracy scores than the CNN algorithm using the Softmax function. Specifically, the Sigmoid algorithm achieved accuracy scores of 91%, 96%, and 83% over datasets 1, 2, and 3, respectively, while the Softmax algorithm achieved scores of 81%, 96%, and 85% over the same datasets. Conclusion: The results of this study suggest that the CNN algorithm using the Sigmoid activation function is more robust and effective in detecting pothole images compared to the CNN algorithm using the Softmax activation function.

We aimed to develop deep learning models based on perinodular regions' shear-wave elastography (SWE) images and ultrasound (US) images of thyroid nodules (TNs) and determine their performances in predicting thyroid cancer. A total of 1747 American College of Radiology Thyroid Imaging Reporting & Data System 4 (TR4) thyroid nodules (TNs) in 1582 patients were included in this retrospective study. US images, SWE images, and 2 quantitative SWE parameters (maximum elasticity of TNs; 5-point average maximum elasticity of TNs) were obtained. Based on US and SWE images of TNs and perinodular tissue, respectively, 7 single-image convolutional neural networks (CNN) models [US, internal SWE, 0.5 mm SWE, 1.0 mm SWE, 1.5 mm SWE, 2.0 mm SWE of perinodular tissue, and whole SWE region of interest (ROI) image] and another 6 fusional-image CNN models (US + internal SWE, US + 0.5 mm SWE, US + 1.0 mm SWE, US + 1.5 mm SWE, US + 2.0 mm SWE, US + ROI SWE) were established using RestNet18. All of the CNN models and quantitative SWE parameters were built on a training cohort (1247 TNs) and evaluated on a validation cohort (500 TNs). In predicting thyroid cancer, US + 2.0 mm SWE image CNN model obtained the highest area under the curve in 10 mm < TNs ≤ 20 mm (0.95 for training; 0.92 for validation) and TNs > 20 mm (0.95 for training; 0.92 for validation), while US + 1.0 mm SWE image CNN model obtained the highest area under the curve in TNs ≤ 10 mm (0.95 for training; 0.92 for validation). The CNN models based on the fusion of SWE segmentation images and US images improve the radiological diagnostic accuracy of thyroid cancer.

Introduction: Artificial intelligence (AI) is increasingly utilized for texture analysis and the development of machine learning (ML) techniques to enhance diagnostic accuracy. ML algorithms are trained to differentiate between normal and malignant conditions based on provided data. Texture feature analysis, including first-order and second-order features, is a critical step in ML development. This study aimed to evaluate quantitative texture features of normal and prostate cancer tissues identified through ultrasound B-mode and shear-wave elastography (SWE) imaging and to develop and assess ML models for predicting and classifying normal versus malignant prostate tissues. Methodology: First-order and second-order texture features were extracted from B-mode and SWE imaging, including four reconstructed regions of interest (ROIs) from SWE images for normal and malignant tissues. A total of 94 texture features were derived, including features for intensity, Gray-Level Co-Occurrence Matrix (GLCM), Gray-Level Dependence Length Matrix (GLDLM), Gray-Level Run Length Matrix (GLRLM), and Gray-Level Size Zone Matrix (GLSZM). Five ML models were developed and evaluated using 5-fold cross-validation to predict normal and malignant tissues. Results: Data from 62 patients were analyzed. All ROIs, except those derived from B-mode imaging, exhibited statistically significant differences in features between normal and malignant tissues. Among the developed models, Support Vector Machines (SVM), Random Forest (RF), and Naive Bayes (NB) demonstrated the highest performance across all ROIs. These models consistently achieved strong predictive accuracy for classifying normal versus malignant tissues. Gray Pure SWE and Gray Reconstructed images Provided the highest sensitivity and specificity in PCa prediction by 82%, 90%, and 98%, 96%, respectively. Conclusions: Texture analysis with machine learning on SWE-US and reconstructed images effectively differentiates malignant from benign prostate lesions, with features like contrast, entropy, and correlation playing a key role. Random Forest, SVM, and Naïve Bayes showed the highest classification performance, while grayscale reconstructions (GPSWE and GRRI) enhanced detection accuracy.

ObjectivesTo compare the diagnostic accuracy of US shear wave elastography (SWE) and magnetic resonance elastography (MRE) for classifying fibrosis stage in patients with nonalcoholic fatty liver disease (NAFLD).MethodsPatients from a prospective single-center cohort with clinical liver biopsy for known or suspected NAFLD underwent contemporaneous SWE and MRE. AUCs for classifying biopsy-determined liver fibrosis stages ≥ 1, ≥ 2, ≥ 3, and = 4, and their respective performance parameters at cutoffs providing ≥ 90% sensitivity or specificity were compared between SWE and MRE.ResultsIn total, 100 patients (mean age, 51.8 ± 12.9 years; 46% males; mean BMI 31.6 ± 4.7 kg/m2) with fibrosis stage distribution (stage 0/1/2/3/4) of 43, 36, 5, 10, and 6%, respectively, were included. AUCs (and 95% CIs) for SWE and MRE were 0.65 (0.54–0.76) and 0.81 (0.72–0.89), 0.81 (0.71–0.91) and 0.94 (0.89–1.00), 0.85 (0.74–0.96) and 0.95 (0.89–1.00), and 0.91 (0.79–1.00) and 0.92 (0.83–1.00), for detecting fibrosis stage ≥ 1, ≥ 2, ≥ 3, and = 4, respectively. The differences were significant for detecting fibrosis stage ≥ 1 and ≥ 2 (p < 0.01) but not otherwise. At ≥ 90% sensitivity cutoff, MRE yielded higher specificity than SWE at diagnosing fibrosis stage ≥ 1, ≥ 2, and ≥ 3. At ≥ 90% specificity cutoff, MRE yielded higher sensitivity than SWE at diagnosing fibrosis stage ≥ 1 and ≥ 2.ConclusionsIn adults with NAFLD, MRE was more accurate than SWE in diagnosing stage ≥ 1 and ≥ 2 fibrosis, but not stage ≥ 3 or 4 fibrosis.Key Points• For detecting any fibrosis or mild fibrosis, MR elastography was significantly more accurate than shear wave elastography.• For detecting advanced fibrosis and cirrhosis, MRE and SWE did not differ significantly in accuracy.• For excluding advanced fibrosis and potentially ruling out the need for biopsy, SWE and MRE did not differ significantly in negative predictive value.• Neither SWE nor MRE had sufficiently high positive predictive value to rule in advanced fibrosis.

Classify chronic liver disease (CLD) from ultrasound shear-wave elastography (SWE) imaging by means of a computer aided diagnosis (CAD) system. The proposed algorithm employs an inverse mapping technique (red-green-blue to stiffness) to quantify 85 SWE images (54 healthy and 31 with CLD). Texture analysis is then applied involving the automatic calculation of 330 first and second order textural features from every transformed stiffness value map to determine functional features that characterize liver elasticity and describe liver condition for all available stages. Consequently, a stepwise regression analysis feature selection procedure is utilized toward a reduced feature subset that is fed into the support vector machines (SVMs) classification algorithm in the design of the CAD system. With regard to the mapping procedure accuracy, the stiffness map values had an average difference of 0.01 ± 0.001 kPa compared to the quantification results derived from the color-box provided by the built-in software of the ultrasound system. Highest classification accuracy from the SVM model was 87.0% with sensitivity and specificity values of 83.3% and 89.1%, respectively. Receiver operating characteristic curves analysis gave an area under the curve value of 0.85 with [0.77-0.89] confidence interval. The proposed CAD system employing color to stiffness mapping and classification algorithms offered superior results, comparing the already published clinical studies. It could prove to be of value to physicians improving the diagnostic accuracy of CLD and can be employed as a second opinion tool for avoiding unnecessary invasive procedures.