Does image normalization and intensity resolution impact texture classification?

Artificial Intelligence-Empowered Radiology-Current Status and Critical Review

Humanity stands at a pivotal moment of technological revolution, with artificial intelligence (AI) reshaping fields traditionally reliant on human cognitive abilities. This transition, driven by advancements in artificial neural networks, has transformed data processing and evaluation, creating opportunities for addressing complex and time-consuming tasks with AI solutions. Convolutional networks (CNNs) and the adoption of GPU technology have already revolutionized image recognition by enhancing computational efficiency and accuracy. In radiology, AI applications are particularly valuable for tasks involving pattern detection and classification; for example, AI tools have enhanced diagnostic accuracy and efficiency in detecting abnormalities across imaging modalities through automated feature extraction. Our analysis reveals that neuroimaging and chest imaging, as well as CT and MRI modalities, are the primary focus areas for AI products, reflecting their high clinical demand and complexity. AI tools are also used to target high-prevalence diseases, such as lung cancer, stroke, and breast cancer, underscoring AI's alignment with impactful diagnostic needs. The regulatory landscape is a critical factor in AI product development, with the majority of products certified under the Medical Device Directive (MDD) and Medical Device Regulation (MDR) in Class IIa or Class I categories, indicating compliance with moderate-risk standards. A rapid increase in AI product development from 2017 to 2020, peaking in 2020 and followed by recent stabilization and saturation, was identified. In this work, the authors review the advancements in AI-based imaging applications, underscoring AI's transformative potential for enhanced diagnostic support and focusing on the critical role of CNNs, regulatory challenges, and potential threats to human labor in the field of diagnostic imaging.

Machine learning-based diagnostics of capsular invasion in thyroid nodules with wide-field second harmonic generation microscopy

Papillary thyroid carcinoma (PTC) is one of the most common, well-differentiated carcinomas of the thyroid gland. PTC nodules are often surrounded by a collagen capsule that prevents the spread of cancer cells. However, as the malignant tumor progresses, the integrity of this protective barrier is compromised, and cancer cells invade the surroundings. The detection of capsular invasion is, therefore, crucial for the diagnosis and the choice of treatment and the development of new approaches aimed at the increase of diagnostic performance are of great importance. In the present study, we exploited the wide-field second harmonic generation (SHG) microscopy in combination with texture analysis and unsupervised machine learning (ML) to explore the possibility of quantitative characterization of collagen structure in the capsule and designation of different capsule areas as either intact, disrupted by invasion, or apt to invasion. Two-step k-means clustering showed that the collagen capsules in all analyzed tissue sections were highly heterogeneous and exhibited distinct segments described by characteristic ML parameter sets. The latter allowed a structural interpretation of the collagen fibers at the sites of overt invasion as fragmented and curled fibers with rarely formed distributed networks. Clustering analysis also distinguished areas in the PTC capsule that were not categorized as invasion sites by the initial histopathological analysis but could be recognized as prospective micro-invasions after additional inspection. The characteristic features of suspicious and invasive sites identified by the proposed unsupervised ML approach can become a reliable complement to existing methods for diagnosing encapsulated PTC, increase the reliability of diagnosis, simplify decision making, and prevent human-related diagnostic errors. In addition, the proposed automated ML-based selection of collagen capsule images and exclusion of non-informative regions can greatly accelerate and simplify the development of reliable methods for fully automated ML diagnosis that can be integrated into clinical practice.

Detection of abdominopelvic lymph nodes in multi-parametric MRI

Reliable localization of lymph nodes (LNs) in multi-parametric MRI (mpMRI) studies plays a major role in the assessment of lymphadenopathy and staging of metastatic disease. Radiologists routinely measure the nodal size in order to distinguish benign from malignant nodes, which require subsequent cancer staging. However, identification of lymph nodes is a cumbersome task due to their myriad appearances in mpMRI studies. Multiple sequences are acquired in mpMRI studies, including T2 fat suppressed (T2FS) and diffusion weighted imaging (DWI) sequences among others; consequently, the sizing of LNs is rendered challenging due to the variety of signal intensities in these sequences. Furthermore, radiologists can miss potentially metastatic LNs during a busy clinical day. To lighten these imaging and workflow challenges, we propose a computer-aided detection (CAD) pipeline to detect both benign and malignant LNs in the body for their subsequent measurement. We employed the recently proposed Dynamic Head (DyHead) neural network to detect LNs in mpMRI studies that were acquired using a variety of scanners and exam protocols. The T2FS and DWI series were co-registered, and a selective augmentation technique called Intra-Label LISA (ILL) was used to blend the two volumes with the interpolation factor drawn from a Beta distribution. In this way, ILL diversified the samples that the model encountered during the training phase, while the requirement for both sequences to be present at test time was nullified. Our results showed a mean average precision (mAP) of 53.5% and a sensitivity of ∼78% with ILL at 4 FP/vol. This corresponded to an improvement of ≥10% in mAP and ≥12% in sensitivity at 4FP (p ¡ 0.05) respectively over current LN detection approaches evaluated on the same dataset. We also established the out-of-distribution robustness of the DyHead model by training it on data acquired by a Siemens Aera scanner and testing it on data from the Siemens Verio, Siemens Biograph mMR, and Philips Achieva scanners. Our pilot work represents an important first step towards automated detection, segmentation, and classification of lymph nodes in mpMRI.

Sex Differentiation of Trabecular Bone Structure Based on Textural Analysis of Pelvic Radiographs

Objectives: The purpose of this paper is to assess the determination of male and female sex from trabecular bone structures in the pelvic region. The study involved analyzing digital radiographs for 343 patients and identifying fourteen areas of interest based on their medical significance, with seven regions on each side of the body for symmetry. Methods: Textural parameters for each region were obtained using various methods, and a thorough investigation of data normalization was conducted. Feature selection approaches were then evaluated to determine a small set of the most representative features, which were input into several classification machine learning models. Results: The findings revealed a sex-dependent correlation in the bone structure observed in X-ray images, with the degree of dependency varying based on the anatomical location. Notably, the femoral neck and ischium regions exhibited distinctive characteristics between sexes. Conclusions: This insight is crucial for medical professionals seeking to estimate sex dependencies from such image data. For these four specific areas, the balanced accuracy exceeded 70%. The results demonstrated symmetry, confirming the genuine dependencies in the trabecular bone structures.

Predicting the progression-free survival of gastrointestinal stromal tumors after imatinib therapy through multi-sequence magnetic resonance imaging

PURPOSE

Identify radiomics features associated with progression-free survival (PFS) and develop a predictive model for accurate PFS prediction in liver metastatic gastrointestinal stromal tumor patients (GIST).

METHODS

This multi-center retrospective study involved a comprehensive review of clinical and imaging data pertaining to 211 patients with gastrointestinal stromal tumors (GIST) from Center A and B. A total of 147 patients with hepatic metastatic GIST were included, with 102 cases as the training set and 45 cases as the external validation set. Radiomics features were extracted from non-enhanced MR images, specifically T2WI, DWI, and ADC, and relevant features were selected through LASSO-Cox regression. A radiomics nomogram model was then constructed using multivariable Cox regression analysis to effectively predict PFS. The models performance were evaluated with the concordance index (C-index).

RESULTS

The median age of the patients was 53 years, with 82 males and 65 females. A total of 21 radiomics features were selected to generate the radiomics signature. Radiomics signature slightly outperformed the clinical model but without significant difference (P > 0.05). Integrated radiomics signature with clinical features to build a nomogram, which exhibited high predictive performance in both training (C-index 0.757, 95% CI 0.692-0.822) and validation cohorts (C-index 0.718, 95% CI 0.618-0.818). Nomogram significantly outperformed the clinical model (P = 0.002 for training cohort, P < 0.001 for validation cohort). Stable long-term predictions shown by time-dependent ROC analysis (AUC 0.765-0.919 in training, 0.766-0.893 in validation). Multivariable Cox regression confirmed radiomics signature as an independent prognostic factor for preoperative survival prediction in hepatic metastatic GIST patients (HR = 3.973).

CONCLUSION

Radiomics signature is valuable for predicting PFS in metastatic GIST patients. Integrating imaging features and clinical factors into a comprehensive nomogram improves accuracy and effectiveness of survival prognosis, guiding personalized treatment strategies.

Radiomics from multisite MRI and clinical data to predict clinically significant prostate cancer

BACKGROUND

Magnetic resonance imaging (MRI) is useful in the diagnosis of clinically significant prostate cancer (csPCa). MRI-derived radiomics may support the diagnosis of csPCa.

PURPOSE

To investigate whether adding radiomics from biparametric MRI to predictive models based on clinical and MRI parameters improves the prediction of csPCa in a multisite-multivendor setting.

MATERIAL AND METHODS

Clinical information (PSA, PSA density, prostate volume, and age), MRI reviews (PI-RADS 2.1), and radiomics (histogram and texture features) were retrieved from prospectively included patients examined at different radiology departments and with different MRI systems, followed by MRI-ultrasound fusion guided biopsies of lesions PI-RADS 3-5. Predictive logistic regression models of csPCa (Gleason score ≥7) for the peripheral (PZ) and transition zone (TZ), including clinical data and PI-RADS only, and combined with radiomics, were built and compared using receiver operating characteristic (ROC) curves.

RESULTS

In total, 456 lesions in 350 patients were analyzed. In PZ and TZ, PI-RADS 4-5 and PSA density, and age in PZ, were independent predictors of csPCa in models without radiomics. In models including radiomics, PI-RADS 4-5, PSA density, age, and ADC energy were independent predictors in PZ, and PI-RADS 5, PSA density and ADC mean in TZ. Comparison of areas under the ROC curve (AUC) for the models without radiomics (PZ: AUC = 0.82, TZ: AUC = 0.80) versus with radiomics (PZ: AUC = 0.82, TZ: AUC = 0.82) showed no significant differences (PZ: P = 0.366; TZ: P = 0.171).

CONCLUSION

PSA density and PI-RADS are potent predictors of csPCa. Radiomics do not add significant information to our multisite-multivendor dataset.

Image annotation and curation in radiology: an overview for machine learning practitioners

"Garbage in, garbage out" summarises well the importance of high-quality data in machine learning and artificial intelligence. All data used to train and validate models should indeed be consistent, standardised, traceable, correctly annotated, and de-identified, considering local regulations. This narrative review presents a summary of the techniques that are used to ensure that all these requirements are fulfilled, with special emphasis on radiological imaging and freely available software solutions that can be directly employed by the interested researcher. Topics discussed include key imaging concepts, such as image resolution and pixel depth; file formats for medical image data storage; free software solutions for medical image processing; anonymisation and pseudonymisation to protect patient privacy, including compliance with regulations such as the Regulation (EU) 2016/679 "General Data Protection Regulation" (GDPR) and the 1996 United States Act of Congress "Health Insurance Portability and Accountability Act" (HIPAA); methods to eliminate patient-identifying features within images, like facial structures; free and commercial tools for image annotation; and techniques for data harmonisation and normalisation.Relevance statement This review provides an overview of the methods and tools that can be used to ensure high-quality data for machine learning and artificial intelligence applications in radiology.Key points• High-quality datasets are essential for reliable artificial intelligence algorithms in medical imaging.• Software tools like ImageJ and 3D Slicer aid in processing medical images for AI research.• Anonymisation techniques protect patient privacy during dataset preparation.• Machine learning models can accelerate image annotation, enhancing efficiency and accuracy.• Data curation ensures dataset integrity, compliance, and quality for artificial intelligence development.

Brain tumor diagnosis from MRI based on Mobilenetv2 optimized by contracted fox optimization algorithm

This research paper presents an innovative approach to brain tumor diagnosis using MRI scans, using the power of deep learning and metaheuristic algorithm. The study employs Mobilenetv2, a deep learning model, optimized by a novel metaheuristic known as the Contracted Fox Optimization Algorithm (MN-V2/CFO). This methodology allows for the optimal selection of Mobilenetv2 hyperparameters, enhancing the accuracy of tumor detection. The model is implemented on the Figshare dataset, a comprehensive collection of MRI scans, and its performance is validated against other processes the results are compared with some published works including Network (RN), wavelet transform, and deep learning (WT/DL), customized VGG19, and Convolutional neural network (CNN). The results of the study, highlight the superior performance of the proposed MN-V2/CFO model compared to other tactics. The recommended strategy achieves a precision of 97.68 %, an F1-score of 86.22 %, a sensitivity of 80.12 %, and an accuracy of 97.32 %. The findings validate the potential of the proposed model in revolutionizing brain tumor diagnosis, contributing to better treatment strategies, and improving patient outcomes.

Analysis of Hybrid Feature Optimization Techniques Based on the Classification Accuracy of Brain Tumor Regions Using Machine Learning and Further Evaluation Based on the Institute Test Data

Aim

The goal of this study was to get optimal brain tumor features from magnetic resonance imaging (MRI) images and classify them based on the three groups of the tumor region: Peritumoral edema, enhancing-core, and necrotic tumor core, using machine learning classification models.

Materials and Methods

This study's dataset was obtained from the multimodal brain tumor segmentation challenge. A total of 599 brain MRI studies were employed, all in neuroimaging informatics technology initiative format. The dataset was divided into training, validation, and testing subsets online test dataset (OTD). The dataset includes four types of MRI series, which were combined together and processed for intensity normalization using contrast limited adaptive histogram equalization methodology. To extract radiomics features, a python-based library called pyRadiomics was employed. Particle-swarm optimization (PSO) with varying inertia weights was used for feature optimization. Inertia weight with a linearly decreasing strategy (W1), inertia weight with a nonlinear coefficient decreasing strategy (W2), and inertia weight with a logarithmic strategy (W3) were different strategies used to vary the inertia weight for feature optimization in PSO. These selected features were further optimized using the principal component analysis (PCA) method to further reducing the dimensionality and removing the noise and improve the performance and efficiency of subsequent algorithms. Support vector machine (SVM), light gradient boosting (LGB), and extreme gradient boosting (XGB) machine learning classification algorithms were utilized for the classification of images into different tumor regions using optimized features. The proposed method was also tested on institute test data (ITD) for a total of 30 patient images.

Results

For OTD test dataset, the classification accuracy of SVM was 0.989, for the LGB model (LGBM) was 0.992, and for the XGB model (XGBM) was 0.994, using the varying inertia weight-PSO optimization method and the classification accuracy of SVM was 0.996 for the LGBM was 0.998, and for the XGBM was 0.994, using PSO and PCA-a hybrid optimization technique. For ITD test dataset, the classification accuracy of SVM was 0.994 for the LGBM was 0.993, and for the XGBM was 0.997, using the hybrid optimization technique.

Conclusion

The results suggest that the proposed method can be used to classify a brain tumor as used in this study to classify the tumor region into three groups: Peritumoral edema, enhancing-core, and necrotic tumor core. This was done by extracting the different features of the tumor, such as its shape, grey level, gray-level co-occurrence matrix, etc., and then choosing the best features using hybrid optimal feature selection techniques. This was done without much human expertise and in much less time than it would take a person.

Universal detection and segmentation of lymph nodes in multi-parametric MRI

PURPOSE

Reliable measurement of lymph nodes (LNs) in multi-parametric MRI (mpMRI) studies of the body plays a major role in the assessment of lymphadenopathy and staging of metastatic disease. Previous approaches do not adequately exploit the complementary sequences in mpMRI to universally detect and segment lymph nodes, and they have shown fairly limited performance.

METHODS

We propose a computer-aided detection and segmentation pipeline to leverage the T2 fat-suppressed (T2FS) and diffusion-weighted imaging (DWI) series from a mpMRI study. The T2FS and DWI series in 38 studies (38 patients) were co-registered and blended together using a selective data augmentation technique, such that traits of both series were visible in the same volume. A mask RCNN model was subsequently trained for universal detection and segmentation of 3D LNs.

RESULTS

Experiments on 18 test mpMRI studies revealed that the proposed pipeline achieved a precision of [Formula: see text]%, sensitivity of [Formula: see text]% at 4 false positives (FP) per volume, and dice score of [Formula: see text]%. This represented an improvement of [Formula: see text]% in precision, [Formula: see text]% in sensitivity at 4 FP/volume, and [Formula: see text]% in dice score, respectively, over current approaches evaluated on the same dataset.

CONCLUSION

Our pipeline universally detected and segmented both metastatic and non-metastatic nodes in mpMRI studies. At test time, the input data used by the trained model could either be the T2FS series alone or a blend of co-registered T2FS and DWI series. Contrary to prior work, this eliminated the reliance on both the T2FS and DWI series in a mpMRI study.

Texture analysis of ultrasound images obtained with different beamforming techniques and dynamic ranges - A robustness study

Texture analysis of medical images gives quantitative information about the tissue characterization for possible pathology discrimination. Ultrasound B-mode images are generated through a process called beamforming. Then, to obtain the final 8-bit image, the dynamic range value must be set. It is currently unknown how different beamforming techniques or dynamic range values may alter the final image texture. We provide here a robustness analysis of first and higher order texture features using six beamforming methods and seven dynamic range values, on experimental phantom and in vivo musculoskeletal images acquired using two different ultrasound research scanners. To investigate the repeatability of the texture parameters, we applied the multivariate analysis of variance (MANOVA) and estimated the intraclass correlation coefficient (ICC) on the texture features calculated on the B-mode images created with different beamforming methods and dynamic range values. We demonstrated the high repeatability of texture features when varying the dynamic range and showed texture features can differentiate between beamforming methods through a MANOVA analysis, hinting at the potential future clinical application of specific beamformers.

Deep learning automates bidimensional and volumetric tumor burden measurement from MRI in pre- and post-operative glioblastoma patients

Tumor burden assessment by magnetic resonance imaging (MRI) is central to the evaluation of treatment response for glioblastoma. This assessment is, however, complex to perform and associated with high variability due to the high heterogeneity and complexity of the disease. In this work, we tackle this issue and propose a deep learning pipeline for the fully automated end-to-end analysis of glioblastoma patients. Our approach simultaneously identifies tumor sub-regions, including the enhancing tumor, peritumoral edema and surgical cavity in the first step, and then calculates the volumetric and bidimensional measurements that follow the current Response Assessment in Neuro-Oncology (RANO) criteria. Also, we introduce a rigorous manual annotation process which was followed to delineate the tumor sub-regions by the human experts, and to capture their segmentation confidences that are later used while training deep learning models. The results of our extensive experimental study performed over 760 pre-operative and 504 post-operative adult patients with glioma obtained from the public database (acquired at 19 sites in years 2021-2020) and from a clinical treatment trial (47 and 69 sites for pre-/post-operative patients, 2009-2011) and backed up with thorough quantitative, qualitative and statistical analysis revealed that our pipeline performs accurate segmentation of pre- and post-operative MRIs in a fraction of the manual delineation time (up to 20 times faster than humans). Volumetric measurements were in strong agreement with experts with the Intraclass Correlation Coefficient (ICC): 0.959, 0.703, 0.960 for ET, ED, and cavity. Similarly, automated RANO compared favorably with experienced readers (ICC: 0.681 and 0.866) producing consistent and accurate results. Additionally, we showed that RANO measurements are not always sufficient to quantify tumor burden. The high performance of the automated tumor burden measurement highlights the potential of the tool for considerably improving and simplifying radiological evaluation of glioblastoma in clinical trials and clinical practice.

External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study

OBJECTIVES

The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers' discriminative performance for pCR prediction.

METHODS

This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve.

RESULTS

Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models.

CONCLUSIONS

The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients.

KEY POINTS

• A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC. • The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer. • The RF classifier performed best in the current study.

Binary classification of multi-magnification histopathological breast cancer images using late fusion and transfer learning

Purpose

Histopathology biopsy imaging is currently the gold standard for the diagnosis of breast cancer in clinical practice. Pathologists examine the images at various magnifications to identify the type of tumor because if only one magnification is taken into account, the decision may not be accurate. This study explores the performance of transfer learning and late fusion to construct multi-scale ensembles that fuse different magnification-specific deep learning models for the binary classification of breast tumor slides.

Design/methodology/approach

Three pretrained deep learning techniques (DenseNet 201, MobileNet v2 and Inception v3) were used to classify breast tumor images over the four magnification factors of the Breast Cancer Histopathological Image Classification dataset (40×, 100×, 200× and 400×). To fuse the predictions of the models trained on different magnification factors, different aggregators were used, including weighted voting and seven meta-classifiers trained on slide predictions using class labels and the probabilities assigned to each class. The best cluster of the outperforming models was chosen using the Scott–Knott statistical test, and the top models were ranked using the Borda count voting system.

Findings

This study recommends the use of transfer learning and late fusion for histopathological breast cancer image classification by constructing multi-magnification ensembles because they perform better than models trained on each magnification separately.

Originality/value

The best multi-scale ensembles outperformed state-of-the-art integrated models and achieved an accuracy mean value of 98.82 per cent, precision of 98.46 per cent, recall of 100 per cent and F1-score of 99.20 per cent.

Universal lymph node detection in T2 MRI using neural networks

PURPOSE

Identification of lymph nodes (LNs) that are suspicious for metastasis in T2 Magnetic Resonance Imaging (MRI) is critical for assessment of lymphadenopathy. Prior work on LN detection has been limited to specific anatomical regions of the body (pelvis, rectum). Therefore, an approach to universally detect both benign and metastatic nodes in T2 MRI studies of the body is highly desirable.

METHODS

We developed a Computer Aided Detection (CAD) pipeline to universally identify LN in T2 MRI. First, we trained various neural networks for detecting LN: Faster RCNN with and without Hard Negative Example Mining (HNEM), FCOS, FoveaBox, VFNet, and Detection Transformer (DETR). Next, we show that VFNet with Adaptive Training Sample Selection (ATSS) outperformed Faster RCNN with HNEM. Finally, we ensembled models that surpassed a 45% mAP threshold.

RESULTS

Experiments on 122 test studies revealed that VFNet achieved a 51.1% mAP and 78.7% recall at 4 false positives (FP) per volume, while the one-stage model ensemble achieved a mAP of 52.3% and sensitivity of 78.7% at 4FP. We found that VFNet and the one-stage model ensemble can be interchangeably used in the CAD pipeline.

CONCLUSION

Our CAD pipeline universally detected both benign and metastatic nodes in T2 MRI studies, resulting in a sensitivity improvement of [Formula: see text]14% over the current LN detection approaches (sensitivity of 78.7% at 4 FP vs. 64.6% at 5 FP per volume).

Application of Two-Dimensional Entropy Measures to Detect the Radiographic Signs of Tooth Resorption and Hypercementosis in an Equine Model

Dental disorders are a serious health problem in equine medicine, their early recognition benefits the long-term general health of the horse. Most of the initial signs of Equine Odontoclastic Tooth Resorption and Hypercementosis (EOTRH) syndrome concern the alveolar aspect of the teeth, thus, the need for early recognition radiographic imaging. This study is aimed to evaluate the applicability of entropy measures to quantify the radiological signs of tooth resorption and hypercementosis as well as to enhance radiographic image quality in order to facilitate the identification of the signs of EOTRH syndrome. A detailed examination of the oral cavity was performed in eighty horses. Each evaluated incisor tooth was assigned to one of four grade-related EOTRH groups (0-3). Radiographs of the incisor teeth were taken and digitally processed. For each radiograph, two-dimensional sample (SampEn2D), fuzzy (FuzzEn2D), permutation (PermEn2D), dispersion (DispEn2D), and distribution (DistEn2D) entropies were measured after image filtering was performed using Normalize, Median, and LaplacianSharpening filters. Moreover, the similarities between entropy measures and selected Gray-Level Co-occurrence Matrix (GLCM) texture features were investigated. Among the 15 returned measures, DistEn2D was EOTRH grade-related. Moreover, DistEn2D extracted after Normalize filtering was the most informative. The EOTRH grade-related similarity between DistEn2D and Difference Entropy (GLCM) confirms the higher irregularity and complexity of incisor teeth radiographs in advanced EOTRH syndrome, demonstrating the greatest sensitivity (0.50) and specificity (0.95) of EOTRH 3 group detection. An application of DistEn2D to Normalize filtered incisor teeth radiographs enables the identification of the radiological signs of advanced EOTRH with higher accuracy than the previously used entropy-related GLCM texture features.

Radiomics: a primer on high-throughput image phenotyping

Radiomics is a high-throughput approach to image phenotyping. It uses computer algorithms to extract and analyze a large number of quantitative features from radiological images. These radiomic features collectively describe unique patterns that can serve as digital fingerprints of disease. They may also capture imaging characteristics that are difficult or impossible to characterize by the human eye. The rapid development of this field is motivated by systems biology, facilitated by data analytics, and powered by artificial intelligence. Here, as part of Abdominal Radiology's special issue on Quantitative Imaging, we provide an introduction to the field of radiomics. The technique is formally introduced as an advanced application of data analytics, with illustrating examples in abdominal radiology. Artificial intelligence is then presented as the main driving force of radiomics, and common techniques are defined and briefly compared. The complete step-by-step process of radiomic phenotyping is then broken down into five key phases. Potential pitfalls of each phase are highlighted, and recommendations are provided to reduce sources of variation, non-reproducibility, and error associated with radiomics.

Performance of Machine Learning and Texture Analysis for Predicting Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer with 3T MRI

Background: To evaluate the diagnostic performance of a Machine Learning (ML) algorithm based on Texture Analysis (TA) parameters in the prediction of Pathological Complete Response (pCR) to Neoadjuvant Chemoradiotherapy (nChRT) in Locally Advanced Rectal Cancer (LARC) patients. Methods: LARC patients were prospectively enrolled to undergo pre- and post-nChRT 3T MRI for initial loco-regional staging. TA was performed on axial T2-Weighted Images (T2-WI) to extract specific parameters, including skewness, kurtosis, entropy, and mean of positive pixels. For the assessment of TA parameter diagnostic performance, all patients underwent complete surgical resection, which served as a reference standard. ROC curve analysis was carried out to determine the discriminatory accuracy of each quantitative TA parameter to predict pCR. A ML-based decisional tree was implemented combining all TA parameters in order to improve diagnostic accuracy. Results: Forty patients were considered for final study population. Entropy, kurtosis and MPP showed statistically significant differences before and after nChRT in patients with pCR; in particular, when patients with Pathological Partial Response (pPR) and/or Pathological Non-Response (pNR) were considered, entropy and skewness showed significant differences before and after nChRT (all p < 0.05). In terms of absolute value changes, pre- and post-nChRT entropy, and kurtosis showed significant differences (0.31 ± 0.35, in pCR, −0.02 ± 1.28 in pPR/pNR, (p = 0.04); 1.87 ± 2.19, in pCR, −0.06 ± 3.78 in pPR/pNR (p = 0.0005); 107.91 ± 274.40, in pCR, −28.33 ± 202.91 in pPR/pNR, (p = 0.004), respectively). According to ROC curve analysis, pre-treatment kurtosis with an optimal cut-off value of ≤3.29 was defined as the best discriminative parameter, resulting in a sensitivity and specificity in predicting pCR of 81.5% and 61.5%, respectively. Conclusions: TA parameters extracted from T2-WI MRI images could play a key role as imaging biomarkers in the prediction of response to nChRT in LARC patients. ML algorithms can be used to efficiently combine all TA parameters in order to improve diagnostic accuracy.

Diagnosis of Alzheimer's Disease using Structure Highlighting Key Slice Stacking and Transfer Learning

BACKGROUND

In recent years, two-dimensional convolutional neural network (2D CNN) have been widely used in the diagnosis of Alzheimer's disease (AD) based on structural magnetic resonance imaging (sMRI). However, due to the lack of targeted processing of the key slices of sMRI images, the classification performance of the CNN model needs to be improved.

PURPOSE

Therefore, in this paper, we propose a key slice processing technique called the structural highlighting key slice stacking (SHKSS) technique, and we apply it to a 2D transfer learning model for AD classification.

METHODS

Specifically, first, 3D MR images were preprocessed. Second, the 2D axial middle-layer image was extracted from the MR image as a key slice. Then, the image was normalized by intensity and mapped to the RGB space, and histogram specification was performed on the obtained RGB image to generate the final three-channel image. The final three-channel image was input into a pre-trained CNN model for AD classification. Finally, classification and generalization experiments were conducted to verify the validity of the proposed method.

RESULTS

The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset show that our SHKSS method can effectively highlight the structural information in MRI slices. Compared with existing key slice processing techniques, our SHKSS method has an average accuracy improvement of at least 26% on the same test dataset, and it has better performance and generalization ability.

CONCLUSIONS

Our SHKSS method not only converts single-channel images into three-channel images to match the input requirements of the 2D transfer learning model but also highlights the structural information of MRI slices to improve the accuracy of AD diagnosis. This article is protected by copyright. All rights reserved.

Metaheuristics based COVID-19 detection using medical images: A review

Many countries in the world have been facing the rapid spread of COVID-19 since February 2020. There is a dire need for efficient and cheap automated diagnosis systems that can reduce the pressure on healthcare systems. Extensive research is being done on the use of image classification for the detection of COVID-19 through X-ray and CT-scan images of patients. Deep learning has been the most popular technique for image classification during the last decade. However, the performance of deep learning-based methods heavily depends on the architecture of the deep neural network. Over the last few years, metaheuristics have gained popularity for optimizing the architecture of deep neural networks. Metaheuristics have been widely used to solve different complex non-linear optimization problems due to their flexibility, simplicity, and problem independence. This paper aims to study the different image classification techniques for chest images, including the applications of metaheuristics for optimization and feature selection of deep learning and machine learning models. The motivation of this study is to focus on applications of different types of metaheuristics for COVID-19 detection and to shed some light on future challenges in COVID-19 detection from medical images. The aim is to inspire researchers to focus their research on overlooked aspects of COVID-19 detection.

Effect of Matrix Size Reduction on Textural Information in Clinical Magnetic Resonance Imaging

The selection of the matrix size is an important element of the magnetic resonance imaging (MRI) process, and has a significant impact on the acquired image quality. Signal to noise ratio, often used to assess MR image quality, has its limitations. Thus, for this purpose we propose a novel approach: the use of texture analysis as an index of the image quality that is sensitive for the change of matrix size. Image texture in biomedical images represents tissue and organ structures visualized via medical imaging modalities such as MRI. The correlation between texture parameters determined for the same tissues visualized in images acquired with different matrix sizes is analyzed to aid in the assessment of the selection of the optimal matrix size. T2-weighted coronal images of shoulders were acquired using five different matrix sizes while maintaining the same field of view; three regions of interest (bone, fat, and muscle) were considered. Lin’s correlation coefficients were calculated for all possible pairs of the 310-element texture feature vectors evaluated for each matrix. The obtained results are discussed considering the image noise and blurring effect visible in images acquired with smaller matrices. Taking these phenomena into account, recommendations for the selection of the matrix size used for the MRI imaging were proposed.

Selection of Filtering and Image Texture Analysis in the Radiographic Images Processing of Horses' Incisor Teeth Affected by the EOTRH Syndrome

Equine odontoclastic tooth resorption and hypercementosis (EOTRH) is one of the horses’ dental diseases, mainly affecting the incisor teeth. An increase in the incidence of aged horses and a painful progressive course of the disease create the need for improved early diagnosis. Besides clinical findings, EOTRH recognition is based on the typical radiographic findings, including levels of dental resorption and hypercementosis. This study aimed to introduce digital processing methods to equine dental radiographic images and identify texture features changing with disease progression. The radiographs of maxillary incisor teeth from 80 horses were obtained. Each incisor was annotated by separate masks and clinically classified as 0, 1, 2, or 3 EOTRH degrees. Images were filtered by Mean, Median, Normalize, Bilateral, Binomial, CurvatureFlow, LaplacianSharpening, DiscreteGaussian, and SmoothingRecursiveGaussian filters independently, and 93 features of image texture were extracted using First Order Statistics (FOS), Gray Level Co-occurrence Matrix (GLCM), Neighbouring Gray Tone Difference Matrix (NGTDM), Gray Level Dependence Matrix (GLDM), Gray Level Run Length Matrix (GLRLM), and Gray Level Size Zone Matrix (GLSZM) approaches. The most informative processing was selected. GLCM and GLRLM return the most favorable features for the quantitative evaluation of radiographic signs of the EOTRH syndrome, which may be supported by filtering by filters improving the edge delimitation.

Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study

Pulmonary medical image analysis using image processing and deep learning approaches has made remarkable achievements in the diagnosis, prognosis, and severity check of lung diseases. The epidemic of COVID-19 brought out by the novel coronavirus has triggered a critical need for artificial intelligence assistance in diagnosing and controlling the disease to reduce its effects on people and global economies. This study aimed at identifying the various COVID-19 medical imaging analysis models proposed by different researchers and featured their merits and demerits. It gives a detailed discussion on the existing COVID-19 detection methodologies (diagnosis, prognosis, and severity/risk detection) and the challenges encountered for the same. It also highlights the various preprocessing and post-processing methods involved to enhance the detection mechanism. This work also tries to bring out the different unexplored research areas that are available for medical image analysis and how the vast research done for COVID-19 can advance the field. Despite deep learning methods presenting high levels of efficiency, some limitations have been briefly described in the study. Hence, this review can help understand the utilization and pros and cons of deep learning in analyzing medical images.

An automatic brain tumor segmentation using modified inception module based U-Net model

Manual segmentation of brain tumor is not only a tedious task that may bring human mistakes. An automatic segmentation gives results faster, and it extends the survival rate with an earlier treatment plan. So, an automatic brain tumor segmentation model, modified inception module based U-Net (IMU-Net) proposed. It takes Magnetic resonance (MR) images from the BRATS 2017 training dataset with four modalities (FLAIR, T1, T1ce, and T2). The concatenation of two series 3×3 kernels, one 5×5, and one 1×1 convolution kernels are utilized to extract the whole tumor (WT), core tumor (CT), and enhance tumor (ET). The modified inception module (IM) collects all the relevant features and provides better segmentation results. The proposed deep learning model contains 40 convolution layers and utilizes intensity normalization and data augmentation operation for further improvement. It achieved the mean dice similarity coefficient (DSC) of 0.90, 0.77, 0.74, and the mean Intersection over Union (IOU) of 0.79, 0.70, 0.70 for WT, CT, and ET during the evaluation.

Using Deep Convolutional Neural Network for Image-Based Diagnosis of Nutrient Deficiencies in Plants Grown in Aquaponics

In the aquaponic system, plant nutrients bioavailable from fish excreta are not sufficient for optimal plant growth. Accurate and timely monitoring of the plant’s nutrient status grown in aquaponics is a challenge in order to maintain the balance and sustainability of the system. This study aimed to integrate color imaging and deep convolutional neural networks (DCNNs) to diagnose the nutrient status of lettuce grown in aquaponics. Our approach consists of multi-stage procedures, including plant object detection and classification of nutrient deficiency. The robustness and diagnostic capability of proposed approaches were evaluated using a total number of 3000 lettuce images that were classified into four nutritional classes—namely, full nutrition (FN), nitrogen deficiency (N), phosphorous deficiency (P), and potassium deficiency (K). The performance of the DCNNs was compared with traditional machine learning (ML) algorithms (i.e., Simple thresholding, K-means, support vector machine; SVM, k-nearest neighbor; KNN, and decision Tree; DT). The results demonstrated that the deep proposed segmentation model obtained an accuracy of 99.1%. Also, the deep proposed classification model achieved the highest accuracy of 96.5%. These results indicate that deep learning models, combined with color imaging, provide a promising approach to timely monitor nutrient status of the plants grown in aquaponics, which allows for taking preventive measures and mitigating economic and production losses. These approaches can be integrated into embedded devices to control nutrient cycles in aquaponics.

Computed tomography radiomics for the prediction of thymic epithelial tumor histology, TNM stage and myasthenia gravis

Objectives

To evaluate CT-derived radiomics for machine learning-based classification of thymic epithelial tumor (TET) stage (TNM classification), histology (WHO classification) and the presence of myasthenia gravis (MG).

Methods

Patients with histologically confirmed TET in the years 2000–2018 were retrospectively included, excluding patients with incompatible imaging or other tumors. CT scans were reformatted uniformly, gray values were normalized and discretized. Tumors were segmented manually; 15 scans were re-segmented after 2 weeks by two readers. 1316 radiomic features were calculated (pyRadiomics). Features with low intra-/inter-reader agreement (ICC<0.75) were excluded. Repeated nested cross-validation was used for feature selection (Boruta algorithm), model training, and evaluation (out-of-fold predictions). Shapley additive explanation (SHAP) values were calculated to assess feature importance.

Results

105 patients undergoing surgery for TET were identified. After applying exclusion criteria, 62 patients (28 female; mean age, 57±14 years; range, 22–82 years) with 34 low-risk TET (LRT; WHO types A/AB/B1), 28 high-risk TET (HRT; WHO B2/B3/C) in early stage (49, TNM stage I-II) or advanced stage (13, TNM III-IV) were included. 14(23%) of the patients had MG. 334(25%) features were excluded after intra-/inter-reader analysis. Discriminatory performance of the random forest classifiers was good for histology(AUC, 87.6%; 95% confidence interval, 76.3–94.3) and TNM stage(AUC, 83.8%; 95%CI, 66.9–93.4) but poor for the prediction of MG (AUC, 63.9%; 95%CI, 44.8–79.5).

Conclusions

CT-derived radiomic features may be a useful imaging biomarker for TET histology and TNM stage.

Differential Diagnosis of Cysts and Granulomas Supported by Texture Analysis of Intraoral Radiographs

The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.

COVID-19 Diagnosis Using Capsule Network and Fuzzy C-Means and Mayfly Optimization Algorithm

The COVID-19 epidemic is spreading day by day. Early diagnosis of this disease is essential to provide effective preventive and therapeutic measures. This process can be used by a computer-aided methodology to improve accuracy. In this study, a new and optimal method has been utilized for the diagnosis of COVID-19. Here, a method based on fuzzy C-ordered means (FCOM) along with an improved version of the enhanced capsule network (ECN) has been proposed for this purpose. The proposed ECN method is improved based on mayfly optimization (MFO) algorithm. The suggested technique is then implemented on the chest X-ray COVID-19 images from publicly available datasets. Simulation results are assessed by considering a comparison with some state-of-the-art methods, including FOMPA, MID, and 4S-DT. The results show that the proposed method with 97.08% accuracy and 97.29% precision provides the highest accuracy and reliability compared with the other studied methods. Moreover, the results show that the proposed method with a 97.1% sensitivity rate has the highest ratio. And finally, the proposed method with a 97.47% F1-score rate gives the uppermost value compared to the others.

Inferior alveolar canal segmentation based on cone-beam computed tomography

PURPOSE

The shape and position of the inferior alveolar canal (IAC) are analyzed to effectively reduce the risk of iatrogenic injury based on cone-beam computer tomography (CBCT). To assist dental clinicians to make better use of the IAC information, we propose an IAC segmentation method based on CBCT images.

METHODS

In this paper, CBCT images are first preprocessed by the Hounsfield unit values clipping and gray normalization. Secondly, based on the multi-plane reconstruction (MPR) and curved surface reconstruction, the curved MPR image sets are generated by the smooth dental arch curve with a sampling distance of 1.00 pixels. Then, the K-means clustering algorithm is used to cluster the texture parameters of the gray level-gradient co-occurrence matrix enhanced by the gradient directions to improve the image contrast of the IAC. Finally, the IAC edges are roughly segmented by the 2D line-tracking method, and smoothed by the fourth-order polynomial to obtain the final segmentation result.

RESULTS

Twenty-one real clinical dental CBCT datasets were used to test the proposed method. The manual segmentation results of two specialized dental clinicians were used as quantitative evaluation criteria. The dice similarity index (DSI), average symmetric surface distance (ASSD), and mean curve distance (MCD) of the left IAC are 0.93 (SD = 0.01), 0.16 mm (SD = 0.05 mm), and 1.59 mm (SD = 0.25 mm), respectively; the DSI, ASSD, and MCD of the right IAC are 0.93 (SD = 0.02), 0.16 mm (SD = 0.05 mm), and 1.60 mm (SD = 0.30 mm), respectively.

CONCLUSIONS

The proposed method provides an effective image enhancement and segmentation solution to analyze the shape and position of the IAC. Experimental results show that the relationships between the IAC and other structures can be accurately reflected in the panoramic images without superimposition and geometric distortion, and the smooth edges of the IAC can be segmented.

Correlations between first order echotextural characteristics and chemical composition of pectoralis major muscles in broiler chickens receiving different dietary fat supplements

This study examined the quantitative relationships among ultrasonographic image attributes and chemical composition of the pectoralis major muscles in broiler chickens that received four different dietary fat supplements (Group SO: soybean oil; Group FO: flaxseed oil; Group SO+FO: soybean oil+flaxseed oil; and Group BT: beef tallow; n=10 birds/group). Ultrasonograms of birds’ pectoral muscles, in a transverse (T) and longitudinal (L) plane, were obtained just before slaughter at 6 weeks of age and were subjected to digital image analyses to determine mean pixel intensity (MPI) and pixel heterogeneity values (standard deviation of numerical pixel values; MPH; a.k.a first order echotextural characteristics). Thirty-eight chemical characteristics of the muscles were determined post-mortem (crude fat, protein, and dry matter as well as fatty acid profiles) and were analyzed for correlations with the echotextural variables. A total of 12 (L-MPI: 7; L-MPH: 4; and T-MPH: 1 correlation), 5 (L-MPI: 2; L-MPH: 2; and T-MPI: 1 correlation), 15 (L-MPI: 10; T-MPI: 4; and T-MPH: 1 correlation) and 8 (L-MPI: 2; L-MPH: 1; and TMPH: 5 correlations) significant correlations were recorded in Groups SO, FO, SO+FO and BT, respectively. When the data were pooled for all 40 birds studied, significant correlations with echotextural attributes were recorded for eighteen different chemical constituents, with the strongest overall correlation found between crude fat content and T-MPI (r=0.52, P=0.0005). In conclusion, there exists a potential application for ultrasonographic imaging in situ combined with computerized image analysis to estimate certain chemical constituents of pectoralis major muscles in broiler chickens. However, the existence and strength of correlations among ultrasonographic image attributes and muscle composition are affected by the source of dietary fat and relative abundance (“threshold concentrations”) of individual chemical components.

Detecting Infected Cucumber Plants with Close-Range Multispectral Imagery

This study used close-range multispectral imagery over cucumber plants inside a commercial greenhouse to detect powdery mildew due to Podosphaera xanthii. It was collected using a MicaSense® RedEdge camera at 1.5 m over the top of the plant. Image registration was performed using Speeded-Up Robust Features (SURF) with an affine geometric transformation. The image background was removed using a binary mask created with the aligned NIR band of each image, and the illumination was corrected using Cheng et al.’s algorithm. Different features were computed, including RGB, image reflectance values, and several vegetation indices. For each feature, a fine Gaussian Support Vector Machines algorithm was trained and validated to classify healthy and infected pixels. The data set to train and validate the SVM was composed of 1000 healthy and 1000 infected pixels, split 70–30% into training and validation datasets, respectively. The overall validation accuracy was 89, 73, 82, 51, and 48%, respectively, for blue, green, red, red-edge, and NIR band image. With the RGB images, we obtained an overall validation accuracy of 89%, while the best vegetation index image was the PMVI-2 image which produced an overall accuracy of 81%. Using the five bands together, overall accuracy dropped from 99% in the training to 57% in the validation dataset. While the results of this work are promising, further research should be considered to increase the number of images to achieve better training and validation datasets.

MIL normalization -- prerequisites for accurate MRI radiomics analysis

The quality of magnetic resonance (MR) images obtained with different instruments and imaging parameters varies greatly. A large number of heterogeneous images are collected, and they suffer from acquisition variation. Such imaging quality differences will have a great impact on the radiomics analysis. The main differences in MR images include modality mismatch (M), intensity distribution variance (I), and layer-spacing differences (L), which are referred to as MIL differences in this paper for convenience. An MIL normalization system is proposed to reconstruct uneven MR images into high-quality data with complete modality, a uniform intensity distribution and consistent layer spacing. Three radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis of glioma, were used to verify the effect of MIL normalization on radiomics analysis. Three retrospective glioma datasets were analyzed in this study: BraTs (285 cases), TCGA (112 cases) and HuaShan (403 cases). They were used to test the effect of MIL on three different radiomics tasks, including tumor segmentation, pathological grading and genetic diagnosis. MIL normalization included three components: multimodal synthesis based on an encoder-decoder network, intensity normalization based on CycleGAN, and layer-spacing unification based on Statistical Parametric Mapping (SPM). The Dice similarity coefficient, areas under the curve (AUC) and six other indicators were calculated and compared after different normalization steps. The MIL normalization system can improved the Dice coefficient of segmentation by 9% (P < .001), the AUC of pathological grading by 32% (P < .001), and IDH1 status prediction by 25% (P < .001) when compared to non-normalization. The proposed MIL normalization system provides high-quality standardized data, which is a prerequisite for accurate radiomics analysis.

Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Intracranial Hemorrhage

OBJECTIVE

To determine the institutional diagnostic accuracy of an artificial intelligence (AI) decision support systems (DSS), Aidoc, in diagnosing intracranial hemorrhage (ICH) on noncontrast head CTs and to assess the potential generalizability of an AI DSS.

METHODS

This retrospective study included 3,605 consecutive, emergent, adult noncontrast head CT scans performed between July 1, 2019, and December 30, 2019, at our institution (51% female subjects, mean age of 61 ± 21 years). Each scan was evaluated for ICH by both a certificate of added qualification certified neuroradiologist and Aidoc. We determined the diagnostic accuracy of the AI model and performed a failure mode analysis with quantitative CT radiomic image characterization.

RESULTS

Of the 3,605 scans, 349 cases of ICH (9.7% of studies) were identified. The neuroradiologist and Aidoc interpretations were concordant in 96.9% of cases and the overall sensitivity, specificity, positive predictive value, and negative predictive value were 92.3%, 97.7%, 81.3%, and 99.2%, respectively, with positive predictive values unexpectedly lower than in previously reported studies. Prior neurosurgery, type of ICH, and number of ICHs were significantly associated with decreased model performance. Quantitative image characterization with CT radiomics failed to reveal significant differences between concordant and discordant studies.

DISCUSSION

This study revealed decreased diagnostic accuracy of an AI DSS at our institution. Despite extensive evaluation, we were unable to identify the source of this discrepancy, raising concerns about the generalizability of these tools with indeterminate failure modes. These results further highlight the need for standardized study design to allow for rigorous and reproducible site-to-site comparison of emerging deep learning technologies.

Combination of Quantitative MRI Fat Fraction and Texture Analysis to Evaluate Spastic Muscles of Children With Cerebral Palsy

Background: Cerebral palsy (CP) is the most common cause of physical disability in childhood. Muscle pathologies occur due to spasticity and contractures; therefore, diagnostic imaging to detect pathologies is often required. Imaging has been used to assess torsion or estimate muscle volume, but additional methods for characterizing muscle composition have not thoroughly been investigated. MRI fat fraction (FF) measurement can quantify muscle fat and is often a part of standard imaging in neuromuscular dystrophies. To date, FF has been used to quantify muscle fat and assess function in CP. In this study, we aimed to utilize a radiomics and FF analysis along with the combination of both methods to differentiate affected muscles from healthy ones. Materials and Methods: A total of 9 patients (age range 8-15 years) with CP and 12 healthy controls (age range 9-16 years) were prospectively enrolled (2018-2020) after ethics committee approval. Multi-echo Dixon acquisition of the calf muscles was used for FF calculation. The images of the second echo (TE = 2.87 ms) were used for feature extraction from the soleus, gastrocnemius medialis, and gastrocnemius lateralis muscles. The least absolute shrinkage and selection operator (LASSO) regression was employed for feature selection. RM, FF model (FFM), and combined model (CM) were built for each calf muscle. The receiver operating characteristic (ROC) curve and their respective area under the curve (AUC) values were used to evaluate model performance. Results: In total, the affected legs of 9 CP patients and the dominant legs of 12 healthy controls were analyzed. The performance of RM for soleus, gastrocnemius medialis, and gastrocnemius lateralis (AUC 0.92, 0.92, 0.82, respectively) was better than the FFM (AUC 0.88, 0.85, 0.69, respectively). The combination of both models always had a better performance than RM or FFM (AUC 0.95, 0.93, 0.83). FF was higher in the patient group (FFS 9.1%, FFGM 8.5%, and FFGL 10.2%) than control group (FFS 3.3%, FFGM 4.1%, FFGL 6.6%). Conclusion: The combination of MRI quantitative fat fraction analysis and texture analysis of muscles is a promising tool to evaluate muscle pathologies due to CP in a non-invasive manner.

Repeatability of CBCT radiomic features and their correlation with CT radiomic features for prostate cancer

PURPOSE

Radiomic features of cone-beam CT (CBCT) images have potential as biomarkers to predict treatment response and prognosis for patients of prostate cancer. Previous studies of radiomic feature analysis for prostate cancer were assessed in a variety of imaging modalities, including MRI, PET, and CT, but usually limited to a pretreatment setting. However, CBCT images may provide an opportunity to capture early morphological changes to the tumor during treatment that could lead to timely treatment adaptation. This work investigated the quality of CBCT-based radiomic features and their relationship with reconstruction methods applied to the CBCT projections and the preprocessing methods used in feature extraction. Moreover, CBCT features were correlated with planning CT (pCT) features to further assess the viability of CBCT radiomic features.

METHODS

The quality of 42 CBCT-based radiomic features was assessed according to their repeatability and reproducibility. Repeatability was quantified by correlating radiomic features between 20 CBCT scans that also had repeated scans within 15 minutes. Reproducibility was quantified by correlating radiomic features between the planning CT (pCT) and the first fraction CBCT for 20 patients. Concordance correlation coefficients (CCC) of radiomic features were used to estimate the repeatability and reproducibility of radiomic features. The same patient dataset was assessed using different reconstruction methods applied to the CBCT projections. CBCT images were generated using 18 reconstruction methods using iterative (iCBCT) and standard (sCBCT) reconstructions, three convolution filters, and five noise suppression filters. Eighteen preprocessing settings were also considered.

RESULTS

Overall, CBCT radiomic features were more repeatable than reproducible. Five radiomic features are repeatable in > 97% of the reconstruction and preprocessing methods, and come from the gray-level size zone matrix (GLSZM), neighborhood gray-tone difference matrix (NGTDM), and gray-level-run length matrix (GLRLM) radiomic feature classes. These radiomic features were reproducible in > 9.8% of the reconstruction and preprocessing methods. Noise suppression and convolution filter smoothing increased radiomic features repeatability, but decreased reproducibility. The top-repeatable iCBCT method (iCBCT-Sharp-VeryHigh) is more repeatable than the top-repeatable sCBCT method (sCBCT-Smooth) in 64% of the radiomic features.

CONCLUSION

Methods for reconstruction and preprocessing that improve CBCT radiomic feature repeatability often decrease reproducibility. The best approach may be to use methods that strike a balance repeatability and reproducibility such as iCBCT-Sharp-VeryLow-1-Lloyd-256 that has 17 repeatable and eight reproducible radiomic features. Previous radiomic studies that only used pCT radiomic features have generated prognostic models of prostate cancer outcome. Since our study indicates that CBCT radiomic features correlated well with a subset of pCT radiomic features, one may expect CBCT radiomics to also generate prognostic models for prostate cancer.

Associations between Mammary Gland Echotexture and Milk Composition in Cows

Simple Summary

Transcutaneous ultrasonography of the four quarters of the cow’s mammary gland with the 5-MHz ultrasound transducer combined with computer-assisted analysis of the resultant grey-scale images have the makings of an inexpensive and rapid technique to determine certain physicochemical properties of the pooled milk. The latter include crude protein, casein and lactose content. The relative ease and practically unlimited frequency with which this method can be used in farm settings makes it an attractive alternative to laboratory testing of milk samples. More studies are needed to determine the suitability of this approach for detecting changes in milk chemical composition in animals with mastitis.

Abstract

Thirty clinically healthy Holstein-Friesian cows underwent twice daily machine milking and ultrasonographic examinations of the udder just prior to and after milking. Digital ultrasonographic images of each udder quarter were subjected to computer-assisted echotextural analyses to obtain mean numerical pixel values (NPVs) and pixel heterogeneity (PSD) of the mammary gland parenchyma. The average milk yield and pH were higher (p < 0.05) in the morning, whereas crude fat, total solids, solids non-fat and citric acid content were higher (p < 0.05) during the evening milking period. Mean NPVs and PSDs of the mammary gland parenchyma were greater (p < 0.05) after than before milking. There were significant correlations among echotextural characteristics of the udder and protein percentage, lactose content and freezing point depression determined in the milk samples collected in the morning and crude protein, casein, lactose and solids non-fat in the evening. Our results can be interpreted to suggest that computerized analysis of the mammary gland ultrasonograms has the makings of a technique for estimating non-fat milk constituents in cows. However, future validating studies are necessary before this method can be employed in commercial settings and research. Moreover, significant inter-quarter differences in udder echogenicity may necessitate further echotextural studies of separate quarters.

Semantic Segmentation for SAR Image Based on Texture Complexity Analysis and Key Superpixels

In recent years, regional algorithms have shown great potential in the field of synthetic aperture radar (SAR) image segmentation. However, SAR images have a variety of landforms and a landform with complex texture is difficult to be divided as a whole. Due to speckle noise, traditional over-segmentation algorithm may cause mixed superpixels with different labels. They are usually located adjacent to two areas or contain more noise. In this paper, a new semantic segmentation method of SAR images based on texture complexity analysis and key superpixels is proposed. Texture complexity analysis is performed and on this basis, mixed superpixels are selected as key superpixels. Specifically, the texture complexity of the input image is calculated by a new method. Then a new superpixels generation method called neighbourhood information simple linear iterative clustering (NISLIC) is used to over-segment the image. For images with high texture complexity, the complex areas are first separated and key superpixels are selected according to certain rules. For images with low texture complexity, key superpixels are directly extracted. Finally, the superpixels are pre-segmented by fuzzy clustering based on the extracted features and the key superpixels are processed at the pixel level to obtain the final result. The effectiveness of this method has been successfully verified on several kinds of images. Comparing with the state-of-the-art algorithms, the proposed algorithm can more effectively distinguish different landforms and suppress the influence of noise, so as to achieve semantic segmentation of SAR images.