Image-based Features Research Articles

3D Object Detection via Residual SqueezeDet

Three-dimensional object detection is a critical task in computer vision with applications in autonomous driving, robotics, and augmented reality. This paper introduces Residual SqueezeDet, a novel network architecture that enhances the performance of 3D object detection on the KITTI dataset. Building upon the efficient SqueezeDet framework, we propose the Residual Fire module, which incorporates skip connections inspired by ResNet architectures into the original Fire module. This innovation improves gradient flow, enhances feature propagation, and allows for more effective training of deeper networks. Our method leverages point cloud and image-based features, employing a Residual SqueezeDet to effectively capture local and global context. Extensive experiments on the KITTI dataset demonstrate that Residual SqueezeDet significantly outperforms the original SqueezeDet, with particularly notable improvements in challenging scenarios. The proposed model maintains computational efficiency while achieving state-of-the-art performance, making it well-suited for real-time applications in autonomous driving. Our work contributes to the field by providing a more accurate and robust solution for 3D object detection, paving the way for improved perception systems in dynamic environments.

Accuracy of radiomics-Based models in distinguishing between ruptured and unruptured intracranial aneurysms: A systematic review and meta-Analysis

IntroductionIntracranial aneurysms (IAs) pose a severe health risk due to the potential for subarachnoid hemorrhage upon rupture. This study aims to conduct a systematic review and meta-analysis on the accuracy of radiomics features derived from computed tomography angiography (CTA) in differentiating ruptured from unruptured IAs. Materials and MethodsA systematic search was performed across multiple databases for articles published up to January 2024. Observational studies analyzing CTA using radiomics features were included. The area under the curve (AUC) for classifying ruptured vs. unruptured IAs was pooled using a random-effects model. Subgroup analyses were conducted based on the use of radiomics-only features versus radiomics plus additional image-based features, as well as the type of filters used for image processing. ResultsSix studies with 4,408 patients were included. The overall pooled AUC for radiomics features in differentiating ruptured from unruptured IAs was 0.86 (95% CI: 0.84–0.88). The AUC was 0.85 (95% CI: 0.82–0.88) for studies using only radiomics features and 0.87 (95% CI: 0.83–0.91) for studies incorporating radiomics plus additional image-based features. Subgroup analysis based on filter type showed an AUC of 0.87 (95% CI: 0.83–0.90) for original filters and 0.86 (95% CI: 0.81–0.90) for studies using additional filters. ConclusionRadiomics-based models demonstrate very good diagnostic accuracy in classifying ruptured and unruptured IAs, with AUC values exceeding 0.8. This highlights the potential of radiomics as a useful tool in the non-invasive assessment of aneurysm rupture risk, particularly in the management of patients with multiple aneurysms.

Predictive Value of Machine Learning Models in Mortality of Coronavirus Disease 2019 (COVID-19) Pneumonia

The coronavirus disease 2019 (COVID-19) became the most spread and lethal disease in the last 3 years. Early predictions could optimize the decision-making process, healthcare outcomes, and effective usage of healthcare resources during peaks. This study set out to predict the mortality risk of COVID-19 patients by investigating 14 machine learning (ML) models using extensive clinical, laboratory, and image-based features. Additionally, feature importances in each model and the influences of features in the mortality prediction of ML models have been evaluated in this study. Data from 252 patients during the 5th peak of the COVID-19 pandemic (July 2021-September 2021) with 42 features were used for the training of ML models. Fourteen ML models were created using the fivefold cross-validation method. Each model was trained using a training-validation dataset with its own optimized parameters. The performance of models has been evaluated by metric parameters of accuracy, precision, sensitivity, specificity, AUC, and F1 score. The highest values of accuracy (87.30%), precision (100%), sensitivity (77.27%), specificity (100%), AUC (91.90%), and F1 score (77.99%) were observed for the linear discriminant analysis (LDA), K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), KNN, Passive Aggressive Classifier (PAC), and LDA models, respectively, when training was performed with all 42 features. By using feature selection techniques, the support vector classifier (SVC) model with 10 features showed the most AUC of 93.40%. The features of mechanical ventilation, consolidation, fatigue, malignancy, dry cough, level of consciousness (LOC), gender, diarrhea, O2 therapy, and SpO2 are potential predictors of mortality rates in COVID-19 patients.

Biophysical profiling of red blood cells from thin-film blood smears using deep learning

Microscopic inspection of thin-film blood smears is widely used to identify red blood cell (RBC) pathologies, including malaria parasitism and hemoglobinopathies, such as sickle cell disease and thalassemia. Emerging research indicates that non-pathologic changes in RBCs can also be detected in images, such as deformability and morphological changes resulting from the storage lesion. In transfusion medicine, cell deformability is a potential biomarker for the quality of donated RBCs. However, a major impediment to the clinical translation of this biomarker is the difficulty associated with performing this measurement. To address this challenge, we developed an approach for biophysical profiling of RBCs based on cell images in thin-film blood smears. We hypothesize that subtle cellular changes are evident in blood smear images, but this information is inaccessible to human expert labellers. To test this hypothesis, we developed a deep learning strategy to analyze Giemsa-stained blood smears to assess the subtle morphologies indicative of RBC deformability and storage-based degradation. Specifically, we prepared thin-film blood smears from 27 RBC samples (9 donors evaluated at 3 storage time points) and imaged them using high-resolution microscopy. Using this dataset, we trained a convolutional neural network to evaluate image-based morphological features related to cell deformability. The prediction of donor deformability is strongly correlated to the microfluidic scores and can be used to categorize images into specific deformability groups with high accuracy. We also used this model to evaluate differences in RBC morphology resulting from cold storage. Together, our results demonstrate that deep learning models can detect subtle cellular morphology differences resulting from deformability and cold storage. This result suggests the potential to assess donor blood quality from thin-film blood smears, which can be acquired ubiquitously in clinical workflows.

Age-dependent changes in skin features and perceived facial appearance in women of five ethnic groups.

Research documents effects of skin features on assessments of age, health and attractiveness of female faces. Ethnic variation also has been reported for the impact of age-related changes in skin features on face assessments. Here, we investigate women's self-ratings across age cohorts and ethnic groups and discrepancies with (non-expert) assessor ratings of facial appearance together with age-dependent changes in skin features. Faces of women 20-65 years from five ethnic groups (each n = 36) were imaged. Participants provided self-ratings of age, health and attractiveness, and were judged on these attributes by members of the same ethnic group (each n = 120). Digital image analysis was used to quantify skin gloss, tone evenness, wrinkling and sagging. Age-dependent changes in ratings and skin features within and between ethnic groups were assessed by comparing information from 10-year cohorts. We also tested whether menopausal status could be predicted by self-ratings, assessor ratings and image-based skin features. Women of all ethnic groups judged themselves younger and higher in attractiveness and health compared to third-party assessors, with the largest discrepancies for age in French women and for attractiveness and health in South African women. In Indian and South African women, specular gloss and skin tone evenness were lower compared to other participants, and sagging was higher in Indian, Japanese and South African women compared to Chinese and French women. Women's menopausal status could be predicted from assessor ratings and image-based skin features but not from self-ratings. There are differences between women's self-ratings and assessor ratings of facial appearance. These discrepancies vary with female age and ethnicity. Age and ethnicity effects also are evident in age-dependent changes in skin features within and across ethnic groups, which together with assessor (but not self-) ratings of facial appearance predict menopausal status.

Machine Learning for Extraction of Image Features Associated with Progression of Geographic Atrophy

Background: Several studies have investigated various features and models in order to understand the growth and progression of the ocular disease geographic atrophy (GA). Commonly assessed features include age, sex, smoking, alcohol consumption, sedentary lifestyle, hypertension, and diabetes. There have been inconsistencies regarding which features correlate with GA progression. Chief amongst these inconsistencies is whether the investigated features are readily available for analysis across various ophthalmic institutions. Methods:In this study, we focused our attention on the association of fundus autofluorescence (FAF) imaging features and GA progression. Our method included feature extraction using radiomic processes and feature ranking by machine learning incorporating the algorithm XGBoost to determine the best-ranked features. This led to the development of an image-based linear mixed-effects model, which was designed to account for slope change based on within-subject variability and inter-eye correlation. Metrics used to assess the linear mixed-effects model included marginal and conditional R2, Pearson’s correlation coefficient (r), root mean square error (RMSE), mean error (ME), mean absolute error (MAE), mean absolute deviation (MAD), the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and loglikelihood. Results: We developed a linear mixed-effects model with 15 image-based features. The model results were as follows: R2 = 0.96, r = 0.981, RMSE = 1.32, ME = −7.3 × 10−15, MAE = 0.94, MAD = 0.999, AIC = 2084.93, BIC = 2169.97, and log likelihood = −1022.46. Conclusions: The advantage of our method is that it relies on the inherent properties of the image itself, rather than the availability of clinical or demographic data. Thus, the image features discovered in this study are universally and readily available across the board.

Effect of variability of mechanical properties on the predictive capabilities of vulnerable coronary plaques

Background and Objective:Coronary plaque rupture is a precipitating event responsible for two thirds of myocardial infarctions. Currently, the risk of plaque rupture is computed based on demographic, clinical, and image-based adverse features. However, using these features the absolute event rate per single higher-risk lesion remains low. This work studies the power of a novel framework based on biomechanical markers accounting for material uncertainty to stratify vulnerable and non-vulnerable coronary plaques. Methods:Virtual histology intravascular ultrasounds from 55 patients, 29 affected by acute coronary syndrome and 26 affected by stable angina pectoris, were included in this study. Two-dimensional vessel cross-sections for finite element modeling (10 sections per plaque) incorporating plaque structure (medial tissue, loose matrix, lipid core and calcification) were reconstructed. A Montecarlo finite element analysis was performed on each section to account for material variability on three biomechanical markers: peak plaque structural stress at diastolic and systolic pressure, and peak plaque stress difference between systolic and diastolic pressures, together with the luminal pressure. Machine learning decision tree classifiers were trained on 75% of the dataset and tested on the remaining 25% with a combination of feature selection techniques. Performance against classification trees based on geometric markers (i.e., luminal, external elastic membrane and plaque areas) was also performed. Results:Our results indicate that the plaque structural stress outperforms the classification capacity of the combined geometric markers only (0.82 vs 0.51 area under curve) when accounting for uncertainty in material parameters. Furthermore, the results suggest that the combination of the peak plaque structural stress at diastolic and systolic pressures with the maximum plaque structural stress difference between systolic and diastolic pressures together with the systolic pressure and the diastolic to systolic pressure gradient is a robust classifier for coronary plaques when the intrinsic variability in material parameters is considered (area under curve equal to [0.91–0.93]). Conclusion:In summary, our results emphasize that peak plaque structural stress in combination with the patient’s luminal pressure is a potential classifier of plaque vulnerability as it independently considers stress in all directions and incorporates total geometric and compositional features of atherosclerotic plaques.

Classification of Intracranial Hemorrhage (CT) Images Using CNN- LSTM Method and Image-Based GLCM Features

In this study, a hybrid approach is utilized, which combines image-based grey-level co-occurrence matrix attributes and transformed-based attributes. The combination of attribute-based techniques is more accurate in categorizing cerebral hemorrhages in CT images when compared with the transformed attribute-based and image-attribute-based approaches. Deep learning methods, particularly long short-term memory (LSTM), have gained popularity in natural language processing applications like text and sentiment analysis. This paper presents an in-depth deep-learning system that is fully automated. The purpose of the system is to organize radiological data and identify cases of intracranial hemorrhage (ICH) for diagnosis. The structure of the proposed DL model includes 1D convolution neural networks (CNN), long short-term memory (LSTM) units, and a logistic function. A significant dataset consisting of 12,852 radiological reports of head computed tomography (CT) was used to train and assess these components.

Radiomics and Clinical Data for the Diagnosis of Incidental Pulmonary Nodules and Lung Cancer Screening: Radiolung Integrative Predictive Model

IntroductionEarly diagnosis of lung cancer (LC) is crucial to improve survival rates. Radiomics models hold promise for enhancing LC diagnosis. This study assesses the impact of integrating a clinical and a radiomic model based on deep learning to predict the malignancy of pulmonary nodules (PN). MethodologyProspective cross-sectional study of 97 PNs from 93 patients. Clinical data included epidemiological risk factors and pulmonary function tests. The region of interest of each chest CT containing the PN was analysed. The radiomic model employed a pre-trained convolutional network to extract visual features. From these features, 500 with a positive standard deviation were chosen as inputs for an optimised neural network. The clinical model was estimated by a logistic regression model using clinical data. The malignancy probability from the clinical model was used as the best estimate of the pre-test probability of disease to update the malignancy probability of the radiomic model using a nomogram for Bayes’ theorem. ResultsThe radiomic model had a positive predictive value (PPV) of 86%, an accuracy of 79% and an AUC of 0.67. The clinical model identified DLCO, obstruction index and smoking status as the most consistent clinical predictors associated with outcome. Integrating the clinical features into the deep-learning radiomic model achieves a PPV of 94%, an accuracy of 76% and an AUC of 0.80. ConclusionsIncorporating clinical data into a deep-learning radiomic model improved PN malignancy assessment, boosting predictive performance. This study supports the potential of combined image-based and clinical features to improve LC diagnosis.

A systematic pan-cancer study on deep learning-based prediction of multi-omic biomarkers from routine pathology images.

The objective of this comprehensive pan-cancer study is to evaluate the potential of deep learning (DL) for molecular profiling of multi-omic biomarkers directly from hematoxylin and eosin (H&E)-stained whole slide images. A total of 12,093 DL models predicting 4031 multi-omic biomarkers across 32 cancer types were trained and validated. The study included a broad range of genetic, transcriptomic, and proteomic biomarkers, as well as established prognostic markers, molecular subtypes, and clinical outcomes. Here we show that 50% of the models achieve an area under the curve (AUC) of 0.644 or higher. The observed AUC for 25% of the models is at least 0.719 and exceeds 0.834 for the top 5%. Molecular profiling with image-based histomorphological features is generally considered feasible for most of the investigated biomarkers and across different cancer types. The performance appears to be independent of tumor purity, sample size, and class ratio (prevalence), suggesting a degree of inherent predictability in histomorphology. The results demonstrate that DL holds promise to predict a wide range of biomarkers across the omics spectrum using only H&E-stained histological slides of solid tumors. This paves the way for accelerating diagnosis and developing more precise treatments for cancer patients.

Impact of Deltoid Computer Tomography Image Data on the Accuracy of Machine Learning Predictions of Clinical Outcomes after Anatomic and Reverse Total Shoulder Arthroplasty.

Background: Despite the importance of the deltoid to shoulder biomechanics, very few studies have quantified the three-dimensional shape, size, or quality of the deltoid muscle, and no studies have correlated these measurements to clinical outcomes after anatomic (aTSA) and/or reverse (rTSA) total shoulder arthroplasty in any statistically/scientifically relevant manner. Methods: Preoperative computer tomography (CT) images from 1057 patients (585 female, 469 male; 799 primary rTSA and 258 primary aTSA) of a single platform shoulder arthroplasty prosthesis (Equinoxe; Exactech, Inc., Gainesville, FL) were analyzed in this study. A machine learning (ML) framework was used to segment the deltoid muscle for 1057 patients and quantify 15 different muscle characteristics, including volumetric (size, shape, etc.) and intensity-based Hounsfield (HU) measurements. These deltoid measurements were correlated to postoperative clinical outcomes and utilized as inputs to train/test ML algorithms used to predict postoperative outcomes at multiple postoperative timepoints (1 year, 2-3 years, and 3-5 years) for aTSA and rTSA. Results: Numerous deltoid muscle measurements were demonstrated to significantly vary with age, gender, prosthesis type, and CT image kernel; notably, normalized deltoid volume and deltoid fatty infiltration were demonstrated to be relevant to preoperative and postoperative clinical outcomes after aTSA and rTSA. Incorporating deltoid image data into the ML models improved clinical outcome prediction accuracy relative to ML algorithms without image data, particularly for the prediction of abduction and forward elevation after aTSA and rTSA. Analyzing ML feature importance facilitated rank-ordering of the deltoid image measurements relevant to aTSA and rTSA clinical outcomes. Specifically, we identified that deltoid shape flatness, normalized deltoid volume, deltoid voxel skewness, and deltoid shape sphericity were the most predictive image-based features used to predict clinical outcomes after aTSA and rTSA. Many of these deltoid measurements were found to be more predictive of aTSA and rTSA postoperative outcomes than patient demographic data, comorbidity data, and diagnosis data. Conclusions: While future work is required to further refine the ML models, which include additional shoulder muscles, like the rotator cuff, our results show promise that the developed ML framework can be used to evolve traditional CT-based preoperative planning software into an evidence-based ML clinical decision support tool.

Towards an AI-Based Objective Prognostic Model for Quantifying Wound Healing.

Chronic wounds affect millions of people worldwide every year. An adequate assessment of a wound's prognosis is critical to wound care, guiding clinical decision making by helping clinicians understand wound healing status, severity, triaging and determining the efficacy of a treatment regimen. The current standard of care involves using wound assessment tools, such as Pressure Ulcer Scale for Healing (PUSH) and Bates-Jensen Wound Assessment Tool (BWAT), to determine wound prognosis. However, these tools involve manual assessment of a multitude of wound characteristics and skilled consideration of a variety of factors, thus, making wound prognosis a slow process which is prone to misinterpretation and high degree of variability. Therefore, in this work we have explored the viability of replacing subjective clinical information with deep learning-based objective features derived from wound images, pertaining to wound area and tissue amounts. These objective features were used to train prognostic models that quantified the risk of delayed wound healing, using a dataset consisting of 2.1 million wound evaluations derived from more than 200,000 wounds. The objective model, which was trained exclusively using image-based objective features, achieved at minimum a 5% and 9% improvement over PUSH and BWAT, respectively. Our best performing model, that used both subjective and objective features, achieved at minimum an 8% and 13% improvement over PUSH and BWAT, respectively. Moreover, the reported models consistently outperformed the standard tools across various clinical settings, wound etiologies, sexes, age groups and wound ages, thus establishing the generalizability of the models.

Classification of intracranial hemorrhage (CT) images using CNN-LSTM method and image-based GLCM features

A hybrid is used, combining feature-based method transformed-based features with image-based grey level co-occurrence matrix features. When it comes to classifying cerebral hemorrhages CT images, the combined feature-based strategy performs better than the image-feature-based and transformed feature-based techniques. Natural language processing using deep learning techniques, particularly long short-term memory (LSTM), has become the go-to choice in applications like sentiment analysis and text analysis. This work presents a completely automated deep learning system for the purpose of classifying radiological data in order to diagnose intracranial hemorrhage (ICH). Long short-term memory (LSTM) units, a logistic function, and 1D convolution neural networks (CNN) make up the suggested automated deep learning architecture. These components were all trained and evaluated using a large dataset of 12,852 head computed tomography (CT) radiological reports.

Enhancing precision: A predictive model for 177Lu-DOTATATE treatment response in neuroendocrine tumors using quantitative 68Ga-DOTATATE PET and clinicopathological biomarkers.

Purpose: This study aims to elucidate the role of quantitative SSTR-PET metrics and clinicopathological biomarkers in the progression-free survival (PFS) and overall survival (OS) of neuroendocrine tumors (NETs) treated with peptide receptor radionuclide therapy (PRRT). Methods: A retrospective analysis including 91 NET patients (M47/F44; age 66 years, range 34-90 years) who completed four cycles of standard 177Lu-DOTATATE was conducted. SSTR-avid tumors were segmented from pretherapy SSTR-PET images using a semiautomatic workflow with the tumors labeled based on the anatomical regions. Multiple image-based features including total and organ-specific tumor volume and SSTR density along with clinicopathological biomarkers including Ki-67, chromogranin A (CgA) and alkaline phosphatase (ALP) were analyzed with respect to the PRRT response. Results: The median OS was 39.4 months (95% CI: 33.1-NA months), while the median PFS was 23.9 months (95% CI: 19.3-32.4 months). Total SSTR-avid tumor volume (HR = 3.6; P = 0.07) and bone tumor volume (HR = 1.5; P = 0.003) were associated with shorter OS. Also, total tumor volume (HR = 4.3; P = 0.01), liver tumor volume (HR = 1.8; P = 0.05) and bone tumor volume (HR = 1.4; P = 0.01) were associated with shorter PFS. Furthermore, the presence of large lesion volume with low SSTR uptake was correlated with worse OS (HR = 1.4; P = 0.03) and PFS (HR = 1.5; P = 0.003). Among the biomarkers, elevated baseline CgA and ALP showed a negative association with both OS (CgA: HR = 4.9; P = 0.003, ALP: HR = 52.6; P = 0.004) and PFS (CgA: HR = 4.2; P = 0.002, ALP: HR = 9.4; P = 0.06). Similarly, number of prior systemic treatments was associated with shorter OS (HR = 1.4; P = 0.003) and PFS (HR = 1.2; P = 0.05). Additionally, tumors originating from the midgut primary site demonstrated longer PFS, compared to the pancreas (HR = 1.6; P = 0.16), and those categorized as unknown primary (HR = 3.0; P = 0.002). Conclusion: Image-based features such as SSTR-avid tumor volume, bone tumor involvement, and the presence of large tumors with low SSTR expression demonstrated significant predictive value for PFS, suggesting potential clinical utility in NETs management. Moreover, elevated CgA and ALP, along with an increased number of prior systemic treatments, emerged as significant factors associated with worse PRRT outcomes.

SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images.

Statistical shape modeling (SSM) is a powerful computational framework for quantifying and analyzing the geometric variability of anatomical structures, facilitating advancements in medical research, diagnostics, and treatment planning. Traditional methods for shape modeling from imaging data demand significant manual and computational resources. Additionally, these methods necessitate repeating the entire modeling pipeline to derive shape descriptors (e.g., surface-based point correspondences) for new data. While deep learning approaches have shown promise in streamlining the construction of SSMs on new data, they still rely on traditional techniques to supervise the training of the deep networks. Moreover, the predominant linearity assumption of traditional approaches restricts their efficacy, a limitation also inherited by deep learning models trained using optimized/established correspondences. Consequently, representing complex anatomies becomes challenging. To address these limitations, we introduce SCorP, a novel framework capable of predicting surface-based correspondences directly from unsegmented images. By leveraging the shape prior learned directly from surface meshes in an unsupervised manner, the proposed model eliminates the need for an optimized shape model for training supervision. The strong shape prior acts as a teacher and regularizes the feature learning of the student network to guide it in learning image-based features that are predictive of surface correspondences. The proposed model streamlines the training and inference phases by removing the supervision for the correspondence prediction task while alleviating the linearity assumption. Experiments on the LGE MRI left atrium dataset and Abdomen CT-1K liver datasets demonstrate that the proposed technique enhances the accuracy and robustness of image-driven SSM, providing a compelling alternative to current fully supervised methods.

MRI/RNA-Seq-Based Radiogenomics and Artificial Intelligence for More Accurate Staging of Muscle-Invasive Bladder Cancer.

Accurate staging of bladder cancer assists in identifying optimal treatment (e.g., transurethral resection vs. radical cystectomy vs. bladder preservation). However, currently, about one-third of patients are over-staged and one-third are under-staged. There is a pressing need for a more accurate staging modality to evaluate patients with bladder cancer to assist clinical decision-making. We hypothesize that MRI/RNA-seq-based radiogenomics and artificial intelligence can more accurately stage bladder cancer. A total of 40 magnetic resonance imaging (MRI) and matched formalin-fixed paraffin-embedded (FFPE) tissues were available for analysis. Twenty-eight (28) MRI and their matched FFPE tissues were available for training analysis, and 12 matched MRI and FFPE tissues were used for validation. FFPE samples were subjected to bulk RNA-seq, followed by bioinformatics analysis. In the radiomics, several hundred image-based features from bladder tumors in MRI were extracted and analyzed. Overall, the model obtained mean sensitivity, specificity, and accuracy of 94%, 88%, and 92%, respectively, in differentiating intra- vs. extra-bladder cancer. The proposed model demonstrated improvement in the three matrices by 17%, 33%, and 25% and 17%, 16%, and 17% as compared to the genetic- and radiomic-based models alone, respectively. The radiogenomics of bladder cancer provides insight into discriminative features capable of more accurately staging bladder cancer. Additional studies are underway.

Can we use a simple blood test to reduce unnecessary adverse effects from radiotherapy by timely identification of radiotherapy-resistant rectal cancers? MeD-Seq rectal study protocol

BackgroundChemoradiation therapy (CRT) followed by surgery is currently the standard of care to treat patients with locally advanced rectal cancer (LARC). CRT reduces local recurrences, but is associated with significant damage to the surrounding healthy tissue that can severely impact patients quality of life. Additionally, a proportion of patients (hardly) benefit from CRT. We aim to develop a diagnostic innovation, using DNA-methylation, which can enable a more selective and thereby more effective use of the available therapies for rectal cancer patients.MethodsMeD-Seq Rectal is a prospective single centre, observational study. 75 patients diagnosed with rectal cancer and will receive CRT as neoadjuvant treatment are will be included. DNA-methylation profiling will be performed on liquid biopsies to predict pathological response to CRT.DiscussionTo data no clinical or image-based features were found that predict response to CRT. we hypothesize that DNA methylation patterns in liquid biopsies may provide a promising and patient-friendly strategy to predict CRT resistance upfront.Trial registrationThis trial is registered at ClinicalTrials.gov (NCT06035471).

Artificial Intelligence for Image-Based Breast Cancer Risk Prediction Using Attention.

Accurate prediction of individual breast cancer risk paves the way for personalised prevention and early detection. The incorporation of genetic information and breast density has been shown to improve predictions for existing models, but detailed image-based features are yet to be included despite correlating with risk. Complex information can be extracted from mammograms using deep-learning algorithms, however, this is a challenging area of research, partly due to the lack of data within the field, and partly due to the computational burden. We propose an attention-based Multiple Instance Learning (MIL) model that can make accurate, short-term risk predictions from mammograms taken prior to the detection of cancer at full resolution. Current screen-detected cancers are mixed in with priors during model development to promote the detection of features associated with risk specifically and features associated with cancer formation, in addition to alleviating data scarcity issues. MAI-risk achieves an AUC of 0.747 [0.711, 0.783] in cancer-free screening mammograms of women who went on to develop a screen-detected or interval cancer between 5 and 55 months, outperforming both IBIS (AUC 0.594 [0.557, 0.633]) and VAS (AUC 0.649 [0.614, 0.683]) alone when accounting for established clinical risk factors.

Survival classification of Gliomas through a novel enhancement-based strategy for class overlap of radiomics features

Conventional radiomics-based models precisely engineered image-based features from Magnetic Resonance Imaging (MRI) to extract the predictive patterns for High-Grade Gliomas (HGGs) survival prediction. But an in-depth exploration and assessment of these extracted features are still not conducted. To the best of our knowledge, this is the first study that perceives the range distributions of radiomics features and gains insight into the problem of class overlap among these features. A novel class-wise feature enhancement strategy addresses the ambiguous data regions in the extracted features without any data loss. This strategy explicitly tunes the data values of only two classes and retains the data of the third class to achieve excellent data separability. The enhancement depends on the difference in the feature values of the two classes and incorporates the scalability of this difference using different scaling factors. Furthermore, Box-Cox and logarithmic transformations are employed to overcome the non-normality of the enhanced features. Consequently, ablation experimentation is conducted to substantiate the classification metrics with pre- and post-enhancement cases. BraTS 2020 benchmark is employed, demonstrating that the proposed approach performs competitively in classifying HGG patients into three survival groups, namely, short, mid, and long survivors. It achieves an overall testing classification accuracy, precision, recall, and F1-score of 0.994, 0.993, 0.996, and 0.994, respectively. Therefore, instead of directly utilizing these raw extracted features, this strategy eliminates the overlapped class regions without any information loss and has proven to be a significant step for HGG survival classification applications.

Semi-Automated Rock Classification for Permeability Estimation Using High-Resolution Computed Tomography Scan Images, Core Photos, and Well Logs

Summary Reliable estimation of petrophysical properties can be challenging, especially in geological formations with rapid variation in the spatial distribution of rock components. The spatial distribution of rock components, also known as rock fabric, is often not captured by conventional well logs that are typically used for the estimation of petrophysical properties. The aforementioned challenge is rooted in the limited vertical resolution of conventional well logging tools. Alternatively, specialized tools and techniques, such as nuclear magnetic resonance (NMR) and computed tomography (CT) scan images, can provide information on the variation in the rock fabric of geological formations. The objectives of this paper are (a) to use 2D CT scan images and core photos, conventional well logs, NMR logs, and core-measured properties for semi-automated rock classification, (b) to develop class-based rock physics models for enhanced petrophysical properties estimation, and (c) to provide a method to expedite the detection of quantitative image-based rock classes in cored wells. First, we conducted conventional formation evaluation (CFE) for the initial assessment of petrophysical properties. Then, we implemented three different rock classification techniques for class-based estimation of petrophysical properties. The first of the rock classification techniques uses routine core analysis (RCA) data to define hydraulic units. The second rock classification technique uses NMR data to characterize the changes in pore-size distribution of the evaluated formation. The last rock classification technique integrates quantitative image-based features from CT scan images and core photos with NMR data. Finally, the obtained rock classes from the abovementioned rock classification techniques are used to derive class-based permeability models. We applied the proposed workflow to a pilot well drilled in a saline water aquifer formation that will be used for CO2 injection and storage in the Northern Lights carbon capture and storage (CCS) project. The extracted image-based rock fabric features were in agreement with the visual aspect of the evaluated depth intervals. The detected rock classes captured the fluid-flow behavior using a permeability-based cost function in two of the implemented rock classification techniques, the variation in petrophysical and compositional properties through well logs, and quantitative rock fabric of the evaluated depth interval through the core image data. Finally, the use of class-based rock physics models improved permeability estimates, decreasing the mean relative error by up to 37% compared with formation-based permeability estimates from a conventional method (formation-based porosity-permeability correlations). One of the key contributions of the proposed workflow is that it integrates conventional well logs, core-measured properties, NMR logs, and high-resolution image data. As a result, the obtained integrated rock classes capture key petrophysical and geological parameters of the evaluated depth intervals that are typically not included in rock classification efforts. The obtained integrated rock classes can potentially improve the development of accurate geological models, which are used in simulation efforts as a screening tool for the selection of geological formations for CO2 storage as well as for storage capacity, selection of CO2 injection intervals, and containment forecasting.