De-biased Disentanglement Learning for Pulmonary Embolism Survival Prediction on Multimodal Data.

Health disparities among marginalized populations with lower socioeconomic status significantly impact the fairness and effectiveness of healthcare delivery. The increasing integration of artificial intelligence (AI) into healthcare presents an opportunity to address these inequalities, provided that AI models are free from bias. This paper aims to address the bias challenges by population disparities within healthcare systems, existing in the presentation of and development of algorithms, leading to inequitable medical implementation for conditions such as pulmonary embolism (PE) prognosis. In this study, we explore the diversity of biases in healthcare systems, which highlights the need for a holistic framework to reduce bias by complementary aggregation. By leveraging de-biasing deep survival prediction models, we propose a framework that disentangles identifiable information from images, text reports, and clinical variables to mitigate potential biases within multimodal datasets. Our study offers several advantages over traditional clinical-based survival prediction methods, including richer survival-related characteristics and bias-complementary predicted results. By improving the robustness of survival analysis through this framework, we aim to benefit patients, clinicians, and researchers by improving fairness and accuracy in healthcare AI systems. The code is available at https://github.com/zzs95/fairPE-SA.

Utilizing Deep Learning and Computed Tomography to Determine Pulmonary Nodule Activity in Patients With Nontuberculous Mycobacterial-Lung Disease.

PURPOSE: To develop and evaluate a deep convolutional neural network (DCNN) model for the classification of acute and chronic lung nodules from nontuberculous mycobacterial-lung disease (NTM-LD) on computed tomography (CT). MATERIALS AND METHODS: We collected a data set of 650 nodules (316 acute and 334 chronic) from the CT scans of 110 patients with NTM-LD. The data set was divided into training, validation, and test sets in a ratio of 4:1:1. Bounding boxes were used to crop the 2D CT images down to the area of interest. A DCNN model was built using 11 convolutional layers and trained on these images. The performance of the model was evaluated on the hold-out test set and compared with that of 3 radiologists who independently reviewed the images. RESULTS: The DCNN model achieved an area under the receiver operating characteristic curve of 0.806 for differentiating acute and chronic NTM-LD nodules, corresponding to sensitivity, specificity, and accuracy of 76%, 68%, and 72%, respectively. The performance of the model was comparable to that of the 3 radiologists, who had area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy of 0.693 to 0.771, 61% to 82%, 59% to 73%, and 60% to 73%, respectively. CONCLUSIONS: This study demonstrated the feasibility of using a DCNN model for the classification of the activity of NTM-LD nodules on chest CT. The model performance was comparable to that of radiologists. This approach can potentially and efficiently improve the diagnosis and management of NTM-LD.

An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer.

Uptake segmentation and classification on PSMA PET/CT are important for automating whole-body tumor burden determinations. We developed and evaluated an automated deep learning (DL)-based framework that segments and classifies uptake on PSMA PET/CT. We identified 193 [18F] DCFPyL PET/CT scans of patients with biochemically recurrent prostate cancer from two institutions, including 137 [18F] DCFPyL PET/CT scans for training and internally testing, and 56 scans from another institution for external testing. Two radiologists segmented and labelled foci as suspicious or non-suspicious for malignancy. A DL-based segmentation was developed with two independent CNNs. An anatomical prior guidance was applied to make the DL framework focus on PSMA-avid lesions. Segmentation performance was evaluated by Dice, IoU, precision, and recall. Classification model was constructed with multi-modal decision fusion framework evaluated by accuracy, AUC, F1 score, precision, and recall. Automatic segmentation of suspicious lesions was improved under prior guidance, with mean Dice, IoU, precision, and recall of 0.700, 0.566, 0.809, and 0.660 on the internal test set and 0.680, 0.548, 0.749, and 0.740 on the external test set. Our multi-modal decision fusion framework outperformed single-modal and multi-modal CNNs with accuracy, AUC, F1 score, precision, and recall of 0.764, 0.863, 0.844, 0.841, and 0.847 in distinguishing suspicious and non-suspicious foci on the internal test set and 0.796, 0.851, 0.865, 0.814, and 0.923 on the external test set. DL-based lesion segmentation on PSMA PET is facilitated through our anatomical prior guidance strategy. Our classification framework differentiates suspicious foci from those not suspicious for cancer with good accuracy.

Active Learning in Brain Tumor Segmentation with Uncertainty Sampling and Annotation Redundancy Restriction.

Deep learning models have demonstrated great potential in medical imaging but are limited by the expensive, large volume of annotations required. To address this, we compared different active learning strategies by training models on subsets of the most informative images using real-world clinical datasets for brain tumor segmentation and proposing a framework that minimizes the data needed while maintaining performance. Then, 638 multi-institutional brain tumor magnetic resonance imaging scans were used to train three-dimensional U-net models and compare active learning strategies. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotating similar images were also considered. We determined the minimum data necessary to achieve performance equivalent to the model trained on the full dataset (α = 0.05). Bayesian approximation with dropout at training and testing showed results equivalent to that of the full data model (target) with around 30% of the training data needed by random query to achieve target performance (p = 0.018). Annotation redundancy restriction techniques can reduce the training data needed by random query to achieve target performance by 20%. We investigated various active learning strategies to minimize the annotation burden for three-dimensional brain tumor segmentation. Dropout uncertainty estimation achieved target performance with the least annotated data.

A radiomics-based brain network in T1 images: construction, attributes, and applications.

T1 image is a widely collected imaging sequence in various neuroimaging datasets, but it is rarely used to construct an individual-level brain network. In this study, a novel individualized radiomics-based structural similarity network was proposed from T1 images. In detail, it used voxel-based morphometry to obtain the preprocessed gray matter images, and radiomic features were then extracted on each region of interest in Brainnetome atlas, and an individualized radiomics-based structural similarity network was finally built using the correlational values of radiomic features between any pair of regions of interest. After that, the network characteristics of individualized radiomics-based structural similarity network were assessed, including graph theory attributes, test-retest reliability, and individual identification ability (fingerprinting). At last, two representative applications for individualized radiomics-based structural similarity network, namely mild cognitive impairment subtype discrimination and fluid intelligence prediction, were exemplified and compared with some other networks on large open-source datasets. The results revealed that the individualized radiomics-based structural similarity network displays remarkable network characteristics and exhibits advantageous performances in mild cognitive impairment subtype discrimination and fluid intelligence prediction. In summary, the individualized radiomics-based structural similarity network provides a distinctive, reliable, and informative individualized structural brain network, which can be combined with other networks such as resting-state functional connectivity for various phenotypic and clinical applications.

A Fully Automated Deep-Learning Model for Predicting the Molecular Subtypes of Posterior Fossa Ependymomas Using T2-Weighted Images.

PURPOSE: We aimed to develop and validate a deep learning (DL) model to automatically segment posterior fossa ependymoma (PF-EPN) and predict its molecular subtypes [Group A (PFA) and Group B (PFB)] from preoperative MR images. EXPERIMENTAL DESIGN: We retrospectively identified 227 PF-EPNs (development and internal test sets) with available preoperative T2-weighted (T2w) MR images and molecular status to develop and test a 3D nnU-Net (referred to as T2-nnU-Net) for tumor segmentation and molecular subtype prediction. The network was externally tested using an external independent set [n = 40; subset-1 (n = 31) and subset-2 (n =9)] and prospectively enrolled cases [prospective validation set (n = 27)]. The Dice similarity coefficient was used to evaluate the segmentation performance. Receiver operating characteristic analysis for molecular subtype prediction was performed. RESULTS: For tumor segmentation, the T2-nnU-Net achieved a Dice score of 0.94 ± 0.02 in the internal test set. For molecular subtype prediction, the T2-nnU-Net achieved an AUC of 0.93 and accuracy of 0.89 in the internal test set, an AUC of 0.99 and accuracy of 0.93 in the external test set. In the prospective validation set, the model achieved an AUC of 0.93 and an accuracy of 0.89. The predictive performance of T2-nnU-Net was superior or comparable to that of demographic and multiple radiologic features (AUCs ranging from 0.87 to 0.95). CONCLUSIONS: A fully automated DL model was developed and validated to accurately segment PF-EPNs and predict molecular subtypes using only T2w MR images, which could help in clinical decision-making.

Using Machine Learning to Predict Response to Image-guided Therapies for Hepatocellular Carcinoma.

Interventional oncology is a rapidly growing field with advances in minimally invasive image-guided local-regional treatments for hepatocellular carcinoma (HCC), including transarterial chemoembolization, transarterial radioembolization, and thermal ablation. However, current standardized clinical staging systems for HCC are limited in their ability to optimize patient selection for treatment as they rely primarily on serum markers and radiologist-defined imaging features. Given the variation in treatment responses, an updated scoring system that includes multidimensional aspects of the disease, including quantitative imaging features, serum markers, and functional biomarkers, is needed to optimally triage patients. With the vast amounts of numerical medical record data and imaging features, researchers have turned to image-based methods, such as radiomics and artificial intelligence (AI), to automatically extract and process multidimensional data from images. The synthesis of these data can provide clinically relevant results to guide personalized treatment plans and optimize resource utilization. Machine learning (ML) is a branch of AI in which a model learns from training data and makes effective predictions by teaching itself. This review article outlines the basics of ML and provides a comprehensive overview of its potential value in the prediction of treatment response in patients with HCC after minimally invasive image-guided therapy.

Ethiodized oil as an imaging biomarker after conventional transarterial chemoembolization.

Conventional transarterial chemoembolization (cTACE) utilizing ethiodized oil as a chemotherapy carrier has become a standard treatment for intermediate-stage hepatocellular carcinoma (HCC) and has been adopted as a bridging and downstaging therapy for liver transplantation. Water-in-oil emulsion made up of ethiodized oil and chemotherapy solution is retained in tumor vasculature resulting in high tissue drug concentration and low systemic chemotherapy doses. The density and distribution pattern of ethiodized oil within the tumor on post-treatment imaging are predictive of the extent of tumor necrosis and duration of response to treatment. This review describes the multiple roles of ethiodized oil, particularly in its role as a biomarker of tumor response to cTACE. CLINICAL RELEVANCE: With the increasing complexity of locoregional therapy options, including the use of combination therapies, treatment response assessment has become challenging; Ethiodized oil deposition patterns can serve as an imaging biomarker for the prediction of treatment response, and perhaps predict post-treatment prognosis. KEY POINTS: • Treatment response assessment after locoregional therapy to hepatocellular carcinoma is fraught with multiple challenges given the varied post-treatment imaging appearance. • Ethiodized oil is unique in that its' radiopacity can serve as an imaging biomarker to help predict treatment response. • The pattern of deposition of ethiodozed oil has served as a mechanism to detect portions of tumor that are undertreated and can serve as an adjunct to enhancement in order to improve management in patients treated with intraarterial embolization with ethiodized oil.

Deep learning-based radiomic nomogram to predict risk categorization of thymic epithelial tumors: A multicenter study.

PURPOSE: The study was aimed to develop and evaluate a deep learning-based radiomics to predict the histological risk categorization of thymic epithelial tumors (TETs), which can be highly informative for patient treatment planning and prognostic assessment. METHOD: A total of 681 patients with TETs from three independent hospitals were included and separated into derivation cohort and external test cohort. Handcrafted and deep learning features were extracted from preoperative contrast-enhanced CT images and selected to build three radiomics signatures (radiomics signature [Rad_Sig], deep learning signature [DL_Sig] and deep learning radiomics signature [DLR_Sig]) to predict risk categorization of TETs. A deep learning-based radiomic nomogram (DLRN) was then depicted to visualize the classification evaluation. The performance of predictive models was compared using the receiver operating characteristic and decision curve analysis (DCA). RESULTS: Among three radiomics signatures, DLR_Sig demonstrated optimum performance with an AUC of 0.883 for the derivation cohort and 0.749 for the external test cohort. Combining DLR_Sig with age and gender, DLRN was depict and exhibited optimum performance among all radiomics models with an AUC of 0.965, accuracy of 0.911, sensitivity of 0.921 and specificity of 0.902 in the derivation cohort, and an AUC of 0.786, accuracy of 0.774, sensitivity of 0.778 and specificity of 0.771 in the external test cohort. The DCA showed that DLRN had greater clinical benefit than other radiomics signatures. CONCLUSIONS: Our study developed and validated a DLRN to accurately predict the risk categorization of TETs, which has potential to facilitate individualized treatment and improve patient prognosis evaluation.

Application of artificial intelligence in predicting lymph node metastasis in breast cancer.

Breast cancer is a leading cause of death for women globally. A characteristic of breast cancer includes its ability to metastasize to distant regions of the body, and the disease achieves this through first spreading to the axillary lymph nodes. Traditional diagnosis of axillary lymph node metastasis includes an invasive technique that leads to potential clinical complications for breast cancer patients. The rise of artificial intelligence in the medical imaging field has led to the creation of innovative deep learning models that can predict the metastatic status of axillary lymph nodes noninvasively, which would result in no unnecessary biopsies and dissections for patients. In this review, we discuss the success of various deep learning artificial intelligence models across multiple imaging modalities in their performance of predicting axillary lymph node metastasis.

Brain Tumor Segmentation for Multi-Modal MRI with Missing Information.

Deep convolutional neural networks (DCNNs) have shown promise in brain tumor segmentation from multi-modal MRI sequences, accommodating heterogeneity in tumor shape and appearance. The fusion of multiple MRI sequences allows networks to explore complementary tumor information for segmentation. However, developing a network that maintains clinical relevance in situations where certain MRI sequence(s) might be unavailable or unusual poses a significant challenge. While one solution is to train multiple models with different MRI sequence combinations, it is impractical to train every model from all possible sequence combinations. In this paper, we propose a DCNN-based brain tumor segmentation framework incorporating a novel sequence dropout technique in which networks are trained to be robust to missing MRI sequences while employing all other available sequences. Experiments were performed on the RSNA-ASNR-MICCAI BraTS 2021 Challenge dataset. When all MRI sequences were available, there were no significant differences in performance of the model with and without dropout for enhanced tumor (ET), tumor (TC), and whole tumor (WT) (p-values 1.000, 1.000, 0.799, respectively), demonstrating that the addition of dropout improves robustness without hindering overall performance. When key sequences were unavailable, the network with sequence dropout performed significantly better. For example, when tested on only T1, T2, and FLAIR sequences together, DSC for ET, TC, and WT increased from 0.143 to 0.486, 0.431 to 0.680, and 0.854 to 0.901, respectively. Sequence dropout represents a relatively simple yet effective approach for brain tumor segmentation with missing MRI sequences.

Genetic events associated with venetoclax resistance in CLL identified by whole-exome sequencing of patient samples.

Although BCL2 mutations are reported as later occurring events leading to venetoclax resistance, many other mechanisms of progression have been reported though remain poorly understood. Here, we analyze longitudinal tumor samples from 11 patients with disease progression while receiving venetoclax to characterize the clonal evolution of resistance. All patients tested showed increased in vitro resistance to venetoclax at the posttreatment time point. We found the previously described acquired BCL2-G101V mutation in only 4 of 11 patients, with 2 patients showing a very low variant allele fraction (0.03%-4.68%). Whole-exome sequencing revealed acquired loss(8p) in 4 of 11 patients, of which 2 patients also had gain (1q21.2-21.3) in the same cells affecting the MCL1 gene. In vitro experiments showed that CLL cells from the 4 patients with loss(8p) were more resistant to venetoclax than cells from those without it, with the cells from 2 patients also carrying gain (1q21.2-21.3) showing increased sensitivity to MCL1 inhibition. Progression samples with gain (1q21.2-21.3) were more susceptible to the combination of MCL1 inhibitor and venetoclax. Differential gene expression analysis comparing bulk RNA sequencing data from pretreatment and progression time points of all patients showed upregulation of proliferation, B-cell receptor (BCR), and NF-κB gene sets including MAPK genes. Cells from progression time points demonstrated upregulation of surface immunoglobulin M and higher pERK levels compared with those from the preprogression time point, suggesting an upregulation of BCR signaling that activates the MAPK pathway. Overall, our data suggest several mechanisms of acquired resistance to venetoclax in CLL that could pave the way for rationally designed combination treatments for patients with venetoclax-resistant CLL.

Beyond antioxidation: Harnessing the CeO2 nanoparticles as a renoprotective contrast agent for in vivo spectral CT angiography.

It is a challenging task to develop a contrast agent that not only provides excellent image contrast but also protects impaired kidneys from oxidative-related stress during angiography. Clinically approved iodinated CT contrast media are associated with potential renal toxicity, making it necessary to develop a renoprotective contrast agent. Here, we develop a CeO2 nanoparticles (NPs)-mediated three-in-one renoprotective imaging strategy, namely, i) renal clearable CeO2 NPs serve as a one-stone-two-birds antioxidative contrast agent, ii) low contrast media dose, and iii) spectral CT, for in vivo CT angiography (CTA). Benefiting from the merits of advanced sensitivity of spectral CT and K-edge energy of Cerium (Ce, 40.4 keV), an improved image quality of in vivo CTA is successfully achieved with a 10 times reduction of contrast agent dosage. In parallel, the sizes of CeO2 NPs and broad catalytic activities are suitable to be filtered via glomerulus thus directly alleviating the oxidative stress and the accompanying inflammatory injury of the kidney tubules. In addition, the low dosage of CeO2 NPs reduces the hypoperfusion stress of renal tubules induced by concentrated contrast agents used in angiography. This three-in-one renoprotective imaging strategy helps prevent kidney injury from being worsened during the CTA examination.

AC-E Network: Attentive Context-Enhanced Network for Liver Segmentation.

Segmentation of liver from CT scans is essential in computer-aided liver disease diagnosis and treatment. However, the 2DCNN ignores the 3D context, and the 3DCNN suffers from numerous learnable parameters and high computational cost. In order to overcome this limitation, we propose an Attentive Context-Enhanced Network (AC-E Network) consisting of 1) an attentive context encoding module (ACEM) that can be integrated into the 2D backbone to extract 3D context without a sharp increase in the number of learnable parameters; 2) a dual segmentation branch including complemental loss making the network attend to both the liver region and boundary so that getting the segmented liver surface with high accuracy. Extensive experiments on the LiTS and the 3D-IRCADb datasets demonstrate that our method outperforms existing approaches and is competitive to the state-of-the-art 2D-3D hybrid method on the equilibrium of the segmentation precision and the number of model parameters.

Head and neck tumor segmentation convolutional neural network robust to missing PET/CT modalities using channel dropout.

Objective. Radiation therapy for head and neck (H&N) cancer relies on accurate segmentation of the primary tumor. A robust, accurate, and automated gross tumor volume segmentation method is warranted for H&N cancer therapeutic management. The purpose of this study is to develop a novel deep learning segmentation model for H&N cancer based on independent and combined CT and FDG-PET modalities.Approach. In this study, we developed a robust deep learning-based model leveraging information from both CT and PET. We implemented a 3D U-Net architecture with 5 levels of encoding and decoding, computing model loss through deep supervision. We used a channel dropout technique to emulate different combinations of input modalities. This technique prevents potential performance issues when only one modality is available, increasing model robustness. We implemented ensemble modeling by combining two types of convolutions with differing receptive fields, conventional and dilated, to improve capture of both fine details and global information.Main Results. Our proposed methods yielded promising results, with a Dice similarity coefficient (DSC) of 0.802 when deployed on combined CT and PET, DSC of 0.610 when deployed on CT, and DSC of 0.750 when deployed on PET.Significance. Application of a channel dropout method allowed for a single model to achieve high performance when deployed on either single modality images (CT or PET) or combined modality images (CT and PET). The presented segmentation techniques are clinically relevant to applications where images from a certain modality might not always be available.

Artificial intelligence and body composition.

AIMS: Although obesity is associated with chronic disease, a large section of the population with high BMI does not have an increased risk of metabolic disease. Increased visceral adiposity and sarcopenia are also risk factors for metabolic disease in people with normal BMI. Artificial Intelligence (AI) techniques can help assess and analyze body composition parameters for predicting cardiometabolic health. The purpose of the study was to systematically explore literature involving AI techniques for body composition assessment and observe general trends. METHODS: We searched the following databases: Embase, Web of Science, and PubMed. There was a total of 354 search results. After removing duplicates, irrelevant studies, and reviews(a total of 303), 51 studies were included in the systematic review. RESULTS: AI techniques have been studied for body composition analysis in the context of diabetes mellitus, hypertension, cancer and many specialized diseases. Imaging techniques employed for AI methods include CT (Computerized Tomography), MRI (Magnetic Resonance Imaging), ultrasonography, plethysmography, and EKG(Electrocardiogram). Automatic segmentation of body composition by deep learning with convolutional networks has helped determine and quantify muscle mass. Limitations include heterogeneity of study populations, inherent bias in sampling, and lack of generalizability. Different bias mitigation strategies should be evaluated to address these problems and improve the applicability of AI to body composition analysis. CONCLUSIONS: AI assisted measurement of body composition might assist in improved cardiovascular risk stratification when applied in the appropriate clinical context.

Radiation hematologic toxicity prediction for locally advanced rectal cancer using dosimetric and radiomics features.

BACKGROUND: Hematologic toxicity (HT) is a common adverse tissue reaction during radiotherapy for rectal cancer patients, which may lead to various negative effects such as reduced therapeutic effect, prolonged treatment period and increased treatment cost. Therefore, predicting the occurrence of HT before radiotherapy is necessary but still challenging. PURPOSE: This study proposes a hybrid machine learning model to predict the symptomatic radiation HT in rectal cancer patients using the combined demographic, clinical, dosimetric, and Radiomics features, and ascertains the most effective regions of interest (ROI) in CT images and predictive feature sets. METHODS: A discovery dataset of 240 rectal cancer patients, including 145 patients with HT symptoms and a validation dataset of 96 patients (63 patients with HT) with different dose prescription were retrospectively enrolled. Eight ROIs were contoured on patient CT images to derive Radiomics features, which were then, respectively, combined with the demographic, clinical, and dosimetric features to classify patients with HT symptoms. Moreover, the survival analysis was performed on risky patients with HT in order to understand the HT progression. RESULTS: The classification models in ROIs of bone marrow and femoral head exhibited relatively high accuracies (accuracy = 0.765 and 0.725) in the discovery dataset as well as comparable performances in the validation dataset (accuracy = 0.758 and 0.714). When combining the two ROIs together, the model performance was the best in both discovery and validation datasets (accuracy = 0.843 and 0.802). In the survival analysis test, only the bone marrow ROI achieved statistically significant performance in accessing risky HT (C-index = 0.658, P = 0.03). Most of the discriminative features were Radiomics features, and only gender and the mean dose in Irradvolume was involved in HT. CONCLUSION: The results reflect that the Radiomics features of bone marrow are significantly correlated with HT occurrence and progression in rectal cancer. The proposed Radiomics-based model may help the early detection of radiotherapy induced HT in rectal cancer patients and thus improve the clinical outcome in future.