Citations

Artificial intelligence (AI)-based object detection in radiology can assist in clinical diagnosis and treatment planning. This article examines the AI-based object detection models currently used in many imaging modalities, including X-ray Magnetic Resonance Imaging (MRI), Computed Tomography (CT), and Ultrasound (US). The key models from the convolutional neural network (CNN) as well as the contemporary transformer and hybrid models are analyzed based on their ability to detect pathological features, such as tumors, lesions, and tissue abnormalities. In addition, this review offers a closer look at the strengths and weaknesses of these models in terms of accuracy, robustness, and speed in real clinical settings. The common issues related to these models, including limited data, annotation quality, and interpretability of AI decisions, are discussed in detail. Moreover, the need for strong applicable models across different populations and imaging modalities are addressed. The importance of privacy and ethics in general data use as well as safety and regulations for healthcare data are emphasized. The future potential of these models lies in their accessibility in low resource settings, usability in shared learning spaces while maintaining privacy, and improvement in diagnostic accuracy through multimodal learning. This review also highlights the importance of interdisciplinary collaboration among artificial intelligence researchers, radiologists, and policymakers. Such cooperation is essential to address current challenges and to fully realize the potential of AI-based object detection in radiology.

INTRODUCTION: The risk of progression to esophageal adenocarcinoma in Barrett's esophagus (BE) increases with advancing degrees of dysplasia. There is a critical need to improve the diagnosis of BE dysplasia, given substantial interobserver variability and overcalls of dysplasia during manual community pathologist reads. We aimed to externally validate a previously cross-validated BE dysplasia diagnosis deep learning model (BEDDLM) that predicts dysplasia grade on whole slide images (WSIs). METHODS: We digitized nondysplastic BE (NDBE), low-grade (LGD), and high-grade dysplasia (HGD) histology slides from 3 external academic centers. A consensus read by 2 expert study pathologists was used as the criterion standard. Slide stain characteristics were normalized using cycle-generative adversarial networks. WSIs were assessed by BEDDLM using an ensemble approach, combining a “You Only Look Once” model followed by a ResNet101 classifier model. RESULTS: We included 489 WSIs. Consensus histopathology revealed 232 NDBE, 117 LGD, and 140 HGD WSIs. The mean age (SD) was 66.9 (11.4) years; 413 (84.7%) were men. Using the BEDDLM ensemble model, sensitivity and specificity for NDBE were 73.3% (95% confidence interval [CI]: 67.09%–78.85%) and 93.4% (95% CI: 89.62%–96.10%); for LGD, 84.6% (95% CI: 76.78%–90.62%) and 80.6% (95% CI: 76.26%–84.54%); and for HGD, 80.7% (95% CI: 73.19%–86.89%) and 94.8% (95% CI: 91.97%–96.91%), respectively. The F1 score was 0.81, 0 0.69, and 0.83 for NDBE, LGD, and HGD, respectively. DISCUSSION: Our externally validated deep learning model demonstrates substantial accuracy for the diagnosis of BE dysplasia grade on WSIs.

Background and Aims: Among those with primary sclerosing cholangitis (PSC), perihilar cholangiocarcinoma (pCCA) is often diagnosed at a late stage and is a leading source of mortality. Detection of pCCA in PSC when curative action can be taken is challenging. Our aim was to create a deep learning model that analyzed MRI to detect early-stage pCCA and compare its diagnostic performance with expert radiologists. Approach and Results: We conducted a multicenter, international, retrospective cohort study involving adults with large duct PSC who underwent contrast-enhanced MRI. Senior abdominal radiologists reviewed the images. All patients with pCCA had early-stage cancer and were registered for liver transplantation. We trained a 3D DenseNet-121 model, a form of deep learning, using MRI images and assessed its performance in a separate test cohort. The study included 398 patients (training cohort n=150; test cohort n=248). pCCA was present in 230 individuals (training cohort n=64; test cohort n=166). In the test cohort, the respective performances of the model compared to the radiologists were: sensitivity 87.9% versus 50.0%, p <0.001; specificity 84.1% versus 100.0%, p <0.001; area under receiving operating curve 86.0% versus 75.0%, p <0.001. Even when a mass was absent, the model had a higher sensitivity for pCCA than radiologists (91.6% vs. 50.6%, p <0.001) and maintained good specificity (84.1%). Conclusions: The 3D DenseNet-121 MRI model effectively detects early-stage pCCA in PSC patients. Compared to expert radiologists, the model missed fewer cases of cancer.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

An uncertainty-aware deep learning model developed using Mondrian conformal prediction demonstrated high performance in intracranial hemorrhage detection on noncontrast head CT volumes and high accuracy in identifying challenging cases.

Introduction Traumatic brain injury (TBI) is a leading cause of disability and mortality worldwide, with epidural hematoma (EDH) being a severe consequence. This study focuses on identifying factors predicting EDH volume changes in TBI patients and developing a machine learning (ML) model to predict EDH expansion. Methods The study includes patients with traumatic EDH between 2019 and 2021. Data were gathered from CT scans performed at the time of admission and 6 hours later, and subsequently analyzed. The data was divided into three cohorts: all cases, adults, and pediatrics. To predict EDH volume changes, we used Logistic Regression (LR), Random Forest (RF), XGBoost, and K-Nearest Neighbors (KNN) models. Data was divided into an 80% training set and a 20% test set. Through a rigorous process of parameter optimization and K-fold cross-validation, focusing on the area under the receiving operating curve (AUROC), we identified the best models in all cohorts. The best models were evaluated on the test sets, reporting AUROC, recall, precision, and accuracy using the youden index threshold. Results Results show that age, initial EDH volume, swirl sign, intra-hematoma air bleb, contusion, otorrhagia, subarachnoid hemorrhage, location, and other side extra-axial hematoma have significant effects on changing EDH volume. Based on test AUROC, the best models were RF for adults (82.4%), KNN for pediatrics (90%), and LR for all cases (81.6%). Discussion In this study, we identified key features for predicting EDH expansion as well as developing ML models. Using high sensitive models, can assist clinicians in identifying high-risk patients early. This allows for enhanced monitoring and timely intervention, improving patient outcomes by facilitating quicker decisions for follow-up imaging or treatment.

Abstract Glioblastoma, the most common malignant primary adult brain tumor, poses significant diagnostic and treatment challenges due to its heterogeneous molecular and micro-environmental profiles. To this end, we organize the BraTS-Path challenge to provide a public benchmarking environment and a comprehensive dataset to develop and validate AI models for identifying distinct histopathologic glioblastoma sub-regions in H&E-stained digitized tissue sections. We identified 188 multi-institutional diagnostic slides of glioblastoma (IDH-wt, Gr.4) cases, from the TCGA-GBM and TCGA-LGG data collections, following their reclassification according to the 2021 WHO classification criteria. Sub-regions were selected according to distinctive morphology of histopathologic features and included aggressive tumor biology and areas consistent with potential treatment effect. Selected sub-region annotations included cellular tumor, geographic necrosis, cortical infiltration, pseudopalisading necrosis, microvascular proliferation, white matter penetration, regions dense with macrophages, leptomeningeal infiltration, and presence of lymphocytes. We obtained 107,340 patches of size 512x512 from the 9 sub-regions. A global network of board-certified expert neuropathologists defined and followed a systematic annotation protocol based on clinical definitions and only delineated sub-regions with high confidence, thus ensuring high-quality standardized data. Each tissue section was assigned to an annotator-approver pair, with the annotator delineating sub-regions and the approver ensuring the consistency of the annotations. By crowdsourcing annotations, the BraTS-Path challenge harnesses the collective expertise of clinical neuropathologists and fosters a collaborative environment to advance the neuro-oncology field. The anticipated developed algorithms are expected to integrate state-of-the-art computational methods, achieving high accuracy in identifying diverse histopathologic features and advancing clinical decision-making processes. The BraTS-Path challenge aims to bridge the gap between research and clinical practice by promoting the development of AI-driven tools for precise tumor characterization. This collaborative effort can significantly enhance our understanding of glioblastoma, improve diagnostic accuracy, and inform treatment strategies, thereby contributing to better patient outcomes.

Oropharyngeal Squamous Cell Carcinoma (OPSCC) is one of the common forms of heterogeneity in head and neck cancer. Infection with human papillomavirus (HPV) has been identified as a major risk factor for OPSCC. Therefore, differentiating the HPV-positive and negative cases in OPSCC patients is an essential diagnostic factor influencing future treatment decisions. In this study, we investigated the accuracy of a deep learning-based method for image interpretation and automatically detected the HPV status of OPSCC in routinely acquired Computed Tomography (CT) and Positron Emission Tomography (PET) images. We introduce a 3D CNN-based multi-modal feature fusion architecture for HPV status prediction in primary tumor lesions. The architecture is composed of an ensemble of CNN networks and merges image features in a softmax classification layer. The pipeline separately learns the intensity, contrast variation, shape, texture heterogeneity, and metabolic assessment from CT and PET tumor volume regions and fuses those multi-modal features for final HPV status classification. The precision, recall, and AUC scores of the proposed method are computed, and the results are compared with other existing models. The experimental results demonstrate that the multi-modal ensemble model with soft voting outperformed single-modality PET/CT, with an AUC of 0.76 and F1 score of 0.746 on publicly available TCGA and MAASTRO datasets. In the MAASTRO dataset, our model achieved an AUC score of 0.74 over primary tumor volumes of interest (VOIs). In the future, more extensive cohort validation may suffice for better diagnostic accuracy and provide preliminary assessment before the biopsy.