Internal Test Set Research Articles

A 18F-FDG PET/CT-based deep learning-radiomics-clinical model for prediction of cervical lymph node metastasis in esophageal squamous cell carcinoma.

To develop an artificial intelligence (AI)-based model using Radiomics, deep learning (DL) features extracted from 18F-fluorodeoxyglucose (18F-FDG) Positron emission tomography/Computed Tomography (PET/CT) images of tumor and cervical lymph node with clinical feature for predicting cervical lymph node metastasis (CLNM) in patients with esophageal squamous cell carcinoma (ESCC). The study included 300 ESCC patients from the First Affiliated Hospital of Zhengzhou University who were divided into a training cohort and an internal testing cohort with an 8:2 ratio. Another 111 patients from Shanghai Chest Hospital were included as the external cohort. For each sample, we extracted 428 PET/CT-based Radiomics features from the gross tumor volume (GTV) and cervical lymph node (CLN) delineated layer by layer and 256 PET/CT-based DL features from the maximum cross-section of GTV and CLN images We input these features into seven different machine learning algorithms and ultimately selected logistic regression (LR) as the model classifier. Subsequently, we evaluated seven models (Clinical, Radiomics, Radiomics-Clinical, DL-Clinical, DL-Radiomics, DL-Radiomics-Clinical) using Radiomics features, DL features and clinical feature. The DL-Radiomics-Clinical (DRC) model demonstrated higher AUC of 0.955 and 0.916 compared to the other six models in both internal and external testing cohorts respectively. The DRC model achieved the highest accuracy among the seven models in both the internal and external test sets, with scores of 0.951 and 0.892, respectively. Through the combination of Radiomics features and DL features from PET/CT imaging and clinical feature, we developed a predictive model exhibiting exceptional classification capabilities. This model can be considered as a non-invasive method for predication of CLNM in patients with ESCC. It might facilitate decision-making regarding to the extend of lymph node dissection, and to select candidates for postoperative adjuvant therapy.

Self-Attention Mechanisms-Based Laryngoscopy Image Classification Technique for Laryngeal Cancer Detection.

The early diagnosis of laryngeal cancer (LCA) is crucial for prognosis, driving our search for an accurate, precise, and sensitive deep learning model to assist in LCA detection. We collected 5768 laryngoscopic images from 1462 patients and created the intelligent laryngeal cancer detection system (ILCDS) based on Swin-Transformer. Following training and validation, we assessed the ILCDS performance on the internal and external test sets and compared it with previous convolutional neural network (CNN) models and three professional laryngologists. The ILCDS outperformed the six CNNs, with the highest accuracy of 92.78% and an area under the curve (AUC) of 0.9732. Despite a slight drop in performance on external sets, the ILCDS maintained the best superiority, with 85.79% accuracy and an AUC of 0.9550. Surpassing professional laryngologists, the ILCDS achieved 92.00% accuracy. The ILCDS offers high accuracy and stability for LCA detection, reducing the burden on laryngologists.

Deep learning model for diagnosis of thyroid nodules with size less than 1 cm: A multicenter, retrospective study

ObjectiveTo develop a ultrasound images based dual-channel deep learning model to achieve accurate early diagnosis of thyroid nodules less than 1 cm. MethodsA dual-channel deep learning model called thyroid nodule transformer network (TNT-Net) was proposed. The model has two input channels for transverse and longitudinal ultrasound images of thyroid nodules, respectively. A total of 9649 nodules from 8455 patients across five hospitals were retrospectively collected. The data were divided into a training set (8453 nodules, 7369 patients), an internal test set (565 nodules, 512 patients), and an external test set (631 nodules, 574 patients). ResultsTNT-Net achieved an area under the curve (AUC) of 0.953 (95 % confidence interval (CI): 0.934, 0.969) on the internal test set and 0.941 (95 % CI: 0.921, 0.957) on the external test set, significantly outperforming traditional deep convolutional neural network models and single-channel swin transformer model, whose AUCs ranged from 0.800 (95 % CI: 0.759, 0.837) to 0.856 (95 % CI: 0.819, 0.881). Furthermore, feature heatmap visualization showed that TNT-Net could extract richer and more energetic malignant nodule patterns. ConclusionThe proposed TNT-Net model significantly improved the recognition capability for thyroid nodules with size less than 1 cm. This model has the potential to reduce overdiagnosis and overtreatment of such nodules, providing essential support for precise management of thyroid nodules while complementing fine-needle aspiration biopsy.

An interpretable deep learning model for detecting BRCA pathogenic variants of breast cancer from hematoxylin and eosin-stained pathological images.

Determining the status of breast cancer susceptibility genes (BRCA) is crucial for guiding breast cancer treatment. Nevertheless, the need for BRCA genetic testing among breast cancer patients remains unmet due to high costs and limited resources. This study aimed to develop a Bi-directional Self-Attention Multiple Instance Learning (BiAMIL) algorithm to detect BRCA status from hematoxylin and eosin (H&E) pathological images. A total of 319 histopathological slides from 254 breast cancer patients were included, comprising two dependent cohorts. Following image pre-processing, 633,484 tumor tiles from the training dataset were employed to train the self-developed deep-learning model. The performance of the network was evaluated in the internal and external test sets. BiAMIL achieved AUC values of 0.819 (95% CI [0.673-0.965]) in the internal test set, and 0.817 (95% CI [0.712-0.923]) in the external test set. To explore the relationship between BRCA status and interpretable morphological features in pathological images, we utilized Class Activation Mapping (CAM) technique and cluster analysis to investigate the connections between BRCA gene mutation status and tissue and cell features. Significantly, we observed that tumor-infiltrating lymphocytes and the morphological characteristics of tumor cells appeared to be potential features associated with BRCA status. An interpretable deep neural network model based on the attention mechanism was developed to predict the BRCA status in breast cancer. Keywords: Breast cancer, BRCA, deep learning, self-attention, interpretability.

Deep learning enables the fully automated quantification of high-resolution cardiac CT images: human in loop for model development

Abstract Introduction Cardiac computed tomography (CCT) images provide vast spatial and temporal information. Segmentation of the structure of interest is necessary to provide quantitative information. However, manual segmentation of cardiac substructures is highly time-consuming. Objective This study aims to develop a robust deep-learning segmentation model for cardiac substructure segmentation in 3D CCT images. Method We initially developed a 3D U-Net architecture, incorporating extensive augmentation, for the segmentation of the Left Ventricle Myocardium (LVM), the blood cavities of the Left and Right Ventricles (LV, RV), and the Left and Right Atria (LA, RA). This model utilized CT images from 20 patients who had available manual segmentation. Subsequently, we applied this initial model to datasets from two centers, including different generations of scanners. We then visually inspected the segmentation, selected the highest-quality segmentations, and modify it if necessary, and excluded the low-quality data. We continued fine-tuning the model with the new dataset until we reached a count of 456 patients. As there were multiple images from one patient during this model's development, we generated datasets to develop a new model using the entire new dataset to avoid any data leakage in the reported metrics. The model was developed using data from Center 1 (5-fold cross-validation) and then evaluated on an external test set from Center 2 (126 patients) and also 4D images from Center 1. Various metrics were calculated to assess the model's performance. Results In the internal test set, utilizing 5-fold CV, the model demonstrated high segmentation accuracy, achieving an overall Dice coefficient of 0.98, with individual scores of 0.96 for LVM, 0.98 for LV, 0.98 for RV, 0.99 for RA, and 0.98 for LA. We assessed the automatic quantification capability of the segmentation model from 256 patients, resulting in an R2 value greater than 0.92 for both LV end-diastolic and systolic volumes. In contrast, the model maintained robust performance on the external dataset, achieving an overall Dice coefficient of 0.96, with individual scores of 0.95 for LVM, 0.98 for LV, 0.97 for RV, 0.98 for RA, and 0.94 for LA. Conclusion We provided a large cohort of ground truth segmentations for different cardiac CT substructures using a human-in-the-loop strategy. Subsequently, we developed a deep learning model for highly accurate automated segmentation of these substructures. This model allows for fast and fully automatic segmentation and quantification of 3D and 4D cardiac CT images, from which various quantitative metrics can be extracted from different cardiac substructures.

Automatic identification of coronary stent in coronary calcium scoring CT using deep learning

Coronary artery calcium (CAC) scoring CT is a useful tool for screening coronary artery disease and for cardiovascular risk stratification. However, its efficacy in patients with coronary stents, who had pre-existing coronary artery disease, remains uncertain. Historically, CAC CT scans of these patients have been manually excluded from the CAC scoring process, even though most of the CAC scoring process is now fully automated. Therefore, we hypothesized that automating the filtering of patients with coronary stents using artificial intelligence could streamline the entire CAC workflow, eliminating the need for manual intervention. Consequently, we aimed to develop and evaluate a deep learning-based coronary stent filtering algorithm (StentFilter) in CAC scoring CT scans using a multicenter CAC dataset. We developed StentFilter comprising two main processes: stent identification and false-positive reduction. Development utilized 108 non-enhanced echocardiography-gated CAC scans (including 74 with manually labeled stents), and for false positive reduction, 2063 CAC scans with significant coronary calcium (average Agatston score: 523.8) but no stents were utilized. StentFilter’s performance was evaluated on two independent internal test sets (Asan cohort- and 2; n = 355 and 396; one without coronary stents) and two external test sets from different institutions (n = 105 and 62), each with manually labeled stents. We calculated the per-patient sensitivity, specificity, and false-positive rate of StentFilter. StentFilter demonstrated a high overall per-patient sensitivity of 98.8% (511/517 cases with stents) and a false-positive rate of 0.022 (20/918). Notably, the false-positive ratio was significantly lower in the dataset containing stents (Asan cohort-1; 0.008 [3/355]) compared with the dataset without stents (Asan cohort-2; 0.043 [17/396], p = 0.008). All false-positive identifications were attributed to dense coronary calcifications, with no false positives identified in extracoronary locations. The automated StentFilter accurately distinguished coronary stents from pre-existing coronary calcifications. This approach holds potential as a filter within a fully automated CAC scoring workflow, streamlining the process efficiently.

Integrating VAI-Assisted Quantified CXRs and Multimodal Data to Assess the Risk of Mortality.

To address the unmet need for a widely available examination for mortality prediction, this study developed a foundation visual artificial intelligence (VAI) to enhance mortality risk stratification using chest X-rays (CXRs). The VAI employed deep learning to extract CXR features and a Cox proportional hazard model to generate a hazard score ("CXR-risk"). We retrospectively collected CXRs from patients visited outpatient department and physical examination center. Subsequently, we reviewed mortality and morbidity outcomes from electronic medical records. The dataset consisted of 41,945, 10,492, 31,707, and 4441 patients in the training, validation, internal test, and external test sets, respectively. During the median follow-up of 3.2 (IQR, 1.2-6.1) years of both internal and external test sets, the "CXR-risk" demonstrated C-indexes of 0.859 (95% confidence interval (CI), 0.851-0.867) and 0.870 (95% CI, 0.844-0.896), respectively. Patients with high "CXR-risk," above 85th percentile, had a significantly higher risk of mortality than those with low risk, below 50th percentile. The addition of clinical and laboratory data and radiographic report further improved the predictive accuracy, resulting in C-indexes of 0.888 and 0.900. The VAI can provide accurate predictions of mortality and morbidity outcomes using just a single CXR, and it can complement other risk prediction indicators to assist physicians in assessing patient risk more effectively.

Personalized three-year survival prediction and prognosis forecast by interpretable machine learning for pancreatic cancer patients: a population-based study and an external validation.

The overall survival of patients with pancreatic cancer is extremely low. We aimed to establish machine learning (ML) based model to accurately predict three-year survival and prognosis of pancreatic cancer patients. We analyzed pancreatic cancer patients from the Surveillance, Epidemiology, and End Results (SEER) database between 2000 and 2021. Univariate and multivariate logistic analysis were employed to select variables. Recursive Feature Elimination (RFE) method based on 6 ML algorithms was utilized in feature selection. To construct predictive model, 13 ML algorithms were evaluated by area under the curve (AUC), area under precision-recall curve (PRAUC), accuracy, sensitivity, specificity, precision, cross-entropy, Brier scores and Balanced Accuracy (bacc) and F Beta Score (fbeta). An optimal ML model was constructed to predict three-year survival, and the predictive results were explained by SHapley Additive exPlanations (SHAP) framework. Meanwhile, 101 ML algorithm combinations were developed to select the best model with highest C-index to predict prognosis of pancreatic cancer patients. A total of 20,064 pancreatic cancer patients from SEER database was consecutively enrolled. We utilized eight clinical variables to establish prediction model for three-year survival. CatBoost model was selected as the best prediction model, and AUC was 0.932 [0.924, 0.939], 0.899 [0.873, 0.934] and 0.826 [0.735, 0.919] in training, internal test and external test sets, with 0.839 [0.831, 0.847] accuracy, 0.872 [0.858, 0.887] sensitivity, 0.803 [0.784, 0.825] specificity and 0.832 [0.821, 0.853] precision. Surgery type had the greatest effects on three-year survival according to SHAP results. For prognosis prediction, "RSF+GBM" algorithm was the best prognostic model with C-index of 0.774, 0.722 and 0.674 in training, internal test and external test sets. Our ML models demonstrate excellent accuracy and reliability, offering more precise personalized prognostic prediction to pancreatic cancer patients.

A multi-model approach integrating whole-slide imaging and clinicopathologic features to predict breast cancer recurrence risk.

Breast cancer is the most common malignancy affecting women worldwide and is notable for its morphologic and biologic diversity, with varying risks of recurrence following treatment. The Oncotype DX Breast Recurrence Score test is an important predictive and prognostic genomic assay for estrogen receptor positive/HER2 negative breast cancer that guides therapeutic strategies; however, such tests can be expensive, delay care, and are not widely available. The aim of this study was to develop a multi-model approach integrating the analysis of whole-slide images and clinicopathologic data to predict their associated breast cancer recurrence risks and categorize these patients into two risk groups according to the predicted score: low-risk and high-risk. The proposed novel methodology uses convolutional neural networks for feature extraction and vision transformers for contextual aggregation, complemented by a logistic regression model that analyzes clinicopathologic data for classification into two risk categories. This method was trained and tested on 956 hematoxylin and eosin-stained whole-slide images of 950 ER+/HER2- breast cancer patients with corresponding clinicopathological features that had prior Oncotype DX testing. The model's performance was evaluated using an internal test set of 192 patients from Dartmouth Health and an external test set of 405 patients from the University of Chicago. The multi-model approach achieved an AUC of 0.91 (95% CI: 0.87-0.95) on the internal set and an AUC of 0.84 (95% CI: 0.78-0.89) on the external cohort for predicting low- and high-breast cancer recurrence risk categories based on the Oncotype DX recurrence score. With further validation, the proposed methodology could provide an alternative to assist clinicians in personalizing treatment for breast cancer patients and potentially improving their outcomes.

Multiparametric MRI Radiomics With Machine Learning for Differentiating HER2-Zero, -Low, and -Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis.

BACKGROUND: MRI radiomics has been explored for three-tiered classification of breast cancer HER2 expression (i.e., HER2-zero, HER2-low, or HER2-positive), although understanding of how such models reach their predictions is lacking. OBJECTIVE: To develop and test multiparametric MRI radiomics machine-learning models for differentiating three-tiered HER2 expression levels in patients with breast cancer, and to explain the contributions of model features through local and global interpretations using SHapley Additive exPlanation (SHAP) analysis. METHODS: This retrospective study included 737 patients (mean age, 54.1±10.6 years) with breast cancer from two centers (center 1: n=578; center 2: n=159), who underwent breast MRI and had HER2 expression determined after excisional biopsy. Analysis entailed two tasks: differentiating HER2-negative (i.e., HER2-zero or HER2-low) from HER2-positive tumors (task 1), and differentiating HER2-zero from HER2-low tumors (task 2). For each task, patients from center 1 were randomly assigned in 7:3 ratio to training (task 1: n=405; task 2: n=284) or internal test (task 1: n=173; task 2: n=122) sets; those from center 2 formed an external test set (task 1: n=159; task 2: n=105). Radiomics features were extracted from early-phase dynamic contrast-enhanced images (DCE), T2-weighted images (T2WI), and DWI. For each task, a support vector machine (SVM) was used for feature selection; a multiparametric radiomics score (radscore) was computed using feature weights from SVM correlation coefficients; conventional MRI and combined models were constructed; and model performances were evaluated. SHAP analysis was used to provide local and global interpretations for model outputs. RESULTS: In the external test set, for task 1, AUCs for the conventional MRI model, radscore, and combined model were 0.624, 0.757, and 0.762, respectively; for task 2, AUC for radscore was 0.754, and no conventional MRI model or combined model could be constructed. SHAP analysis identified early-phase DCE features as having the strongest influence for both tasks; T2WI features also had a prominent role for task 2. CONCLUSION: The findings indicate suboptimal performance of MRI radiomics models for noninvasive characterization of HER2 expression. CLINICAL IMPACT: The study provides an example of the use of SHAP interpretation analysis to better understand predictions of imaging-based machine learning models.

Addressing the Generalizability of AI in Radiology Using a Novel Data Augmentation Framework with Synthetic Patient Image Data: Proof-of-Concept and External Validation for Classification Tasks in Multiple Sclerosis.

Artificial intelligence (AI) models often face performance drops after deployment to external datasets. This study evaluated the potential of a novel data augmentation framework based on generative adversarial networks (GANs) that creates synthetic patient image data for model training to improve model generalizability. Model development and external testing were performed for a given classification task, namely the detection of new fluid-attenuated inversion recovery lesions at MRI during longitudinal follow-up of patients with multiple sclerosis (MS). An internal dataset of 669 patients with MS (n = 3083 examinations) was used to develop an attention-based network, trained both with and without the inclusion of the GAN-based synthetic data augmentation framework. External testing was performed on 134 patients with MS from a different institution, with MR images acquired using different scanners and protocols than images used during training. Models trained using synthetic data augmentation showed a significant performance improvement when applied on external data (area under the receiver operating characteristic curve [AUC], 83.6% without synthetic data vs 93.3% with synthetic data augmentation; P = .03), achieving comparable results to the internal test set (AUC, 95.0%; P = .53), whereas models without synthetic data augmentation demonstrated a performance drop upon external testing (AUC, 93.8% on internal dataset vs 83.6% on external data; P = .03). Data augmentation with synthetic patient data substantially improved performance of AI models on unseen MRI data and may be extended to other clinical conditions or tasks to mitigate domain shift, limit class imbalance, and enhance the robustness of AI applications in medical imaging. Keywords: Brain, Brain Stem, Multiple Sclerosis, Synthetic Data Augmentation, Generative Adversarial Network Supplemental material is available for this article. © RSNA, 2024.

A hybrid of supervised and unsupervised deep learning models for multi-vendor kernel conversion of chest CT images

ObjectiveWhen reconstructing a computed tomography (CT) volume, different filter kernels can be used to highlight different structures depending on the medical purpose. The aim of this study was to perform CT conversion for intra-/inter-vendor kernel conversion while preserving image quality. Materials and methodsThis study used CT scans from 632 patients who underwent contrast-enhanced chest CT on either a GE or Siemens scanner. Raw data from each CT scan was reconstructed with Standard and Chest kernels of GE or B10f, B30f, B50f, and B70f kernels of Siemens. In intra-vendor, all images reconstructed with one kernel are paired with another kernel, so the U-Net based supervised method was applied. In the case of inter-vendor where the input and target kernels have each different vendor, Siemens' B30f and GE's Standard kernel were trained through unsupervised image-to-image translation using contrastive learning. ResultsIn the intra-vendor, quantitative evaluation of the image quality of our model showed reasonable performance on the internal test set (structural similarity index measure (SSIM) > 0.96, peak signal-to-noise ratio (PSNR) > 42.55) compared with the SR-block model (SSIM > 0.93, PSNR > 42.92). In the 6-class classification to evaluate the inter-vendor conversion performance, similar accuracy was shown in the converted image (0.977) compared to the original image (0.998). ConclusionsIn this study, we developed a network that can translate a given CT image into a target kernel among multi-vendors. Our model showed clinically acceptable quality in quantitative and qualitative evaluations, including image quality metrics.

Development and external validation of a prediction model for interstitial lung disease in systemic lupus erythematosus patients: A cross-sectional study

ObjectiveThe aim of this study is to develop and validate a nomogram that can assist clinicians in identifying female systemic lupus erythematosus (SLE) patients of reproductive age complicated with interstitial lung disease (ILD). MethodsClinical, laboratory data of SLE patients were first collected. Meteorological data were then gathered according to the geographical locations of the SLE patients. Diagnostic results, univariate logistic regression, elastic net regression, and multivariate logistic regression were used to screen for risk factors for female SLE patients of reproductive age complicated with ILD. A nomogram was constructed using these risk factors and was internally and externally validated through methods such as calculating the concordance index, plotting calibration curves, drawing receiver operating characteristic curves, and clinical decision curves. ResultsA total of 4798 SLE patients were included in this study, with 2488 patients in the development set and 2310 patients in the external validation set. The patients in the development set were randomly divided into a training set (N = 1742) and an internal testing set (N = 746) at a ratio of 7:3. Eight independent risk factors for ILD were identified, including APOB, APOA1, ALP, PLT, HCT, EOS-R, LYM-R, and age. The nomogram model was developed, and the areas under the receiver operating characteristic curve was 0.811 (0.748, 0.875), 0.820 (0.727,0.913), and 0.889 (0.869, 0.909) for the three sets, respectively. ConclusionWe established a nomogram model using easily accessible clinical and laboratory data to predict the probability of female SLE patients of reproductive age developing ILD.

A deep learning model to enhance the classification of primary bone tumors based on incomplete multimodal images in X-ray, CT, and MRI

BackgroundAccurately classifying primary bone tumors is crucial for guiding therapeutic decisions. The National Comprehensive Cancer Network guidelines recommend multimodal images to provide different perspectives for the comprehensive evaluation of primary bone tumors. However, in clinical practice, most patients’ medical multimodal images are often incomplete. This study aimed to build a deep learning model using patients’ incomplete multimodal images from X-ray, CT, and MRI alongside clinical characteristics to classify primary bone tumors as benign, intermediate, or malignant.MethodsIn this retrospective study, a total of 1305 patients with histopathologically confirmed primary bone tumors (internal dataset, n = 1043; external dataset, n = 262) were included from two centers between January 2010 and December 2022. We proposed a Primary Bone Tumor Classification Transformer Network (PBTC-TransNet) fusion model to classify primary bone tumors. Areas under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the model’s classification performance.ResultsThe PBTC-TransNet fusion model achieved satisfactory micro-average AUCs of 0.847 (95% CI: 0.832, 0.862) and 0.782 (95% CI: 0.749, 0.817) on the internal and external test sets. For the classification of benign, intermediate, and malignant primary bone tumors, the model respectively achieved AUCs of 0.827/0.727, 0.740/0.662, and 0.815/0.745 on the internal/external test sets. Furthermore, across all patient subgroups stratified by the distribution of imaging modalities, the PBTC-TransNet fusion model gained micro-average AUCs ranging from 0.700 to 0.909 and 0.640 to 0.847 on the internal and external test sets, respectively. The model showed the highest micro-average AUC of 0.909, accuracy of 84.3%, micro-average sensitivity of 84.3%, and micro-average specificity of 92.1% in those with only X-rays on the internal test set. On the external test set, the PBTC-TransNet fusion model gained the highest micro-average AUC of 0.847 for patients with X-ray + CT.ConclusionsWe successfully developed and externally validated the transformer-based PBTC-Transnet fusion model for the effective classification of primary bone tumors. This model, rooted in incomplete multimodal images and clinical characteristics, effectively mirrors real-life clinical scenarios, thus enhancing its strong clinical practicability.

Pathologist-level diagnosis of ulcerative colitis inflammatory activity level using an automated histological grading method

Background and AimsInflammatory bowel disease (IBD) is a global disease that is evolving with increasing incidence. However, there are few works on computationally assisted diagnosis of IBD based on pathological images. Therefore, based on the UK and Chinese IBD diagnostic guidelines, our study established an artificial intelligence-assisted diagnostic system for histologic grading of inflammatory activity in ulcerative colitis (UC). MethodsWe proposed an efficient deep-learning (DL) method for grading inflammatory activity in whole-slide images (WSIs) of UC pathology. Our model was constructed using 603 UC WSIs from Nanjing Drum Tower Hospital for model train set and internal test set. We collected 212 UC WSIs from Zhujiang Hospital as an external test set. Initially, the pre-trained ResNet50 model on the ImageNet dataset was employed to extract image patch features from UC patients. Subsequently, a multi-instance learning (MIL) approach with embedded self-attention was utilized to aggregate tissue image patch features, representing the entire WSI. Finally, the model was trained based on the aggregated features and WSI annotations provided by senior gastrointestinal pathologists to predict the level of inflammatory activity in UC WSIs. ResultsIn the task of distinguishing the presence or absence of inflammatory activity, the Area Under Curve (AUC) value in the internal test set is 0.863 (95% confidence interval [CI] 0.829, 0.898), with a sensitivity of 0.913 (95% [CI] 0.866, 0.961), and specificity of 0.816 (95% [CI] 0.771, 0.861). The AUC in the external test set is 0.947 (95% confidence interval [CI] 0.939, 0.955), with a sensitivity of 0.889 (905% [CI] 0.837, 0.940), and specificity of 0.858 (95% [CI] 0.777, 0.939). For distinguishing different levels of inflammatory activity in UC, the average Macro-AUC in the internal test set and the external test set are 0.827 (95% [CI] 0.803, 0.850) and 0.908 (95% [CI] 0.882, 0.935). the average Micro-AUC in the internal test set and the external test set are 0.816 (95% [CI] 0.792, 0.840) and 0.898 (95% [CI] 0.869, 0.926). ConclusionsComparative analysis with diagnoses made by pathologists at different expertise levels revealed that the algorithm reached a proficiency comparable to the pathologist with 5 years of experience. Furthermore, our algorithm performed superior to other MIL algorithms.

Deep learning model using planar whole-body bone scintigraphy for diagnosis of skull base invasion in patients with nasopharyngeal carcinoma

PurposeThis study assesses the reliability of deep learning models based on planar whole-body bone scintigraphy for diagnosing Skull base invasion (SBI) in nasopharyngeal carcinoma (NPC) patients.MethodsIn this multicenter study, a deep learning model was developed using data from one center with a 7:3 allocation to training and internal test sets, to diagnose SBI in patients newly diagnosed with NPC using planar whole-body bone scintigraphy. Patients were diagnosed based on a composite reference standard incorporating radiologic and follow-up data. Ten different convolutional neural network (CNN) models were applied to both whole-image and partial-image input modes to determine the optimal model for each analysis. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration, decision curve analysis (DCA), and compared with expert assessments by two nuclear medicine physicians.ResultsThe best-performing model using partial-body input achieved AUCs of 0.80 (95% CI: 0.73, 0.86) in the internal test set, 0.84 (95% CI: 0.77, 0.91) in the external cohort, and 0.78 (95% CI: 0.73, 0.83) in the treatment test cohort. Calibration curves and DCA confirmed the models’ excellent discrimination, calibration, and potential clinical utility across internal and external datasets. The AUCs of both nuclear medicine physicians were lower than those of the best-performing deep learning model in external test set (AUC: 0.75 vs. 0.77 vs. 0.84).ConclusionDeep learning models utilizing partial-body input from planar whole-body bone scintigraphy demonstrate high discriminatory power for diagnosing SBI in NPC patients, surpassing experienced nuclear medicine physicians.

Ranking attention multiple instance learning for lymph node metastasis prediction on multicenter cervical cancer MRI.

In the current clinical diagnostic process, the gold standard for lymph node metastasis (LNM) diagnosis is histopathological examination following surgical lymphadenectomy. Developing a non-invasive and preoperative method for predicting LNM is necessary and holds significant clinical importance. We develop a ranking attention multiple instance learning (RA-MIL) model that integrates convolutional neural networks (CNNs) and ranking attention pooling to diagnose LNM from T2 MRI. Our RA-MIL model applies the CNNs to derive imaging features from 2D MRI slices and employs ranking attention pooling to create patient-level feature representation for diagnostic classification. Based on the MIL and attention theory, informative regions of top-ranking MRI slices from LNM-positive patients are visualized to enhance the interpretability of automatic LNM prediction. This retrospective study collected 300 female patients with cervical cancer who underwent T2-weighted magnetic resonance imaging (MRI) scanning and histopathological diagnosis from one hospital (289 patients) and one open-source dataset (11 patients). Our RA-MIL model delivers promising LNM prediction performance, achieving the area under the receiver operating characteristic curve (AUC) of 0.809 on the internal test set and 0.833 on the public dataset. Experiments show significant improvements in LNM status prediction using the proposed RA-MIL model compared with other state-of-the-art (SOTA) comparative deep learning models. The developed RA-MIL model has the potential to serve as a non-invasive auxiliary tool for preoperative LNM prediction, offering visual interpretability regarding informative MRI slices and regions in LNM-positive patients.

Prediction and validation of pathologic complete response for locally advanced rectal cancer under neoadjuvant chemoradiotherapy based on a novel predictor using interpretable machine learning

BackgroundPrecise evaluation of pathological complete response (pCR) is essential for determining the prognosis of patients with locally advanced rectal cancer (LARC) undergoing neoadjuvant chemoradiotherapy (NCRT) and can offer clues for the selection of subsequent treatment strategies. Most current predictive models for pCR focus primarily on pre-treatment factors, neglecting the dynamic systemic changes that occur during neoadjuvant chemoradiotherapy, and are constrained by low accuracy and lack of integrity. PurposeThis study devised a novel predictor of pCR using dynamic alterations in systemic inflammation-nutritional marker indexes (SINI) during neoadjuvant therapy and developed a machine-learning model to predict pCR. MethodsTwo cohorts of patients with LARC from center one from 2012 to 2017 and from center two from 2020 to 2023 were integrated for analysis. This study compared dynamic changes in blood indexes before and after neoadjuvant therapy and surgical operation. A least absolute shrinkage and selection operator (LASSO) regression analysis was conducted to mitigate collinearity and identify key indexes, constructing the SINI. Univariate and multiple logistic regression analyses were used to identify the independent risk factors associated with pCR. Additionally, 10 machine learning algorithms were employed to develop predictive models to assess risk. The hyperparameters of the machine learning models were optimized using a random search and 10-fold cross-validation. The models were assessed by examining various metrics, including the area under the receiver operating characteristic curves (AUC), the area under the precision-recall curve (AUPRC), decision curve analysis, calibration curves, and the precision and accuracy of the internal and external validation cohorts. Additionally, Shapley's additive explanations (SHAP) were employed to interpret the machine learning models. ResultsThe study cohort comprised 677 patients from the center one and 224 patients from the center two. Six key indexes were identified, and a predictive index, SINI, was constructed. Univariate and multiple logistic regression analyses revealed that SINI, clinical T-stage, clinical N-stage, tumor size, and the distance from the anal verge were independent risk factors for pCR in patients with LARC following NCRT. The mean AUC value of the extreme gradient boosting (XGB) model in the 10-fold cross-validation of the training set was 0.877. The XGB model demonstrated superior performance in the internal and external validation sets. Specifically, in the internal test set, the XGB model achieved an AUC of 0.86, AUPRC of 0.707, accuracy of 0.82, and precision of 0.80. In the external validation set, the XGB model exhibited an AUC of 0.83, AUPRC of 0.702, accuracy of 0.81, and precision of 0.81. Additionally, the predictions generated by the XGB model were analyzed using SHAP. ConclusionThis study involved developing and validating an XGB model using SINI to predict pCR in patients with LARC. Besides, a SINI-based machine learning model shows promise in accurately predicting pCR following NCRT in patients with resectable LARC, offering valuable insights for personalized treatment approaches.

MRI-based radiomics for stratifying recurrence risk of early-onset rectal cancer: a multicenter study

Early-onset rectal cancer (EORC) is characterized by a unique disease process with different clinicopathological features compared with late-onset rectal cancer (LORC). Research on the risk of recurrence in EORC patients, however, is limited. We aim to develop a predictive model to accurately predict EORC recurrence risk. Rectal cancer patients who underwent radical surgery and T2-weighted imaging and diffusion-weighted imaging magnetic resonance imaging (MRI) were retrospectively enrolled from three medical institutions from November 2012 to November 2018. Differences in clinicopathological characteristics between EORC and LORC were compared. Five prediction models for disease-free survival were constructed based on clinicopathological variables and five radiomic features from pretreatment MRI of the EORC. A fixed cut-off value calculated in the training set was used to stratify EORC patients into high-risk and low-risk groups of post-operative recurrence. Model performance was evaluated by concordance index (C-index) and receiver operating characteristic curve. A total of 264 EORC patients (median age, 43 years, 163 males) and 778 LORC patients (median age, 62 years, 520 males) were enrolled. Pretreatment positive carcinoembryonic antigen [hazard ratio (HR)= 2.84, P= 0.006], pathological positive lymph node status (pN positive) [HR= 2.86, P= 0.011] and MRI-based radiomics score [HR= 2.72, P < 0.001] are independent risk factors for disease-free survival in EORC patients. The EORC-ClinPathRadiom model, constructed by integrating the clinicopathological characteristics and MRI-based radiomics features of EORC, showed C-index of 0.82, 0.82, and 0.81 in the training, internal, and external test sets, respectively. This model effectively stratified EORC patients into high risk and low risk of recurrence (HRs for the training, internal, and external test sets were 8.96, 6.81, and 7.46, respectively). The EORC-ClinPathRadiom model can effectively predict and stratify the risk of post-operative recurrence in EORC patients.

Development and external validation of a machine-learning based model to predict pre-sarcopenia in MASLD population: Results from NHANES 2017–2018

Introduction and ObjectivesWith rising prevalence of pre-sarcopenia in metabolic dysfunction-associated steatotic liver disease (MASLD), this study aimed to develop and validate machine learning-based model to identify pre-sarcopenia in MASLD population. Materials and MethodsA total of 571 MASLD subjects were screened from the National Health and Nutrition Examination Survey 2017–2018. This cohort was randomly divided into training set and internal testing set with a ratio of 7:3. Sixty-six MASLD subjects were collected from our institution as external validation set. Four binary classifiers, including Random Forest (RF), support vector machine, and extreme gradient boosting and logistic regression, were fitted to identify pre-sarcopenia. The best-performing model was further validated in external validation set. Model performance was assessed in terms of discrimination and calibration. Shapley Additive explanations were used for model interpretability. ResultsThe pre-sarcopenia rate was 17.51 % and 15.16 % in NHANES cohort and external validation set, respectively. RF outperformed other models with area under receiver operating characteristic curve (AUROC) of 0.819(95 %CI: 0.749, 0.889). When six top-ranking features were retained as per variable importance, including weight-adjusted waist, sex, race, creatinine, education and alkaline phosphatase, a final RF model reached an AUROC being 0.824(0.737, 0.910) and 0.732(95 %CI: 0.529, 0.936) in internal and external validation sets, respectively. The model robustness was proved in sensitivity analysis. The calibration curve and decision curve analysis confirmed a good calibration capacity and good clinical usage. ConclusionsThis study proposed a user-friendly model using explainable machine learning algorithm to predict pre-sarcopenia in MASLD population. A web-based tool was provided to screening pre-sarcopenia in community and hospitalization settings.