JLJoseph K. Leader

Joseph K. Leader

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Joseph K. Leader has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • CT-fibrosis score: development and internal validation for identifying advanced fibrosis in metabolic dysfunction-associated steatotic liver disease

    by Grant Kokenberger, Omar Almetwali, Tong Yu, Jatin Singh, Adriana L. Cifuentes De La Torre, Shruthi Sethuraman, Joseph K. Leader, Jiantao Pu, Jaideep Behari, Xin Meng

  • Open Access

    Vascular Biomarkers for Pulmonary Nodule Malignancy: Arteries vs. Veins

    by Tong Yu, Xiaoyan Zhao, Joseph K. Leader, Jing Wang, Xin Meng, James Herman, David Wilson, Jiantao Pu

    Objective: This study aims to investigate the association between the arteries and veins surrounding a pulmonary nodule and its malignancy. Methods: A dataset of 146 subjects from a LDCT lung cancer screening program was used in this study. AI algorithms were used to automatically segment and quantify nodules and their surrounding macro-vasculature. The macro-vasculature was differentiated into arteries and veins. Vessel branch count, volume, and tortuosity were quantified for arteries and veins at different distances from the nodule surface. Univariate and multivariate logistic regression (LR) analyses were performed, with a special emphasis on the nodules with diameters ranging from 8 to 20 mm. ROC-AUC was used to assess the performance based on the k-fold cross-validation method. Average feature importance was evaluated in several machine learning models. Results: The LR models using macro-vasculature features achieved an AUC of 0.78 (95% CI: 0.71–0.86) for all nodules and an AUC of 0.67 (95% CI: 0.54–0.80) for nodules between 8–20 mm. Models including macro-vasculature features, demographics, and CT-derived nodule features yielded an AUC of 0.91 (95% CI: 0.87–0.96) for all nodules and an AUC of 0.82 (95% CI: 0.71–0.92) for nodules between 8–20 mm. In terms of feature importance, arteries within 5.0 mm from the nodule surface were the highest-ranked among macro-vasculature features and retained their significance even with the inclusion of demographics and CT-derived nodule features. Conclusions: Arteries within 5.0 mm from the nodule surface emerged as a potential biomarker for effectively discriminating between malignant and benign nodules.


  • Batch-balanced focal loss: a hybrid solution to class imbalance in deep learning

    by Jatin Singh, Cameron Beeche, Zhiyi Shi, Oliver Beale, Boris Rosin, Joseph K. Leader, Jiantao Pu

    PurposeTo validate the effectiveness of an approach called batch-balanced focal loss (BBFL) in enhancing convolutional neural network (CNN) classification performance on imbalanced datasets.Materials and MethodsBBFL combines two strategies to tackle class imbalance: (1) batch-balancing to equalize model learning of class samples and (2) focal loss to add hard-sample importance to the learning gradient. BBFL was validated on two imbalanced fundus image datasets: a binary retinal nerve fiber layer defect (RNFLD) dataset (n = 7,258) and a multiclass glaucoma dataset (n = 7,873). BBFL was compared to several imbalanced learning techniques, including random oversampling (ROS), cost-sensitive learning, and thresholding, based on three state-of-the-art CNNs. Accuracy, F1-score, and the area under the receiver operator characteristic curve (AUC) were used as the performance metrics for binary classification. Mean accuracy and mean F1-score were used for multiclass classification. Confusion matrices, t-distributed neighbor embedding plots, and GradCAM were used for the visual assessment of performance.ResultsIn binary classification of RNFLD, BBFL with InceptionV3 (93.0% accuracy, 84.7% F1, 0.971 AUC) outperformed ROS (92.6% accuracy, 83.7% F1, 0.964 AUC), cost-sensitive learning (92.5% accuracy, 83.8% F1, 0.962 AUC), and thresholding (91.9% accuracy, 83.0% F1, 0.962 AUC) and others. In multiclass classification of glaucoma, BBFL with MobileNetV2 (79.7% accuracy, 69.6% average F1 score) outperformed ROS (76.8% accuracy, 64.7% F1), cost-sensitive learning (78.3% accuracy, 67.8.8% F1), and random undersampling (76.5% accuracy, 66.5% F1).ConclusionThe BBFL-based learning method can improve the performance of a CNN model in both binary and multiclass disease classification when the data are imbalanced.


  • Predicting left/right lung volumes, thoracic cavity volume, and heart volume from subject demographics to improve lung transplant

    by Lucas Pu, Joseph K. Leader, Alaa Ali, Zihan Geng, David O. Wilson

    PurposeLung transplantation is the standard treatment for end-stage lung diseases. A crucial factor affecting its success is size matching between the donor’s lungs and the recipient’s thorax. Computed tomography (CT) scans can accurately determine recipient’s lung size, but donor’s lung size is often unknown due to the absence of medical images. We aim to predict donor’s right/left/total lung volume, thoracic cavity, and heart volume from only subject demographics to improve the accuracy of size matching.ApproachA cohort of 4610 subjects with chest CT scans and basic demographics (i.e., age, gender, race, smoking status, smoking history, weight, and height) was used in this study. The right and left lungs, thoracic cavity, and heart depicted on chest CT scans were automatically segmented using U-Net, and their volumes were computed. Eight machine learning models [i.e., random forest, multivariate linear regression, support vector machine, extreme gradient boosting (XGBoost), multilayer perceptron (MLP), decision tree, k-nearest neighbors, and Bayesian regression) were developed and used to predict the volume measures from subject demographics. The 10-fold cross-validation method was used to evaluate the performances of the prediction models. R-squared (R2), mean absolute error (MAE), and mean absolute percentage error (MAPE) were used as performance metrics.ResultsThe MLP model demonstrated the best performance for predicting the thoracic cavity volume (R2: 0.628, MAE: 0.736 L, MAPE: 10.9%), right lung volume (R2: 0.501, MAE: 0.383 L, MAPE: 13.9%), and left lung volume (R2: 0.507, MAE: 0.365 L, MAPE: 15.2%), and the XGBoost model demonstrated the best performance for predicting the total lung volume (R2: 0.514, MAE: 0.728 L, MAPE: 14.0%) and heart volume (R2: 0.430, MAE: 0.075 L, MAPE: 13.9%).ConclusionsOur results demonstrate the feasibility of predicting lung, heart, and thoracic cavity volumes from subject demographics with superior performance compared with available studies in predicting lung volumes.


  • Open Access

    CT-Derived Body Composition Is a Predictor of Survival after Esophagectomy

    by Kartik Iyer, Cameron A. Beeche, Naciye S. Gezer, Joseph K. Leader, Shangsi Ren, Rajeev Dhupar, Jiantao Pu

    Background: Body composition can be accurately quantified based on computed tomography (CT) and typically reflects an individual’s overall health status. However, there is a dearth of research examining the relationship between body composition and survival following esophagectomy. Methods: We created a cohort consisting of 183 patients who underwent esophagectomy for esophageal cancer without neoadjuvant therapy. The cohort included preoperative PET-CT scans, along with pathologic and clinical data, which were collected prospectively. Radiomic, tumor, PET, and body composition features were automatically extracted from the images. Cox regression models were utilized to identify variables associated with survival. Logistic regression and machine learning models were developed to predict one-, three-, and five-year survival rates. Model performance was evaluated based on the area under the receiver operating characteristics curve (ROC/AUC). To test for the statistical significance of the impact of body composition on survival, body composition features were excluded for the best-performing models, and the DeLong test was used. Results: The one-year survival model contained 10 variables, including three body composition variables (bone mass, bone density, and visceral adipose tissue (VAT) density), and demonstrated an AUC of 0.817 (95% CI: 0.738–0.897). The three-year survival model incorporated 14 variables, including three body composition variables (intermuscular adipose tissue (IMAT) volume, IMAT mass, and bone mass), with an AUC of 0.693 (95% CI: 0.594–0.792). For the five-year survival model, 10 variables were included, of which two were body composition variables (intramuscular adipose tissue (IMAT) volume and visceral adipose tissue (VAT) mass), with an AUC of 0.861 (95% CI: 0.783–0.938). The one- and five-year survival models exhibited significantly inferior performance when body composition features were not incorporated. Conclusions: Body composition features derived from preoperative CT scans should be considered when predicting survival following esophagectomy.


  • Size and Morphology of the Trachea Before and After Lung Volume Reduction Surgery

    by Joseph K. Leader, Robert M. Rogers, Carl R. Fuhrman, Frank C. Sciurba, Bin Zheng, Paul F. Thompson, Joel L. Weissfeld, Sara K. Golla, David Gur

    OBJECTIVE. The purpose of this investigation was to determine the effect of lung volume reduction surgery on measured tracheal features.MATERIALS AND METHODS. Twenty-four male and 19 female patients with emphysema underwent lung volume reduction surgery, pulmonary function testing, and repeated CT. The tracheal air column was segmented from axial images. The sagittal and coronal dimensions of the intrathoracic trachea were determined. Tracheal morphology was quantified using the tracheal (coronal and sagittal dimensions) and circularity indexes. The results were compared with pulmonary function test results.RESULTS. Morphologic appearance of the intrathoracic trachea was consistent before and 3 months after surgery. The group means of the tracheal length, mean area, and volume were 78.60 mm (± 16.88 mm), 283.84 mm2 (± 61.47 mm2), and 22.59 cm3 (± 7.69 cm3), respectively, before surgery and 67.53 mm (± 15.78 mm), 309.12 mm2 (± 79.83 mm2), and 20.99 cm3 (± 7.27 cm3), respectively, after surgery (p < 0.05). ...


  • Mandibular kinematics represented by a non-orthogonal floating axis joint coordinate system

    by Joseph K. Leader, J.RObert Boston, Richard E. Debski, Thomas E. Rudy


  • Relation of jaw sounds and kinematics visualized and quantified using 3-D computer animation

    by Joseph K. Leader, J.RObert Boston, Thomas E. Rudy, Carol M. Greco, Hussein S. Zaki

    The management of jaw pain or temporomandibular disorders (TMD) has been controversial regarding temporomandibular joint (TMJ) sounds and their implication regarding TMD prognosis. 3-D computer animation was used to visualize and quantify the internal mechanics of natural mandibular motion synchronized with TMJ sounds. Mandibular movements of four TMD patients and two healthy subjects were recorded using CCD cameras and reflective markers. Sounds were recorded with electret microphones. Magnetic resonance imaging was used to create 3-D geometric models. Visualization of the internal anatomy, mandibular condyle and glenoid fossa, revealed that the condyle initially rotated within the fossa and then moved out of the fossa along, and well beyond, the articular eminence. Power in the opening sound recordings after the condyle moved out of the fossa was significantly greater than when the condyle was within the fossa (p<0.001). The louder opening sounds were often classified as TMJ clicks, implying that clicks occur after the condyle moves out of the fossa. The 3-D computer animation should help resolve the implication of TMJ sounds regarding TMD prognosis by providing visualization and quantization of the TMJ internal mechanics during sound production.