Radiomics and Deep Features: Robust Classification of Brain Hemorrhages and Reproducibility Analysis Using a 3D Autoencoder Neural Network.

This study evaluates the reproducibility of machine learning models that integrate radiomics and deep features (features extracted from a 3D autoencoder neural network) to classify various brain hemorrhages effectively. Using a dataset of 720 patients, we extracted 215 radiomics features (RFs) and 15,680 deep features (DFs) from CT brain images. With rigorous screening based on Intraclass Correlation Coefficient thresholds (>0.75), we identified 135 RFs and 1054 DFs for analysis. Feature selection techniques such as Boruta, Recursive Feature Elimination (RFE), XGBoost, and ExtraTreesClassifier were utilized alongside 11 classifiers, including AdaBoost, CatBoost, Decision Trees, LightGBM, Logistic Regression, Naive Bayes, Neural Networks, Random Forest, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN). Evaluation metrics included Area Under the Curve (AUC), Accuracy (ACC), Sensitivity (SEN), and F1-score. The model evaluation involved hyperparameter optimization, a 70:30 train-test split, and bootstrapping, further validated with the Wilcoxon signed-rank test and q-values. Notably, DFs showed higher accuracy. In the case of RFs, the Boruta + SVM combination emerged as the optimal model for AUC, ACC, and SEN, while XGBoost + Random Forest excelled in F1-score. Specifically, RFs achieved AUC, ACC, SEN, and F1-scores of 0.89, 0.85, 0.82, and 0.80, respectively. Among DFs, the ExtraTreesClassifier + Naive Bayes combination demonstrated remarkable performance, attaining an AUC of 0.96, ACC of 0.93, SEN of 0.92, and an F1-score of 0.92. Distinguished models in the RF category included SVM with Boruta, Logistic Regression with XGBoost, SVM with ExtraTreesClassifier, CatBoost with XGBoost, and Random Forest with XGBoost, each yielding significant q-values of 42. In the DFs realm, ExtraTreesClassifier + Naive Bayes, ExtraTreesClassifier + Random Forest, and Boruta + k-NN exhibited robustness, with 43, 43, and 41 significant q-values, respectively. This investigation underscores the potential of synergizing DFs with machine learning models to serve as valuable screening tools, thereby enhancing the interpretation of head CT scans for patients with brain hemorrhages.

Bone Scan With Pulmonary Uptake in Scleroderma.

ABSTRACT: We present a 61-year-old woman with a history of scleroderma and suspicion of osteomyelitis in her left wrist. She underwent a 3-phase bone scan for evaluation of osteomyelitis. Incidentally, the scan showed bilateral pulmonary MDP uptake, especially in lower lobes, which was proven to be due to the nonfibrotic form of nonspecific interstitial pneumonia.

Ectopic intrathyroidal thymic tissue in an adult patient: a case report and review of the literature.

BACKGROUND: Ectopic intrathyroidal thymic tissue is a rare diagnosis, specifically in adults. Such ectopic tissue is usually misdiagnosed as benign or malignant thyroid lesions and is mainly investigated by ultrasonography and pathologic examination. CASE PRESENTATION: We present the case of an adult 31-year-old Persian female patient with a cervical mass and no other significant medical history. The lesion had hypo- to isoechoic features on sonographic imaging, and needle aspiration examination revealed lymphoid cells suspicious of lymphoid malignancies. However, pathologic examination after resection of the lesion showed normal thymic tissue. CONCLUSIONS: The rare entity of ectopic thymic tissue within the thyroid gland in adult patients requires meticulous examination by clinicians, radiologists, and pathologists to diagnose the condition with high accuracy and plan appropriate management.

Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT.

The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID-) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis.

Primary skeletal muscle lymphoma with unusual soft tissue metastases in the stomach and pancreas detected by 18F-FDG PET/CT.

A 69 y/o woman with a history of primary diffuse large B cell lymphoma in the right thigh muscle was referred for recurrence evaluation with 18F-FDG PET/CT. After routine courses of chemoradiation, MRI was done in order to evaluate treatment response with inconclusive findings. 18FDG PET/CT revealed abnormal uptake in the primary site of the disease as well as secondary involvement of stomach, pancreas, pelvic lymph nodes, and both tibiae. Our case showed the importance of 18F-FDG PET/CT in the detection of unusual soft tissue extension of lymphoma.

99mTc-DMSA Scintigraphy Revealed A Unilateral Multicystic Anomaly In A Horseshoe Kidney.

The multicystic dysplastic pattern in a half of a horseshoe kidney is a very uncommon presentation. We present a 6-month-old male infant with a history of antenatally unilateral cystic abnormality in the right kidney which was reevaluated after birth by ultrasonography (US) and 99m Tc-DMSA scintigraphy. The US showed a horseshoe kidney with the multicystic dysplastic area on the right side, which proved to be non-functional on 99m Tc-DMSA scintigraphy.