Abstract: A novel system and method for accurate detection and quantification of fibrous tissue produces a virtual medical image of tissue treated with a second stain based on a received medical image of tissue treated with a first stain using a computer-implemented trained deep learning model. The model is trained to learn the deep texture patterns associated with collagen fibers using conditional generative adversarial networks to detect and quantify fibrous tissue.

Abstract: Systems and methods for diagnosing prostate cancer. Image sets (e.g., MRI collected at one or more b-values) and biological values (e.g., prostate specific antigen (PSA)) have features extracted and integrated to produce a diagnosis of prostate cancer. The image sets are analyzed primarily in three steps: (1) segmentation, (2) feature extraction, smoothing, and normalization, and (3) classification. The biological values are analyzed primarily in two steps: (1) feature extraction and (2) classification. Each analysis results in diagnostic probabilities, which are then combined to pass through an additional classification stage. The end result is a more accurate diagnosis of prostate cancer.

Abstract: A computer aided diagnostic system and automated method to classify a kidney utilizes medical image data and clinical biomarkers in evaluation of kidney function pre- and post-transplantation. The system receives image data from a medical scan that includes image data of a kidney, then segments kidney image data from other image data of the medical scan. The kidney is then classified by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.

Abstract: Systems and methods for diagnosing prostate cancer. Image sets (e.g., MRI collected at one or more b-values) and biological values (e.g., prostate specific antigen (PSA)) have features extracted and integrated to produce a diagnosis of prostate cancer. The image sets are analyzed primarily in three steps: (1) segmentation, (2) feature extraction, smoothing, and normalization, and (3) classification. The biological values are analyzed primarily in two steps: (1) feature extraction and (2) classification. Each analysis results in diagnostic probabilities, which are then combined to pass through an additional classification stage. The end result is a more accurate diagnosis of prostate cancer.

Abstract: A system and computation method is disclosed that identifies radiation-induced lung injury after radiation therapy using 4D computed tomography (CT) scans. After deformable image registration, the method segments lung fields, extracts functional and textural features, and classifies lung tissues. The deformable registration locally aligns consecutive phases of the respiratory cycle using gradient descent minimization of the conventional dissimilarity metric. Then an adaptive shape prior, a first-order intensity model, and a second-order lung tissues homogeneity descriptor are integrated to segment the lung fields. In addition to common lung functionality features, such as ventilation and elasticity, specific regional textural features are estimated by modeling the segmented images as samples of a novel 7th-order contrast-offset-invariant Markov-Gibbs random field (MGRF). Finally, a tissue classifier is applied to distinguish between the injured and normal lung tissues.

Abstract: Systems and methods for diagnosing prostate cancer. Image sets (e.g., MRI collected at one or more b-values) and biological values (e.g., prostate specific antigen (PSA)) have features extracted and integrated to produce a diagnosis of prostate cancer. The image sets are analyzed primarily in three steps: (1) segmentation, (2) feature extraction, smoothing, and normalization, and (3) classification. The biological values are analyzed primarily in two steps: (1) feature extraction and (2) classification. Each analysis results in diagnostic probabilities, which are then combined to pass through an additional classification stage. The end result is a more accurate diagnosis of prostate cancer.

Abstract: A computer aided diagnostic system and automated method to classify a kidney. Image data for a medical scan that includes image data of a kidney may be received. The kidney image data may be segmented from other image data of the medical scan. One or more iso-contours may be registered for the kidney image data, and renal cortex image data may be segmented from the kidney image data based on the one or more registered iso-contours. The kidney may be classified by analyzing one or more features determined from the segmented renal cortex image data using a learned model associated with the one or more features.

Abstract: A computer aided diagnostic system and automated method to classify a kidney utilizes medical image data and clinical biomarkers in evaluation of kidney function pre- and post-transplantation. The system receives image data from a medical scan that includes image data of a kidney, then segments kidney image data from other image data of the medical scan. The kidney is then classified by analyzing at least one feature determined from the kidney image data and the at least one clinical biomarker.

Abstract: A computer aided diagnostic system and automated method to classify a kidney. Image data for a medical scan that includes image data of a kidney may be received. The kidney image data may be segmented from other image data of the medical scan. One or more iso-contours may be registered for the kidney image data, and renal cortex image data may be segmented from the kidney image data based on the one or more registered iso-contours. The kidney may be classified by analyzing one or more features determined from the segmented renal cortex image data using a learned model associated with the one or more features.

Abstract: A computer aided diagnostic system and automated method to classify a kidney. Image data for a medical scan that includes image data of a kidney may be received. The kidney image data may be segmented from other image data of the medical scan. One or more iso-contours may be registered for the kidney image data, and renal cortex image data may be segmented from the kidney image data based on the one or more registered iso-contours. The kidney may be classified by analyzing one or more features determined from the segmented renal cortex image data using a learned model associated with the one or more features.

Abstract: A system and computation method is disclosed that identifies radiation-induced lung injury after radiation therapy using 4D computed tomography (CT) scans. After deformable image registration, the method segments lung fields, extracts functional and textural features, and classifies lung tissues. The deformable registration locally aligns consecutive phases of the respiratory cycle using gradient descent minimization of the conventional dissimilarity metric. Then an adaptive shape prior, a first-order intensity model, and a second-order lung tissues homogeneity descriptor are integrated to segment the lung fields. In addition to common lung functionality features, such as ventilation and elasticity, specific regional textural features are estimated by modeling the segmented images as samples of a novel 7th-order contrast-offset-invariant Markov-Gibbs random field (MGRF). Finally, a tissue classifier is applied to distinguish between the injured and normal lung tissues.

Abstract: A computer aided diagnostic system and automated method to classify a kidney. Image data for a medical scan that includes image data of a kidney may be received. The kidney image data may be segmented from other image data of the medical scan. One or more iso-contours may be registered for the kidney image data, and renal cortex image data may be segmented from the kidney image data based on the one or more registered iso-contours. The kidney may be classified by analyzing one or more features determined from the segmented renal cortex image data using a learned model associated with the one or more features.