Prostate cancer is the most common male cancer in the United States, and the third most common worldwide. Prostate biopsies are often performed to confirm a cancer diagnosis and examine suspect tissue. Prostate biopsies are most often performed under transrectal ultrasound imaging (TRUS) guidance. TRUS images in real-time, at relatively low cost, and shows both prostate and boundaries. However, major problems with TRUS imaging are poor spatial resolution and low sensitivity for cancer detection.

Accurate automated organ and disease feature segmentation is a challenge for medical imaging analysis. The pancreas, for example, is a small, soft, organ with low uniformity of shape and volume between patients. Because of the lack of uniform image patterns, there are few features that can be used to aid in automated identification of anatomy and boundaries. Segmentation of high variability features is uniquely difficult for a computer to perform.

Accurate automated organ and disease feature segmentation is a challenge for medical imaging analysis. The pancreas, for example, is a small, soft, organ with low uniformity of shape and volume between patients. Because of the lack of uniform image patterns, there are few features that can be used to aid in automated identification of anatomy and boundaries. Segmentation of high variability features is uniquely difficult for a computer to perform.

Medical image datasets are an important clinical resource. Effectively referencing patient images against similar related images and case histories can inform and produce better treatment outcomes. Labeling and identifying disease features and relations between images within a large image database has not been a task capable of automation. Rather, it is a task that must be performed by highly trained clinicians who can identify and label the medically meaningful image features.

Medical imaging is an important resource for early diagnostic, detection, and effective treatment of cancers. However, the screening and review processes for radiologists have been shown to overlook a certain percentage of potentially cancerous image features. Such review errors may result in misdiagnosis and failure to identify tumors. These errors result from human fallibility, fatigue, and from the complexity of visual search required.

Existing microsphere technologies are used as therapy for certain cancers. The therapy is by way of occlusion, when the microspheres are delivered into blood vessels that feed a tumor. The physical dimensions of the microspheres occlude the blood supply and thus, killing the tumor. Some microspheres have also been modified to bind protein, elute drugs, and reduce inflammatory reactions as part of the therapy. However, one technical short-coming of existing microsphere technology is a limited capability to be visualized in real-time.

Conventional free-hand needle puncture procedures for biopsy and other procedures, often rely on unguided manual movements to guide a needle to its destination. Freehand procedures risk missing the tumor, or accidental injury, such as puncturing a vital organ. Needle guidance systems may improve accuracy and reduce risks but available guidance technologies are cumbersome and expensive and may carry other risks.

Ultrasound-based cancer screening and biopsy imaging technologies are a clinical need. Ultrasound based biopsy imaging can provide a real-time modality for lower cost that is comparable to, or complimentary to MRI imaging.  This technology may enable more accurate, less costly and more accessible cancer screening.

The technology relates to software, systems, and methods for automated medical image segmentation via deep learning. Standard holistically-nested networks (HNNs) used in computer vision and medical imaging for segmentation and edge detection have a problem with coarsening resolution. The described technology addresses this.
 

Multiparametric MRI improves image detail and prostate cancer detection rates compared to standard MRI. Computer aided diagnostics (CAD) used in combination with multiparametric MRI images may further improve prostate cancer detection and visualization. The technology, developed by researchers at the National Institutes of Health Clinical Center (NIHCC), is an automated CAD system for use in processing and visualizing prostate lesions on multiparametric MRI images.