Deep Learning Reveals Cancer Metastasis and Therapeutic Antibody Targeting in the Entire Body.

Reliable detection of disseminated tumor cells and of the biodistribution of tumor-targeting therapeutic antibodies within the entire body has long been needed to better understand and treat cancer metastasis. Here, we developed an integrated pipeline for automated quantification of cancer metastases and therapeutic antibody targeting, named DeepMACT. First, we enhanced the fluorescent signal of cancer cells more than 100-fold by applying the vDISCO method to image metastasis in transparent mice. Second, we developed deep learning algorithms for automated quantification of metastases with an accuracy matching human expert manual annotation. Deep learning-based quantification in 5 different metastatic cancer models including breast, lung, and pancreatic cancer with distinct organotropisms allowed us to systematically analyze features such as size, shape, spatial distribution, and the degree to which metastases are targeted by a therapeutic monoclonal antibody in entire mice. DeepMACT can thus considerably improve the discovery of effective antibody-based therapeutics at the pre-clinical stage. VIDEO ABSTRACT.

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

Whole-body imaging of mice is a key source of information for research. Organ segmentation is a prerequisite for quantitative analysis but is a tedious and error-prone task if done manually. Here, we present a deep learning solution called AIMOS that automatically segments major organs (brain, lungs, heart, liver, kidneys, spleen, bladder, stomach, intestine) and the skeleton in less than a second, orders of magnitude faster than prior algorithms. AIMOS matches or exceeds the segmentation quality of state-of-the-art approaches and of human experts. We exemplify direct applicability for biomedical research for localizing cancer metastases. Furthermore, we show that expert annotations are subject to human error and bias. As a consequence, we show that at least two independently created annotations are needed to assess model performance. Importantly, AIMOS addresses the issue of human bias by identifying the regions where humans are most likely to disagree, and thereby localizes and quantifies this uncertainty for improved downstream analysis. In summary, AIMOS is a powerful open-source tool to increase scalability, reduce bias, and foster reproducibility in many areas of biomedical research.

Multiple software based 3D modeling protocol for printing anatomical structures / Protocolo de impresión 3D de estructuras anatómicas basados en la utilización de software múltiple

With the increasing number of medical programs, research for new teaching methods has also emerged. Computer software and diagnostic images have been used for anatomy teaching as an alternative to cadaver dissection, which means students cannot develop a mental image of the human body without compromising spatial reasoning. Also the cadavers present flaws such as color, texture and smell. This paper explains in details the protocol used to reconstruct 3D models for rapid prototyping as an overcome to these difficulties. Online Computerized Tomography scans were obtained in DICOM format from OsiriX and InVesalius. Reconstruction of 3D models from aortic and superior tracheobronchial tract structures were created, InVesalius and Rhinoceros software were used. 3D models of a heart with its aorta, superior tracheobronchial tract and an aneurysm at the aortic bifurcation were obtained for rapid prototyping. The superior tracheobronchial tract model was printed. It is possible to produce printed models from CT scans using different softwares for 3D modeling and rapid prototyping. These models could allow the student to develop a three dimensional mental image of the human body according to literature.

Con el incremento en el número de programas médicos, la búsqueda por nuevos métodos de enseñanza también ha emergido. Software computarizado e imágenes diagnósticas han sido utilizados en la enseñanza de anatomía como una alternativa a la disección cadavérica, lo que conlleva a que los estudiantes no puedan desarrollar una imagen mental del cuerpo humano sin comprometer el raciocinio espacial. También los cadáveres presentan desventajas como color, textura y olor. Este artículo explica en detalle el protocolo usado para la reconstrucción de modelos 3D para prototipado rápido como un recurso para superar estas dificultades. Tomografías computarizadas online fueron obtenidas en formato DICOM de OsiriX e InVesalius. La reconstrucción en 3D de modelos de estructuras aórticas y del ducto traqueobronquial fueron creadas con los software InVesalius y Rhinoceros. Modelos 3D de corazón y aorta, el ducto traqueobronquial y un aneurisma aórtico abdominal en su bifurcación fueron obtenidos para la prototipado rápido. El modelo de ducto traqueobronquial fue impreso. Es posible producir modelos de TC usando diferentes programas de modelado 3D. Estos modelos podrían permitir a los estudiantes desarrollar una imagen metal tridimensional del cuerpo humano según la literatura.