Presstek, Inc.

Art Eye-d Associates LLC

Steven J Frank

Larry Reback

Thomas E Lewis

Karen Martirosyan

Frederick R Kearney

Eugene L Langlais

Accurate tissue segmentation is performed without a priori knowledge of tissue type or other extrinsic information not found within the subject image, and may be combined with classification analysis so that diseased tissue is not only delineated within an image but also characterized in terms of disease type. In various embodiments, a source image is decomposed into smaller overlapping subimages such as square or rectangular tiles. A predictor such as a convolutional neural network produces tile-level classifications that are aggregated to produce a tissue segmentation and, in some embodiments, to classify the source image or a subregion thereof.

Digital tissue segmentation and mapping with concurrent subtyping

Large digital images are classified by analyzing them at a subimage level and assigning classification probabilities to the subimages; these may be combined into a classification probability for the entire image. Classification probabilities may be visualized across the image using probabilities computed for the subimages. This enables ready identification of the image subregions upon which classification is based as well as the classification scores or probabilities associated therewith. For example, a large source image&#x2014;too large to be analyzed directly by a neural network&#x2014;may be decomposed into smaller subimages such as square tiles, which are sifted based on a visual criterion. The visual criterion may be image entropy, density, background percentage, or other discriminator. A neural network produces tile-level classifications that are aggregated to classify the source image, and overlapping tiles are used to create a probability map showing subimage probabilities.

Visualization of subimage classifications

Lithographic imaging using non-ablative printing members combines the benefits of simple construction, the ability to utilize traditional metal base supports, and amenability to imaging with low-power lasers that need not impart ablation-inducing energy levels. A representative printing member has a topmost layer that is ink-receptive and does not significantly absorb imaging radiation, a second layer thereunder that is hydrophilic and does absorb imaging radiation, and a metal substrate under the second layer. The printing member is selectively exposed to laser radiation in an imagewise pattern, and laser energy passes substantially unabsorbed through the first layer and is absorbed by the second layer. Heat builds up in the second layer sufficiently to detach the first layer, which is formulated to resist reattachment. But the first layer and, more significantly, the third layer act to dissipate heat from the second layer to prevent its ablation. Where the printing member has received laser exposure&mdash;that is, where the first and second layers have been detached&mdash;remnants of the first layer are readily removed to produce a finished printing plate.

Lithographic imaging with non-ablative wet printing members

Methods and apparatus for lithographic imaging without ablation function by irreversibly debonding intermediate printing-plate layers, thereby rendering at least the surface layer removable by cleaning to expose, in an imagewise pattern, an underlying layer having a different affinity for ink and/or an abhesive fluid for ink. In contrast to ablation-type systems, it is unnecessary to destroy a plate layer, thereby reducing power requirements and facilitating increased imaging speeds.

Growing community of inventors

Framingham, MA, United States of America

Steven J Frank