# US 2018/0025210 A1 · Method and system for analyzing biological specimens by spectral imaging > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0025210 A1 - Document ID: US20180025210A1 - Status: Published application - Kind: A1 - Application number: 15/707,499 - Filed: 2017-09-18 - Published: 2018-01-25 - Earliest claimed: 2012-10-05 - Applicants: Cireca Theranostics, LLC - Inventors: Stanley H. REMISZEWSKI; Clay M. THOMPSON; Max DIEM; Aysegul ERGIN - Web page: https://patentgrep.com/patent/US20180025210A1 ## CPC - G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06V 30/1916: {Validation; Performance evaluation} - G06V 30/248: {involving plural approaches, e.g. verification by template match; Resolving confusion among similar patterns, e.g. "O" versus "Q" (G06V30/242 takes precedence)} - G06F 18/231: Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The methods, devices, and systems may allow a practitioner to obtain information regarding a biological sample, including analytical data, a medical diagnosis, and/or a prognosis or predictive analysis. The method, devices, and systems may provide a grade or level of development for identified diseases. In addition, the methods, devices and systems may generate a confidence value for the predictive classifications generated, which may, for example be generated in a format to show such confidence value or other feature in a graphical representation (e.g., a color code). Further, the methods, devices and system may aid in the identification and discovery of new classes and tissue sub-types. ## Claims ### Claim 1 A method for classifying a biological sample, the method comprising: receiving, at a system, a spectral image of a biological sample; applying a heuristic to the spectral image to identify one or more regions in the biological sample for isolated testing or analysis; identifying at least one region of interest in the spectral image based on the applied heuristic for micro-dissection of the biological sample to perform the isolated testing or analysis; and aiding in a harvesting of the at least one region of interest of the biological sample. ### Claim 2 (depends on 1) The method of claim 1, wherein the spectral image includes one or more selected from a group consisting of a prediction image, a true image, a confidence prediction image, a confidence image, an infrared (IR) wavelength image, an image generated by binning the image data thereby reducing the number of pixels, a hierarchical cluster analysis (HCA) image, and a cluster image. ### Claim 3 (depends on 1) The method of claim 1, wherein the at least one region of interest includes one or more selected from a group consisting of a region with a low confidence level, a region with multiple attributes, a region classified by a particular type of tissue, a labeled region, a region selected by variation reduction, a region classified with a particular disease or condition, and clinical data associated with the biological sample. ### Claim 4 (depends on 1) The method of claim 1, wherein the isolated testing or analysis includes one or more selected from a group consisting of gene expression analysis, gene sequencing, molecular analysis, and targeted therapies for a patient. ### Claim 5 (depends on 1) The method of claim 1, further comprising: performing the isolated testing or analysis on the harvested at least one region of interest of the biological sample, wherein the isolated testing or analysis is used to make one or more of a diagnosis, prognosis, and predictive decision. ### Claim 6 (depends on 1) The method of claim 1, wherein the at least one region of interest is automatically selected for removal by the system. ### Claim 7 (depends on 1) The method of claim 1, wherein the at least one region of interest is manually selected by a user for removal. ### Claim 8 (depends on 1) The method of claim 1, wherein aiding in the harvesting of the at least one region of interest of the biological sample further comprises: directing an automated tool to remove the at least one region of interest from the biological sample. ### Claim 9 (depends on 8) The method of claim 8, wherein the automated tool comprises a laser or other milling apparatus. ### Claim 10 A system for classifying a biological sample, comprising: a memory in communication with a processor, wherein the memory and the processor are cooperatively configured to: receive a spectral image of a biological sample; apply a heuristic to the spectral image to identify one or more regions in the biological sample for isolated testing or analysis; identify at least one region of interest in the spectral image based on the applied heuristic for micro-dissection of the biological sample to perform the isolated testing or analysis; and aid in a harvesting of the at least one region of interest of the biological sample. ### Claim 11 (depends on 10) The system of claim 10, wherein the spectral image includes one or more selected from a group consisting of a prediction image, a true image, a confidence prediction image, a confidence image, an infrared (IR) wavelength image, an image generated by binning the image data thereby reducing the number of pixels, a hierarchical cluster analysis (HCA) image, and a cluster image. ### Claim 12 (depends on 10) The system of claim 10, wherein the at least one region of interest includes one or more selected from a group consisting of a region with a low confidence level, a region with multiple attributes, a region classified by a particular type of tissue, a labeled region, a region selected by variation reduction, a region classified with a particular disease or condition, and clinical data associated with the biological sample. ### Claim 13 (depends on 10) The system of claim 10, wherein the isolated testing or analysis includes one or more selected from a group consisting of gene expression analysis, gene sequencing, molecular analysis, and targeted therapies for a patient. ### Claim 14 (depends on 10) The system of claim 10, wherein the memory and processor are further configured to: perform the isolated testing or analysis on the harvested at least one region of interest of the biological sample, wherein the isolated testing or analysis is used to make one or more of a diagnosis, prognosis, and predictive decision. ### Claim 15 (depends on 10) The system of claim 10, wherein the at least one region of interest is automatically selected for removal by the system. ### Claim 16 (depends on 10) The system of claim 10, wherein the at least one region of interest is manually selected by a user for removal. ### Claim 17 (depends on 10) The system of claim 10, wherein the memory and processor are further configured to aid in the harvesting of the at least one region of interest of the biological sample by directing an automated tool to remove the at least one region of interest from the biological sample. ### Claim 18 (depends on 17) The system of claim 17, wherein the automated tool comprises a laser or other milling apparatus. ### Claim 19 A computer-readable medium storing instructions executable by a computer device, comprising: at least one instruction for causing the computer device to receive a spectral image of a biological sample; at least one instruction for causing the computer device to apply a heuristic to the spectral image to identify one or more regions in the biological sample for isolated testing or analysis; at least one instruction for causing the computer device to identify at least one region of interest in the spectral image based on the applied heuristic for micro-dissection of the biological sample to perform the isolated testing or analysis; and at least one instruction for causing the computer device to aid in a harvesting of the at least one region of interest of the biological sample.