WO2010027761A1 - Spectral signature extraction for drug verification and identification - Google Patents
Spectral signature extraction for drug verification and identification Download PDFInfo
- Publication number
- WO2010027761A1 WO2010027761A1 PCT/US2009/054836 US2009054836W WO2010027761A1 WO 2010027761 A1 WO2010027761 A1 WO 2010027761A1 US 2009054836 W US2009054836 W US 2009054836W WO 2010027761 A1 WO2010027761 A1 WO 2010027761A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- spectrum
- pharmaceutical
- spectrometer
- acquired spectrum
- acquired
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H70/00—ICT specially adapted for the handling or processing of medical references
- G16H70/40—ICT specially adapted for the handling or processing of medical references relating to drugs, e.g. their side effects or intended usage
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
Definitions
- Embodiments of the present invention relate generally to systems and methods of signature extraction applied to the identification and verification of pharmaceuticals. More specifically, embodiments of the present invention relate to an intelligent computational system that extracts signatures from the spectra of pharmaceuticals contained in a vial using methods of signal processing and spectral analysis. BACKGROUND INFORMATION
- U.S. Patent No. 7,218,395 (the "395 patent") to Stephen T. Kaye et al, which is incorporated herein by reference in its entirety, describes a rapid pharmaceutical identification system.
- a Raman spectrometer measures the spectrum of a pharmaceutical in a vial, with no need of opening the vial cap.
- the collected spectrum is matched against a database that contains a plurality of spectral signatures corresponding to known pharmaceuticals. Based on the matching results, the system validates whether the vial contains the pharmaceutical consistent with the prescription (i.e., a scanned barcode).
- the ⁇ 395 patent has a detailed description of a sensor and system framework, and a brief description of the algorithmic methods of matching the collected spectrum to the spectral signature database. For example, the ⁇ 395 patent lists several algorithms used to achieve this match including a correlation search and a first derivative search. The "395 patent also explains that the sensor identifies the tablets with the spectra in database that correlates with the best match.
- systems and methods are used to acquire a spectrum and extract a signature of a pharmaceutical from the acquired spectrum, with the challenges above addressed.
- These systems and methods integrate a set of algorithms related to signal processing and spectral analysis.
- One method includes five software modules: a spectrum acquisition module, a system-response correction module, an exposure-time normalization module, a baseline correction module, and an extraction collection module.
- a spectrum acquired by a spectrometer is obtained by the spectrum acquisition module and sent to the system-response correction module.
- Every instrument has its own system-response function and the output signal (i.e., the acquired spectrum) is a convolution of an input signal (i.e., the actual spectrum) and the system-response function.
- the system-response function can be characterized by a Raman spectrum obtained from a National Institute of Standards and Technology (NIST) standard glass material.
- the objective of the system-response correction module is to recover the actual spectrum by reversing the effects of convolution.
- the exposure-time normalization module is used to normalize an intensity of the acquired spectrum to a predetermined scale.
- pharmaceuticals are exposed to the laser (transmitted by the spectrometer) for a variable time length ranging from 50ms to 20s, for example. It is known that the intensity of the acquired spectrum is linearly proportional to the exposure time. The variations due to the exposure times have to be normalized to a certain standard, in order to quantify the spectrum strength of a pharmaceutical.
- the baseline correction module is used remove fluorescence from the spectrum.
- a Raman spectrum has a few sharp peaks and a flat baseline, while a fluorescence spectrum is relatively smooth with a sloped or curved baseline. Based on these observations, methods have been designed to separate a Raman spectrum and fluorescence spectrum by fitting a baseline to the mixed spectrum.
- the baseline corresponds to the fluorescence spectrum, and the residual of subtracting the baseline corresponds to the Raman spectrum.
- the extraction collection module is used to obtain the extracted signature of the pharmaceutical from the remainder of the acquired spectrum. If, however, the acquired spectrum of the pharmaceutical is measured by the spectrometer through a container holding the pharmaceutical, the remainder of the acquired spectrum includes the spectrum of the pharmaceutical and the spectrum of the container. The latter can be measured through lab experiments. Therefore, it is important to determine the proportion of two spectra in the linear mix. Several methods can be used to extract the pharmaceutical spectrum from the mixed spectrum.
- Figure 1 is a schematic diagram of a system for signature extraction, in accordance with an embodiment of the present invention.
- Figure 2 is a flowchart showing a method for signature extraction, in accordance with an embodiment of the present invention.
- Figure 3 is a schematic diagram of a software system for signature extraction, in accordance with an embodiment of the present invention.
- Figure 4 is an exemplary plot showing a theoretical NIST spectrum and the actual measured spectrum of a first instrument and the actual measured spectrum of a second instrument, in accordance with an embodiment of the present invention.
- Figure 5 is an exemplary plot showing the acquired spectrum of Lithium
- FIG. 6 is an exemplary plot showing the extracted signature of Lithium
- FIG. 7 is a flowchart showing a method for signature extraction using a software system, in accordance with an embodiment of the present invention.
- Spectral signature extraction is an important component of a pharmaceutical identification and verification system, such as the system described in the ⁇ 395 patent.
- a system of the '395 patent uses a static multimode multiplex spectrometer (MMS).
- MMS static multimode multiplex spectrometer
- 2D coded aperture static MMS is described in U.S. Patent Application No. 11/334,546 (the '"546 application"), filed January 19, 2006 now U.S. Patent No. 7,301,625 (the '"625 patent).
- the spectrum acquired by a spectrometer is actually a superposition of several components. This superposition can occur for a number of reasons. For example, in Raman spectroscopy, it is sometimes the case that spectra can be contaminated by fluorescence. Also, if the spectrometer reads though a vial, it is likely that the spectrometer will receive scattering from the vial material. Therefore, in Raman spectroscopy, it is possible that the acquired spectrum is a superposition of the pharmaceutical Raman spectrum, the pharmaceutical fluorescence spectrum, the vial Raman spectrum, and the vial fluorescence spectrum. Among these spectra, only the pharmaceutical Raman spectrum is the signature that distinguishes a pharmaceutical from others. The pharmaceutical fluorescence spectrum could change, but not the Raman spectrum. As a result, in various embodiments, the pharmaceutical Raman spectrum is extracted from the acquired spectrum before applying matching algorithms. The extraction of the pharmaceutical Raman spectrum is called signature extraction.
- systems and methods perform signature extraction from the spectrum of a pharmaceutical through an open or closed vial for pharmaceutical verification and identification.
- a signature is the collection of features that characterize an object and its behavior. It can be directly measurable or it can be extracted from a measured signal, depending on the specific applications and signal characteristics.
- a signature refers to the unique spectrum a pharmaceutical emits when it is exposed to a laser with a certain wavelength.
- a pharmaceutical or a particular strength of a pharmaceutical can be verified by matching its signature against a database that contains spectral signatures corresponding to known pharmaceuticals or strengths of pharmaceuticals.
- the spectrum captured by the spectrometer is actually a superposition of multiple spectra, as discussed above. Therefore, it is important to extract the signature (i.e., the pharmaceutical spectrum) before implementing the matching algorithms.
- FIG. 1 is a schematic diagram of a system 100 for signature extraction, in accordance with an embodiment of the present invention.
- System 100 includes spectrometer 110 and processor 120.
- Processor 120 is in communication with spectrometer 110. This communication can include, but is not limited to, wired or wireless data communication.
- Spectrometer 110 includes laser 115, for example.
- Spectrometer 110 can include, but is not limited to, a Raman spectrometer, an MMS, a 2D coded aperture static MMS and/or a FTIR spectrometer.
- Processor 120 can include, but is not limited to, a computer, a microprocessor, an application specific integrated circuit, a field programmable gate array (FPGA), or any device capable of executing a series of instructions.
- FPGA field programmable gate array
- Spectrometer 110 of system 100 acquires a spectrum of pharmaceutical
- spectrometer 110 can also acquire a spectrum of pharmaceutical 130 and container 140 through a side of container 140, or spectrometer 110 can acquire a spectrum of pharmaceutical 130 and lid 150 through the top of container 140. In various embodiments and alternatively spectrometer 110 can acquire a spectrum of pharmaceutical 130 without the spectrum of container 140 by illuminating pharmaceutical 130 through the top of container 140 without lid 150, for example.
- Pharmaceutical 130 can include, but is not limited to, a medication or a controlled substance.
- Pharmaceutical 130 is shown in system 100 as a pharmaceutical solid.
- a pharmaceutical solid is, for example, a pill.
- a pill can include, but is not limited to, a tablet, a caplet, a suppository, a gelcap, or a capsule.
- pharmaceutical 130 can also include a liquid or a powder, for example.
- Container 140 is shown as a prescription vial.
- container 140 can also include a bottle, blister pack, Intravenous bags, syringes, cuvettes or trays, for example.
- Processor 120 receives the acquired spectrum from spectrometer 110.
- Processor 120 removes a system-response function of spectrometer 110 from the acquired spectrum. For example, processor 120 removes a system-response function of spectrometer 110 by reversing a convolution of the acquired spectrum and the system-response function of spectrometer 110.
- Processor 120 normalizes an intensity of the acquired spectrum to a predetermined scale. For example, processor 120 normalizes an intensity of the acquired spectrum to a predetermined scale by dividing the intensity by an exposure time of spectrometer 110 to pharmaceutical 130 normalized to the predetermined scale.
- Processor 120 removes fluorescence from the acquired spectrum.
- the fluorescence from the acquired spectrum can include fluorescence from container 140.
- Processor 120 removes fluorescence from the acquired spectrum by fitting a baseline spectrum of the fluorescence to the acquired spectrum and removing the baseline spectrum from the acquired spectrum. Fitting a baseline spectrum of the fluorescence to the acquired spectrum can include, but is not limited to, applying a line algorithm, a horizontal algorithm, a peak detection algorithm, or a linear least squares regression algorithm.
- processor 120 obtains an extracted signature of pharmaceutical
- processor 120 additionally removes a spectrum of container 140 from the remainder of the acquired spectrum to obtain the extracted signature of pharmaceutical 130. Additionally removing a spectrum of container 140 from the remainder of the acquired spectrum to produce the extracted signature of pharmaceutical 130 can include, but is not limited to, applying an optimization algorithm, a principal component analysis algorithm, a blind source separation algorithm, a Fourier-domain analysis algorithm, or a wavelet-domain analysis algorithm. Determining a spectrum of container 140 can also include acquiring a spectrum of empty container 140, removing a system- response function of the spectrometer from the acquired spectrum, normalizing the intensity of the acquired spectrum, and obtaining the spectrum of container 140 from the remainder of the acquired spectrum.
- processor 120 can remove the spectrum of a known compound in pharmaceutical 130 in a fashion similar to the removal of the spectrum of container 140. For example, if pharmaceutical 130 includes a known compound, processor 120 additionally removes a spectrum of the known compound from the remainder of the acquired spectrum to obtain the extracted signature of pharmaceutical 130. Additionally removing a spectrum of the known compound from the remainder of the acquired spectrum to produce the extracted signature of pharmaceutical 130 can include, but is not limited to, applying an optimization algorithm, a principal component analysis algorithm, a blind source separation algorithm, a Fourier-domain analysis algorithm, or a wavelet-domain analysis algorithm.
- FIG. 2 is a flowchart showing a method 200 for signature extraction, in accordance with an embodiment of the present invention.
- step 210 of method 200 an acquired spectrum of a pharmaceutical is measured using a spectrometer.
- step 220 the acquired spectrum is obtained from the spectrometer using a processor.
- step 230 a system-response function of the spectrometer is removed from the acquired spectrum using the processor.
- step 240 an intensity of the acquired spectrum is normalized to a predetermined scale using the processor.
- step 250 fluorescence is removed from the acquired spectrum using the processor.
- step 260 an extracted signature of the pharmaceutical is obtained from a remainder of the acquired spectrum using the processor.
- a spectrum of the container is removed from the remainder of the acquired spectrum to produce the extracted signature of the pharmaceutical using the processor.
- a spectrum of the known compound is removed from the remainder of the acquired spectrum to produce the extracted signature of the pharmaceutical using the processor.
- FIG. 3 is a schematic diagram of a software system 300 for signature extraction, in accordance with an embodiment of the present invention.
- System 300 includes distinct software modules embodied on a computer-readable medium, for example.
- the distinct software modules include a spectrum acquisition module 310, a system-response correction module 320, an exposure- time normalization module 330, a baseline correction module 340, and an extraction collection module 350.
- Spectrum acquisition module 310 is used to obtain an acquired spectrum of a pharmaceutical from a spectrometer.
- Spectrum acquisition module 310 can, for example, read data from the spectrometer or receive data from the spectrometer.
- System-response correction module 320 is used to remove a system- response function of the spectrometer from the acquired spectrum.
- System- response correction module 320 can use a National Institute of Standards and Technology (NIST) standard correction method, for example.
- NIST National Institute of Standards and Technology
- the NIST standard refers to a NIST glass reference material whose luminescence spectrum is calibrated.
- Figure 4 is an exemplary plot 400 showing a theoretical NIST spectrum
- the response curve of an ideal Raman spectrometer is close to the sloped straight line of theoretical NIST spectrum 410.
- the actual response curve of a real instrument is a concave curve such as spectrum 420 of the first spectrometer and spectrum 430 of the second spectrometer.
- the ratio of the ideal response curve to the actual response curve at every wavelength is stored by system-response correction module 320 as a vector of correction coefficients, for example.
- the measured pharmaceutical spectrum is multiplied (element-by-element) by the vector of correction coefficients such that the distortion effect of the system-response function is reversed.
- Exposure-time normalization module 330 is used to normalize an intensity of the acquired spectrum to a predetermined scale.
- the exposure time of the spectrometer to the pharmaceutical is a parameter that is used by exposure-time normalization module 330. It is pharmaceutical-specific.
- the acquired spectrum is divided by the corresponding exposure time, such that it is normalized to a predetermined scale. This scale is, for example, a one second scale.
- Baseline correction module 340 is used to remove fluorescence from the acquired spectrum.
- Baseline correction module 340 can use, but is not limited to, techniques that include an optimization algorithm, a line algorithm, a horizontal algorithm, a peak detection algorithm, or a linear least squares regression algorithm.
- the problem of baseline correction is modeled as a constrained optimization problem.
- a constrained optimization problem involves, for example, finding a curve that doesn't exceed any point on the spectrum and has the minimal distance from the spectrum.
- the constraint condition is relaxed, as the curve can go above the spectrum to a certain distance, which corresponds to the noise level. The distance is estimated by dividing the spectrum into many small segments and taking the minimal standard derivation of the intensity over all segments.
- Extraction collection module 350 is used to obtain the extracted signature of the pharmaceutical from the remainder of the acquired spectrum. It is important to note that only the middle range of the acquired spectrum is used by extraction collection module 350 and all of the other modules of software system 300. Relatively large distortions appear at the edge of the detector of a Raman spectrometer. That leads to signification measurement errors in the acquired spectrum's head and tail parts.
- a container subtraction module is added to software system 300.
- the container subtraction module is used to remove a spectrum of the container from the remainder of the acquired spectrum.
- Extraction collection module 350 then obtains the extracted signature of the pharmaceutical from the remainder of the acquired spectrum.
- X X P + aX r , where X p is the pharmaceutical Raman spectrum, X v is the vial Raman spectrum,
- the task is to recover X p with a
- a few methods developed in the fields of signal processing and pattern recognition can be used for vial subtraction, such as optimization, principle component analysis (PCA), blind source separation, Fourier-domain analysis, or wavelet-domain analysis.
- PCA principle component analysis
- an optimization method can be used for vial subtraction, for example.
- An iterative optimization algorithm includes the following steps:
- a pharmaceutical composition can include multiple compounds.
- X p is a superposition of the spectra of the
- FIG. 5 is an exemplary plot 500 showing the acquired spectrum 510 of
- FIG. 6 is an exemplary plot 600 showing the extracted signature 610 of
- FIG. 7 is a flowchart showing a method 700 for signature extraction using a software system, in accordance with an embodiment of the present invention.
- a system is provided that includes distinct software modules embodied on a computer-readable medium.
- the distinct software modules include a spectrum acquisition module, a system-response correction module, an exposure-time normalization module, a baseline correction module, and an extraction collection module.
- an acquired spectrum of a pharmaceutical is obtained from a spectrometer using the spectrum acquisition module.
- step 730 a system-response function of the spectrometer is removed from the acquired spectrum using the system-response correction module.
- step 740 an intensity of the acquired spectrum is normalized to a predetermined scale using the exposure-time normalization module.
- step 750 fluorescence is removed from the acquired spectrum using the baseline correction module.
- step 760 an extracted signature of the pharmaceutical is obtained from the remainder of the acquired spectrum using the extraction collection module.
- a container subtraction module is added the system. The container subtraction module is used to remove a spectrum of the container from the remainder of the acquired spectrum.
- the extraction collection module then obtains the extracted signature of the pharmaceutical from the remainder of the acquired spectrum.
- a compound subtraction module is added the system.
- the compound subtraction module is used to remove a spectrum of the known compound from the remainder of the acquired spectrum.
- the extraction collection module then obtains the extracted signature of the pharmaceutical from the remainder of the acquired spectrum.
- a computer-readable medium can be a device that stores digital information.
- a computer-readable medium includes a read-only memory (e.g., a Compact Disc-ROM ("CD-ROM”) as is known in the art for storing software.
- CD-ROM Compact Disc-ROM
- the computer-readable medium can be accessed by a processor suitable for executing instructions or program code adapted to be executed.
- instructions configured to be executed are meant to encompass any instructions that are ready to be executed in their present form (e.g., machine code) by a processor, or require further manipulation (e.g., compilation, decryption, or provided with an access code, etc.) to be ready to be executed by a processor.
- program code adapted to be executed or require further manipulation (e.g., compilation, decryption, or provided with an access code, etc.) to be ready to be executed by a processor.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011525133A JP2012500994A (en) | 2008-08-25 | 2009-08-25 | Spectral feature extraction for drug verification and identification |
CA2736385A CA2736385A1 (en) | 2008-08-25 | 2009-08-25 | Spectral signature extraction for drug verification and identification |
EP09811997A EP2316013A1 (en) | 2008-08-25 | 2009-08-25 | Spectral signature extraction for drug verification and identification |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US9172208P | 2008-08-25 | 2008-08-25 | |
US61/091,722 | 2008-08-25 | ||
US12/545,368 US8417540B2 (en) | 2005-01-19 | 2009-08-21 | Spectral signature extraction for drug verification and identification |
US12/545,368 | 2009-08-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010027761A1 true WO2010027761A1 (en) | 2010-03-11 |
Family
ID=41797417
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2009/054836 WO2010027761A1 (en) | 2008-08-25 | 2009-08-25 | Spectral signature extraction for drug verification and identification |
Country Status (5)
Country | Link |
---|---|
US (1) | US8417540B2 (en) |
EP (1) | EP2316013A1 (en) |
JP (1) | JP2012500994A (en) |
CA (1) | CA2736385A1 (en) |
WO (1) | WO2010027761A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101423988B1 (en) * | 2012-12-13 | 2014-08-01 | 광주과학기술원 | Quantitative analysis method for mesuring element in sample using laser plasma spectrum |
US9665689B2 (en) | 2013-05-17 | 2017-05-30 | Viavi Solutions Inc. | Medication assurance system and method |
US10467586B2 (en) | 2017-03-23 | 2019-11-05 | International Business Machines Corporation | Blockchain ledgers of material spectral signatures for supply chain integrity management |
JP7374425B2 (en) * | 2018-11-17 | 2023-11-07 | 圭 森山 | Drug identification equipment and methods |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5850623A (en) * | 1997-03-14 | 1998-12-15 | Eastman Chemical Company | Method for standardizing raman spectrometers to obtain stable and transferable calibrations |
US20070008523A1 (en) * | 2003-04-16 | 2007-01-11 | Kaye Stephen T | Rapid pharmaceutical identification and verification system |
US20080059240A1 (en) * | 2003-04-16 | 2008-03-06 | Prasant Potuluri | Pharmaceutical verification network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2309253A2 (en) * | 2001-09-05 | 2011-04-13 | Life Technologies Corporation | Apparatus for reading signals generated from resonance light scattered particle labels |
US6771369B2 (en) * | 2002-03-12 | 2004-08-03 | Analytical Spectral Devices, Inc. | System and method for pharmacy validation and inspection |
US20070059356A1 (en) * | 2002-05-31 | 2007-03-15 | Almarsson Oern | Pharmaceutical co-crystal compositions of drugs such as carbamazepine, celecoxib, olanzapine, itraconazole, topiramate, modafinil, 5-fluorouracil, hydrochlorothiazide, acetaminophen, aspirin, flurbiprofen, phenytoin and ibuprofen |
-
2009
- 2009-08-21 US US12/545,368 patent/US8417540B2/en not_active Expired - Fee Related
- 2009-08-25 JP JP2011525133A patent/JP2012500994A/en active Pending
- 2009-08-25 WO PCT/US2009/054836 patent/WO2010027761A1/en active Application Filing
- 2009-08-25 CA CA2736385A patent/CA2736385A1/en not_active Abandoned
- 2009-08-25 EP EP09811997A patent/EP2316013A1/en not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5850623A (en) * | 1997-03-14 | 1998-12-15 | Eastman Chemical Company | Method for standardizing raman spectrometers to obtain stable and transferable calibrations |
US20070008523A1 (en) * | 2003-04-16 | 2007-01-11 | Kaye Stephen T | Rapid pharmaceutical identification and verification system |
US20080059240A1 (en) * | 2003-04-16 | 2008-03-06 | Prasant Potuluri | Pharmaceutical verification network |
Also Published As
Publication number | Publication date |
---|---|
US8417540B2 (en) | 2013-04-09 |
EP2316013A1 (en) | 2011-05-04 |
CA2736385A1 (en) | 2010-03-11 |
JP2012500994A (en) | 2012-01-12 |
US20100045978A1 (en) | 2010-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Custers et al. | ATR-FTIR spectroscopy and chemometrics: an interesting tool to discriminate and characterize counterfeit medicines | |
US7218395B2 (en) | Rapid pharmaceutical identification and verification system | |
EP3553783B1 (en) | Medication identification system | |
ES2555992T3 (en) | System and procedure to analyze at least one characteristic of the skin | |
US20150286783A1 (en) | Peer group discovery for anomaly detection | |
US8417540B2 (en) | Spectral signature extraction for drug verification and identification | |
Gao et al. | Comparison of several chemometric methods of libraries and classifiers for the analysis of expired drugs based on Raman spectra | |
EP2853883A1 (en) | Genetic algorithm for grouping objects on the basis of their hyperspectral images | |
US8731959B2 (en) | Spectroscopic chemical compound identification | |
Friedrich et al. | Miniature near-infrared spectrometer for point-of-use chemical analysis | |
Hattori et al. | Rapid identification of oral solid dosage forms of counterfeit pharmaceuticals by discrimination using near-infrared spectroscopy | |
Zhao et al. | A non-invasive method for the determination of liquid injectables by Raman spectroscopy | |
Custers et al. | Chemometrical analysis of fingerprints for the detection of counterfeit and falsified medicines | |
Gupta et al. | Through-container quantitative analysis of hand sanitizers using spatially offset Raman spectroscopy | |
Saifee et al. | Development and validation of automated visual field report extraction platform using computer vision tools | |
Holtkötter et al. | Development and validation of a digital image processing-based pill detection tool for an oral medication self-monitoring system | |
Fauzi et al. | Segmentation and automated measurement of chronic wound images: probability map approach | |
Oliver et al. | Attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy as a bedside diagnostic tool for detecting renal disease biomarkers in fresh urine samples | |
RU2701702C2 (en) | System and method for uniform comparison of unstructured recorded features with associated therapeutic features | |
Zhu et al. | Measurement and analysis of fluorescent whitening agent content in soybean milk based on image techniques | |
Kistenev et al. | Diagnostics of oral lichen planus based on analysis of volatile organic compounds in saliva | |
Jähme et al. | Recognition of pharmaceuticals with compact mini-Raman-spectrometer and automized pattern recognition algorithms | |
Le et al. | Machine learning for classification and quantification of monoclonal antibody preparations for cancer therapy | |
US20230270374A1 (en) | Method and devices for point-of-care applications | |
Komsta et al. | Chemometric detection of acetaminophen in pharmaceuticals by infrared spectroscopy combined with pattern recognition techniques: Comparison of attenuated total reflectance-FTIR and Raman spectroscopy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09811997 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2736385 Country of ref document: CA |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009811997 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2011525133 Country of ref document: JP Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1933/CHENP/2011 Country of ref document: IN |