Systems and methods of testing that provide early warning of contamination

Abstract

One among various embodiments discloses a computer-implemented method to evaluate a specimen for microorganisms. The method involves generating a first plurality of sub-pixel shifted images of the specimen, generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images, determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images, and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

Description

SYSTEMS AND METHODS OF TESTING THAT PROVIDE EARLY WARNING OF CONTAMINATION CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims the benefit of U.S. Provisional Application titled, “SYSTEM AND METHODS FOR IMPROVED BIOBURDEN AND / OR STERILITY TESTING,” filed on May 6, 2024, and having Serial No. 63 / 643,126. The present application claims the benefit of U.S. Provisional Application titled, “SYSTEM AND METHODS FOR IMPROVED TIMING FOR BIOBURDEN AND / OR STERILITY TESTING,” filed on May 6, 2024, and having Serial No. 63 / 643,140. The present application claims the benefit of U.S. Provisional Application titled, “SYSTEM AND METHODS FOR IMPROVED FILTRATION FOR BIOBURDEN AND / OR STERILITY TESTING,” filed on May 6, 2024, and having Serial No. 63 / 643,142. The present application claims the benefit of U.S. Provisional Application titled, “IMPROVED CARTRIDGES / CONSUMABLES FOR BIOBURDEN AND / OR STERILITY TESTING,” filed on May 6, 2024, and having Serial No. 63 / 643,132. The present application claims the benefit of U.S. Provisional Application titled, “SYSTEM AND METHODS FOR IMPROVED CONTACT AND IMAGING IN BIOBURDEN AND / OR STERILITY TESTING,” filed on May 6, 2024, and having Serial No. 63 / 643,135. The subject matter of these related applications is hereby incorporated herein by reference.BACKGROUNDField of the Various Embodiments

[0002] The various embodiments relate generally to specimen testing, and more specifically, to specimen testing that includes an early warning indication of contamination.Description of the Related Art

[0003] Microbial organisms are generally invisible to the naked eye. Consequently, testing for microbial contaminants in a specimen typically involves placing the specimen on a petri dish and observing the specimen over a period of time. In many cases the observation period can extend over several days. Typically, a sample of the specimen can be transferred at various intervals during the evaluation period onto a microscope slide and observed by a lab technician under a microscope. If a microbial contaminant is seen under the microscope, the lab technician may note various characteristics of the microbial contaminant such as a size of a microbial cluster and a rate of growth of the microbial cluster.

[0004] There are several drawbacks in existing test procedures such as the one described above. One drawback can be attributable to human errors. For example, a lab technician with limited experience may miscount the number of microbial organisms present in a specimen and / or may draw erroneous conclusions from his / her observations of the microbial organisms, especially during the initial stages of a test when the microbial organisms are very small in size.

[0005] Another drawback can be associated with the limitations of a conventional microscope. Not only is the conventional microscope unsuitable for directly examining a specimen on a petri dish without transferring a portion of the specimen to a microscope slide at various times, the conventional microscope fails to offer adequate magnification to detect microbial organisms until the organisms have grown relatively large (such as, after growing into a microbial cluster). In the meantime, the parent product from which the specimen has been drawn in the form of a sample may have reached a contamination level that renders the parent product unfit for use. Discarding of the parent product such as a pharmaceutical product, can be very costly.

[0006] As the foregoing illustrates, what is needed in the art are more effective ways to test a product and to minimize wastage of the product due to delays in obtaining a test result.SUMMARY

[0007] In an example embodiment, a computer-implemented method to evaluate a specimen for microorganisms includes generating a first plurality of sub-pixel shifted images of the specimen, generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images, determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images, and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

[0008] In one embodiment, the contaminant is a fungal spore and the computer-implemented method further includes generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, generating a deferred indication of contamination based on detecting a germination of the fungal spore in the second plurality of high-resolution images during a second time period.

[0009] At least one technical advantage of the disclosed techniques herein relative to the prior art is that, with the disclosed techniques, at least some drawbacks associated with human errors is addressed. More particularly, certain operations that are traditionally performed by humans are automatically performed by a computer with higher accuracy, speed, and consistency. An example operation pertains to eliminating the need for a human to transfer a sample of a specimen from a petri dish to a microscope slide for examination. Another example operation pertains to examination of a specimen on an automated schedule, thereby eliminating any delays that may occur if such evaluation is performed by a human.

[0010] Another technical advantage of the disclosed techniques includes a faster time to detect a contaminant based on evaluating high resolution images that are generated by a computer from sub-pixel shifted images. The high-resolution images provide a level of magnification that significantly exceeds a level of magnification obtainable through use of a conventional microscope, and also offer image resolution down to a sub-pixel level in comparison to a conventional digital image that offers pixel level resolution. Furthermore, the high-resolution images enable various operations in the digital domain such as image enhancement, image manipulation, image portability, and automated image evaluation for detecting contaminants.

[0011] These technical advantages provide one or more technological improvements over prior art approaches.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] So that the manner in which the above recited features of the various embodiments can be understood in detail, a more particular description of the inventive concepts, briefly summarized above, can be had by reference to various embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of the inventive concepts and are therefore not to be considered limiting of scope in any way, and that there are other equally effective embodiments.

[0013] FIG. 1 A illustrates a flow diagram of a method to evaluate a specimen for contamination according to an embodiment.

[0014] FIG. IB shows an example list of contaminants that may be generated during implementation of the flow diagram shown in FIG. 1 A.

[0015] FIG. 1C shows an example histogram that can be used for implementing of the flow diagram shown in FIG. 1 A.

[0016] FIG. ID shows an example time-to-detect function graphic for some contaminants.

[0017] FIG. 2 shows an example evaluation system that includes a specimen evaluation unit communicatively coupled to a computer for evaluating a specimen according to an embodiment.

[0018] FIG. 3 illustrates an example sample module that can be a part of the specimen evaluation unit shown in FIG. 2.

[0019] FIG. 4 illustrates an example imaging system that can be included in the example sample module shown in FIG. 3.

[0020] FIG. 5 illustrates another example imaging system that can be included in the example sample module shown in FIG. 3.

[0021] FIG. 6 is a flow diagram of method steps to evaluate a specimen according to various embodiments.DETAILED DESCRIPTION

[0022] In the following description, numerous specific details are set forth to provide a more thorough understanding of the various embodiments. However, it will be apparent to one skilled in the art that the inventive concepts can be practiced without one or more of these specific details. For explanatory purposes, multiple instances of like objects are symbolized with reference numbers identifying the object and parenthetical numbers identifying the instance where needed. While the invention may be described within the context of a use case associated with a specific imaging system, the inventive concepts described herein are broader than that particular use case and can be applied in any appropriate context / use case. In certain instances, this application may reference directly or indirectly to ePetri technology which, in some instances, refers to certain technology described in U.S. Patent Nos. 9,426,429, 9,643,184, 9,569,664, and 9,343,494, the disclosures of all of which are incorporated herein by reference in their entireties.

[0023] Microbial contamination by Gram positive bacteria, Gram negative bacteria, fungi, yeasts, molds, or other microorganisms, can cause severe illness and, in some cases, even death in human and animal subjects. Manufacturers in certain industries, for example, food,water, cosmetic, pharmaceutical, and medical device industries, must typically meet exacting standards to verify that their products do not contain levels of microbial contaminants that would otherwise compromise the health of a consumer or recipient. These industries require frequent, accurate, and sensitive testing for the presence of microbial contaminants to meet certain standards, such as standards imposed by the United States Food and Drug Administration or Environmental Protection Agency.

[0024] Depending upon the situation, the ability to distinguish between viable and nonviable cells can also be important. For example, during the manufacture of pharmaceuticals and biologies, it is important that the water used in the manufacturing process is sterile and free of contaminants. Furthermore, it is important that water contained in medicines (for example, liquid pharmaceutical dosage forms, biological dosage forms, and injectable dosage forms) and liquids (for example, saline) that are administered to a subject via non-parenteral routes, is also sterile and free of contaminants. In order to be potable, drinking water must meet exacting standards. However, water obtained from a water supply may be deemed acceptable for human consumption when a small quantity of viable microorganisms is present. The water is deemed unfit for human consumption when the level of viable microorganisms exceeds a threshold level.

[0025] Similarly, the presence of certain predetermined levels of microorganisms in certain food products (for example, fresh produce) and drinks (for example, milk) may be acceptable. However, once those levels have been exceeded the food or drink may be considered to have spoiled and no longer be safe for human consumption.

[0026] Traditional cell culture methods for assessing the presence of microbial contamination and / or the extent of microbial contamination can take several days to perform, which can depend upon the organisms that are being tested for. During this period, the products in question (for example, the food, drink, or medical products) may be quarantined until the results are available and the product can be released. As a result, there is a need for systems and methods for rapidly detecting (for example, within hours or less) the presence and / or amount of microbial contaminants, in particular, viable microbial contaminants, in a sample. An important part of the process is capturing the cells to be analyzed, which must be completed in a quick, safe and consistent manner to enable the efficiency of the overall detection system and methods.

[0027] FIG. 1 A shows a flow diagram of an example computer-executed method 100 toperform specimen testing that includes providing an early warning of contamination if contamination is present. Although the method steps are described with respect to an example system that is described herein, persons skilled in the art will understand that any system configured to perform the method steps, in any order, is within the scope of the various embodiments.

[0028] As shown, computer-implemented method 100 begins at step 105, where the test is started by placing a specimen upon a transparent layer that is typically made of glass and may be referred to as a petri plate, petri dish, or a cell-culture dish. The transparent layer 310 can then be placed inside a specimen evaluation unit at an intermediate location between a lighting element and an image sensor. Light emitted by the lighting element produces a shadow of the transparent layer and the specimen upon a top surface of the image sensor. The image sensor generates electrical output signals in response to each of multiple shadows falling upon the top surface of the image sensor over a period of time. The electrical output signals are conveyed to a computer that is configured to generate sub-pixel shifted shadow images based upon the received electrical output signals. The computer can be further configured to generate high resolution images from the sub-pixel shifted shadow images. The high-resolution images provide a wide-angle view of the specimen and have a level of magnification that significantly exceeds a level of magnification obtainable through use of a conventional microscope.Furthermore, the high-resolution images offer image resolution down to a sub-pixel level in comparison to a conventional digital image that offers pixel level resolution. Some details pertaining to an example system for generating such high-resolution images are provided below.

[0029] At step 110, a short-term timer is started for detecting a microbial contaminant as early as feasible. More particularly, microbial contaminants such as bacteria clusters are observable in a microscope within a relatively short period of time, such as within eight hours. However, fungal spores tend to be detectable only after a longer period of time after developing to an observable size. In an example implementation of the method 100, the shortterm timer can be set to about eight hours.

[0030] At step 115, the specimen can be observed under a microscope. If a microorganism such as a bacteria cluster, is observed in the specimen, at block 120, an early indication of contamination is generated. In an example scenario, the early indication can be generated by use of a computer that is communicatively coupled to the microscope and displayed on a display screen. The early warning indication can be displayed in any of various forms such asin the form of a list that identifies each of one or more contaminants and details about the contaminants. The details can include a canonical count of viable cells. The canonical count can be indicated in the form of colony-forming units (CFUs) per volume or weight of the specimen. In another implementation, the early-warning indication is provided in the form of a visual signal (via an LED, for example) and / or in the form of an audible signal (via a speaker or buzzer, for example).

[0031] The early warning indication can be used for various purposes such as to quarantine a product from which the specimen was obtained, or to decontaminate the product. The product can be a pharmaceutical product. As another example, the specimen can be a water sample obtained from a water supply source such as a reservoir or a filtration tank. In this case, the early warning indication can be ignored if the level of contamination is lower than an acceptable threshold for human consumption. However, in one implementation, even if the level of contamination is lower than an acceptable threshold for human consumption during the short-term period, the action indicated at step 130 and subsequent steps that are described below can be performed to identify any long-term contamination that may occur. In another implementation, criteria for detecting an organism in the water (at step 115) may be set to avoid generation of the early-warning indication if the amount of contamination is lower than the acceptable threshold for human consumption and / or if the organisms are non-viable organisms that are acceptable to be present in the water.

[0032] If at step 115 no organism is detected at any given moment in time, at step 125, a determination is made whether the short-term timer has expired. If the short-term timer has not expired, the action indicated in step 115 is repeated. In an example implementation, step 125 is performed on a periodic basis, such as every 30 minutes or every hour. The periodic basis can be defined by a lab technician prior to the start of the test at step 105 or as a part of the actions associated with step 105.

[0033] If, at step 125, the short-term timer has expired and no organisms have been detected at step 115, at step 130, a determination is made whether a likelihood of existence of any potential contaminant, particularly fungal spores, is present in the specimen. The determination can be made at various times such as on a periodic basis, and the results displayed in various ways such as in the form of the table 180 shown in FIG. IB. The confidence levels indicated in the table 180 are unknown for some time (about 2 hours) and narrow over time as additional data is collected.

[0034] In an example implementation, the determination at step 130, can be based on the likelihood of existence of any potential contaminant, particularly fungal spores, exceeding a threshold level. The threshold level can be defined by a lab technician prior to the start of the test at step 105 or as a part of the actions associated with step 105. In an example scenario, the determination at step 130 can be based on high-resolution images that are automatically evaluated by a computer to detect various types of objects (microorganisms and / or inorganic materials) if present in the specimen. In an example scenario, the automatic evaluation can involve the use of techniques such as computer vision and convolutional neural networks. If the likelihood of existence of fungal spores fails to exceed the threshold level after a period of time that is greater than the short-term period but less than a long-term period (such as 24 hours), at step 145, an indication of sterility can be generated. In one implementation, the indication of sterility is displayed on a display screen.

[0035] If the likelihood of existence of fungal spores exceeds the threshold level at any time, at step 135, a long-term evaluation of the specimen is carried out. In an example scenario, the long-term evaluation can be based on a statistical model and can be carried out over a period of time such as 24 hours. In an example implementation, the long-term evaluation can be based on a statistical model such as an empirical model. The empirical model can be a histogram of time-to-detect operations having a distribution characteristic such as a Poisson distribution. An example histogram associated with Aspergillus brasilensis is shown in FIG. 1C. In another implementation, a statistical model can be characterized by a probability density function based on time-to-detect. FIG. ID shows example time-to-detect characteristics of some example contaminants.

[0036] In another example implementation, the long-term evaluation can be based on high-resolution images that can be automatically evaluated by a computer to detect fungal spores. In an example scenario, the automatic evaluation can involve the use of techniques such as computer vision and convolutional neural networks. In one case, such techniques may be used to automatically identify in a high-resolution image, one or more dark spots that are equal to, or exceeding, a threshold size (a few microns in diameter such as 2-10 microns). However, in several cases, the dark spots may be caused by debris (microplastics, for example). Consequently, the evaluation is carried out over the long-term period in order to identify any change in size, such as due to germination of a fungal spore. The debris will remain unchanged in size during this period.

[0037] At block 140, a determination is made whether fungal spores are present in thespecimen. If no fungal spores are present, at block 145, the indication of sterility can be generated.

[0038] If, on the other hand, at block 140, the determination indicates the presence of fungal spores, at block 150, an indication of fungal contamination is generated. The indication can be displayed in any of various forms such as in the format that provides information about the detected fungal spores.

[0039] FIG. 2 shows an evaluation system 200 that includes a specimen evaluation unit 205 communicatively coupled to a computer 215. In one embodiment, the specimen evaluation unit 205 is a stand-alone unit that is communicatively coupled to the computer 215 either wirelessly or via a wired connection. An example wireless connection is a Bluetooth connection. An example wired connection is an Ethernet connection. In another embodiment, the specimen evaluation unit 205 and the computer 215 are co-located in an integrated configuration inside an enclosure.

[0040] The specimen evaluation unit 205 can include “n” sample modules 210 (n > 1). Each of the sample modules 210 can include a lighting assembly, a transparent layer, and an image sensor. In an embodiment, each of the one or more sample modules 210 can be configured to evaluate a specimen such as described above with reference to the flow diagram of the method 100. In an example embodiment, the “n” sample modules 210 can be configured for evaluating “n” specimens over an extended period of time under different conditions based on the method 100. For example, a first specimen placed in sample module (1) 210-1 can be evaluated at a first ambient temperature, a second identical specimen placed in sample module (2) 210-2 can be evaluated at a second ambient temperature, and so on. In one implementation, evaluation of each of the specimens can involve detecting a contaminant such as detecting a contaminant in a drug specimen, detecting a contaminant in a fluid specimen, or detecting a pollutant in a liquid specimen. In another implementation, evaluation of a culture specimen can involve an automated enumeration of bacterial and fungal colonies. In another implementation, two or more sample modules 210 can be configured to enable concurrent evaluation of more than one identical specimen or more than one kind of specimen.

[0041] Communication link 240 is selected to support conveying of electrical signals generated by image sensors included in the “n” sample modules. The computer 215 includes a processor 220 and a memory 225 and can further include components (not shown) such as an input / output interface (keyboard, display, etc.) and communication components (for wirelesscommunications, connectivity to a communication network, etc.).

[0042] In this example embodiment, the memory 225 includes a high-resolution image generation software application 230 and a high-resolution image evaluation software application 235. The processor 220 can execute the high-resolution image generation software application 230 for generating one or more high-resolution images each based on a sequence of sub-pixel shifted images and can execute the high-resolution image evaluation software application 235 for evaluating the high-resolution images to detect contamination according to various embodiments. In an example embodiment , the sub-pixel shifted images are generated based on electrical signals provided by sensing elements of an image sensor and position information of randomly placed LEDs of a lighting element that is described below in more detail.

[0043] In an example embodiment, the processor 220 performs a digital focusing operation to obtain focus upon a high-resolution image corresponding to a plane of interest through the specimen. The plane of interest provides a cross-sectional view of the specimen and can be located height-wise, for example, along a horizontal axis that extends cross-sectionally through a central portion of the specimen. The focusing operation includes determining and using a motion vector calculated at the plane of interest. In general, a motion vector can refer to a translational motion of projection images in a sequence of low-resolution projection images. The translational motion can be dependent on one or more factors, primarily on an amount of shift observed in any of various 2D planes that are parallel to the transparent layer on which the specimen is placed and / or parallel to the surface of the image sensor upon which light propagated through the specimen is incident. In an example implementation, the motion vector is defined by 2D Cartesian coordinates, and a high-resolution image of the specimen is constructed by use of an algorithm that operates upon data associated with a sequence of a subpixel shifted projection images and a motion vector of the sub-pixel shifted images of the sequence. In this embodiment, the sequence of sub-pixel shifted images used for generating the high-resolution image corresponds to the number of lighting elements of the lighting element that are activated for generating the sub-pixel shifted images.

[0044] In an embodiment, the computer 215 is configured to generate a set of high-resolution images over an extended time period based on electrical signals provided by the specimen evaluation unit 205. In various implementations, the electrical signals can be provided by the specimen evaluation unit 205 to the computer 215 in accordance with one of arepetitive schedule, an intermittent schedule, or a random schedule.

[0045] The processor 220 can execute the high-resolution image evaluation software 235 for evaluating one or more high-resolution images generated by the high-resolution image generation software application 230. In some cases, evaluating the high-resolution image(s) can involve detecting a contaminant, and / or evaluating growth characteristics of a culture. The high-resolution image evaluation software 235 is typically configured to detect and provide an indication of contaminants that may be invisible to the human eye or are not yet at a stage where visible to the human eye. In some cases, the high-resolution image evaluation software 235 is configured to provide interactivity with a human who can visually inspect one or more images. The visual inspection may be carried out via a display screen of the computer 215.

[0046] FIG. 3 illustrates an embodiment of a sample module 210 of the specimen evaluation unit 205 shown in FIG. 2. The sample module 210 includes a sub-pixel shifted imager 350 housing a lighting element 305, a nutrient cartridge 310, and an image sensor 325. The example sample module 210 further includes a temperature control element 330. The nutrient cartridge 310 houses the specimen 315 on a transparent layer 320. The specimen 315 may be placed in contact with a nutrient such as agar that is filled into the nutrient cartridge 310 on top of the specimen 315. In other embodiments, the nutrient cartridge 310 can be replaced by one or more other elements that provide support to the transparent layer 320.

[0047] As shown, a separation distance exists between the transparent layer 320 of the nutrient cartridge 310 and a top surface of the image sensor 325 upon which light is incident after propagating through the specimen 315 contained in the nutrient cartridge 315. The separation distance can vary in accordance with various factors such as the structure of the nutrient cartridge 315 and the structure of the sample module 210. The electrical signals generated by the image sensor 325 are provided to the computer 215 via an I / O 335 (an Ethernet card or Bluetooth circuit, for example). The computer 215 generates one or more high resolution images that can be evaluated for purposes such as detecting the presence of contaminants in the specimen 315 if any such contaminants are present.

[0048] In various embodiments, the nutrient cartridge 310 is disposable after use. An advantage offered by the disposable cartridge is savings in cost compared to a prior art image sensor that is typically discarded after a single use. The reason for discarding the prior art image sensor after a single use is due to residual contamination of a top surface of the sensor upon which a specimen has been placed. The prior art image sensor is typically moreexpensive than the disposable nutrient cartridge 310.

[0049] The temperature control element 330 can be provided in the sample module 210 for incubation purposes of the specimen 315. In a prior art scenario, heat generated by a CMOS image sensor was used to generate heat. Heating control was implemented in a relatively crude fashion by turning the CMOS image sensor on and off by use of a “bang-bang” control loop. Cooling was achieved by use of an additional component in the form of a forward-biased thermo-electric cooler (TEC).

[0050] An improvement provided in accordance with one or more embodiments involves the use of a single component to achieve both heating and cooling. In one such embodiment, the temperature control element 330 is a TEC configured to operate in a dual-purpose role as both a heating element and a cooling element. In an example implementation, the TEC is a part of a H-bridge circuit that is configured to place the TEC in a forward bias condition over a first period of time to operate as a heating element, and to place the TEC in a reverse bias condition over a second period of time to operate as a cooling element. The time periods, repetition rate, and other factors of the forward bias and reverse bias conditions can be controlled by a computer in order to achieve a desired ambient temperature processor in the sample module 210. In terms of heating operations, a TEC intrinsically operates as a heat pump and thus achieves very high operating efficiency. The efficiency can be greater than 100% in some cases when used for heating.

[0051] FIG. 4 illustrates a first example embodiment of the sub-pixel shifted image sensor 350 shown in FIG. 3. In this example embodiment, the image sensor 325 includes a number of detection elements such as CMOS detectors or charge coupled detectors (CCD). Eight detection elements are shown arranged adjacent to each other in one row. Additional detection elements can be present in additional rows of the image sensor 325.

[0052] The transparent layer 320 is typically made of glass and may be referred to as a petri plate, petri dish, or a cell-culture dish. The transparent layer 320 can be either mounted directly upon a top surface of the image sensor 325 or upon an intermediate film (a plastic sheet, for example) that is placed upon the top surface of the image sensor 325. This arrangement effectively renders a separation distance “d2” between the transparent layer 320 and the top surface of the image sensor 325 as being close to zero. Furthermore, the distance “d2” is negligible in comparison to a separation distance “dl” between the transparent layer 320 and a light-emitting surface of the lighting element 305.

[0053] In one example implementation, the lighting element 305 emits light generated by a number of light-emitting components arranged in a uniform configuration that conforms to a grid or matrix format.

[0054] In another example implementation, the lighting element 305 emits light generated by a number of light-emitting components arranged in a spatially non-uniform configuration. In one embodiment, each of the light-emitting components is a light emitting diode (LED) and the non-uniform configuration is based on a random arrangement of the LEDs upon a substrate. In another embodiment, a repetition of LEDs is avoided along any radial axis of the lighting element 205. Such an arrangement can improve performance of a Fourier transform as will be understood by those skilled in the art. The random arrangement of LEDs does not conform to a square matrix array grid notwithstanding the position of some LEDs randomly coinciding with grid lines or vertices of the grid. In one implementation, all the LEDs are identical. In another implementation, some or all of the LEDs differ from each other in various ways such as emission wavelength, emission color, shape, and / or size.

[0055] In one implementation, a sequential activation operation is carried out upon the LEDs of the lighting element 305 in accordance with one or more pre-configured activation sequences. In another implementation, a sequential activation operation is carried out upon the LEDs of the lighting element 305 in accordance with random activation sequences.

[0056] The illustration shows a cutaway view of the lighting element 305 containing eight LEDs. In this example, the cutaway view includes eight LEDs placed in accordance with a random arrangement. LED l can be at a first location on a 3D map 405, LED 2 can be at a second location on the 3D map 405, and so on for all eight LEDs. Each of the LEDs emits non-coherent light that radiates in multiple directions. Not shown are many other light beams that are emitted by each LED and produce a shadow of the transparent layer 320 and the specimen 315 placed thereon, upon the top surface of the image sensor 325.

[0057] The illustrated set of light beams correspond to a focal point 410 on the transparent layer 320, which is negligibly close to the top surface of the image sensor 325. The dashed line oval 415 shows an expanded view of the light beams propagating through the specimen 315 at the focal point 410 and falling upon detection element (4) of the image sensor 325. The designation “pl” corresponds to a width of the detection element (4) and thus corresponds to one pixel. The sub-pixel spacing of the eight beams shown inside dashed line oval 415 has a non-uniform characteristic and can encompass various sub-pixel widths as a result of the eightLEDs being arranged in a spatially non-uniform configuration. For example, the distance between LED l and LED 2 in the 3D map 405 is different than a distance between LED 2 and LED 3 in the 3D map 405, and so on. In this example, a pixel (indicated by distance “pl”) includes eight sub-pixels having non-uniform widths.

[0058] The image sensor 325 generates electrical signals in response to the incident light beams and provides the electrical signals to the computer 215 (shown in FIGs. 2 and 3) for generating eight sub-pixel shifted images. The eight sub-pixel shifted images can be operated upon by the computer 215 (by executing a software algorithm, for example) to generate a high-resolution image of the specimen 315 in accordance with an embodiment.

[0059] FIG. 5 illustrates a second example embodiment of the sub-pixel shifted image sensor 350. In this example embodiment, the transparent layer 320 is located at a distance “d4” above the top surface of the image sensor 325, where d4 > d2 (d2 is shown in FIG. 4). The illustrated set of example light beams correspond to a focal point 510 on the transparent layer 320. Unlike the shadow created by the light beams shown in FIG. 4 upon the detection element (4) of the image sensor 325, the shadow created by the light beams shown in FIG. 5 is spread out over a larger area on the top surface of the image sensor 325. More particularly, the illustrated light beam produced by LED l is incident upon a detection element (8) of the image sensor 325 at an activation time “tl” of LED L The detection element (8) produces a first electrical signal in response.

[0060] The first electrical signal can be provided to the computer 215, which, in one embodiment, generates a first sub-pixel shifted image based at least in part on the first electrical signal and position information associated with LED L The computer 215 can be pre-configured with position information of LED l and the other LEDs of the lighting element 305. In one implementation, the position of each LED is defined by Cartesian coordinates, such as a set of eight two-dimensional (2D) x-y Cartesian coordinates corresponding to the eight LEDs. The position information of the LEDs can be stored in a lookup table that is accessible to the computer 215.

[0061] In another embodiment, the computer 215 generates the first sub-pixel shifted image based at least in part on the first electrical signal, position information associated with LED l, and in at least some cases, based on additional information. The additional information can include a separation distance between the lighting element 305 and the transparent layer 320 (“d3” in the illustrated example), a separation distance between thetransparent layer 320 and the image sensor 325 (“d4” in the illustrated example), a separation distance between the lighting element 305 and the image sensor 325, and / or an angle of incidence of light upon a respective detection element of the image sensor 325 (detection element (8), in this example).

[0062] Furthermore, the illustrated light beam produced by LED 2 is incident upon the detection element (7) of the image sensor 325 at an activation time “t2” of LED 2. The detection element (7) produces a second electrical signal in response. The second electrical signal is provided to the computer 215 which generates a second sub-pixel shifted image based at least in part on the second electrical signal, position information associated with LED 2, and in at least some cases, based on additional information such as described above.

[0063] The illustrated light beam produced by LED 3 is incident upon the detection element (6) of the image sensor 325 at an activation time “t3” of LED 3. The detection element (6) produces a third electrical signal in response. The third electrical signal is provided to the computer which generates a third sub-pixel shifted image based at least in part on the third electrical signal, position information associated with LED 3, and in at least some cases, based on additional information such as described above.

[0064] The illustrated light beam produced by LED 4 is incident upon the detection element (6) of the image sensor 325 at an activation time “t4” of LED 4. The detection element (6) produces a fourth electrical signal in response. The fourth electrical signal is provided to the computer 215 which generates a fourth sub-pixel shifted image based at least in part on the fourth electrical signal, position information associated with LED 4, and in at least some cases, based on additional information such as described above.

[0065] The illustrated light beam produced by LED 5 is incident upon the detection element (5) of the image sensor 325 at an activation time “t5” of LED 5. The detection element (5) produces a fifth electrical signal in response. The fifth electrical signal is provided to the computer 215 which generates a fifth sub-pixel shifted image based at least in part on the fifth electrical signal, position information associated with LED 5, and in at least some cases, based on additional information such as described above.

[0066] The illustrated light beam produced by LED 6 is incident upon the detection element (3) of the image sensor 325 at an activation time “t6” of LED 6. The detection element (6) produces a sixth electrical signal in response. The sixth electrical signal isprovided to the computer 215 which generates a sixth sub-pixel shifted image based at least in part on the sixth electrical signal, position information associated with LED 6, and in at least some cases, based on additional information such as described above.

[0067] The illustrated light beam produced by LED 7 is incident upon the detection element (2) of the image sensor 325 at an activation time “t7” of LED 7. The detection element (2) produces a seventh electrical signal in response. The seventh electrical signal is provided to the computer 215 which generates a seventh sub-pixel shifted image based at least in part on the seventh electrical signal, position information associated with LED 7, and in at least some cases, based on additional information such as described above.

[0068] The illustrated light beam produced by LED 8 is incident upon the detection element (1) of the image sensor 325 at an activation time “t8” of LED 8. The detection element (1) produces an eighth electrical signal in response. The eighth electrical signal is provided to the computer 215 which generates an eighth sub-pixel shifted image based at least in part on the eighth electrical signal, position information associated with LED 8, and in at least some cases, based on additional information such as described above.

[0069] The eight sub-pixel shifted images can be operated upon by the computer 215 by executing the high-resolution image generation software application 230 (shown in FIG. 2) to generate a high-resolution image of the specimen 315 in accordance with an embodiment. In an example implementation, the high-resolution image generation software application 230 can include an algorithm that evaluates sub-pixel shifted images generated by use of the electrical signals provided by the image sensor 325 based on light emitted by the eight LEDs at the times “tl” through “t8” (corresponding to one activation sequence) and at other times corresponding to additional activation sequences. One or more of the sub-pixel shifted images offer the best focus for viewing contaminants (if any) that may be present in the specimen 315.

[0070] In one implementation, a high-resolution image of the specimen 315 is based on evaluating a number of sub-pixel shifted images generated over an extended period of time using multiple activation sequences. Evaluating the sub-pixel shifted images over the extended period of time can be carried out to evaluate a specimen culture that changes over time.

[0071] The description provided above with reference to FIG. 5 is equally applicable to any other sub-pixel shifted image sensor that includes the lighting element 305. Thetransparent layer 320 can be at any location between the lighting element 305 and the image sensor 325 in such an sub-pixel shifted image sensor. More particularly, the separation distance “d3” can have any value over a first range of separation distances, the separation distance “d4” can have any value over a second range of separation distances, and the separation distance between the lighting element 305 and the image sensor 325 can have any value over a third range of separation distances.

[0072] FIG. 6 is a flow diagram of an example method 600 to evaluate a specimen for contamination. Although the method steps are described with respect to FIGS 1-5, persons skilled in the art will understand that any system configured to perform the method steps, in any order, is within the scope of the various embodiments.

[0073] As shown, method 600 begins at step 605, which involves generating a first plurality of sub-pixel shifted images of the specimen. This aspect is described above with reference to FIGs. 3-5.

[0074] Step 610 involves generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images. This aspect is described above with reference to the computer 215 shown in FIG. 3.

[0075] Step 615 involves determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images. This aspect is described above with reference to step 110 of the flow diagram shown in FIG. 1.

[0076] Step 620 involves generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period. This aspect is described above with reference to step 120 of the flow diagram shown in FIG. 1.

[0077] In sum, a computer-implemented method to evaluate a specimen for contamination includes performing a test procedure that includes evaluating high-resolution images generated from sub-pixel shifted images of the specimen and providing an early indication of contamination, subject to detecting at least one contaminant in the specimen within a first time period. The method further includes providing an indication of a sterility of the specimen, subject to failing to detect the contaminant(s) within a second time period that exceeds the first time period. In one embodiment, the contaminant is a fungal spore and the computer-implemented method further includes providing an indication of potential contaminationand / or a deferred indication of contamination, subject to detecting the fungal spore or a germination of the fungal spore during the second time period. In another embodiment, the contaminant is a bacterium, and the computer-implemented method further includes providing an indication of potential contamination and / or a deferred indication of contamination, subject to either detecting the bacterium or a binary fission of the bacterium during the second time period.

[0078] At least one technical advantage of the disclosed techniques herein relative to the prior art is that, with the disclosed techniques, at least some drawbacks associated with human errors is addressed. More particularly, certain operations that are traditionally performed by humans are automatically performed by a computer with higher accuracy, speed, and consistency. An example operation pertains to eliminating the need for a human to transfer a sample of a specimen from a petri dish to a microscope slide for examination. Another example operation pertains to examination of a specimen on an automated schedule, thereby eliminating any delays that may occur if such evaluation is performed by a human.

[0079] Another technical advantage of the disclosed techniques includes a faster time to detect a contaminant based on evaluating high resolution images that are generated by a computer from sub-pixel shifted images. The high-resolution images provide a level of magnification that significantly exceeds a level of magnification obtainable through use of a conventional microscope, and also offer image resolution down to a sub-pixel level in comparison to a conventional digital image that offers pixel level resolution. Furthermore, the high-resolution images enable various operations in the digital domain such as image enhancement, image manipulation, image portability, and automated image evaluation for detecting contaminants. These technical advantages provide one or more technological improvements over prior art approaches.

[0080] 1. In some embodiments, a computer-implemented method to evaluate a specimen for microorganisms comprises generating a first plurality of sub-pixel shifted images of the specimen, generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images, determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images, and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

[0081] 2. The computer-implemented method of clause 1, wherein the computer-implemented method further comprises generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, generating a deferred indication of contamination based on detecting at least one of a second microorganism or a germination of a fungal spore in one or more of the second plurality of high-resolution images during a second time period.

[0082] 3. The computer-implemented method of clauses 1 or 2, wherein the second microorganism is a bacterium.

[0083] 4. The computer-implemented method of any of clauses 1-3, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of subpixel shifted images, and generating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

[0084] 5. The computer-implemented method of any of clauses 1-4, wherein detecting the fungal spore comprises executing an image processing operation based on a statistical model.

[0085] 6. The computer-implemented method of any of clauses 1-5, wherein the statistical model comprises a probability density function of time-to-detect.

[0086] 7. The computer-implemented method of any of clauses 1-6, wherein the early indication of contamination comprises information based on colony forming units per milliliter (CFUs / mL).

[0087] 8. The computer-implemented method of any of clauses 1-7, wherein the early indication of contamination further comprises at least one of a confidence interval associated with the CFUs / mL or a rate of change of the CFUs / mL over at least a portion of the first time period.

[0088] 9. The computer-implemented method of any of clauses 1-8, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, and performing a long-term evaluation of the specimen for detecting the fungal spore, the long-term evaluation based on the second plurality of high-resolution images.

[0089] 10. The computer-implemented method of any of clauses 1-9, wherein the longterm evaluation is performed over a second time period that exceeds the first time period.

[0090] 11. In some embodiments, one or more non-transitory computer-readable media store instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of generating a first plurality of sub-pixel shifted images of the specimen, generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images, determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images, and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

[0091] 12. The one or more non-transitory computer-readable media of clause 11, wherein the steps further comprise generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, generating a deferred indication of contamination based on detecting at least one of a second microorganism or a germination of the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

[0092] 13. The one or more non-transitory computer-readable media of clauses 11 or 12, wherein the second microorganism is a bacterium.

[0093] 14. The one or more non-transitory computer-readable media of any of clauses 11- 13, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, and generating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

[0094] 15. The one or more non-transitory computer-readable media of any of clauses 11- 14, wherein detecting the fungal spore comprises executing an image processing operation based on a statistical model.

[0095] 16. The one or more non-transitory computer-readable media of any of clauses Ills, wherein the statistical model comprises a probability density function of time-to-detect.

[0096] 17. The one or more non-transitory computer-readable media of any of clauses 11- 16, wherein the early indication of contamination comprises information based on colony forming units per milliliter (CFUs / mL).

[0097] 18. The one or more non-transitory computer-readable media of any of clauses 11- 17, wherein the early indication of contamination further comprises at least one of a confidence interval associated with the CFUs / mL or a rate of change of the CFUs / mL over at least a portion of the first time period.

[0098] 19. In some embodiments, an evaluation system comprises a specimen evaluation system, and a computer coupled to the specimen evaluation system, the computer comprises a memory storing a high-resolution image generation application and a high-resolution image evaluation application, and a processor coupled to the memory that executes the high-resolution image generation application and a high-resolution image evaluation application to generate a first plurality of sub-pixel shifted images of the specimen, generating a first plurality of high-resolution images based on the first plurality of sub-pixel shifted images, determine a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images, and generate an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

[0099] 20. The evaluation system of clause 19, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises generating a second plurality of sub-pixel shifted images of the specimen, generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images, and generating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

[0100] Any and all combinations of any of the claim elements recited in any of the claims and / or any elements described in this application, in any fashion, fall within the contemplated scope of the present invention and protection.

[0101] The descriptions of the various embodiments have been presented for purposes of illustration but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.

[0102] Aspects of the present embodiments can be embodied as a system, method or computer program product. Accordingly, aspects of the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that can all generally be referred to herein as a “module,” a “system,” or a “computer.” In addition, any hardware and / or software technique, process, function, component, engine, module, or system described in the present disclosure can be implemented as a circuit or set of circuits. Furthermore, aspects of the present disclosure can take the form of a computer program product embodied in one or more computer readable medium having computer readable program code embodied thereon.

[0103] Any combination of one or more computer readable medium can be utilized. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable readonly memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium can be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0104] Aspects of the present disclosure are described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine. The instructions, when executed via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / acts specified in the flowchart and / or block diagram block or blocks. Suchprocessors can be, without limitation, general purpose processors, special-purpose processors, application-specific processors, or field-programmable gate arrays.

[0105] The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the block can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks can sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0106] While the preceding is directed to embodiments of the present disclosure, other and further embodiments of the disclosure can be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.

Claims

WHAT IS CLAIMED IS:

1. A computer-implemented method to evaluate a specimen for microorganisms, the method comprising:generating a first plurality of sub-pixel shifted images of the specimen; generating a first plurality of high-resolution images based on the first plurality of subpixel shifted images;determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images; and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

2. The computer-implemented method of claim 1, wherein the computer-implemented method further comprises:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images;generating a deferred indication of contamination based on detecting at least one of a second microorganism or a germination of a fungal spore in one or more of the second plurality of high-resolution images during a second time period.

3. The computer-implemented method of claim 2, wherein the second microorganism is a bacterium.

4. The computer-implemented method of claim 1, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images; andgenerating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

5. The computer-implemented method of claim 4, wherein detecting the fungal spore comprises executing an image processing operation based on a statistical model.

6. The computer-implemented method of claim 5, wherein the statistical model comprisesa probability density function of time-to-detect.

7. The computer-implemented method of claim 1, wherein the early indication of contamination comprises information based on colony forming units per milliliter (CFUs / mL).

8. The computer-implemented method of claim 7, wherein the early indication of contamination further comprises at least one of a confidence interval associated with the CFUs / mL or a rate of change of the CFUs / mL over at least a portion of the first time period.

9. The computer-implemented method of claim 1, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images; andperforming a long-term evaluation of the specimen for detecting the fungal spore, the long-term evaluation based on the second plurality of high-resolution images.

10. The computer-implemented method of claim 9, wherein the long-term evaluation is performed over a second time period that exceeds the first time period.

11. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:generating a first plurality of sub-pixel shifted images of the specimen; generating a first plurality of high-resolution images based on the first plurality of subpixel shifted images;determining a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images; and generating an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

12. The one or more non-transitory computer-readable media of claim 11, wherein the steps further comprise:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images;generating a deferred indication of contamination based on detecting at least one of a second microorganism or a germination of the fungal spore in one or more ofthe second plurality of high-resolution images during a second time period.

13. The one or more non-transitory computer-readable media of claim 11, wherein the second microorganism is a bacterium.

14. The one or more non-transitory computer-readable media of claim 11, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images; andgenerating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

15. The one or more non-transitory computer-readable media of claim 14, wherein detecting the fungal spore comprises executing an image processing operation based on a statistical model.

16. The one or more non-transitory computer-readable media of claim 15, wherein the statistical model comprises a probability density function of time-to-detect.

17. The one or more non-transitory computer-readable media of claim 11, wherein the early indication of contamination comprises information based on colony forming units per milliliter (CFUs / mL).

18. The one or more non-transitory computer-readable media of claim 17, wherein the early indication of contamination further comprises at least one of a confidence interval associated with the CFUs / mL or a rate of change of the CFUs / mL over at least a portion of the first time period.

19. An evaluation system comprising:a specimen evaluation system; anda computer coupled to the specimen evaluation system, the computer comprising: a memory storing a high-resolution image generation application and a high-resolution image evaluation application; anda processor coupled to the memory that executes the high-resolution image generationapplication and a high-resolution image evaluation application to: generate a first plurality of sub-pixel shifted images of the specimen;generating a first plurality of high-resolution images based on the first plurality of subpixel shifted images;determine a first time period for detection of a first microorganism that develops to a threshold size in the first plurality of high-resolution images; and generate an early indication of contamination based on detecting the first microorganism that develops to the threshold size within the first time period.

20. The evaluation system of claim 19, wherein the specimen includes a fungal spore, and wherein the computer-implemented method further comprises:generating a second plurality of sub-pixel shifted images of the specimen; generating a second plurality of high-resolution images based on the second plurality of sub-pixel shifted images; andgenerating a deferred indication of contamination based on detecting the fungal spore in one or more of the second plurality of high-resolution images during a second time period.

Images