WO2024074898A1

WO2024074898A1 - Detecting pulmonary inflammation based on fern patterns in sputum samples

Info

Publication number: WO2024074898A1
Application number: PCT/IB2023/053632
Authority: WO
Inventors: Mohammad Ali Khayamian; Reihaneh SHAKIBI; Mohammadreza Ghaderinia; Hamed Abadijoo; Seyed Mohammad Reza TAHERI
Original assignee: Mohammad Ali Khayamian
Priority date: 2022-10-04
Filing date: 2023-04-10
Publication date: 2024-04-11

Abstract

A method for detecting pulmonary inflammation in a subject. The method includes acquiring a sputum sample from the subject, acquiring a magnified image of the sputum sample, and detecting the pulmonary inflammation based on fern patterns in the magnified image. An imaging system is utilized for acquiring magnified image. One or more processors are utilized for detecting the pulmonary inflammation.

Description

DETECTING PULMONARY INFLAMMATION BASED ON FERN PATTERNS IN SPUTUM SAMPLES

TECHNICAL FIELD

[0001] The present disclosure generally relates to medical diagnosis, and particularly, to pulmonary inflammation detection.

BACKGROUND ART

[0002] During immunological phase of the COVID-19 disease and when immune systems are activated, lungs of patients become a battlefield for viruses and white blood cells. Many other immune cells are called and recruited by immune systems, and a resulting inflammation is mostly accompanied by disintegration and leakiness of blood vessels. Consequently, this vascular permeability results in a flow of blood fluid into air sacs or alveolus. Such a situation is currently diagnosed by computed tomography (CT) imaging of lungs.

[0003] In cases with positive COVID- 19 test, lung involvement and inflammation determine a treatment regime. Respiratory inflammation is typically arisen due to a cytokine storm and a leakage of the vessels for immune cell recruitment. Currently, respiratory inflammation due to COVID-19 is detected by a clinical judgment of a specialist or more precisely by a chest CT scan [US Patents no. 11,308,612 B2, 11,357,464 B2, and 11,361,440 B2], However, lack of accessibility to CT machines in many poor medical centers as well relatively high cost, may impose limitations on widespread utilization of CT imaging for detection of respiratory inflammation.

[0004] There is, therefore, a need for a simple, fast, and accessible method for detection of lung inflammation in pulmonary diseases such as COVID-19 infections. There is further a need for a cost-efficient system for detection of pulmonary inflammation.

SUMMARY OF THE DISCLOSURE

[0005] This summary is intended to provide an overview of the subject matter of the present disclosure, and is not intended to identify essential elements or key elements of the subject matter, nor is it intended to be used to determine the scope of the claimed implementations. The proper scope of the present disclosure may be ascertained from the claims set forth below in view of the detailed description below and the drawings. [0006] In one general aspect, the present disclosure describes an exemplary method for detecting pulmonary inflammation in a subject. An exemplary method may include acquiring a sputum sample from the subject, acquiring a magnified image of the sputum sample, and detecting the pulmonary inflammation based on fem patterns in the magnified image. An exemplary imaging system may be utilized for acquiring the magnified image. An exemplary processor may be utilized for detecting the pulmonary inflammation.

[0007] In an exemplary embodiment, acquiring the sputum sample may include acquiring a drop of sputum from the subject, placing the drop of sputum at a center of a sample slide, and obtaining the sputum sample by air-drying the drop of sputum.

[0008] In an exemplary embodiment, acquiring the magnified image may include inserting the sample slide inside a mini-microscope of the imaging system between a condensing lens of the mini-microscope and a magnifying lens of the mini-microscope, holding an imaging device of the imaging system above the magnifying lens by a stand, and capturing the magnified image through the magnifying lens. An exemplary imaging device may be utilized for capturing the magnified image.

[0009] In an exemplary embodiment, detecting the pulmonary inflammation may include obtaining a classified output by applying the magnified image to a convolutional neural network (CNN) and detecting the pulmonary inflammation based on the classified output. An exemplary classified output may include one of a non-pulmonary inflammation output or a pulmonary inflammation output.

[0010] An exemplary method may further include training the CNN by obtaining a first plurality of salivary images, obtaining a second plurality of salivary images, mapping the first plurality of salivary images to the pulmonary inflammation output by applying each of the first plurality of salivary images to the CNN, and mapping the second plurality of salivary images to the non-pulmonary inflammation output by applying each of the second plurality of salivary images to the CNN. An exemplary first plurality of salivary images may be associated with pulmonary inflammation in a plurality of patients. In an exemplary embodiment, each of the first plurality of salivary images may include fem patterns in at least 60% of an area of each respective salivary image of the first plurality of salivary images. An exemplary second plurality of salivary images may be associated with healthy subjects.

[0011] Other exemplary systems, methods, features and advantages of the implementations will be, or will become, apparent to one of ordinary skill in the art upon examination of the following figures and detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description and this summary, be within the scope of the implementations, and be protected by the claims herein.

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The drawing figures depict one or more implementations in accord with the present teachings, by way of example only, not by way of limitation. In the figures, like reference numerals refer to the same or similar elements.

[0013] FIG. 1A shows a flowchart of a method for detecting pulmonary inflammation in a subject, consistent with one or more exemplary embodiments of the present disclosure.

[0014] FIG. IB shows a flowchart for acquiring a sputum sample, consistent with one or more exemplary embodiments of the present disclosure.

[0015] FIG. 1C shows a flowchart for acquiring a magnified image of a sputum sample, consistent with one or more exemplary embodiments of the present disclosure.

[0016] FIG. ID shows a flowchart for detecting pulmonary inflammation based on fern patterns in a magnified image, consistent with one or more exemplary embodiments of the present disclosure.

[0017] FIG. IE shows a flowchart of a method for training a CNN, consistent with one or more exemplary embodiments of the present disclosure.

[0018] FIG. 2A shows a schematic of acquiring a drop of sputum from a subject, consistent with one or more exemplary embodiments of the present disclosure.

[0019] FIG. 2B shows a schematic of placing a drop of sputum at a center of a sample slide, consistent with one or more exemplary embodiments of the present disclosure.

[0020] FIG. 3A shows a top view of an imaging system, consistent with one or more exemplary embodiments of the present disclosure.

[0021] FIG. 3B shows a schematic of an exploded view of a mini-microscope, consistent with one or more exemplary embodiments of the present disclosure.

[0022] FIG. 4A shows a magnified image of a sputum sample of a subject with pulmonary inflammation, consistent with one or more exemplary embodiments of the present disclosure.

[0023] FIG. 4B shows a magnified image of a sputum sample of a subject without pulmonary inflammation, consistent with one or more exemplary embodiments of the present disclosure. [0024] FIG. 5 shows a schematic of a convolutional neural network (CNN), consistent with one or more exemplary embodiments of the present disclosure.

[0025] FIG. 6 shows a high-level functional block diagram of a computer system, consistent with one or more exemplary embodiments of the present disclosure.

[0026] FIG. 7 shows receiver operating characteristic (ROC) curve of a method for detecting pulmonary inflammation, consistent with exemplary embodiments of the present disclosure.

DESCRIPTION OF EMBODIMENTS

[0027] In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. However, it should be apparent that the present teachings may be practiced without such details. In other instances, well known methods, procedures, components, and/or circuitry have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present teachings.

[0028] The following detailed description is presented to enable a person skilled in the art to make and use the methods and devices disclosed in exemplary embodiments of the present disclosure. For purposes of explanation, specific nomenclature is set forth to provide a thorough understanding of the present disclosure. However, it will be apparent to one skilled in the art that these specific details are not required to practice the disclosed exemplary embodiments. Descriptions of specific exemplary embodiments are provided only as representative examples. Various modifications to the exemplary implementations will be readily apparent to one skilled in the art, and the general principles defined herein may be applied to other implementations and applications without departing from the scope of the present disclosure. The present disclosure is not intended to be limited to the implementations shown, but is to be accorded the widest possible scope consistent with the principles and features disclosed herein.

[0029] Herein is disclosed exemplary methods and systems for detection of pulmonary inflammation due to diseases such as COVID-19. Exemplary sputum samples may be obtained from suspicious subjects to be air-dried and imaged by an imaging system. An exemplary imaging system may include a mini-microscope for magnifying air-dried samples and an imaging device equipped with a processor (such as a smartphone camera) to capture a magnified image of air-dried samples and process exemplary captured images. Exemplary sputum samples of infected subjects may contain fem patterns after air-drying due to presence of electrolytes sodium (Na) or potassium (K) ions in the sputum sample in sputum of subjects with pulmonary inflammation. Therefore, an exemplary convolutional neural network may be trained to detect fern patterns in images of sputum samples of infected subjects and distinguish infected subjects from non-infected ones based on fern patterns in exemplary images of airdried samples.

[0030] FIG. 1A shows a flowchart of a method for detecting pulmonary inflammation in a subject, consistent with one or more exemplary embodiments of the present disclosure. An exemplary method 100 may include acquiring a sputum sample from the subject (step 102), acquiring a magnified image of the sputum sample (step 104), and detecting the pulmonary inflammation based on fern patterns in the magnified image (step 106).

[0031] In further detail regarding step 102, FIG. IB shows a flowchart for acquiring a sputum sample, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, acquiring the sputum sample in step 102 may include acquiring a drop of sputum from the subject (step 108), placing the drop of sputum at a center of a sample slide (step 110), and obtaining the sputum sample by air-drying the drop of sputum (step 112).

[0032] For further detail with respect to 108, FIG. 2A shows a schematic of acquiring a drop of sputum from a subject, consistent with one or more exemplary embodiments of the present disclosure. To acquire an exemplary drop 202 of sputum in step 108, an exemplary subject 202 may spit into a sample tube 206.

[0033] In further detail with regards to 110, FIG. 2B shows a schematic of placing a drop of sputum at a center of a sample slide, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, drop 202 may be pulled into a dropper 208 from sample tube 206. Next, in an exemplary embodiment, drop 202 may be dropped on a center 210 of a sample slide 212 by dropper 208. In an exemplary embodiment, sample slide 212 may be a thin rectangular glass and center 210 may include a semi-circular area around a center of a rectangular surface of sample slide 212.

[0034] In an exemplary embodiment, step 112 may include obtaining the sputum sample by air-drying drop 204. For this purpose, in an exemplary embodiment, drop 204 may be left on sample slide 212 at room temperature for a given amount of time until drop 204 is died. An exemplary amount of time for air-drying drop 204 may be about 30 minutes.

[0035] Referring again to FIG. 1A, in an exemplary embodiment, step 104 may include acquiring a magnified image of the sputum sample. In an exemplary embodiment, an imaging system may be utilized for acquiring the magnified image. FIG. 3 A shows a top view of an imaging system, consistent with one or more exemplary embodiments of the present disclosure. An exemplary imaging system 300 may include a mini-microscope 302, an imaging device 304, and a stand 306. In an exemplary embodiment, imaging system 300 may be utilized for acquiring a magnified image 308 of the sputum sample, as described below.

[0036] In further detail regarding step 104, FIG. 1C shows a flowchart for acquiring a magnified image of a sputum sample, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, acquiring the magnified image in step 104 may include inserting the sample slide inside the mini-microscope between a condensing lens of the mini -microscope and a magnifying lens of the mini -microscope (step 114), holding the imaging device above the magnifying lens by the stand (step 116), and capturing the magnified image through the magnifying lens (step 118).

[0037] For further detail with regards to 114, FIG. 3B shows a schematic of an exploded view of a mini-microscope, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, mini-microscope 302 may include a magnifying lens 310 In an exemplary embodiment, magnifying lens 310 may provide an about 40X magnification that is sufficient to see an air-dried sputum sample with a diameter of about 5 mm.

[0038] In an exemplary embodiment, mini-microscope 302 may further include a light emitting diode (LED) 312 that is attached to an electronic board 314 to provide lighting for minimicroscope 302. In an exemplary embodiment, mini-microscope 302 may also include a condensing lens 316 that may be placed above LED 312 for uniform illumination of a sputum sample. In an exemplary embodiment, sample slide 212 may be inserted in step 114 in a zone 318 between condensing lens 316 and magnifying lens 310 at an optimized working distance for having a best focus on fem structures of a sputum sample. As a result, a magnified view of an exemplary sputum sample placed on sample slide 212 may be observed from above minimicroscope 302 through magnifying lens 310.

[0039] In further detail with respect to step 116, in an exemplary embodiment, minimicroscope 302 may further include a cap 320. Referring to FIGs. 3A and 3B, in an exemplary embodiment, cap 320 may have a top side 322 with a flat surface so that cap 320 may function as stand 306 for holding imaging device 304. In an exemplary embodiment, imaging device 304 may be placed in step 116 on top side 322 above magnifying lens 310. [0040] In an exemplary embodiment, step 118 may include capturing magnified image 308 through magnifying lens 310. For this purpose, an aperture of imaging device 304 may be aligned with magnifying lens 310 to observe a sputum sample placed on sample slide 212 through magnifying lens 310. Next, imaging device 304 may focus on an exemplary sputum sample and an observed scene by imaging device 304 may be captured. In an exemplary embodiment, imaging device 304 may be a smartphone equipped with a camera so that magnified image 308 may be sent to a processor of an exemplary smartphone after being captured by an exemplary camera of the smartphone. An exemplary processor may perform proceeding steps of method 100 on magnified image 308, as described below.

[0041] Referring again to FIGs. 1A and 3A, in an exemplary embodiment, step 106 may include detecting pulmonary inflammation based on fem patterns in magnified image 308. During pulmonary inflammation, several white blood cells may be called by an exemplary immune system to come to a lung ambient for fighting against viruses. For this purpose, tiny micro-vessels around an exemplary respiratory alveolus may be dilated and become permeable for the traverse of immune cells. Such leakiness of vessels may result in filling of exemplary air sacs by a blood fluid and a consequent acute respiratory distress syndrome (ARDS), causing failure in some parts of lungs. An exemplary blood serum infiltration to a lung ambient may change sputum components' contents and concentration, especially electrolyte salts such as Na and K.

[0042] FIG. 4A shows a magnified image of a sputum sample of a subject with pulmonary inflammation, consistent with one or more exemplary embodiments of the present disclosure. An exemplary magnified image 402 may be obtained (similar to obtaining magnified image 308) from a sputum sample of a subject with pulmonary inflammation. In an exemplary embodiment, crystallization of Na and K salts in sputum components of a subject with pulmonary inflammation may lead to formation of branchy and fem-like patterns in the sputum sample of the subject. Therefore, in an exemplary embodiment, magnified image 402 may include several fern patterns. In other words, in an exemplary embodiment, an increased salt concentration in a sputum of a subject with pulmonary inflammation may be translated into a graphical image of sputum (such as magnified image 402). As a result, an exemplary area 404 of fern patterns in magnified image 402 may occupy a significant portion (more than 60%) of a total area 406 of magnified image 402. [0043] FIG. 4B shows a magnified image of a sputum sample of a subject without pulmonary inflammation, consistent with one or more exemplary embodiments of the present disclosure. An exemplary magnified image 408 may be obtained (similar to obtaining magnified image 308) from a sputum sample of a subject without pulmonary inflammation. An exemplary area 410 of fem patterns in magnified image 408 may occupy a minor portion (less than 40%) of a total area 412 of magnified image 408. Therefore, in an exemplary embodiment, fern patterns in magnified images of sputum samples may be efficiently utilized for distinguishing subjects that suffer from pulmonary inflammation from subjects without pulmonary inflammation, as described below.

[0044] FIG. ID shows a flowchart for detecting pulmonary inflammation based on fern patterns in a magnified image, consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, detecting the pulmonary inflammation in step 106 may include obtaining a classified output by applying the magnified image to a convolutional neural network (step 120) and detecting the pulmonary inflammation based on the classified output (step 122).

[0045] In further detail with respect to step 120, FIG. 5 shows a schematic of a convolutional neural network (CNN), consistent with one or more exemplary embodiments of the present disclosure. In an exemplary embodiment, magnified image 308 may be applied to a CNN 500 in step 120. In an exemplary embodiment, CNN 500 may resize magnified image 308 to about 224x224 pixels and may be uniformly scaled in depth, width, and resolution. In an exemplary embodiment, CNN 500 may include 7 main blocks, each containing a varying number of subblocks. In an exemplary embodiment, CNN 500 may be trained prior to step 120 with a training dataset to produce a classified output 504 by processing magnified image 308. In an exemplary embodiment, classified output 504 may be either a non-pulmonary inflammation output or a pulmonary inflammation output. An exemplary non-pulmonary inflammation output may correspond to not detecting pulmonary inflammation in an exemplary subject (such as subject 202). On a contrary, an exemplary pulmonary inflammation output may correspond to detection of pulmonary inflammation in an exemplary subject.

[0046] In an exemplary embodiment, step 122 may include detecting pulmonary inflammation in subject 202 responsive to the inflammation output being obtained at classified output 504. In an exemplary embodiment, obtaining the non-pulmonary inflammation output at classified output 504 may indicate that no pulmonary inflammation is detected in subject 202 based on magnified image 308. In an exemplary embodiment, obtaining the pulmonary inflammation output at classified output 504 may indicate that pulmonary inflammation is detected in subject 202 based on magnified image 308.

[0047] In an exemplary embodiment, method 100 may further include training CNN 500 prior to step 120. FIG. IE shows a flowchart of a method for training a CNN, consistent with one or more exemplary embodiments of the present disclosure. An exemplary method 124 may include obtaining a first plurality of salivary images (step 126), obtaining a second plurality of salivary images (step 128), mapping the first plurality of salivary images to the pulmonary inflammation output (step 130), and mapping the second plurality of salivary images to the non-pulmonary inflammation output (step 132).

[0048] In an exemplary embodiment, step 126 may include obtaining a first plurality of salivary images. An exemplary first plurality of salivary images may be obtained from salivary samples of a plurality of patients that suffer from pulmonary inflammation. Each exemplary salivary image of the first plurality of salivary images may include fern patterns in at least 60% of an area of an exemplary salivary image. In an exemplary embodiment, each of the first plurality of salivary images may be obtained utilizing imaging system 300 of FIG 3A, similar to obtaining magnified image 308 and presence of fern patterns in each salivary image may be validated before being added to the first plurality of salivary images.

[0049] In an exemplary embodiment, step 128 may include obtaining a second plurality of salivary images. An exemplary second plurality of salivary images may be obtained from salivary samples of a healthy subjects. In an exemplary embodiment, a “healthy subject” may refer to an individual without pulmonary inflammation. In an exemplary embodiment, each of the second plurality of salivary images may be obtained utilizing imaging system 300 of FIG 3A, similar to obtaining magnified image 308.

[0050] Referring to FIGs. IE and 4, in an exemplary embodiment, step 130 may include mapping the first plurality of salivary images to the pulmonary inflammation output. For this purpose, in an exemplary embodiment, each of the first plurality of salivary images may be applied to CNN 500 and CNN 500 may be trained to generate the pulmonary inflammation output at classified output 504 when each of the first plurality of salivary images is applied to CNN 500

[0051] In an exemplary embodiment, step 132 may include mapping the second plurality of salivary images to the non-pulmonary inflammation output. For this purpose, in an exemplary embodiment, each of the second plurality of salivary images may be applied to CNN 500 and CNN 500 may be trained to generate the non-pulmonary inflammation output at classified output 504 when each of the first plurality of salivary images is applied to CNN 500.

[0052] FIG. 6 shows an example computer system 600 in which an embodiment of the present invention, or portions thereof, may be implemented as computer-readable code, consistent with exemplary embodiments of the present disclosure. For example, different steps of method 100 may be implemented in computer system 600 using hardware, software, firmware, tangible computer readable media having instructions stored thereon, or a combination thereof and may be implemented in one or more computer systems or other processing systems. Hardware, software, or any combination of such may embody any of the modules and components in FIGs. 1A-1E, 3A, 3B, and 5

[0053] If programmable logic is used, such logic may execute on a commercially available processing platform or a special purpose device. One ordinary skill in the art may appreciate that an embodiment of the disclosed subject matter can be practiced with various computer system configurations, including multi-core multiprocessor systems, minicomputers, mainframe computers, computers linked or clustered with distributed functions, as well as pervasive or miniature computers that may be embedded into virtually any device.

[0054] For instance, a computing device having at least one processor device and a memory may be used to implement the above-described embodiments. A processor device may be a single processor, a plurality of processors, or combinations thereof. Processor devices may have one or more processor “cores.”

[0055] An embodiment of the invention is described in terms of this example computer system 600. After reading this description, it will become apparent to a person skilled in the relevant art how to implement the invention using other computer systems and/or computer architectures. Although operations may be described as a sequential process, some of the operations may in fact be performed in parallel, concurrently, and/or in a distributed environment, and with program code stored locally or remotely for access by single or multiprocessor machines. In addition, in some embodiments the order of operations may be rearranged without departing from the spirit of the disclosed subject matter.

[0056] Processor device 604 may be a special purpose (e g., a graphical processing unit) or a general -purpose processor device. As will be appreciated by persons skilled in the relevant art, processor device 604 may also be a single processor in a multi-core/multiprocessor system, such system operating alone, or in a cluster of computing devices operating in a cluster or server farm. Processor device 604 may be connected to a communication infrastructure 606, for example, a bus, message queue, network, or multi-core message-passing scheme.

[0057] In an exemplary embodiment, computer system 600 may include a display interface 602, for example a video connector, to transfer data to a display unit 630, for example, a monitor. Computer system 600 may also include a main memory 608, for example, random access memory (RAM), and may also include a secondary memory 610. Secondary memory 610 may include, for example, a hard disk drive 612, and a removable storage drive 614. Removable storage drive 614 may include a floppy disk drive, a magnetic tape drive, an optical disk drive, a flash memory, or the like. Removable storage drive 614 may read from and/or write to a removable storage unit 618 in a well-known manner. Removable storage unit 618 may include a floppy disk, a magnetic tape, an optical disk, etc., which may be read by and written to by removable storage drive 614. As will be appreciated by persons skilled in the relevant art, removable storage unit 618 may include a computer usable storage medium having stored therein computer software and/or data.

[0058] In alternative implementations, secondary memory 610 may include other similar means for allowing computer programs or other instructions to be loaded into computer system 600. Such means may include, for example, a removable storage unit 622 and an interface 620. Examples of such means may include a program cartridge and cartridge interface (such as that found in video game devices), a removable memory chip (such as an EPROM, or PROM) and associated socket, and other removable storage units 622 and interfaces 620 which allow software and data to be transferred from removable storage unit 622 to computer system 600. [0059] Computer system 600 may also include a communications interface 624. Communications interface 624 allows software and data to be transferred between computer system 600 and external devices. Communications interface 624 may include a modem, a network interface (such as an Ethernet card), a communications port, a PCMCIA slot and card, or the like. Software and data transferred via communications interface 624 may be in the form of signals, which may be electronic, electromagnetic, optical, or other signals capable of being received by communications interface 624. These signals may be provided to communications interface 624 via a communications path 626. Communications path 626 carries signals and may be implemented using wire or cable, fiber optics, a phone line, a cellular phone link, an RF link or other communications channels. [0060] In this document, the terms “computer program medium” and “computer usable medium” are used to generally refer to media such as removable storage unit 618, removable storage unit 622, and a hard disk installed in hard disk drive 612. Computer program medium and computer usable medium may also refer to memories, such as main memory 608 and secondary memory 610, which may be memory semiconductors (e.g. DRAMs, etc.).

[0061] Computer programs (also called computer control logic) are stored in main memory 508 and/or secondary memory 610. Computer programs may also be received via communications interface 624. Such computer programs, when executed, enable computer system 600 to implement different embodiments of the present disclosure as discussed herein. In particular, the computer programs, when executed, enable processor device 604 to implement the processes of the present disclosure, such as the operations in method 100 illustrated by flowcharts of FIG. 1A-FIG. IE discussed above. Accordingly, such computer programs represent controllers of computer system 600. Where an exemplary embodiment of method 100 is implemented using software, the software may be stored in a computer program product and loaded into computer system 600 using removable storage drive 614, interface 620, and hard disk drive 612, or communications interface 624.

[0062] Embodiments of the present disclosure also may be directed to computer program products including software stored on any computer useable medium. Such software, when executed in one or more data processing device, causes a data processing device to operate as described herein. An embodiment of the present disclosure may employ any computer useable or readable medium. Examples of computer useable mediums include, but are not limited to, primary storage devices (e.g., any type of random access memory), secondary storage devices (e.g., hard drives, floppy disks, CD ROMS, ZIP disks, tapes, magnetic storage devices, and optical storage devices, MEMS, nanotechnological storage device, etc.).

[0063] The embodiments have been described above with the aid of functional building blocks illustrating the implementation of specified functions and relationships thereof. The boundaries of these functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternate boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed.

EXAMPLE [0064] In this example, performance of an exemplary method similar to method 100 in detecting pulmonary inflammation is demonstrated. A number of COVID-19 positive patients who were suspicious of pulmonary involvement underwent lung CT imaging and were divided into two cohorts of positive and negative CT. An exemplary positive CT scan refers to presence of common patterns such as glass ground opacification (GGO), consolidation, hazy patch, etc. Exemplary sputum samples were collected from all of the two groups (53 subjects in total). All of exemplary sputum samples were collected in an early morning and before the volunteers consume food or drink. Also, subjects with a history of tobacco and alcohol consumption were excluded from cohorts. After sampling, each exemplary sputum sample was left alone for about 30 minutes for precipitation of cells and other residues. A part of each collected sputum sample was utilized for electrolyte measurement, and a small volume (about 10 pl) was dropped on a surface of a sample slide (similar to sample slide 212) and left at room temperature for air drying. Then the dried sample was inserted into an exemplary mini-microscope (similar to mini-microscope 302) to image fem patterns in each exemplary sputum sample.

[0065] In order to observe fem patterns with a desired resolution by a smartphone camera, a smartphone-based microscopy tool (60x60x60 mm) was considered and 3D printed from polylactic acid (PLA). An exemplary imaging system (similar to imaging system 300) consisted of a plano-convex lens of about 5 mm diameter with a focal length of about 6 mm as a magnifying lens (similar to magnifying lens 310) and a commercial acrylic condensing lens (similar to condensing lens 316) compatible with a chosen LED. A 3V and 5W white LED (similar to LED 312) was used for illumination. An exemplary LED was powered by a battery with an about 1.2 kQ resistor to obtain an optimum light intensity. A whole electronic circuit (similar to electronic board 314) was integrated on a printed circuit board. All of the exemplary lenses, the exemplary smartphone lens, and the exemplary LED had a common optical axis.

[0066] To detect fem patterns in saliva on a smartphone, an exemplary CNN (similar to CNN 500) was pre-trained with a large dataset that included about 14 million images. Next, the exemplary CNN was retrained and validated using a dataset of 403 salivary images derived from 53 participants. All exemplary images were labeled into two groups of fern (corresponding to the pulmonary inflammation output) and non-fern (corresponding to the non- pulmonary inflammation output). The exemplary dataset of labeled images was split into two training and validation groups, 80% (323) and 20% (80) of total images, respectively. All exemplary input images were resized to 224 x 224 pixels, and the retraining process was done for 80 training steps (epochs) with a learning rate of about 0.001. Cross-entropy as a loss function and accuracy was measured to evaluate the learning process of the exemplary CNN. “Training accuracy” and “validation accuracy” refer to percentages of correctly detected images by the exemplary CNN in training and validation datasets, respectively. A variance between training and validation accuracies was calculated to know if the exemplary CNN was overfitting. At the 80^th training step (epoch), the validation cross-entropy/loss and accuracy were about 0.118 and 97.53%, respectively. Exemplary weights corresponding to the best performance were saved and used for the exemplary CNN.

[0067] Table 1 shows a 2><2 confusion matrix of the exemplary method for detecting pulmonary inflammation. An exemplary 2x2 confusion matrix shows an accuracy of about 96.6% for the exemplary method. Meanwhile, the specificity and sensitivity are 100% and about 93.97%, respectively. Furthermore, based on the resulting specificity and sensitivity, a positive predictive value (PPV) of 100% and a negative predictive value (NPV) of about 93% are obtained for the exemplary method.

Table 1. 2x2 confusion matrix for detecting pulmonary inflammation

[0068] FIG. 7 shows receiver operating characteristic (ROC) curve of a method for detecting pulmonary inflammation, consistent with exemplary embodiments of the present disclosure. An exemplary output of the trained CNN is a continuous number between 0 and 1, representing a probability of an exemplary image of a sputum sample belonging to a specific class. An exemplary ROC curve 700 is plotted based on different threshold values to find the best operating point for classifying images of a sputum sample into pulmonary inflammation and non- pulmonary inflammation classes. An area under ROC curve 700 (AUC) shows the ability of the exemplary method to distinguish different classes. The exemplary AUC shows a value of about 0.99, which is highly acceptable.

[0069] While the foregoing has described what may be considered to be the best mode and/or other examples, it is understood that various modifications may be made therein and that the subject matter disclosed herein may be implemented in various forms and examples, and that the teachings may be applied in numerous applications, only some of which have been described herein. It is intended by the following claims to claim any and all applications, modifications and variations that fall within the true scope of the present teachings.

[0070] Unless otherwise stated, all measurements, values, ratings, positions, magnitudes, sizes, and other specifications that are set forth in this specification, including in the claims that follow, are approximate, not exact. They are intended to have a reasonable range that is consistent with the functions to which they relate and with what is customary in the art to which they pertain.

[0071] The scope of protection is limited solely by the claims that now follow. That scope is intended and should be interpreted to be as broad as is consistent with the ordinary meaning of the language that is used in the claims when interpreted in light of this specification and the prosecution history that follows and to encompass all structural and functional equivalents. Notwithstanding, none of the claims are intended to embrace subject matter that fails to satisfy the requirement of Sections 101, 102, or 103 of the Patent Act, nor should they be interpreted in such a way. Any unintended embracement of such subject matter is hereby disclaimed.

[0072] Except as stated immediately above, nothing that has been stated or illustrated is intended or should be interpreted to cause a dedication of any component, step, feature, object, benefit, advantage, or equivalent to the public, regardless of whether it is or is not recited in the claims.

[0073] It will be understood that the terms and expressions used herein have the ordinary meaning as is accorded to such terms and expressions with respect to their corresponding respective areas of inquiry and study except where specific meanings have otherwise been set forth herein. Relational terms such as first and second and the like may be used solely to distinguish one entity or action from another without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms “comprises,” “comprising,” or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by “a” or “an” does not, without further constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0074] The Abstract of the Disclosure is provided to allow the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the foregoing Detailed Description, it can be seen that various features are grouped together in various implementations. This is for purposes of streamlining the disclosure, and is not to be interpreted as reflecting an intention that the claimed implementations require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed implementation. Thus, the following claims are hereby incorporated into the Detailed Description, with each claim standing on its own as a separately claimed subject matter.

[0075] While various implementations have been described, the description is intended to be exemplary, rather than limiting and it will be apparent to those of ordinary skill in the art that many more implementations and implementations are possible that are within the scope of the implementations. Although many possible combinations of features are shown in the accompanying figures and discussed in this detailed description, many other combinations of the disclosed features are possible. Any feature of any implementation may be used in combination with or substituted for any other feature or element in any other implementation unless specifically restricted. Therefore, it will be understood that any of the features shown and/or discussed in the present disclosure may be implemented together in any suitable combination. Accordingly, the implementations are not to be restricted except in light of the attached claims and their equivalents. Also, various modifications and changes may be made within the scope of the attached claims.

Claims

What is claimed is:

1. A method for detecting pulmonary inflammation in a subject, the method comprising: obtaining, utilizing an imaging system, a first plurality of salivary images associated with pulmonary inflammation in a plurality of patients, each of the first plurality of salivary images comprising fern patterns in at least 60% of an area of each respective salivary image of the first plurality of salivary images; obtaining, utilizing the imaging system, a second plurality of salivary images associated with healthy subjects; mapping, utilizing one or more processors, the first plurality of salivary images to a pulmonary inflammation output of a convolutional neural network (CNN) by applying each of the first plurality of salivary images to the CNN; mapping the second plurality of salivary images to a non-pulmonary inflammation output by applying each of the second plurality of salivary images to the CNN; acquiring a drop of sputum from the subject; placing the drop of sputum at a center of a sample slide; obtaining a sputum sample by air-drying the drop of sputum; inserting the sample slide inside a mini-microscope of the imaging system between a condensing lens of the mini-microscope and a magnifying lens of the mini-microscope; holding an imaging device of the imaging system above the magnifying lens by a stand; capturing, utilizing the imaging device, the magnified image through the magnifying lens; obtaining, utilizing the one or more processors, a classified output by applying the magnified image to the CNN, the classified output comprising one of the non-pulmonary inflammation output or the pulmonary inflammation output; and detecting, utilizing the one or more processors, the pulmonary inflammation responsive to the inflammation output being obtained at the classified output.

2. A method for detecting pulmonary inflammation in a subject, the method comprising: acquiring a sputum sample from the subject; acquiring, utilizing an imaging system, a magnified image of the sputum sample; and detecting, utilizing one or more processors, the pulmonary inflammation based on fern patterns in the magnified image.

3. The method of claim 2, wherein detecting the pulmonary inflammation comprises: obtaining a classified output by applying the magnified image to a convolutional neural network (CNN), the classified output comprising one of a non-pulmonary inflammation output or a pulmonary inflammation output; and detecting the pulmonary inflammation responsive to the inflammation output being obtained at the classified output.

4. The method of claim 3, further comprising training the CNN by: obtaining a first plurality of salivary images associated with pulmonary inflammation in a plurality of patients, each of the first plurality of salivary images comprising fern patterns in at least 60% of an area of each respective salivary image of the first plurality of salivary images; obtaining a second plurality of salivary images associated with healthy subjects; mapping the first plurality of salivary images to the pulmonary inflammation output by applying each of the first plurality of salivary images to the CNN; and mapping the second plurality of salivary images to the non-pulmonary inflammation output by applying each of the second plurality of salivary images to the CNN.

5. The method of claim 2, wherein acquiring the sputum sample comprises: acquiring a drop of sputum from the subject; placing the drop of sputum at a center of a sample slide; and obtaining the sputum sample by air-drying the drop of sputum.

6. The method of claim 5, wherein acquiring the magnified image comprises: inserting the sample slide inside a mini-microscope of the imaging system between a condensing lens of the mini-microscope and a magnifying lens of the mini-microscope; holding an imaging device of the imaging system above the magnifying lens by a stand; and capturing, utilizing the imaging device, the magnified image through the magnifying lens.

7. A system for detecting pulmonary inflammation in a subject, the system comprising: a sample slide configured to hold a sputum sample of the subject at a center of the sample slide; an imaging system configured to acquire a magnified image of the sputum sample; a memory having processor-readable instructions stored therein; and one or more processors configured to access the memory and execute the processor- readable instructions, which, when executed by the one or more processors configures the one or more processors to perform a method, the method comprising: detecting the pulmonary inflammation based on fern patterns in the magnified image.

8. The system of claim 7, wherein detecting the pulmonary inflammation comprises: obtaining a classified output by applying the magnified image to a convolutional neural network (CNN), the classified output comprising one of a non-pulmonary inflammation output or a pulmonary inflammation output; and detecting the pulmonary inflammation responsive to the inflammation output being obtained at the classified output.

9. The system of claim 8, wherein the method further comprises training the CNN by: obtaining a first plurality of salivary images associated with pulmonary inflammation in a plurality of patients, each of the first plurality of salivary images comprising fern patterns in at least 60% of an area of each respective salivary image of the first plurality of salivary images; obtaining a second plurality of salivary images associated with healthy subjects; mapping the first plurality of salivary images to the pulmonary inflammation output by applying each of the first plurality of salivary images to the CNN; and mapping the second plurality of salivary images to the non-pulmonary inflammation output by applying each of the second plurality of salivary images to the CNN.

10. The system of claim 7, wherein the imaging system comprises a mini-microscope configured to magnify an image of the sputum sample, the mini-microscope comprising a condensing lens placed below the sample slide; and a magnifying lens placed above the sample slide.

11. The system of claim 10, wherein the imaging system further comprises an imaging device configured to capture the magnified image through the magnifying lens.

12. The system of claim 11, wherein the imaging system further comprises a stand configured to hold the imaging device above the magnifying lens.