TWI828009B - 免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 - Google Patents
免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 Download PDFInfo
- Publication number
- TWI828009B TWI828009B TW110143123A TW110143123A TWI828009B TW I828009 B TWI828009 B TW I828009B TW 110143123 A TW110143123 A TW 110143123A TW 110143123 A TW110143123 A TW 110143123A TW I828009 B TWI828009 B TW I828009B
- Authority
- TW
- Taiwan
- Prior art keywords
- cell
- image
- cell sample
- activity
- car
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 title claims abstract description 18
- 230000003833 cell viability Effects 0.000 title abstract description 4
- 238000012544 monitoring process Methods 0.000 title abstract 2
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 210000004027 cell Anatomy 0.000 claims description 211
- 230000000694 effects Effects 0.000 claims description 107
- 238000009647 digital holographic microscopy Methods 0.000 claims description 64
- 238000013473 artificial intelligence Methods 0.000 claims description 39
- 238000001514 detection method Methods 0.000 claims description 23
- 210000001744 T-lymphocyte Anatomy 0.000 claims description 14
- 238000001000 micrograph Methods 0.000 claims description 10
- 108091007741 Chimeric antigen receptor T cells Proteins 0.000 claims description 2
- 108010019670 Chimeric Antigen Receptors Proteins 0.000 claims 1
- 238000002073 fluorescence micrograph Methods 0.000 abstract description 13
- 230000035899 viability Effects 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000002372 labelling Methods 0.000 description 5
- 230000001363 autoimmune Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000002560 therapeutic procedure Methods 0.000 description 4
- 206010028980 Neoplasm Diseases 0.000 description 3
- 230000010261 cell growth Effects 0.000 description 3
- 238000009169 immunotherapy Methods 0.000 description 3
- 210000004369 blood Anatomy 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 238000002659 cell therapy Methods 0.000 description 2
- 238000002512 chemotherapy Methods 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000007850 fluorescent dye Substances 0.000 description 2
- 238000012239 gene modification Methods 0.000 description 2
- 230000005017 genetic modification Effects 0.000 description 2
- 235000013617 genetically modified food Nutrition 0.000 description 2
- 210000002865 immune cell Anatomy 0.000 description 2
- 238000001802 infusion Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 1
- 238000001069 Raman spectroscopy Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000006907 apoptotic process Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000011324 bead Substances 0.000 description 1
- 201000011510 cancer Diseases 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229910052801 chlorine Inorganic materials 0.000 description 1
- 239000000460 chlorine Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000004043 dyeing Methods 0.000 description 1
- 238000001215 fluorescent labelling Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000003368 label free method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 238000001959 radiotherapy Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 238000002626 targeted therapy Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
- 229960005486 vaccine Drugs 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G01N15/1433—
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/5005—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells
- G01N33/5008—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics
- G01N33/5044—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving human or animal cells for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics involving specific cell types
- G01N33/5047—Cells of the immune system
- G01N33/505—Cells of the immune system involving T-cells
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N15/14—Electro-optical investigation, e.g. flow cytometers
- G01N15/1429—Electro-optical investigation, e.g. flow cytometers using an analyser being characterised by its signal processing
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/0005—Adaptation of holography to specific applications
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/04—Processes or apparatus for producing holograms
- G03H1/0443—Digital holography, i.e. recording holograms with digital recording means
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/04—Processes or apparatus for producing holograms
- G03H1/08—Synthesising holograms, i.e. holograms synthesized from objects or objects from holograms
- G03H1/0866—Digital holographic imaging, i.e. synthesizing holobjects from holograms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume, or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N15/14—Electro-optical investigation, e.g. flow cytometers
- G01N15/1434—Electro-optical investigation, e.g. flow cytometers using an analyser being characterised by its optical arrangement
- G01N2015/1454—Electro-optical investigation, e.g. flow cytometers using an analyser being characterised by its optical arrangement using phase shift or interference, e.g. for improving contrast
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/0005—Adaptation of holography to specific applications
- G03H2001/0033—Adaptation of holography to specific applications in hologrammetry for measuring or analysing
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/0005—Adaptation of holography to specific applications
- G03H2001/005—Adaptation of holography to specific applications in microscopy, e.g. digital holographic microscope [DHM]
-
- G—PHYSICS
- G03—PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
- G03H—HOLOGRAPHIC PROCESSES OR APPARATUS
- G03H1/00—Holographic processes or apparatus using light, infrared or ultraviolet waves for obtaining holograms or for obtaining an image from them; Details peculiar thereto
- G03H1/04—Processes or apparatus for producing holograms
- G03H1/0443—Digital holography, i.e. recording holograms with digital recording means
- G03H2001/0447—In-line recording arrangement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10056—Microscopic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10064—Fluorescence image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Abstract
本發明提供一種訓練人工智慧執行免標記式細胞活性檢測的方法。獲取細胞樣本的螢光影像和數位全像顯微影像。根據細胞樣本的螢光影像確定細胞樣本具有特定細胞活性。將細胞樣本的數位全像顯微影像標記為具有特定細胞活性的範例。以細胞樣本的數位全像顯微影像進行人工智慧的機器學習。
Description
本發明係關於一種免標記式細胞活性檢測的方法,以及訓練人工智慧執行免標記式細胞活性檢測的方法。
按,以往在醫學領域對抗腫瘤的方式包含外科手術、放射線治療、化學治療、標靶治療等,而傳統化學治療的專一性較低,容易殺死腫瘤以外的健康細胞而導致全身性的不良副作用。近來,有發展出自體免疫療法做為新的腫瘤治療對策。自體免疫療法可包含藥物、細胞治療和疫苗。其中,T細胞免疫療法透過嵌合抗原受體T細胞(CAR-T cells)而能更有效地識別腫瘤細胞並精確地將其殺傷,並且CAR-T細胞可以是來自於對αβT免疫細胞或γδT免疫細胞進行基因改造。用於T細胞免疫療法之CAR-T細胞的製造涉及了從患者體內取出T細胞、T細胞分離、基因改造、細胞擴增等流程。由於CAR-T細胞需要輸回患者體內,因此關於輸回人體前的CAR-T細胞活性檢測必須採用非標記、非破壞性的活性檢測技術。
隨著細胞治療產業應用需求擴大,細胞產品需要大規模,標準規格與工業化生產技術,因此整合細胞產品製造、品質檢測和繼代培養等功能的細胞生產自動化系統的發展備受關注。目前,有一種非標記且非破壞性的細胞活性檢測方法是採用數位全像顯微技術(Digital holographic microscopy,DHM)拍攝活體CAR-T細胞,以根據CAR-T細胞影像的光強度及相位差反應評估細胞活性高低程度。然而,現有的方法存在高成本且效率低的問題,因此難以被應用至細胞生產自動化系統。
鑑於上述問題,本發明提供一種訓練人工智慧執行細胞活性檢測的方法,藉此讓DHM影像能應用於訓練人工智慧執行細胞活性檢測。
本發明一實施例所揭露之訓練人工智慧執行免標記式細胞活性檢測的方法包含:提供一細胞樣本;獲取細胞樣本的螢光影像和數位全像顯微影像;根據細胞樣本的螢光影像確定細胞樣本具有特定細胞活性;將細胞樣本的數位全像顯微影像標記為具有特定細胞活性的範例;以及以細胞樣本的數位全像顯微影像進行人工智慧的機器學習。
根據本發明揭露之根據本發明揭露之訓練人工智慧執行免標記式細胞活性檢測的方法,提供一種利用被標記特定細胞活性的DHM影像作為數據訓練人工智慧。採用螢光影像確定CAR-T細胞的活性,並且以此結果標記DHM影像為高/低活性範例。後續機器學習階段,將高/低活性範例之DHM影像中的所有CAR-T細胞影像皆視為具有高/低活性特徵。藉此,可以大幅提升機器學習的效率,進而讓DHM影像適用於人工智慧的機器學習。
本發明一實施例所揭露之免標記式細胞活性檢測的方法包含:藉由人工智慧根據受測細胞樣本的數位全像顯微影像判斷受測細胞樣本的細胞活性,其中人工智慧以前述之方法進行訓練。
以上關於本發明內容之說明及以下實施方式之說明係用以示範與解釋本發明之原理,並提供本發明之專利申請範圍更進一步之解釋。
於以下實施方式中詳細敘述本發明之詳細特徵及優點,其內容足以使任何熟習相關技藝者了解本發明之技術內容並據以實施,且根據本說明書所揭露的內容、申請專利範圍及圖式,任何熟習相關技藝者可輕易理解本發明相關之目的及優點。以下實施例係進一步詳細說明本發明之觀點,但非以任何觀點限制本發明之範疇。
請參閱圖1,為自體免疫療法的示意圖。此處,以T細胞免疫療法作為範例說明,其包含從患者體內取出血液(圖1(a))、從血液分離出T細胞(圖1(b))、T細胞基因改造成CAR-T細胞(圖1(c))、CAR-T細胞擴增(圖1(d))以及CAR-T細胞輸液回到患者體內(圖1(e)),並且在T細胞基因改造成CAR-T細胞或CAR-T細胞擴增後需要檢測CAR-T細胞活性後再輸回患者體內。在T細胞基因改造成CAR-T細胞後,檢測CAR-T細胞活性可以篩選出品質較好的CAR-T細胞進行後續的擴增。在CAR-T細胞擴增後檢測CAR-T細胞活性,可以幫助醫護人員評估所述CAR-T細胞是否適合輸液回到患者。細胞生產自動化致力於至少實現CAR-T細胞活性檢測的自動化。
細胞活性檢測一般而言大致可分為需標記和免標記(Lable-free)的類型。需標記類型例如螢光標記法和磁珠標記法,其有很高機率會改變細胞的物化性質甚至導致檢測完成後的細胞凋亡,致使如果採用需標記類型進行CAR-T細胞的活性檢測,檢測後的CAR-T細胞無法被輸回到患者體內。免標記的類型例如拉曼散射法、光學繞射斷層掃描(ODT)法以及DHM較適合應用於活體T細胞的活性檢測。其中,DHM因為對於細胞的表面起伏具有優異的光強度及相位差反應,成為較佳的選擇。
關於現有的DHM應用於細胞活性檢測,普遍作法是以人工方式判別DHM影像中的細胞位置以及此細胞的活性。具體來說,可用肉眼根據DHM影像中各個細胞影像的形狀、尺寸等資訊判斷細胞活性,然而這種方式效率差且無法應用於細胞生產自動化系統。因此,本發明考量兼顧使用DHM影像檢測CAR-T細胞活性以及滿足細胞生產自動化需求,而開發出一種訓練人工智慧執行免標記式細胞活性檢測的方法,並且搭載有已受訓練人工智慧的自動化系統可以執行CAR-T細胞的自動化活性檢測。
圖2為根據本發明一實施例之訓練人工智慧執行免標記式細胞活性檢測的方法的流程示意圖。此方法包含步驟S1至S5。更具體來說,此方法涉及如何建立用於訓練人工智慧的訓練集、驗證集和/或測試集。
步驟S1為提供細胞樣本。在一實施例中,可提供CAR-T細胞樣本,其包含由取自患者之T細胞進行基因改造後的CAR-T細胞,或是已經進行擴增的CAR-T細胞。進一步來說,步驟S1可以提供預估會有不同程度之細胞活性的多個細胞樣本;例如,提供第一CAR-T細胞樣本和第二CAR-T細胞樣本,其中第一CAR-T細胞樣本為從培養室中取出的CAR-T細胞樣本,第二CAR-T細胞樣本為培養室中取出的CAR-T細胞樣本以紫外光照射或以含氯溶液沖洗,因此可以預估第二CAR-T細胞樣本相較第一CAR-T細胞樣本具有較低的細胞活性。雖然前述提及了一些能調控細胞活性程度的方式,但本發明所採用的細胞樣本並不一定要進行這些調控作業,只要細胞樣本都是相同細胞即可。
步驟S2為獲取細胞樣本的螢光影像和DHM影像。在一實施例中,可獲取活體CAR-T細胞樣本的螢光影像和DHM影像。進一步來說,可以活體的第一CAR-T細胞樣本和第二CAR-T細胞樣本作為被攝物分別拍攝螢光影像和DHM影像,例如取用CAR-T細胞樣本的一部分以螢光染色(例如PI染色)用來拍攝螢光影像,未被螢光染色的另一部分則用來拍攝DHM影像。另外在步驟S2中,可藉由無透鏡式(Lens-free)數位全像顯微鏡根據相位差和光強度生成DHM影像。無透鏡式數位全像顯微鏡具有體積小、像差少和高解析度等優點。
圖3為圖2之流程示意圖中使用之螢光影像的示意圖。步驟S3為根據螢光影像確定細胞樣本具有特定細胞活性。在一實施例中,於步驟S2獲取之活體CAR-T細胞樣本的螢光影像中,會因為細胞活性高低而有不同的螢光訊號,因此能根據螢光訊號確定活體CAR-T細胞樣本的細胞活性。舉例來說,螢光訊號會因為細胞活性高低而有不同的表現,例如訊號強度或是螢光顏色會因為細胞活性高低而有所變化。在一實施例中,第一CAR-T細胞樣本的螢光影像(圖3(A))顯示出大部分的CAR-T細胞發出綠色螢光,因此判斷第一CAR-T細胞樣本具有較高細胞活性。第二CAR-T細胞樣本的螢光影像(圖3(B))顯示出大部分的CAR-T細胞發出紅色螢光,因此判斷第二CAR-T細胞樣本具有較低細胞活性。此處,細胞活性是依據螢光影像中特定螢光顏色的細胞數量或是螢光強度單純以「高」或「低」的二分法表示,但在其他實施例中可以是用數值將細胞活性予以量化,例如判斷第一CAR-T細胞樣本具有98%的活性,且第二CAR-T細胞樣本具有1%的活性。
圖4為圖2之流程示意圖中使用之DHM影像的示意圖。步驟S4為將細胞樣本的數位全像顯微影像標記為具有特定細胞活性的範例。在一實施例中,於步驟S2獲取之活體CAR-T細胞樣本的DHM影像包含複數個CAR-T細胞,並且藉由步驟S3中判斷的細胞活性程度標記DHM影像。具體來說,於步驟S3中根據螢光影像確定第一CAR-T細胞樣本具有高細胞活性,以及確定第二CAR-T細胞樣本具有低細胞活性,藉此第一CAR-T細胞樣本的DHM影像(圖4(A))被標記為高活性範例,並且第二CAR-T細胞樣本的DHM影像(圖4(B))被標記為低活性範例。
步驟S5為以細胞樣本的數位全像顯微影像進行人工智慧的機器學習。在一實施例中,第一CAR-T細胞樣本的DHM影像中的所有CAR-T細胞影像都被視為具有高活性特徵,第二CAR-T細胞樣本的DHM影像中的所有CAR-T細胞影像都被視為具有低活性特徵。將第一CAR-T細胞樣本和第二CAR-T細胞樣本的DHM影像提供給人工智慧作為機器學習模型的數據進行訓練。在人工智慧被訓練完成後,當人工智慧接收到未知活性的DHM影像時,人工智慧能判斷這個DHM影像中的CAR-T細胞影像是屬於高活性還是低活性。
此處提及的「DHM影像」係指以DHM拍攝CAR-T細胞樣本而得到包含複數個CAR-T細胞的一張影像,如圖4所示。另外,此處提及的「CAR-T細胞影像」係指單一CAR-T細胞於DHM影像中的成像。
本發明所適用的人工智慧機器學習包含監督式學習(Supervised Learning)和半監督式學習(Semi-supervised learning)。在接收一些標記特定細胞活性的DHM影像後,機器學習模型根據這些DHM影像中的細胞影像的光強度和相位差來預測具有特定細胞活性的DHM影像需要具備哪些特徵,從而建立一個函數(Learning model)。當人工智慧接收到未知活性的DHM影像時,此函數可以輸出迴歸分析(例如可以量化細胞活性的數值),或是預測分類(例如將細胞分為高活性群體或低活性群體)。常見被廣泛被使用的分類有類神經網路、支持向量機、最近鄰居法、高斯混合模型、樸素貝葉斯方法、決策樹和徑向基函數分類。
假設考量一種參考現有之人工判別DHM影像中CAR-T細胞活性高低的方法來訓練人工智慧,最直接的想法會是根據DHM影像確定CAR-T細胞活性來進行DHM影像之標記。然而實務上,根據DHM影像判斷CAR-T細胞活性除了相位差和光強度等可量化參數之外,還需要配合DHM影像中每個CAR-T細胞影像的尺寸、形狀等非量化參數才能提高判斷細胞活性的準確度,而這些非量化參數的判斷涉及了經驗法則而難以用機器取代。因此,若是採用根據CAR-T細胞影像確定細胞活性的方式來對DHM影像進行標記,需要針對DHM影像中的多個CAR-T細胞影像個別地人工確認細胞活性,這相當耗時而導致機器學習的效率非常差。
與前述方法相較,本發明所揭露的訓練人工智慧方法採用螢光影像確認CAR-T細胞的活性,並且以此確認結果標記DHM影像為高活性範例或低活性範例。在後續機器學習階段,將高活性範例之DHM影像中的所有CAR-T細胞影像皆視為具有高活性特徵的CAR-T細胞影像,且將低活性範例之DHM影像中的所有CAR-T細胞影像皆視為具有低活性特徵的CAR-T細胞影像。儘管這種方式無可避免地會將高活性範例之DHM影像中實際上是低活性的CAR-T細胞影像視為高活性,或是將低活性範例之DHM影像中實際上是高活性的CAR-T細胞影像視為低活性,但這種標記方法可以大幅提升機器學習的效率,或者更可以說這種標記方法能讓DHM影像應用於人工智慧的機器學習。
本發明還揭露一種免標記式細胞活性檢測的方法,包含藉由人工智慧根據受測細胞樣本的數位全像顯微影像判斷受測細胞樣本的細胞活性,其中人工智慧以前述之方法進行訓練。以前述的CAR-T細胞為例,受訓練的人工智慧能夠識別DHM影像中CAR-T細胞影像的高活性特徵或低活性特徵。將受測CAR-T細胞樣本的DHM影像輸入給人工智慧後,可根據DHM影像中CAR-T細胞影像的特徵得到DHM影像中高活性CAR-T細胞數量與低活性CAR-T細胞數量,進而確定受測CAR-T細胞樣本的細胞活性。本發明還觀察到以前述方法訓練後的人工智慧實際執行細胞活性檢測的表現並不會太差,甚至以50張有標記的DHM影像訓練後的人工智慧有約81.27%的準確度,也就是說DHM影像中的所有CAR-T細胞影像僅有近兩成會被誤判活性。
綜上所述,根據本發明揭露之訓練人工智慧執行免標記式細胞活性檢測的方法,提供一種利用被標記特定細胞活性的DHM影像作為數據訓練人工智慧。採用螢光影像確定CAR-T細胞的活性,並且以此結果標記DHM影像為高/低活性範例。後續機器學習階段,將高/低活性範例之DHM影像中的所有CAR-T細胞影像皆視為具有高/低活性特徵。藉此,可以大幅提升機器學習的效率,進而讓DHM影像適用於人工智慧的機器學習。
本發明之實施例揭露雖如上所述,然並非用以限定本發明,任何熟習相關技藝者,在不脫離本發明之精神和範圍內,舉凡依本發明申請範圍所述之形狀、構造、特徵及精神當可做些許之變更,因此本發明之專利保護範圍須視本說明書所附之申請專利範圍所界定者為準。
S1~S5:步驟
圖1為自體免疫療法的示意圖。
圖2為根據本發明一實施例之訓練人工智慧執行免標記式細胞活性檢測的方法的流程示意圖。
圖3為圖2之流程示意圖中使用之螢光影像的示意圖。
圖4為圖2之流程示意圖中使用之DHM影像的示意圖。
S1~S5:步驟
Claims (10)
- 一種訓練人工智慧執行免標記式細胞活性檢測的方法,包含: 提供一細胞樣本;獲取該細胞樣本的螢光影像和數位全像顯微(Digital holographic microscopy,DHM)影像;根據該細胞樣本的螢光影像確定該細胞樣本具有一第一細胞活性;將該細胞樣本的數位全像顯微影像標記為具有該第一細胞活性的範例;以及以該細胞樣本的數位全像顯微影像進行人工智慧的機器學習。
- 如請求項1所述之方法,更包含: 提供另一細胞樣本,其中該細胞樣本與該另一細胞樣本為相同細胞;獲取該另一細胞樣本的螢光影像和數位全像顯微影像;根據該另一細胞樣本的螢光影像確定該另一細胞樣本具有一第二細胞活性,其中該第二細胞活性與該第一細胞活性相異;將該另一細胞樣本的數位全像顯微影像標記為具有該第二細胞活性的範例;以及以該另一細胞樣本的數位全像顯微影像進行人工智慧的機器學習。
- 如請求項2所述之方法,其中該細胞樣本的數位全像顯微影像和該另一細胞樣本的數位全像顯微影像皆包含複數個細胞。
- 如請求項2所述之方法,其中藉由一無透鏡式(Lens-free)數位全像顯微鏡獲取數位全像顯微影像。
- 如請求項4所述之方法,其中該無透鏡式數位全像顯微鏡根據細胞的相位差和光強度生成數位全像顯微影像。
- 如請求項2所述之方法,其中以活體的該細胞樣本和活體的該另一細胞樣本為被攝物分別獲取數位全像顯微影像。
- 如請求項1所述之方法,其中該細胞樣本為嵌合抗原受體T細胞(CAR-T cells)。
- 一種免標記式細胞活性檢測的方法,包含藉由一人工智慧根據一受測細胞樣本的數位全像顯微影像判斷該受測細胞樣本的細胞活性,其中該人工智慧以請求項1所述之方法進行訓練。
- 如請求項8所述之方法,其中以活體的該受測細胞樣本為被攝物獲取該受測細胞樣本的數位全像顯微影像。
- 如請求項8所述之方法,其中該受測細胞樣本為嵌合抗原受體T細胞。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110143123A TWI828009B (zh) | 2021-11-19 | 2021-11-19 | 免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 |
US17/563,701 US20230160879A1 (en) | 2021-11-19 | 2021-12-28 | Method of training ai for label-free cell viability determination and label-free cell viability determination method by trained ai |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW110143123A TWI828009B (zh) | 2021-11-19 | 2021-11-19 | 免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202321689A TW202321689A (zh) | 2023-06-01 |
TWI828009B true TWI828009B (zh) | 2024-01-01 |
Family
ID=86384630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW110143123A TWI828009B (zh) | 2021-11-19 | 2021-11-19 | 免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 |
Country Status (2)
Country | Link |
---|---|
US (1) | US20230160879A1 (zh) |
TW (1) | TWI828009B (zh) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI726920B (zh) * | 2015-10-14 | 2021-05-11 | 耶魯大學 | 基因體規模的t細胞活性陣列、其製造方法、其用於辨識免疫調節因子的方法及其用途 |
US20210142472A1 (en) * | 2018-03-15 | 2021-05-13 | Ovizio Imaging Systems NV/SA | Digital holographic microscopy for determining a viral infection status |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018237239A1 (en) * | 2017-06-23 | 2018-12-27 | Texas Tech University System | METHOD AND DEVICE FOR HIGH-PERFORMANCE, LABEL-FREE HOLOGRAPHIC SCREENING AND TUMOR CELL ENUMERATION IN BLOOD |
CN111051955B (zh) * | 2017-08-15 | 2022-04-15 | 西门子医疗有限公司 | 通过使用卷积神经网络来标识利用数字全息显微镜所获取的细胞图像的品质 |
BR112020008340A2 (pt) * | 2017-11-01 | 2020-11-17 | Juno Therapeutics Inc | processo para gerar composições terapêuticas de células modificadas |
-
2021
- 2021-11-19 TW TW110143123A patent/TWI828009B/zh active
- 2021-12-28 US US17/563,701 patent/US20230160879A1/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI726920B (zh) * | 2015-10-14 | 2021-05-11 | 耶魯大學 | 基因體規模的t細胞活性陣列、其製造方法、其用於辨識免疫調節因子的方法及其用途 |
US20210142472A1 (en) * | 2018-03-15 | 2021-05-13 | Ovizio Imaging Systems NV/SA | Digital holographic microscopy for determining a viral infection status |
Non-Patent Citations (1)
Title |
---|
期刊 Dries Vercruysse, Alexandra Dusa, Richard Stahl, Geert Vanmeerbeeck, Koen de Wijs, Chengxun Liu, Dimiter Prodanov, Peter Peumans, and Liesbet Lagae Three-part differential of unlabeled leukocytes with a compact lens-free imaging flow cytometer Lab on a Chip Vol. 15 Royal Society of Chemistry 2014/12/15 1123-1132 * |
Also Published As
Publication number | Publication date |
---|---|
US20230160879A1 (en) | 2023-05-25 |
TW202321689A (zh) | 2023-06-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Raman et al. | Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy | |
Albanese et al. | Multiscale 3D phenotyping of human cerebral organoids | |
JP2021515586A (ja) | 細胞療法、創薬および診断法における使用のための幹細胞およびその誘導体を検証するために機械学習および/またはニューラルネットワークを使用すること | |
Zeng et al. | Integrative in situ mapping of single-cell transcriptional states and tissue histopathology in a mouse model of Alzheimer’s disease | |
US8831327B2 (en) | Systems and methods for tissue classification using attributes of a biomarker enhanced tissue network (BETN) | |
Niioka et al. | Classification of C2C12 cells at differentiation by convolutional neural network of deep learning using phase contrast images | |
Lin et al. | Automated classification of hepatocellular carcinoma differentiation using multiphoton microscopy and deep learning | |
Chen et al. | Automated evaluation of tumor spheroid behavior in 3D culture using deep learning-based recognition | |
Li et al. | FecalNet: Automated detection of visible components in human feces using deep learning | |
Sangeetha et al. | Deep learning-based early parkinson’s disease detection from brain mri image | |
LaChance et al. | Learning the rules of collective cell migration using deep attention networks | |
Choi et al. | Analyzing angiogenesis on a chip using deep learning-based image processing | |
Bajaj et al. | Classification And Prediction of Brain Tumors and its Types using Deep Learning | |
Herold et al. | Automated detection and quantification of fluorescently labeled synapses in murine brain tissue sections for high throughput applications | |
Tajudin et al. | Deep learning in the grading of diabetic retinopathy: A review | |
Du et al. | Organoids revealed: morphological analysis of the profound next generation in-vitro model with artificial intelligence | |
WO2022061176A1 (en) | Methods and systems for predicting neurodegenerative disease state | |
TWI828009B (zh) | 免標記式細胞活性檢測的方法及訓練人工智慧執行免標記式細胞活性檢測的方法 | |
Fishman et al. | Practical segmentation of nuclei in brightfield cell images with neural networks trained on fluorescently labelled samples | |
Devi et al. | A deep transfer learning approach for identification of diabetic retinopathy using data augmentation | |
Narotamo et al. | A machine learning approach for single cell interphase cell cycle staging | |
WO2022111367A1 (zh) | 基于高内涵成像的细胞耐药性检测方法、介质及电子设备 | |
Krishnan et al. | Deep Learning Approaches for Detecting Diabetic Retinopathy using CNN Models | |
Pathak et al. | Diagnosis and Analysis of Tuberculosis Disease Using Simple Neural Network and Deep Learning Approach for Chest X-Ray Images | |
JP2024515512A (ja) | 迅速で自動化された画像ベースのウイルスプラークおよびポテンシーアッセイ |