You’re using a public version of DrugPatentWatch with 5 free searches available | Register to unlock more free searches. CREATE FREE ACCOUNT

Last Updated: March 29, 2024

Claims for Patent: 10,492,723


✉ Email this page to a colleague

« Back to Dashboard


Summary for Patent: 10,492,723
Title:Predicting immunotherapy response in non-small cell lung cancer patients with quantitative vessel tortuosity
Abstract: Embodiments classify a region of tissue demonstrating non-small cell lung cancer using quantified vessel tortuosity (QVT). One example apparatus includes annotation circuitry configured to segment a lung region from surrounding anatomy in the region of tissue represented in a radiological image and segment a nodule from the lung region by defining a nodule boundary; vascular segmentation circuitry configured to generate a three dimensional (3D) segmented vasculature by segmenting a vessel associated with the nodule, and to identify a center line of the 3D segmented vasculature; QVT feature extraction circuitry configured to extract a set of QVT features from the radiological image; and classification circuitry configured to compute a probability that the region of tissue will respond to immunotherapy and generate a classification that the region of tissue is a responder or a non-responder based, at least in part, on the probability.
Inventor(s): Madabhushi; Anant (Shaker Heights, OH), Alilou; Mehdi (Cleveland, OH), Velcheti; Vamsidhar (Pepper Pike, OH)
Assignee: Case Western Reserve University (Cleveland, OH)
Application Number:15/883,649
Patent Claims:1. An immunotherapy response prediction apparatus, configured to generate a classification of a region of tissue demonstrating non-small cell lung cancer (NSCLC) based on a set of quantitative vessel tortuosity (QVT) features extracted from a radiological image of the region of tissue, the apparatus comprising: a processor; a memory; an input/output interface; a set of circuitry; and an interface to connect the processor, the memory, the input/output interface and the set of circuitry, where the set of circuitry includes: image acquisition circuitry configured to access a radiological image of a region of tissue demonstrating NSCLC; annotation circuitry configured to: segment a lung region from surrounding anatomy in the region of tissue represented in the radiological image; segment a nodule from the lung region by defining a nodule boundary; vascular segmentation circuitry configured to: generate a three dimensional (3D) segmented vasculature by segmenting a vessel associated with the nodule from the nodule; identify a center line of the 3D segmented vasculature; QVT feature extraction circuitry configured to extract a set of QVT features from the radiological image based, at least in part, on the center line; and classification circuitry configured to: compute a probability that the region of tissue will respond to immunotherapy based, at least in part, on the set of QVT features; and generate a classification of the region of tissue as a responder or a non-responder based, at least in part, on the probability.

2. The immunotherapy response prediction apparatus of claim 1, where accessing the radiological image comprises accessing a computed tomography (CT) image of a region of lung tissue, where the CT image is a no-contrast chest CT image.

3. The immunotherapy response prediction apparatus of claim 2, where the CT image is a baseline pre-treatment CT image.

4. The immunotherapy response prediction apparatus of claim 2, where the CT image is a post-treatment CT image acquired at least two weeks after administration of immunotherapy treatment to a patient represented in the image.

5. The immunotherapy response prediction apparatus of claim 1, where the annotation circuitry is configured to segment the lung region from surrounding anatomy in the region of tissue represented in the radiological image by distinguishing the lung region from the surrounding anatomy using a multi-threshold based approach or a heuristic threshold based approach.

6. The immunotherapy response prediction apparatus of claim 1, where the annotation circuitry is configured to segment the nodule from the lung region by defining the nodule boundary by: distinguishing nodule tissue in the radiological image from the background of the radiological image using a spectral embedding gradient vector flow active contour (SEGvAC) approach; or distinguishing nodule tissue in the radiological image from the background of the radiological image using a heuristic threshold approach, a deformable boundary model, an active-appearance model, an active shape model, a Markov random fields (MRF) graph-based model, or a min-max cut approach.

7. The immunotherapy response prediction apparatus of claim 1, where the vascular segmentation circuitry is configured to segment the vessel from the nodule using a three dimensional (3D) click and grow approach.

8. The immunotherapy response prediction apparatus of claim 7, where the vascular segmentation circuitry is configured to segment the vessel from the nodule using the 3D click and grow approach by: identifying a plurality of seed points within a volume of interest, where a member of the plurality of seed points has an intensity, where the volume of interest is in the nodule; computing an intensity similarity between a first member of the plurality of seed points and a second, different member of the plurality of seed points; and growing the volume of interest using a 3D region growing approach based, at least in part, on the intensity similarity.

9. The immunotherapy response prediction apparatus of claim 1, where the vascular segmentation circuitry is configured to identify the center line of the 3D segmented vasculature using a fast marching approach.

10. The immunotherapy response prediction apparatus of claim 1, where the set of QVT features includes a maximum curvature of vessels branch feature, a standard deviation of vessel torsion feature, and a mean curvature feature.

11. The immunotherapy response prediction apparatus of claim 1, where the classification circuitry comprises a machine learning classifier.

12. The immunotherapy response prediction apparatus of claim 11, where the machine learning classifier is a support vector machine (SVM) classifier trained on a set of QVT training features selected from a set of QVT candidate features extracted from a set of training images, where the set of training images includes a set of computed tomography (CT) images of a region of tissue demonstrating NSCLC, where the set of CT images includes a first subset of CT images representing a region of tissue demonstrating NSCLC classified as a responder to immunotherapy, and a second, disjoint subset of CT images representing a region of tissue demonstrating NSCLC classified as a non-responder to immunotherapy, and where the set of QVT training features are selected based on a univariate analysis and a multivariate analysis of the ability of a member of the set of QVT candidate features to discriminate a region of tissue represented in the set of training images as a responder to immunotherapy.

13. The immunotherapy response prediction apparatus of claim 1, where computing the probability that the region of tissue will respond to immunotherapy based, at least in part, on the set of QVT features, includes computing the probability that the region of tissue will respond to nivolumab immunotherapy, pembrolizumab immunotherapy, or atezolizumab immunotherapy.

14. The immunotherapy response prediction apparatus of claim 1, further comprising immunotherapy treatment plan circuitry configured to: generate an NSCLC immunotherapy treatment plan based, at least in part, on the classification and at least one of the probability, the set QVT features, or the radiological image, where the NSCLC immunotherapy treatment plan defines an immunotherapy dosage amount and an immunotherapy dosage schedule.

15. The immunotherapy response prediction apparatus of claim 14, where the immunotherapy treatment plan circuitry is further configured to: provide the NSCLC immunotherapy treatment plan and at least one of the classification, the probability, the set of QVT features, or the radiological image to a personalized medicine system; and control the personalized medicine system to display the NSCLC immunotherapy treatment plan and at least one of the classification, the probability, the set of QVT features, or the radiological image.

16. A non-transitory computer-readable storage device storing computer executable instructions that when executed by a computer control the computer to perform a method for predicting non-small cell lung cancer (NSCLC) patient response to immunotherapy, the method comprising: accessing a radiological image of a region of tissue demonstrating NSCLC pathology, where accessing the radiological image includes accessing a baseline pre-treatment computed tomography (CT) image of the region of tissue, or a post-treatment CT image of the region of tissue; segmenting a nodule in the image by extracting a nodule boundary from the image; generating a three dimensional (3D) segmented vasculature by segmenting a vessel associated with the nodule from the nodule; identifying a center line of the 3D segmented vasculature; extracting a set of quantitative vessel tortuosity (QVT) features from the 3D segmented vasculature based, at least in part, on the center line; providing the set of QVT features to a machine learning classifier; receiving, from the machine learning classifier, a classification of the region of tissue as a responder or non-responder, where the classification is based on a probability computed by the machine learning classifier that the region of tissue will respond to immunotherapy based, at least in part, on the set of QVT features; and generating an NSCLC immunotherapy treatment plan based, at least in part, on the classification and at least one of the probability, the set of QVT features, or the radiological image.

17. The non-transitory computer-readable storage device of claim 16, where segmenting the nodule in the image includes segmenting the nodule using a spectral embedding active contour (SEGvAC) approach, a heuristic threshold approach, threshold based segmentation, a deformable boundary model, an active-appearance model, an active shape model, a Markov random fields (MRF) graph-based model, or a min-max cut approach, and where segmenting the vessel from the nodule includes segmenting the vessel from the nodule using a 3D click and grow approach.

18. The non-transitory computer-readable storage device of claim 16 where the set of QVT features includes a maximum curvature of vessels branch feature, a standard deviation of vessel torsion feature, and a mean curvature feature.

19. The non-transitory computer-readable storage device of claim 16, where the machine learning classifier is a support vector machine (SVM) classifier trained on a set of QVT training features selected from a set of QVT candidate features extracted from a set of training images, where the set of training images includes a set of CT images of a region of tissue demonstrating NSCLC, where the set of CT images includes a first subset of CT images representing a region of tissue demonstrating NSCLC classified as a responder to immunotherapy, and a second, disjoint subset of CT images representing a region of tissue demonstrating NSCLC classified as a non-responder to immunotherapy.

20. A computer-readable storage device storing processor-executable instructions that, in response to execution, cause a processor to perform operations comprising: accessing a radiological image of a region of tissue demonstrating non-small cell lung cancer (NSCLC), where the radiological image is a baseline pre-immunotherapy treatment image, or a post-immunotherapy treatment image; segmenting a lung region from surrounding anatomy in the region of tissue represented in the radiological image; segmenting a nodule from the lung region by defining a nodule boundary; generating a three dimensional (3D) segmented vasculature by segmenting a vessel from the nodule; identifying a center line of the 3D segmented vasculature using a fast marching approach; extracting a set of quantitative vessel tortuosity (QVT) features from the 3D segmented vasculature based, at least in part, on the center line; providing the set of QVT features to a support vector machine (SVM) classifier; receiving, from the SVM classifier, a probability that the region of tissue will respond to immunotherapy based, at least in part, on the set of QVT features; and generating a classification by classifying the region of tissue as a responder or non-responder based, at least in part, on the probability.

Details for Patent 10,492,723

Applicant Tradename Biologic Ingredient Dosage Form BLA Approval Date Patent No. Expiredate
Merck Sharp & Dohme Corp. KEYTRUDA pembrolizumab For Injection 125514 09/04/2014 ⤷  Try a Trial 2037-02-27
Merck Sharp & Dohme Corp. KEYTRUDA pembrolizumab Injection 125514 01/15/2015 ⤷  Try a Trial 2037-02-27
Bristol-myers Squibb Company OPDIVO nivolumab Injection 125554 12/22/2014 ⤷  Try a Trial 2037-02-27
Bristol-myers Squibb Company OPDIVO nivolumab Injection 125554 10/04/2017 ⤷  Try a Trial 2037-02-27
Bristol-myers Squibb Company OPDIVO nivolumab Injection 125554 08/27/2021 ⤷  Try a Trial 2037-02-27
>Applicant >Tradename >Biologic Ingredient >Dosage Form >BLA >Approval Date >Patent No. >Expiredate

Make Better Decisions: Try a trial or see plans & pricing

Drugs may be covered by multiple patents or regulatory protections. All trademarks and applicant names are the property of their respective owners or licensors. Although great care is taken in the proper and correct provision of this service, thinkBiotech LLC does not accept any responsibility for possible consequences of errors or omissions in the provided data. The data presented herein is for information purposes only. There is no warranty that the data contained herein is error free. thinkBiotech performs no independent verification of facts as provided by public sources nor are attempts made to provide legal or investing advice. Any reliance on data provided herein is done solely at the discretion of the user. Users of this service are advised to seek professional advice and independent confirmation before considering acting on any of the provided information. thinkBiotech LLC reserves the right to amend, extend or withdraw any part or all of the offered service without notice.