Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition

• US 20100184093A1
• Filed: 08/28/2009
• Published: 07/22/2010
• Est. Priority Date: 07/25/2008
• Status: Active Grant

• Current Assignee: Champalimaud Foundation
• Original Assignee: Aureon Biosciences, Inc.
• Inventors: Powell, Douglas, Donovan, Michael, Hamann, Stefan, Cordon-Cardo, Carlos, Fernandez, Gerardo, Costa, Jose, Alter, Jason, Mesa-Tejada, Ricardo, Zubek, Valentina Bayer, Khan, Faisal
• Granted Patent: US 9,779,213 B2
• Time in Patent Office: Days
• US Class Current: 435/7.210
• CPC Class Codes: G16B 25/00 ICT specially adapted for hybridisation; ICT specially adapted for gene or protein expression
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Clinical information, molecular information and/or computer-generated morphometric information is used in a predictive model for predicting the occurrence of a medical condition. In an embodiment, a model predicts whether a patient is likely to have a favorable pathological stage of prostate cancer, where the model is based on features including one or more (e.g., all) of preoperative PSA, Gleason Score, a measurement of expression of androgen receptor (AR) in epithelial and stromal nuclei and/or a measurement of expression of Ki67-positive epithelial nuclei, a morphometric measurement of a ratio of area of epithelial nuclei outside gland units to area of epithelial nuclei within gland units, and a morphometric measurement of area of epithelial nuclei distributed away from gland units. In some embodiments, quantitative measurements of protein expression in cell lines are utilized to objectively assess assay (e.g., multiplex immunofluorescence (IF)) performance and/or to normalize features for use within a predictive model.

Claims

1. Apparatus for evaluating whether a patient is likely to have a favorable pathological stage of prostate cancer, the apparatus comprising:

a model predictive of favorable pathological stage of prostate cancer configured to evaluate a dataset for a patient to thereby evaluate a likelihood of favorable pathological stage of prostate cancer in the patient, wherein the model is based on one or more features selected from the following group of features;

preoperative PSA;

Gleason Score;

at least one of a measurement of expression of androgen receptor (AR) in epithelial nuclei and stromal nuclei and a measurement of expression of Ki67-positive epithelial nuclei;

a morphometric measurement of a ratio of area of epithelial nuclei outside gland units to area of epithelial nuclei within gland units; and

a morphometric measurement of area of epithelial nuclei distributed away from gland units.

2. The apparatus of claim 1, wherein the Gleason Score comprises a biopsy Gleason Score.

3. The apparatus of claim 1, wherein the measurement of the expression of androgen receptor (AR) in epithelial and stromal nuclei and the measurement of the expression of Ki67-positive epithelial nuclei form a combined feature, wherein the predictive model evaluates the measurement of the expression of androgen receptor (AR) in epithelial and stromal nuclei for the combined feature when a dominant Gleason Grade for the patient is less than or equal to 3, and evaluates the measurement of the expression of Ki67-positive epithelial nuclei for the combined feature when the dominant Gleason Grade for the patient is 4 or 5.

4. The apparatus of claim 1, wherein the morphometric measurement of epithelial nuclei distributed away from gland units comprises a morphometric measurement of the area of epithelial nuclei with centers in a band located a predetermined distance away from lumen borders.

5. The apparatus of claim 4, wherein the band located a predetermined distance away from the lumen borders comprises the region between three and five units away from a lumen border, where a unit is approximately equal to a diameter of one epithelial nucleus.

6. The apparatus of claim 1, wherein based on the evaluation the model is configured to output a value indicative of a likelihood of favorable pathological stage of prostate cancer in the patient.

7. The apparatus of claim 6, wherein the value comprises a probability of favorable pathological stage of prostate cancer in the patient.

8. The apparatus of claim 1, wherein the model is based on two features from the group.

9. The apparatus of claim 1, wherein the model is based on three features from the group.

10. The apparatus of claim 1, wherein the model is based on four features from the group.

11. The apparatus of claim 1, wherein the model is based on all of the features in the group.

12. The apparatus of claim 1, wherein the model is based on one or more features in the group and is further based on at least one additional clinical, molecular, or morphometric feature.

13. The apparatus of claim 1, wherein the model predictive of favorable pathological stage of prostate cancer is predictive of whether the patient is likely to have a pathological stage as assessed by prostatectomy data of T2 or less, a total Gleason score as assessed at prostatectomy of six or less with each component of the Gleason score being three or less, and having a first PSA reading post-prostatectomy of approximately zero.

14. The apparatus of claim 1, wherein the dataset consists essentially of data available at the time of diagnosis of prostate cancer and from a biopsy of the patient'"'"'s tissue and wherein the model is predictive of whether the patient would have a favorable pathological stage if the patient were to undergo a radical prostatectomy.

15. A method of evaluating whether a patient is likely to have a favorable pathological stage of prostate cancer, the method comprising:

evaluating a dataset for a patient with a model predictive of favorable pathological stage of prostate cancer, wherein the model is based on one or more features selected from the following group of features;

preoperative PSA;

Gleason Score;

at least one of a measurement of expression of androgen receptor (AR) in epithelial nuclei and stromal nuclei and a measurement of expression of Ki67-positive epithelial nuclei;

a morphometric measurement of a ratio of area of epithelial nuclei outside gland units to area of epithelial nuclei within gland units; and

a morphometric measurement of area of epithelial nuclei distributed away from gland units;

thereby evaluating the likelihood of favorable pathological stage of prostate cancer in the patient.

16. The method of claim 15, wherein the Gleason Score comprises a biopsy Gleason Score.

17. The method of claim 15, wherein the measurement of the expression of androgen receptor (AR) in epithelial and stromal nuclei and the measurement of the expression of Ki67-positive epithelial nuclei form a combined feature, wherein the evaluating comprises evaluating the measurement of the expression of androgen receptor (AR) in epithelial nuclei and stromal nuclei for the combined feature with the predictive model when a dominant Gleason Grade for the patient is less than or equal to 3, and evaluating the measurement of the expression of Ki67-positive epithelial nuclei for the combined feature with the predictive model when the dominant Gleason Grade for the patient is 4 or 5.

18. The method of claim 15, wherein the morphometric measurement of epithelial nuclei distributed away from gland units comprises a morphometric measurement of the area of epithelial nuclei with centers in a band located a predetermined distance away from lumen borders.

19. The method of claim 18, wherein the band located a predetermined distance away from the lumen borders comprises the region between three and five units away from a lumen border, where a unit is approximately equal to a diameter of one epithelial nucleus.

20. The method of claim 15, further comprising outputting with the predictive model a value indicative of the likelihood of favorable pathological stage of prostate cancer in the patient.

21. The method of claim 15, wherein the model predictive of favorable pathological stage of prostate cancer is predictive of whether the patient is likely to have a pathological stage as assessed by prostatectomy data of T2 or less, a total Gleason score as assessed at prostatectomy of six or less with each component of the Gleason score being three or less, and having a first PSA reading post-prostatectomy of approximately zero.

22. The method of claim 15, wherein the dataset consists essentially of data available at the time of diagnosis of prostate cancer and from a biopsy of the patient'"'"'s tissue and wherein the model is predictive of whether the patient would have a favorable pathological stage if the patient were to undergo a radical prostatectomy.

23. A computer readable medium comprising computer executable instructions recorded thereon for performing the method comprising:

evaluating a dataset for a patient with a model predictive of favorable pathological stage of prostate cancer, wherein the model is based on one or more features selected from the following group of features;

preoperative PSA;

Gleason Score;

at least one of a measurement of expression of androgen receptor (AR) in epithelial nuclei and stromal nuclei and a measurement of expression of Ki67-positive epithelial nuclei;

a morphometric measurement of a ratio of area of epithelial nuclei outside gland units to area of epithelial nuclei within gland units; and

a morphometric measurement of area of epithelial nuclei distributed away from gland units;

thereby evaluating the likelihood of favorable pathological stage of prostate cancer in the patient.

24. The computer readable medium of claim 23 further comprising computer executable instructions recorded thereon for outputting with the predictive model a value indicative of the likelihood of favorable pathological stage of prostate cancer in the patient.

25. Apparatus for evaluating a likelihood of responsiveness to a hormonal therapy for prostate cancer, the apparatus comprising:

a model predictive of responsiveness to a hormonal therapy for prostate cancer configured to evaluate a dataset for a patient to thereby evaluate the likelihood that prostate cancer in the patient will be responsive to the hormonal therapy, wherein the model is based on one or more features selected from the following group of features;

androgen receptor (AR) area in AMACR-positive tumor epithelial cells;

dynamic range of AR intensity in tumor epithelial cells; and

median lumen area.

26. Apparatus for evaluating a time to prostate cancer specific mortality, the apparatus comprising:

a model predictive of a time to prostate cancer specific mortality (PCSM) configured to evaluate a dataset for a patient to thereby evaluate the risk of occurrence of PCSM in the patient, wherein the model is based on a measurement of a level of nuclear androgen receptor (AR) expression in a prostate cancer tissue specimen obtained from the patient prior to treatment for prostate cancer.

27. A method for performing a multiplex immunofluorescence assay, the method comprising:

subjecting cell lines known to express high and low levels of a protein under consideration to a multiplex immunofluorescence (IF) assay to establish baseline levels of expression of the protein in the cell lines;

subjecting the cell lines to the same multiplex IF assay simultaneously with at least one of tissue and isolated cells for one or more patients under consideration;

measuring with an image analysis tool one or more measurements of the expression of the protein in the cells lines which were subject to the multiplex IF assay simultaneously with the at least one of the tissue and isolated cells for the one or more patients under consideration; and

based on a comparison of the one or more measurements with the baseline expression levels, determining whether the multiplex IF assay performed simultaneously on the cell lines and the at least one of the tissue and isolated cells for the one or more patients under consideration has produced reliable results.

28. The method of claim 27, further comprising disregarding the results from the multiplex IF assay performed simultaneously on the cell lines and the at least one of the tissue and isolated cells for the one or more patients under consideration when the comparison indicates a deviation in the one or more measurements from the baseline levels of expression of the protein in the cell lines.

29. The method of claim 27, further comprising re-subjecting the at least one of the tissue and isolated cells for the one or more patients under consideration to the multiplex IF assay when the comparison indicates a deviation in the one or more measurements from the baseline levels of expression of the protein in the cell lines.

30. The method of claim 27, further comprising:

subsequent to performing the multiplex IF assay, measuring with an image analysis tool one or more measurements of protein expression from the at least one of the tissue and isolated cells, or one or more images thereof, for the one or more patients under consideration;

normalizing the one or more measurements of protein expression from the at least one of the tissue and isolated cells, or one or more images thereof, based on at least one of the baseline levels of expression of the protein in the cell lines, the one or more measurements of the expression of the protein in the cells lines, one or more other measurements relating to the cell lines, or a combination thereof; and

utilizing the normalized one or more measurements for at least one of generating a predictive model or evaluation of a patient'"'"'s risk with a final predictive model.

31. The method of claim 27, wherein measuring with an image analysis tool one or more measurements of the expression of the protein in the cells lines comprises measuring one or more of the following measurements:

mean biomarker intensity in a total cell nuclei population in a positive control;

mean biomarker intensity in positive cell nuclei population, indicative of nuclei with intensity above a corresponding threshold in the positive control;

percentage of positive cells nuclei in the positive control; and

mean biomarker intensity in total cell nuclei population in a negative control.

32. The method of claim 27, wherein:

the cell lines comprise cultured cells with a known profile characteristic of a phenotype of a disease;

the phenotype of the disease comprises one or more features measurable by quantitative immunofluorescence analysis; and

the method further comprises measuring with the image analysis tool the one or more features in the tissue or isolated cells for the one or more patients under consideration for use in determining for the one or more patients under consideration a disease state, a risk of one or more outcomes with respect to the disease, or probable responsiveness or unresponsiveness to a therapy for the disease.