バイオメカニクス的モデリングにより前立腺がんの成長を予測(Using Biomechanistic Modeling, Researchers Predict Prostate Cancer Growth)

ad

2024-04-03 テキサス大学オースチン校(UT Austin)

ギジェルモ・ロレンソ氏率いる研究チームは、前立腺がんの個別化予測モデルを開発しました。このモデルは、患者のMRIデータを用いてがん細胞の移動性と分裂率を分析し、これらがどのように相互作用して腫瘍成長を影響するかを空間的・時間的に予測します。この研究は「Cancer Research Communications」に掲載され、個別の治療戦略を導くための次世代ツールとして期待されています。ロレンソ氏の技術は、リスクが高い腫瘍の早期識別を可能にし、MRIスキャンや治療の最適なタイミングを定める手助けをします。この技術は将来的にほぼ全ての医療センターで利用可能になる見込みです。

<関連情報>

画像情報に基づくバイオメカニスティック・モードを用いた積極的サーベイランス中の前立腺がん増殖の患者別計算予測に関するパイロット研究 A Pilot Study on Patient-specific Computational Forecasting of Prostate Cancer Growth during Active Surveillance Using an Imaging-informed Biomechanistic Mode

Guillermo Lorenzo;Jon S. Heiselman;Michael A. Liss;Michael I. Miga;Hector Gomez;Thomas E. Yankeelov;Alessandro Reali;Thomas J.R. Hughes
Cancer Research Communications  Published:March 01 2024
DOI:https://doi.org/10.1158/2767-9764.CRC-23-0449

Imaging-informed computational pipeline for tumor forecasting to support clinical decision-making in AS for prostate cancer. A, Standard-of-care AS protocol for an illustrative patient. Following the detection of a serum PSA level moderately larger than 4 ng/mL, the patient undergoes an initial mpMRI scan that finds an organ-confined cancerous lesion. This radiological lesion is then confirmed as prostate cancer with GS = 3 + 3 in an ensuing biopsy. Because the prostate cancer risk is low, the patient enrolls in AS and periodic PSA tests are performed until the date of the next mpMRI scan in the AS protocol. This second imaging session does not reveal progression in the lesion, so the AS monitoring plan remains unchanged. However, the patient starts exhibiting a fast increase in PSA, which motivates an earlier imaging session before the originally prescribed date according to the AS protocol. This third mpMRI scan reveals radiological progression, which is further confirmed histopathologically as an upgrade to GS = 4 + 3 in an ensuing biopsy. At this point, the patient is offered a radical treatment for prostate cancer, which usually consists of surgery (i.e., radical prostatectomy) or radiotherapy (e.g., external beam radiotherapy, brachytherapy). B, Changes to the standard-of-care AS protocol after implementing the computational tumor forecasting pipeline presented in this study. The modified protocol is identical to the standard of care up to the second mpMRI. At this point, the longitudinal imaging data collected for the patient can be used to personalize our biomechanistic model of prostate cancer growth and obtain a computational forecast of prostate cancer growth over the patient's prostate anatomy. The forecast reveals progression toward high-risk prostate cancer and provides the time up to this event. This prediction enables optimizing the timing of the third mpMRI to confirm progression and proceed to treatment. Thus, our approach avoids PSA testing and biopsy after the second mpMRI, provides a personalized prediction of the patient's prostate cancer progression that enables an early detection of this event, and supports the decision and optimal timing to perform treatment. C, Main steps in our computational pipeline for prostate cancer forecasting during AS. In the cohort of this study (n = 7), all patients had three mpMRI scans. We first analyze the ability of our model to represent patient-specific prostate cancer growth after being informed by three mpMRI scans. Then, we also investigate the ability of our model to forecast prostate cancer growth when informed by only the first two mpMRI scans, and we use the third one to assess the predictive performance of the model. The first step of the computational pipeline is segmentation. We delineate the prostate and the tumor region of interest (ROI) on the longitudinal mpMRI data collected for the patient. After segmentation, the second and third mpMRI datasets and segments are co-registered with a nonrigid elastic method to the first one (registration transforms R21 and R31, respectively). Next, we build a virtual model of the prostate anatomy, consisting of a 3D isogeometric (IGA) mesh and we project the registered tumor ROIs onto it. Then, we map the ADC values within each tumor ROI to tumor cell density values, which are subsequently used to guide model calibration and determine the personalized model parameters. Finally, we perform a patient-specific tumor forecast, including the prediction of tumor volume, tumor cell density map, and prostate cancer risk.

Abstract

Active surveillance (AS) is a suitable management option for newly diagnosed prostate cancer, which usually presents low to intermediate clinical risk. Patients enrolled in AS have their tumor monitored via longitudinal multiparametric MRI (mpMRI), PSA tests, and biopsies. Hence, treatment is prescribed when these tests identify progression to higher-risk prostate cancer. However, current AS protocols rely on detecting tumor progression through direct observation according to population-based monitoring strategies. This approach limits the design of patient-specific AS plans and may delay the detection of tumor progression. Here, we present a pilot study to address these issues by leveraging personalized computational predictions of prostate cancer growth. Our forecasts are obtained with a spatiotemporal biomechanistic model informed by patient-specific longitudinal mpMRI data (T2-weighted MRI and apparent diffusion coefficient maps from diffusion-weighted MRI). Our results show that our technology can represent and forecast the global tumor burden for individual patients, achieving concordance correlation coefficients from 0.93 to 0.99 across our cohort (n = 7). In addition, we identify a model-based biomarker of higher-risk prostate cancer: the mean proliferation activity of the tumor (P = 0.041). Using logistic regression, we construct a prostate cancer risk classifier based on this biomarker that achieves an area under the ROC curve of 0.83. We further show that coupling our tumor forecasts with this prostate cancer risk classifier enables the early identification of prostate cancer progression to higher-risk disease by more than 1 year. Thus, we posit that our predictive technology constitutes a promising clinical decision-making tool to design personalized AS plans for patients with prostate cancer.

Significance:
Personalization of a biomechanistic model of prostate cancer with mpMRI data enables the prediction of tumor progression, thereby showing promise to guide clinical decision-making during AS for each individual patient.

ad
医療・健康
前立腺がん個別化治療予測モデル
ad
ad


Share
Follow
ad
テック・アイ生命科学
ad
タイトルとURLをコピーしました