Comparing and Combining Artificial Intelligence and Spectral/Statistical Approaches for Elevating Prostate Cancer Assessment in a Biparametric MRI: A Pilot Study.

Prostate cancer management optimally requires non-invasive, objective, quantitative, accurate evaluation of prostate tumors. The current research applies visual inspection and quantitative approaches, such as artificial intelligence (AI) based on deep learning (DL), to evaluate MRI. Recently, a different spectral/statistical approach has been used to successfully evaluate spatially registered biparametric MRIs for prostate cancer.

Urinary IR700 Ligand as an Early Biomarker of Therapeutic Efficacy of Near-Infrared Photoimmunotherapy.

Near-infrared photoimmunotherapy (NIR-PIT) is a cell-selective cancer therapy employing monoclonal antibody-photoabsorber conjugates (APCs) and near-infrared (NIR) light. When exposed to NIR light, the photoabsorber, IR700, releases an axial ligand, resulting in a transition of the remaining molecule from water-soluble to hydrophobic. This results in the death of APC-bound cells by physical damage to the cell membrane.

Assessing the Impact of Transition and Peripheral Zone PSA Densities Over Whole-Gland PSA Density for Prostate Cancer Detection on Multiparametric MRI.

Background: Whole-gland (WG) prostate-specific antigen (PSA) density (PSAD) has proven useful in diagnosing to be beneficial in localized prostate cancer (PCa). This study aimed to evaluate the predictive performance of WG and zonal (transition zone [TZ] and peripheral zone [PZ]) PSAD in predicting PCa and clinically significant PCa (csPCa) in prostate MRI.

Methods: A retrospective analysis was conducted on consecutive patients who underwent multiparametric MRI and MRI/US fusion-guided biopsy between March 2019 and July 2024.

Carbonic anhydrase-9-targeted near-infrared photoimmunotherapy as a theranostic modality for clear cell renal cell carcinoma.

Carbonic anhydrase-9 (CA9) is highly expressed in clear cell renal cell carcinoma (ccRCC) cells despite no expression in normal kidney tissues. Thus, CA9 has been proposed as a theranostic target for radioligand therapy (RLT). However, ccRCC tends to be radioresistant and may not effectively respond to RLT.

Unraveling the dynamics of B7-H3-targeting therapeutic antibodies in cancer through PET imaging and antibody pharmacokinetics.

B7-H3, an immunomodulatory protein overexpressed in many cancers, is associated with tumor aggressiveness and poor prognosis, making it a crucial target for imaging to elucidate its role in cancer progression and guide therapeutic interventions. This study employed PET imaging to investigate the in vivo delivery and pharmacokinetics of two anti-B7-H3 antibodies, Ab-1 and Ab-2, in mouse xenograft models with varying B7-H3 expression levels. The antibodies were radiolabeled with [Zr]Zr and evaluated through PET imaging, biodistribution studies, and in vitro assays to assess binding, tumor uptake, and retention.

Impact of Endorectal Coil Use on Extraprostatic Extension Detection in Prostate MRI: A Retrospective Monocentric Study.

Rationale And Objectives: Accurate preoperative mpMRI-based detection of extraprostatic extension (EPE) in prostate cancer (PCa) is critical for surgical planning and patient outcomes. This study aims to evaluate the impact of endorectal coil (ERC) use on the diagnostic performance of mpMRI in detecting EPE.

Materials And Methods: This retrospective study with prospectively collected data included participants who underwent mpMRI and subsequent radical prostatectomy for PCa between 2007 and 2024.

Tissue factor targeted near-infrared photoimmunotherapy: a versatile therapeutic approach for malignancies.

Tissue factor (TF) is a cell surface protein that plays a role in blood clotting but is also commonly expressed in many cancers. Recent research implicated TF in cancer proliferation, metastasis, angiogenesis, and immune escape. Therefore, TF can be considered a viable therapeutic target against cancer.

Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images.

Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients.

Masked Image Modeling Meets Self-Distillation: A Transformer-Based Prostate Gland Segmentation Framework for Pathology Slides.

Detailed evaluation of prostate cancer glands is an essential yet labor-intensive step in grading prostate cancer. Gland segmentation can serve as a valuable preliminary step for machine-learning-based downstream tasks, such as Gleason grading, patient classification, cancer biomarker building, and survival analysis. Despite its importance, there is currently a lack of a reliable gland segmentation model for prostate cancer.

Comparative Kidney Uptake of Nanobody-Based PET Tracers Labeled with Various Fluorine-18-Labeled Prosthetic Groups.

Nanobodies, or single-domain antibody fragments, are promising candidates for molecular imaging due to their small size, rapid tissue penetration, and high target specificity. However, a significant challenge in their use is high renal uptake and retention, which can limit the therapeutic efficacy and complicate image interpretation. This study compares five different fluorine-18-labeled prosthetic groups for nanobodies, aiming to optimize pharmacokinetics and minimize kidney retention while maintaining tumor targeting.

Antitumor host immunity enhanced by near-infrared photoimmunotherapy.

Near-infrared photoimmunotherapy (NIR-PIT) is a novel antitumor therapy that selectively kills cancer cells by NIR light-triggered photochemical reaction of IRDye700DX within Ab-photoabsorber conjugates (APCs). NIR-PIT induces immunogenic cell death, causing immune cell migration between the tumor and tumor-draining lymph nodes, and expanding multiclonal tumor-infiltrating CD8 T cells. Crucially, the cytotoxic effects of NIR-PIT are limited to cancer cells, sparing immune cells such as antigen-presenting cells and T cells, which are key players in boosting antitumor host immunity.

A Prostate Imaging-Reporting and Data System version 2.1-based predictive model for clinically significant prostate cancer diagnosis.

Objectives: To develop and validate a Prostate Imaging-Reporting and Data System (PI-RADS) version 2.1 (v2.1)-based predictive model for diagnosis of clinically significant prostate cancer (csPCa), integrating clinical and multiparametric magnetic resonance imaging (mpMRI) data, and compare its performance with existing models.

Tumor growth suppression in adoptive T cell therapy via IFN-γ targeting of tumor vascular endothelial cells.

In adoptive T cell therapy (ACT), the direct cytotoxic effects of CD8 T cells on tumor cells, including the release of interferon-gamma (IFN-γ), are considered the primary mechanism for tumor eradication. Cancer antigen escape diminishes the T cell responses, thereby limiting the therapeutic success. The impacts of IFN-γ targeting non-tumor cells in ACT, on the other hand, remains under-investigated.

Multimodal approach to optimize biopsy decision-making for PI-RADS 3 lesions on multiparametric MRI.

Purpose: To develop and evaluate a multimodal approach including clinical parameters and biparametric MRI-based artificial intelligence (AI) model for determining the necessity of prostate biopsy in patients with PI-RADS 3 lesions.

Methods: This retrospective study included a prospectively recruited patient cohort with PI-RADS 3 lesions who underwent prostate MRI and MRI/US fusion-guided biopsy between April 2019 and February 2024 in a single institution. The study examined demographic data, PSA and PSA density (PSAD) levels, prostate volumes, prospective PI-RADS v2.

An automated pheochromocytoma and paraganglioma lesion segmentation AI-model at whole-body Ga- DOTATATE PET/CT.

Background: Somatostatin receptor (SSR) targeting radiotracer Ga-DOTATATE is used for Positron Emission Tomography (PET)/Computed Tomography (CT) imaging to assess patients with Pheochromocytoma and paraganglioma (PPGL), rare types of Neuroendocrine tumor (NET) which can metastasize thereby becoming difficult to quantify. The goal of this study is to develop an artificial intelligence (AI) model for automated lesion segmentation on whole-body 3D DOTATATE-PET/CT and to automate the tumor burden calculation. 132 Ga-DOTATATE PET/CT scans from 38 patients with metastatic and inoperable PPGL, were split into 70, and 62 scans, from 20, and 18 patients for training, and test sets, respectively.

Update on PSMA-based Prostate Cancer Imaging.

The increased use of prostate-specific membrane antigen (PSMA) based PET imaging for prostate cancer (Pca) detection has revolutionized the clinical management of Pca, with higher diagnostic sensitivity for extraprostatic disease and increasing clinical utility across different stages of the disease. The integration of PSMA PET imaging into clinical guidelines and consensus documents reflects its growing importance in the personalized management of Pca. This review of recent literature highlights the rapid evolution of PSMA PET into the mainstream of staging and restaging and the decreasing reliance on conventional imaging modalities.

AI-ADC: Channel and Spatial Attention-Based Contrastive Learning to Generate ADC Maps from T2W MRI for Prostate Cancer Detection.

Background/objectives: Apparent Diffusion Coefficient (ADC) maps in prostate MRI can reveal tumor characteristics, but their accuracy can be compromised by artifacts related with patient motion or rectal gas associated distortions. To address these challenges, we propose a novel approach that utilizes a Generative Adversarial Network to synthesize ADC maps from T2-weighted magnetic resonance images (T2W MRI).

Methods: By leveraging contrastive learning, our model accurately maps axial T2W MRI to ADC maps within the cropped region of the prostate organ boundary, capturing subtle variations and intricate structural details by learning similar and dissimilar pairs from two imaging modalities.

Comparison of Transatlantic Recommendations for Prostate Gland Evaluation with MRI after Focal Therapy (TARGET) and Prostate Imaging after Focal Ablation (PI-FAB) for Detecting Recurrent Prostate Cancer at Prostate MRI.

Rationale And Objectives: The increasing use of focal therapy (FT) in localized prostate cancer (PCa) management requires a standardized MRI interpretation system to detect recurrent clinically significant PCa (csPCa). This pilot study evaluates the novel Transatlantic Recommendations for Prostate Gland Evaluation with MRI after Focal Therapy (TARGET) and compares its performance to that of the Prostate Imaging after Focal Ablation (PI-FAB) system.

Materials And Methods: This retrospective study included 38 patients who underwent primary FT for localized PCa, with follow-up multiparametric MRI (mpMRI) and biopsy.

A Phase 1 Trial of Image Guided Risk Volume-Adapted Postprostatectomy Radiation Therapy.

Purpose: This was a phase 1 trial with the primary objective of identifying the most compressed dose schedule (DS) tolerable using risk volume-adapted, hypofractionated, postoperative radiation therapy (PORT) for biochemically recurrent prostate cancer. Secondary endpoints included biochemical progression-free survival and quality of life (QOL).

Methods And Materials: Patients were treated with 1 of 3 isoeffective DSs (DS1: 20 fractions, DS2: 15 fractions, and DS3: 10 fractions) that escalated the dose to the imaging-defined local recurrence (73 Gy equivalent dose in 2Gy fractions) and de-escalated the dose to the remainder of the prostate bed (48 Gy equivalent dose in 2Gy fractions).

Location-based Radiology Report-Guided Semi-supervised Learning for Prostate Cancer Detection.

Prostate cancer is one of the most prevalent malignancies in the world. While deep learning has potential to further improve computer-aided prostate cancer detection on MRI, its efficacy hinges on the exhaustive curation of manually annotated images. We propose a novel methodology of semisupervised learning (SSL) guided by automatically extracted clinical information, specifically the lesion locations in radiology reports, allowing for use of unannotated images to reduce the annotation burden.