American Cancer Society's report on the status of cancer disparities in the United States, 2023.

In 2021, the American Cancer Society published its first biennial report on the status of cancer disparities in the United States. In this second report, the authors provide updated data on racial, ethnic, socioeconomic (educational attainment as a marker), and geographic (metropolitan status) disparities in cancer occurrence and outcomes and contributing factors to these disparities in the country. The authors also review programs that have reduced cancer disparities and provide policy recommendations to further mitigate these inequalities. There are substantial variations in risk factors, stage at diagnosis, receipt of care, survival, and mortality for many cancers by race/ethnicity, educational attainment, and metropolitan status. During 2016 through 2020, Black and American Indian/Alaska Native people continued to bear a disproportionately higher burden of cancer deaths, both overall and from major cancers. By educational attainment, overall cancer mortality rates were about 1.6-2.8 times higher in individuals with ≤12 years of education than in those with ≥16 years of education among Black and White men and women. These disparities by educational attainment within each race were considerably larger than the Black-White disparities in overall cancer mortality within each educational attainment, ranging from 1.03 to 1.5 times higher among Black people, suggesting a major role for socioeconomic status disparities in racial disparities in cancer mortality given the disproportionally larger representation of Black people in lower socioeconomic status groups. Of note, the largest Black-White disparities in overall cancer mortality were among those who had ≥16 years of education. By area of residence, mortality from all cancer and from leading causes of cancer death were substantially higher in nonmetropolitan areas than in large metropolitan areas. For colorectal cancer, for example, mortality rates in nonmetropolitan areas versus large metropolitan areas were 23% higher among males and 21% higher among females. By age group, the racial and geographic disparities in cancer mortality were greater among individuals younger than 65 years than among those aged 65 years and older. Many of the observed racial, socioeconomic, and geographic disparities in cancer mortality align with disparities in exposure to risk factors and access to cancer prevention, early detection, and treatment, which are largely rooted in fundamental inequities in social determinants of health. Equitable policies at all levels of government, broad interdisciplinary engagement to address these inequities, and equitable implementation of evidence-based interventions, such as increasing health insurance coverage, are needed to reduce cancer disparities.

Screening for lung cancer: 2023 guideline update from the American Cancer Society.

Lung cancer is the leading cause of mortality and person-years of life lost from cancer among US men and women. Early detection has been shown to be associated with reduced lung cancer mortality. Our objective was to update the American Cancer Society (ACS) 2013 lung cancer screening (LCS) guideline for adults at high risk for lung cancer. The guideline is intended to provide guidance for screening to health care providers and their patients who are at high risk for lung cancer due to a history of smoking. The ACS Guideline Development Group (GDG) utilized a systematic review of the LCS literature commissioned for the US Preventive Services Task Force 2021 LCS recommendation update; a second systematic review of lung cancer risk associated with years since quitting smoking (YSQ); literature published since 2021; two Cancer Intervention and Surveillance Modeling Network-validated lung cancer models to assess the benefits and harms of screening; an epidemiologic and modeling analysis examining the effect of YSQ and aging on lung cancer risk; and an updated analysis of benefit-to-radiation-risk ratios from LCS and follow-up examinations. The GDG also examined disease burden data from the National Cancer Institute's Surveillance, Epidemiology, and End Results program. Formulation of recommendations was based on the quality of the evidence and judgment (incorporating values and preferences) about the balance of benefits and harms. The GDG judged that the overall evidence was moderate and sufficient to support a strong recommendation for screening individuals who meet the eligibility criteria. LCS in men and women aged 50-80 years is associated with a reduction in lung cancer deaths across a range of study designs, and inferential evidence supports LCS for men and women older than 80 years who are in good health. The ACS recommends annual LCS with low-dose computed tomography for asymptomatic individuals aged 50-80 years who currently smoke or formerly smoked and have a ≥20 pack-year smoking history (strong recommendation, moderate quality of evidence). Before the decision is made to initiate LCS, individuals should engage in a shared decision-making discussion with a qualified health professional. For individuals who formerly smoked, the number of YSQ is not an eligibility criterion to begin or to stop screening. Individuals who currently smoke should receive counseling to quit and be connected to cessation resources. Individuals with comorbid conditions that substantially limit life expectancy should not be screened. These recommendations should be considered by health care providers and adults at high risk for lung cancer in discussions about LCS. If fully implemented, these recommendations have a high likelihood of significantly reducing death and suffering from lung cancer in the United States.

Stem cell dynamics and cellular heterogeneity across lineage subtypes of castrate-resistant prostate cancer.

To resist lineage-dependent therapies such as androgen receptor inhibition, prostate luminal epithelial adenocarcinoma cells often adopt a stem-like state resulting in lineage plasticity and phenotypic heterogeneity. Castrate-resistant prostate adenocarcinoma can transition to neuroendocrine (NE) and occasionally to amphicrine, co-expressed luminal and NE, phenotypes. We developed castrate-resistant prostate cancer (CRPC) patient-derived organoid models that preserve heterogeneity of the originating tumor, including an amphicrine model displaying a range of luminal and NE phenotypes. To gain biological insight and to identify potential treatment targets within heterogeneous tumor cell populations, we assessed the lineage hierarchy and molecular characteristics of various CRPC tumor subpopulations. Transcriptionally similar stem/progenitor (St/Pr) cells were identified for all lineage populations. Lineage tracing in amphicrine CRPC showed that heterogeneity originated from distinct subclones of infrequent St/Pr cells that produced mainly quiescent differentiated amphicrine progeny. By contrast, adenocarcinoma CRPC progeny originated from St/Pr cells and self-renewing differentiated luminal cells. Neuroendocrine prostate cancer (NEPC) was composed almost exclusively of self-renewing St/Pr cells. Amphicrine subpopulations were enriched for secretory luminal, mesenchymal, and enzalutamide treatment persistent signatures that characterize clinical progression. Finally, the amphicrine St/Pr subpopulation was specifically depleted with an AURKA inhibitor, which blocked tumor growth. These data illuminate distinct stem cell (SC) characteristics for subtype-specific CRPC in addition to demonstrating a context for targeting differentiation-competent prostate SCs.

Flutamide With or Without PROSTVAC in Non-metastatic Castration Resistant (M0) Prostate Cancer.

BACKGROUND: Before 2018, there was no standard of care for non-metastatic (M0) castration resistant prostate cancer nmCRPC. Androgen receptor antagonists (ARAs) were commonly used sequentially nmCRPC. METHODS: This was a multicenter, randomized clinical trial comparing the ARA flutamide+/-PROSTVAC, a pox viral vaccine targeting PSA that includes T-cell co-stimulatory molecules. Eligible men had negative CT and Tc99 bone scans, and rising PSA on ADT. Previous treatment with ARA was a stratification factor. Patients were also evaluated for antigen-specific immune responses using intracellular cytokine staining. RESULTS: Thirty-three patients randomized to flutamide and 31 to flutamide+vaccine. The median age was 71.8 and 69.8 years, respectively. The median time to treatment failure after a median potential follow-up of 46.7 months was, 4.5 months (range 2-70) for flutamide alone vs. 6.9 months (2.5-40; P = .38) with flutamide+vaccine. Seven patients in each arm had a >50% PSA response. Antigen-specific responses were similar in both arms (58% of patients in flutamide alone and 56% in flutamide+vaccine). The treatments were well tolerated. The most common side effect > grade 2 was injection site reaction seen in 29/31 vaccine patients which were self-limiting. CONCLUSION: The combination of flutamide+PROSTVAC did not improve outcomes in men with nmCRPC compared with flutamide alone. (ClinicalTrials.gov Identifier: NCT00450463).

A tripartite approach toward ending cancer as we know it, for everyone: An American Cancer Society perspective.

Gaps in the cancer care continuum are vast, both in the United States and globally. The American Cancer Society orchestrates an integrated, tripartite approach toward improving the lives of cancer patients and their families through research, advocacy, and patient support. With a focus on eradicating cancer disparities, the American Cancer Society aims to scale and deploy best practices worldwide through partnerships, to ensure everyone has an opportunity to prevent, detect, treat, and survive cancer.

A Single-arm Phase II Study Combining NLG207, a Nanoparticle Camptothecin, with Enzalutamide in Advanced Metastatic Castration-resistant Prostate Cancer Post-Enzalutamide.

BACKGROUND: Despite the clinical efficacy of enzalutamide monotherapy in patients with advanced prostate cancer, therapeutic resistance and disease progression are inevitable. We proposed a study to evaluate NLG207, a nanoparticle-drug conjugate (NDC) of the potent topoisomerase I inhibitor camptothecin, in combination with enzalutamide, in patients with metastatic castration-resistant prostate cancer (mCRPC) following progression on enzalutamide. METHODS: This was a single-arm, optimal two-stage, phase II study to evaluate the efficacy of NLG207 in combination with enzalutamide in patients with mCRPC who received prior enzalutamide. A lead-in dose escalation evaluated the recommended phase 2 dose of NLG207 in combination with enzalutamide. Patients received NLG207 via IV infusion every 2 weeks and enzalutamide 160 mg orally once daily. RESULTS: Between March 2019 and June 2021, four patients were accrued to the lead-in dose escalation. Two of the four patients were evaluable and both experienced DLTs at the NLG207 12 mg/m2 dose level; one DLT was related to a dose delay for noninfective cystitis and myelosuppression, the other a grade 3 noninfective cystitis. Further evaluation of NLG207 in combination with enzalutamide was halted and the study was ultimately terminated. PSA declines from baseline were observed in two patients. CONCLUSION: NLG207 12 mg/m2 in combination with enzalutamide was not well tolerated in patients with mCRPC following several lines of the standard of care therapy. CLINICALTRIALS.GOV IDENTIFIER: NCT03531827.

Cabozantinib plus docetaxel and prednisone in metastatic castration-resistant prostate cancer.

OBJECTIVE: To evaluate the safety and efficacy of cabozantinib combined with docetaxel. PATIENTS AND METHODS: This was a phase 1/2 multicentre study in patients with metastatic castration-resistant prostate cancer (mCRPC). Docetaxel (75 mg/m2 every 3 weeks with daily prednisone 10 mg) was combined with escalating doses of daily cabozantinib (20, 40 and 60 mg). Based on the results of the phase 1 study, the investigation was expanded into a randomized study of docetaxel with prednisone (hereafter 'docetaxel/prednisone') plus the maximum tolerated dose (MTD) of cabozantinib compared with docetaxel/prednisone alone. RESULTS: A total of 44 men with mCRPC were enrolled in this phase 1/2 trial. An MTD of 40 mg cabozantinib plus docetaxel/prednisone was determined. Dose-limiting toxicities were neutropenic fever and palmar-plantar erythrodysesthesia, and there was one death attributable to a thromboembolic event. In addition, grade 3 or 4 myelosuppression, hypophosphataemia and neuropathy were seen in three or more patients. In the phase 1 study, the median time to progression (TTP) and overall survival (OS) time were 13.6 and 16.3 months, respectively. In the phase 2 study, which was terminated early because of poor accrual, the median TTP and OS favoured the combination (n = 13) compared to docetaxel/prednisone alone (n = 12; 21.0 vs 6.6 months; P = 0.035 and 23.8 vs 15.6 months; P = 0.072, respectively). CONCLUSION: Despite the limited number of patients in this study, preliminary data suggest that cabozantinib can be safely added to docetaxel/prednisone with possible enhanced efficacy.

Cabozantinib in patients with platinum-refractory metastatic urothelial carcinoma: an open-label, single-centre, phase 2 trial.

BACKGROUND: Cabozantinib is a multikinase inhibitor of MET, VEGFR, AXL, and RET, which also has an effect on the tumour immune microenvironment by decreasing regulatory T cells and myeloid-derived suppressor cells. In this study, we examined the activity of cabozantinib in patients with metastatic platinum-refractory urothelial carcinoma. METHODS: This study was an open-label, single-arm, three-cohort phase 2 trial done at the National Cancer Institute (Bethesda, MD, USA). Eligible patients were 18 years or older, had histologically confirmed urothelial carcinoma or rare genitourinary tract histologies, Karnofsky performance scale index of 60% or higher, and documented disease progression after at least one previous line of platinum-based chemotherapy (platinum-refractory). Cohort one included patients with metastatic urothelial carcinoma with measurable disease as defined by Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1. Two additional cohorts that enrolled in parallel (patients with bone-only urothelial carcinoma metastases and patients with rare histologies of the genitourinary tract) were exploratory. Patients received cabozantinib 60 mg orally once daily in 28-day cycles until disease progression or unacceptable toxicity. The primary endpoint was investigator-assessed objective response rate by RECIST in cohort one. Response was assessed in all patients who met the eligibility criteria and who received at least 8 weeks of therapy. All patients who received at least one dose of cabozantinib were included in the safety analysis. This completed study is registered with ClinicalTrials.gov, NCT01688999. FINDINGS: Between Sept 28, 2012, and Oct, 20, 2015, 68 patients were enrolled on the study (49 in cohort one, six in cohort two, and 13 in cohort three). All patients received at least one dose of cabozantinib. The median follow-up was 61·2 months (IQR 53·8-70·0) for the 57 patients evaluable for response. In the 42 evaluable patients in cohort one, there was one complete response and seven partial responses (objective response rate 19%, 95% CI 9-34). The most common grade 3-4 adverse events were fatigue (six [9%] patients), hypertension (five [7%]), proteinuria (four [6%]), and hypophosphataemia (four [6%]). There were no treatment-related deaths. INTERPRETATION: Cabozantinib has single-agent clinical activity in patients with heavily pretreated, platinum-refractory metastatic urothelial carcinoma with measurable disease and bone metastases and is generally well tolerated. Cabozantinib has innate and adaptive immunomodulatory properties providing a rationale for combining cabozantinib with immunotherapeutic strategies. FUNDING: National Cancer Institute Intramural Program and the Cancer Therapy Evaluation Program.

Natural history and imaging in men with high genetic risk for developing prostate cancer.

Prostate cancer is the most common malignancy and the second leading cause of cancer related deaths in the United States. Established risk factors for prostate cancer incidence include older age, African-American race, and positive family history. Prostate cancer has substantial inherited predisposition and certain genetic variants are associated with increased risk of disease. Screening and imaging should target high-risk populations based on their genetic predisposition.

Management Options for Biochemically Recurrent Prostate Cancer.

Prostate cancer is the most common solid tumor malignancy in men worldwide. Treatment with surgery and radiation can be curative in organ-confined disease. Unfortunately, about one third of men develop biochemically recurrent disease based only on rising prostate-specific antigen (PSA) in the absence of visible disease on conventional imaging. For these patients with biochemical recurrent prostate cancer, there is no uniform guideline for subsequent management. Based on available data, it seems prudent that biochemical recurrent prostate cancer should initially be evaluated for salvage radiation or prostatectomy, with curative intent. In selected cases, high-intensity focused ultrasound and cryotherapy may be considered in patients that meet very narrow criteria as defined by non-randomized trials. If salvage options are not practical or unsuccessful, androgen deprivation therapy (ADT) is a standard option for disease control. While some patients prefer ADT to manage the disease immediately, others defer treatment because of the associated toxicity. In the absence of definitive randomized data, patients may be followed using PSA doubling time as a trigger to initiate ADT. Based on retrospective data, a PSA doubling time of less than 3-6 months has been associated with near-term development of metastasis and thus could be used signal to initiate ADT. Once treatment is begun, patients and their providers can choose between an intermittent and continuous ADT strategy. The intermittent approach may limit side effects but in patients with metastatic disease studies could not exclude a 20% greater risk of death. In men with biochemical recurrence, large studies have shown that intermittent therapy is non-inferior to continuous therapy, thus making this a reasonable option. Since biochemically recurrent prostate cancer is defined by technological limitations of radiographic detection, as new imaging (i.e., PSMA) strategies are developed, it may alter how the disease is monitored and perhaps managed. Furthermore, patients have no symptoms related to their disease and thus many prefer options that minimize toxicity. For this reason, herbal agents and immunotherapy are under investigation as potential alternatives to ADT and its accompanying side effects. New therapeutic options combined with improved imaging to evaluate the disease may markedly change how biochemically recurrent prostate cancer is managed in the future.

Phase II trial of docetaxel, bevacizumab, lenalidomide and prednisone in patients with metastatic castration-resistant prostate cancer.

OBJECTIVE: To determine the safety and clinical efficacy of two anti-angiogenic agents, bevacizumab and lenalidomide, with docetaxel and prednisone. PATIENTS AND METHODS: Eligible patients with metastatic castration-resistant prostate cancer enrolled in this open-label, phase II study of lenalidomide with bevacizumab (15 mg/kg), docetaxel (75 mg/m(2) ) and prednisone (10 mg daily). Docetaxel and bevacizumab were administered on day 1 of a 3-week treatment cycle. To establish safety, lenalidomide dosing in this combination was escalated in a conventional 3 + 3 design (15, 20 and 25 mg daily for 2 weeks followed by 1 week off). Patients received supportive measures including prophylactic pegfilgrastim and enoxaparin. The primary endpoints were safety and clinical efficacy. RESULTS: A total of 63 patients enrolled in this trial. Toxicities were manageable with most common adverse events (AEs) being haematological, and were ascertained by weekly blood counts. Twenty-nine patients (46%) had grade 4 neutropenia, 20 (32%) had grade 3 anaemia and seven (11%) had grade 3 thrombocytopenia. Despite frequent neutropenia, serious infections were rare. Other common non-haematological grade 3 AEs included fatigue (10%) and diarrhoea (10%). Grade 2 AEs in >10% of patients included anorexia, weight loss, constipation, osteonecrosis of the jaw, rash and dyspnoea. Of 61 evaluable patients, 57 (93%), 55 (90%) and 33 (54%) had PSA declines of >30, >50 and >90%, respectively. Of the 29 evaluable patients, 24 (86%) had a confirmed radiographic partial response. The median times to progression and overall survival were 18.2 and 24.6 months, respectively. CONCLUSIONS: With appropriate supportive measures, combination angiogenesis inhibition can be safely administered and potentially provide clinical benefit. These hypothesis-generating data would require randomized trials to confirm the findings.

Metabolic syndrome in prostate cancer: impact on risk and outcomes.

Androgen-deprivation therapy (ADT) is a fundamental element of treatment for nonlocalized prostate cancer and for patients with high-risk disease who are not candidates for radical treatment. ADT has been linked to metabolic syndrome, which involves changes in metabolic factors. While distinct from classic metabolic syndrome, this type does include changes in body composition, lipid profiles and insulin resistance. The constellation of risk factors may be associated with cardiovascular morbidity and the onset of diabetes mellitus. Physicians should discuss in detail the risk and benefits of ADT, as well as any needed lifestyle modifications with patients before beginning therapy.

A phase I study of TRC105 anti-endoglin (CD105) antibody in metastatic castration-resistant prostate cancer.

OBJECTIVE: TRC105 is a chimeric immunoglobulin G1 monoclonal antibody that binds endoglin (CD105). This phase I open-label study evaluated the safety, pharmacokinetics and pharmacodynamics of TRC105 in patients with metastatic castration-resistant prostate cancer (mCRPC). PATIENTS AND METHODS: Patients with mCRPC received escalating doses of i.v. TRC105 until unacceptable toxicity or disease progression, up to a predetermined dose level, using a standard 3 + 3 phase I design. RESULTS: A total of 20 patients were treated. The top dose level studied, 20 mg/kg every 2 weeks, was the maximum tolerated dose. Common adverse effects included infusion-related reaction (90%), low grade headache (67%), anaemia (48%), epistaxis (43%) and fever (43%). Ten patients had stable disease on study and eight patients had declines in prostate specific antigen (PSA). Significant plasma CD105 reduction was observed at the higher dose levels. In an exploratory analysis, vascular endothelial growth factor (VEGF) was increased after treatment with TRC105 and VEGF levels were associated with CD105 reduction. CONCLUSION: TRC105 was tolerated at 20 mg/kg every other week with a safety profile distinct from that of VEGF inhibitors. A significant induction of plasma VEGF was associated with CD105 reduction, suggesting anti-angiogenic activity of TRC105. An exploratory analysis showed a tentative correlation between the reduction of CD105 and a decrease in PSA velocity, suggestive of potential activity of TRC105 in the patients with mCRPC. The data from this exploratory analysis suggest that rising VEGF level is a possible compensatory mechanism for TRC105-induced anti-angiogenic activity.

A combination trial of vaccine plus ipilimumab in metastatic castration-resistant prostate cancer patients: immune correlates.

We recently reported the clinical results of a Phase I trial combining ipilimumab with a vaccine containing transgenes for prostate-specific antigen (PSA) and for a triad of costimulatory molecules (PROSTVAC) in patients with metastatic castration-resistant prostate cancer. Thirty patients were treated with escalating ipilimumab and a fixed dose of vaccine. Of 24 chemotherapy-naïve patients, 58 % had a PSA decline. Combination therapy did not exacerbate the immune-related adverse events associated with ipilimumab. Here, we present updated survival data and an evaluation of 36 immune cell subsets pre- and post-therapy. Peripheral blood mononuclear cells were collected before therapy, at 13 days and at 70 days post-initiation of therapy, and phenotyped by flow cytometry for the subsets of T cells, regulatory T cells, natural killer cells, and myeloid-derived suppressor cells. Associations between overall survival (OS) and immune cell subsets prior to treatment, and the change in a given immune cell subset 70 days post-initiation of therapy, were evaluated. The median OS was 2.63 years (1.77-3.45). There were trends toward associations for longer OS and certain immune cell subsets before immunotherapy: lower PD-1(+)Tim-3(NEG)CD4EM (P = 0.005, adjusted P = 0.010), higher PD-1(NEG)Tim-3(+)CD8 (P = 0.002, adjusted P = 0.004), and a higher number of CTLA-4(NEG) Tregs (P = 0.005, adjusted P = 0.010). We also found that an increase in Tim-3(+) natural killer cells post- versus pre-vaccination associated with longer OS (P = 0.0074, adjusted P = 0.015). These results should be considered as hypothesis generating and should be further evaluated in larger immunotherapy trials.

Tyrosine kinase inhibitors in the treatment of prostate cancer: taking the next step in clinical development.

INTRODUCTION: Prostate cancer (PCa) is the most frequently diagnosed, non-cutaneous malignancy in Western countries. Until recently, few therapeutic options were available for patients with advanced PCa. Although these treatments may delay progression of disease, none are curative. Therefore, research continues to investigate other treatments for advanced PCa. Tyrosine kinase inhibitors (TKIs) have been extensively studied as a treatment for multiple malignancies and may represent an additional strategy. In addition to limiting cellular proliferation and metastasis, there is also growing interest in using these treatments to impact the bone microenvironment and reduce associated morbidity from PCa. AREAS COVERED: Several TKIs have been evaluated in the preclinical setting in advanced PCa. Targets reviewed include the epidermal growth factor family, VEGF receptor, c-Src family kinases, platelet-derived growth factor and c-Met. EXPERT OPINION: Despite strong biological rationale for the use of TKIs therapy for the treatment of PCa, Phase III clinical trials have produced disappointing results. As TKI strategies move forward, the failures of past trials need to be better understood. New approaches with these treatments will also have to take into account modern anti-androgens and a treatment landscape that now includes immunotherapy.

Reflections on the state of telehealth and cancer care research and future directions.

Telemedicine has routinely been used in cancer care delivery for the past 3 years. The current state of digital health provides convenience and efficiency for both health-care professional and patient, but challenges exist in equitable access to virtual services. As increasingly newer technologies are added to telehealth platforms, it is essential to eliminate barriers to access through technical, procedural, and legislative improvements. Moving forward, implementation of new strategies can help eliminate disparities in virtual cancer care, facilitate delivery of treatment in the home, and improve real-time data collection for patient safety and clinical trial participation. The ultimate goal will be to extend high-quality survival for all patients with cancer through improved digital delivery of cancer care.

Deep learning-based whole-body PSMA PET/CT attenuation correction utilizing Pix-2-Pix GAN.

PURPOSE: Sequential PET/CT studies oncology patients can undergo during their treatment follow-up course is limited by radiation dosage. We propose an artificial intelligence (AI) tool to produce attenuation-corrected PET (AC-PET) images from non-attenuation-corrected PET (NAC-PET) images to reduce need for low-dose CT scans. METHODS: A deep learning algorithm based on 2D Pix-2-Pix generative adversarial network (GAN) architecture was developed from paired AC-PET and NAC-PET images. 18F-DCFPyL PSMA PET-CT studies from 302 prostate cancer patients, split into training, validation, and testing cohorts (n = 183, 60, 59, respectively). Models were trained with two normalization strategies: Standard Uptake Value (SUV)-based and SUV-Nyul-based. Scan-level performance was evaluated by normalized mean square error (NMSE), mean absolute error (MAE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Lesion-level analysis was performed in regions-of-interest prospectively from nuclear medicine physicians. SUV metrics were evaluated using intraclass correlation coefficient (ICC), repeatability coefficient (RC), and linear mixed-effects modeling. RESULTS: Median NMSE, MAE, SSIM, and PSNR were 13.26%, 3.59%, 0.891, and 26.82, respectively, in the independent test cohort. ICC for SUVmax and SUVmean were 0.88 and 0.89, which indicated a high correlation between original and AI-generated quantitative imaging markers. Lesion location, density (Hounsfield units), and lesion uptake were all shown to impact relative error in generated SUV metrics (all p < 0.05). CONCLUSION: The Pix-2-Pix GAN model for generating AC-PET demonstrates SUV metrics that highly correlate with original images. AI-generated PET images show clinical potential for reducing the need for CT scans for attenuation correction while preserving quantitative markers and image quality.

Deep Learning-Based Detection and Classification of Bone Lesions on Staging Computed Tomography in Prostate Cancer: A Development Study.

RATIONALE AND OBJECTIVES: Efficiently detecting and characterizing metastatic bone lesions on staging CT is crucial for prostate cancer (PCa) care. However, it demands significant expert time and additional imaging such as PET/CT. We aimed to develop an ensemble of two automated deep learning AI models for 1) bone lesion detection and segmentation and 2) benign vs. metastatic lesion classification on staging CTs and to compare its performance with radiologists. MATERIALS AND METHODS: This retrospective study developed two AI models using 297 staging CT scans (81 metastatic) with 4601 benign and 1911 metastatic lesions in PCa patients. Metastases were validated by follow-up scans, bone biopsy, or PET/CT. Segmentation AI (3DAISeg) was developed using the lesion contours delineated by a radiologist. 3DAISeg performance was evaluated with the Dice similarity coefficient, and classification AI (3DAIClass) performance on AI and radiologist contours was assessed with F1-score and accuracy. Training/validation/testing data partitions of 70:15:15 were used. A multi-reader study was performed with two junior and two senior radiologists within a subset of the testing dataset (n = 36). RESULTS: In 45 unseen staging CT scans (12 metastatic PCa) with 669 benign and 364 metastatic lesions, 3DAISeg detected 73.1% of metastatic (266/364) and 72.4% of benign lesions (484/669). Each scan averaged 12 extra segmentations (range: 1-31). All metastatic scans had at least one detected metastatic lesion, achieving a 100% patient-level detection. The mean Dice score for 3DAISeg was 0.53 (median: 0.59, range: 0-0.87). The F1 for 3DAIClass was 94.8% (radiologist contours) and 92.4% (3DAISeg contours), with a median false positive of 0 (range: 0-3). Using radiologist contours, 3DAIClass had PPV and NPV rates comparable to junior and senior radiologists: PPV (semi-automated approach AI 40.0% vs. Juniors 32.0% vs. Seniors 50.0%) and NPV (AI 96.2% vs. Juniors 95.7% vs. Seniors 91.9%). When using 3DAISeg, 3DAIClass mimicked junior radiologists in PPV (pure-AI 20.0% vs. Juniors 32.0% vs. Seniors 50.0%) but surpassed seniors in NPV (pure-AI 93.8% vs. Juniors 95.7% vs. Seniors 91.9%). CONCLUSION: Our lesion detection and classification AI model performs on par with junior and senior radiologists in discerning benign and metastatic lesions on staging CTs obtained for PCa.

Localized high-risk prostate cancer harbors an androgen receptor low subpopulation susceptible to HER2 inhibition.

Patients diagnosed with localized high-risk prostate cancer have higher rates of recurrence, and the introduction of neoadjuvant intensive hormonal therapies seeks to treat occult micrometastatic disease by their addition to definitive treatment. Sufficient profiling of baseline disease has remained a challenge in enabling the in-depth assessment of phenotypes associated with exceptional vs. poor pathologic responses after treatment. In this study, we report comprehensive and integrative gene expression profiling of 37 locally advanced prostate tumors prior to six months of androgen deprivation therapy (ADT) plus the androgen receptor (AR) inhibitor enzalutamide prior to radical prostatectomy. A robust transcriptional program associated with HER2 activity was positively associated with poor outcome and opposed AR activity, even after adjusting for common genomic alterations in prostate cancer including PTEN loss and expression of the TMPRSS2:ERG fusion. Patients experiencing exceptional pathologic responses demonstrated lower levels of HER2 and phospho-HER2 by immunohistochemistry of biopsy tissues. The inverse correlation of AR and HER2 activity was found to be a universal feature of all aggressive prostate tumors, validated by transcriptional profiling an external cohort of 121 patients and immunostaining of tumors from 84 additional patients. Importantly, the AR activity-low, HER2 activity-high cells that resist ADT are a pre-existing subset of cells that can be targeted by HER2 inhibition alone or in combination with enzalutamide. In summary, we show that prostate tumors adopt an AR activity-low prior to antiandrogen exposure that can be exploited by treatment with HER2 inhibitors.