Analysis of Circulating Tumor DNA Predicts Outcomes of Short-Course Consolidation Immunotherapy in Unresectable Stage III NSCLC.

INTRODUCTION: The current standard of care for patients with inoperable stage III non-small cell lung cancer includes chemoradiotherapy (CRT) followed by 1 year of checkpoint inhibitor (CPI) therapy. Nevertheless, the optimal duration of consolidation CPI remains unknown. Here, we characterized the relationship between circulating tumor DNA (ctDNA) minimal residual disease (MRD) and clinical outcomes of patients with unresectable locally advanced non-small cell lung cancer treated on a phase 2 trial of short-course consolidation immunotherapy after CRT, with the goal of testing whether ctDNA may be able to identify patients who do not require a full year of treatment. METHODS: Plasma samples for ctDNA analysis were collected from patients on the Big Ten Cancer Research Consortium LUN 16-081 trial after completion of CRT, before day 1 of cycle 2 (C2D1) of CPI (i.e., 1 mo after treatment start), and at the end of up to 6 months of treatment. Tumor-informed ctDNA MRD analysis was performed using cancer personalized profiling by deep sequencing. Levels of ctDNA at each time point were correlated with clinical outcomes. RESULTS: Detection of ctDNA predicted significantly inferior progression-free survival after completion of CRT (24-mo 29% versus 65%, p = 0.0048), before C2D1 of CPI (24-mo 0% versus 72%, p < 0.0001) and at the end of CPI (24-mo 15% versus 67%, p = 0.0011). In addition, patients with decreasing or undetectable ctDNA levels after 1 cycle of CPI had improved outcomes compared with patients with increasing ctDNA levels (24-mo progression-free survival 72% versus 0%, p < 0.0001). Progression of disease occurred within less than 12 months of starting CPI in all patients with increasing ctDNA levels at C2D1. CONCLUSIONS: Detection of ctDNA before, during, or after 6 months of consolidation CPI is strongly associated with inferior outcomes. Our findings suggest that analysis of ctDNA MRD may enable personalizing the duration of consolidation immunotherapy treatment.

External validation of an artificial intelligence model for Gleason grading of prostate cancer on prostatectomy specimens.

OBJECTIVES: To externally validate the performance of the DeepDx Prostate artificial intelligence (AI) algorithm (Deep Bio Inc., Seoul, South Korea) for Gleason grading on whole-mount prostate histopathology, considering potential variations observed when applying AI models trained on biopsy samples to radical prostatectomy (RP) specimens due to inherent differences in tissue representation and sample size. MATERIALS AND METHODS: The commercially available DeepDx Prostate AI algorithm is an automated Gleason grading system that was previously trained using 1133 prostate core biopsy images and validated on 700 biopsy images from two institutions. We assessed the AI algorithm's performance, which outputs Gleason patterns (3, 4, or 5), on 500 1-mm2 tiles created from 150 whole-mount RP specimens from a third institution. These patterns were then grouped into grade groups (GGs) for comparison with expert pathologist assessments. The reference standard was the International Society of Urological Pathology GG as established by two experienced uropathologists with a third expert to adjudicate discordant cases. We defined the main metric as the agreement with the reference standard, using Cohen's kappa. RESULTS: The agreement between the two experienced pathologists in determining GGs at the tile level had a quadratically weighted Cohen's kappa of 0.94. The agreement between the AI algorithm and the reference standard in differentiating cancerous vs non-cancerous tissue had an unweighted Cohen's kappa of 0.91. Additionally, the AI algorithm's agreement with the reference standard in classifying tiles into GGs had a quadratically weighted Cohen's kappa of 0.89. In distinguishing cancerous vs non-cancerous tissue, the AI algorithm achieved a sensitivity of 0.997 and specificity of 0.88; in classifying GG ≥2 vs GG 1 and non-cancerous tissue, it demonstrated a sensitivity of 0.98 and specificity of 0.85. CONCLUSION: The DeepDx Prostate AI algorithm had excellent agreement with expert uropathologists and performance in cancer identification and grading on RP specimens, despite being trained on biopsy specimens from an entirely different patient population.

High-grade Anaplastic Transformation of Ovarian Serous Borderline Tumor: A Distinctive Morphology With Abundant Dense Eosinophilic Cytoplasm and Dismal Prognosis.

Ovarian serous borderline tumors (SBTs) have a generally favorable prognosis. Although the risk of progression to low-grade serous carcinoma is well documented, progression to high-grade carcinoma is rare. We report the clinicopathologic features of seven SBTs, each associated with the presence of a morphologically unique high-grade component with an extremely dismal prognosis. All of the SBTs exhibited typical hierarchical branching and scattered eosinophilic cells, whereas the high-grade component consisted of a profuse proliferation of epithelioid cells with abundant dense, eosinophilic cytoplasm, variable nuclear pleomorphism, and evident loss of WT1, estrogen receptor, and p16 positivity. In most cases, the SBT demonstrated an abrupt transition to the high-grade component, but one patient initially presented with the usual SBT and developed a recurrent disease that was composed entirely of the high-grade component. Targeted next-generation sequencing revealed identical driver mutations in both the SBT and high-grade components (BRAF in 3, KRAS in 1), confirming clonality. Three cases, in addition, harbored telomerase reverse transcriptase promoter mutations in both components. One case, despite insufficient material for sequencing, was BRAF V600E-positive by immunohistochemistry. Most patients with available follow-up data died within 9 months of diagnosis. This study confirms prior reports of ovarian SBT transformation to high-grade carcinoma and further characterizes a distinct subset with abundant dense eosinophilic cytoplasm and an extremely dismal prognosis. The presence of BRAF mutations in a major subset of these tumors questions the notion that BRAF is associated with senescent eosinophilic cells and improved outcomes in SBT. The role of the additional telomerase reverse transcriptase promoter mutations merits further investigation.

A pathologist-AI collaboration framework for enhancing diagnostic accuracies and efficiencies.

In pathology, the deployment of artificial intelligence (AI) in clinical settings is constrained by limitations in data collection and in model transparency and interpretability. Here we describe a digital pathology framework, nuclei.io, that incorporates active learning and human-in-the-loop real-time feedback for the rapid creation of diverse datasets and models. We validate the effectiveness of the framework via two crossover user studies that leveraged collaboration between the AI and the pathologist, including the identification of plasma cells in endometrial biopsies and the detection of colorectal cancer metastasis in lymph nodes. In both studies, nuclei.io yielded considerable diagnostic performance improvements. Collaboration between clinicians and AI will aid digital pathology by enhancing accuracies and efficiencies.

RAPHIA: A deep learning pipeline for the registration of MRI and whole-mount histopathology images of the prostate.

Image registration can map the ground truth extent of prostate cancer from histopathology images onto MRI, facilitating the development of machine learning methods for early prostate cancer detection. Here, we present RAdiology PatHology Image Alignment (RAPHIA), an end-to-end pipeline for efficient and accurate registration of MRI and histopathology images. RAPHIA automates several time-consuming manual steps in existing approaches including prostate segmentation, estimation of the rotation angle and horizontal flipping in histopathology images, and estimation of MRI-histopathology slice correspondences. By utilizing deep learning registration networks, RAPHIA substantially reduces computational time. Furthermore, RAPHIA obviates the need for a multimodal image similarity metric by transferring histopathology image representations to MRI image representations and vice versa. With the assistance of RAPHIA, novice users achieved expert-level performance, and their mean error in estimating histopathology rotation angle was reduced by 51% (12 degrees vs 8 degrees), their mean accuracy of estimating histopathology flipping was increased by 5% (95.3% vs 100%), and their mean error in estimating MRI-histopathology slice correspondences was reduced by 45% (1.12 slices vs 0.62 slices). When compared to a recent conventional registration approach and a deep learning registration approach, RAPHIA achieved better mapping of histopathology cancer labels, with an improved mean Dice coefficient of cancer regions outlined on MRI and the deformed histopathology (0.44 vs 0.48 vs 0.50), and a reduced mean per-case processing time (51 vs 11 vs 4.5 min). The improved performance by RAPHIA allows efficient processing of large datasets for the development of machine learning models for prostate cancer detection on MRI. Our code is publicly available at: https://github.com/pimed/RAPHIA.

Critical evaluation of artificial intelligence as a digital twin of pathologists for prostate cancer pathology.

Prostate cancer pathology plays a crucial role in clinical management but is time-consuming. Artificial intelligence (AI) shows promise in detecting prostate cancer and grading patterns. We tested an AI-based digital twin of a pathologist, vPatho, on 2603 histological images of prostate tissue stained with hematoxylin and eosin. We analyzed various factors influencing tumor grade discordance between the vPatho system and six human pathologists. Our results demonstrated that vPatho achieved comparable performance in prostate cancer detection and tumor volume estimation, as reported in the literature. The concordance levels between vPatho and human pathologists were examined. Notably, moderate to substantial agreement was observed in identifying complementary histological features such as ductal, cribriform, nerve, blood vessel, and lymphocyte infiltration. However, concordance in tumor grading decreased when applied to prostatectomy specimens (κ = 0.44) compared to biopsy cores (κ = 0.70). Adjusting the decision threshold for the secondary Gleason pattern from 5 to 10% improved the concordance level between pathologists and vPatho for tumor grading on prostatectomy specimens (κ from 0.44 to 0.64). Potential causes of grade discordance included the vertical extent of tumors toward the prostate boundary and the proportions of slides with prostate cancer. Gleason pattern 4 was particularly associated with this population. Notably, the grade according to vPatho was not specific to any of the six pathologists involved in routine clinical grading. In conclusion, our study highlights the potential utility of AI in developing a digital twin for a pathologist. This approach can help uncover limitations in AI adoption and the practical application of the current grading system for prostate cancer pathology.

UCHL1 is a potential molecular indicator and therapeutic target for neuroendocrine carcinomas.

Neuroendocrine carcinomas, such as neuroendocrine prostate cancer and small-cell lung cancer, commonly have a poor prognosis and limited therapeutic options. We report that ubiquitin carboxy-terminal hydrolase L1 (UCHL1), a deubiquitinating enzyme, is elevated in tissues and plasma from patients with neuroendocrine carcinomas. Loss of UCHL1 decreases tumor growth and inhibits metastasis of these malignancies. UCHL1 maintains neuroendocrine differentiation and promotes cancer progression by regulating nucleoporin, POM121, and p53. UCHL1 binds, deubiquitinates, and stabilizes POM121 to regulate POM121-associated nuclear transport of E2F1 and c-MYC. Treatment with the UCHL1 inhibitor LDN-57444 slows tumor growth and metastasis across neuroendocrine carcinomas. The combination of UCHL1 inhibitors with cisplatin, the standard of care used for neuroendocrine carcinomas, significantly delays tumor growth in pre-clinical settings. Our study reveals mechanisms of UCHL1 function in regulating the progression of neuroendocrine carcinomas and identifies UCHL1 as a therapeutic target and potential molecular indicator for diagnosing and monitoring treatment responses in these malignancies.

High expression of Trop2 is associated with aggressive localized prostate cancer and is a candidate urinary biomarker.

Distinguishing indolent from clinically significant localized prostate cancer is a major clinical challenge and influences clinical decision-making between treatment and active surveillance. The development of novel predictive biomarkers will help with risk stratification, and clinical decision-making, leading to a decrease in over or under-treatment of patients with prostate cancer. Here, we report that Trop2 is a prognostic tissue biomarker for clinically significant prostate cancer by utilizing the Canary Prostate Cancer Tissue Microarray (CPCTA) cohort composed of over 1100 patients from a multi-institutional study. We demonstrate that elevated Trop2 expression is correlated with worse clinical features including Gleason score, age, and pre-operative PSA levels. More importantly, we demonstrate that elevated Trop2 expression at radical prostatectomy predicts worse overall survival in men undergoing radical prostatectomy. Additionally, we detect shed Trop2 in urine from men with clinically significant prostate cancer. Our study identifies Trop2 as a novel tissue prognostic biomarker and a candidate non-invasive marker for prostate cancer.

Diagnostic impact of RNA-based next-generation sequencing fusion panel for solid tumors: A single-institution experience.

OBJECTIVES: Gene rearrangements frequently act as oncogenic driver mutations and determine the onset and progression of cancer. RNA-based next-generation sequencing (NGS) is being used with increasing frequency for solid tumors. The purpose of our study is to investigate the feasibility and utility of an RNA-based NGS fusion panel for solid tumors. METHODS: We conducted a retrospective, single-institution review of fusion panels requested between May 2022 and March 2023. Demographic, clinical, pathologic, and molecular findings of the patients were reviewed. The utility of the RNA-based NGS fusion panel for the pathologic diagnosis of solid tumors was assessed. RESULTS: Our study included 345 cases, and a fusion event was identified in 24.3% (78/321) of cases. Among the 110 cases submitted for diagnostic purposes, a fusion event was detected in 42.7% (47/110) of cases. The results led to refinement or clarification of the initial diagnosis in 31.9% (15/47) of cases and agreement or support for the initial diagnosis in 59.6% (28/47) of cases. Furthermore, our study indicated that the overall cellularity (tumor and normal tissue) of the tested specimen influences the success of the testing process. CONCLUSIONS: In summary, this study demonstrated the feasibility and utility of an RNA-based NGS fusion panel for a wide variety of solid tumors in the appropriate clinicopathologic context. These findings warrant further validation in larger studies involving multiple institutional patient cohorts.

Spatial transcriptomics identifies candidate stromal drivers of benign prostatic hyperplasia.

Benign prostatic hyperplasia (BPH) is the nodular proliferation of the prostate transition zone in older men, leading to urinary storage and voiding problems that can be recalcitrant to therapy. Decades ago, John McNeal proposed that BPH originates with the "reawakening" of embryonic inductive activity by adult prostate stroma, which spurs new ductal proliferation and branching morphogenesis. Here, by laser microdissection and transcriptional profiling of the BPH stroma adjacent to hyperplastic branching ducts, we identified secreted factors likely mediating stromal induction of prostate glandular epithelium and coinciding processes. The top stromal factors were insulin-like growth factor 1 (IGF1) and CXC chemokine ligand 13 (CXCL13), which we verified by RNA in situ hybridization to be coexpressed in BPH fibroblasts, along with their cognate receptors (IGF1R and CXCR5) on adjacent epithelium. In contrast, IGF1 but not CXCL13 was expressed in human embryonic prostate stroma. Finally, we demonstrated that IGF1 is necessary for the generation of BPH-1 cell spheroids and patient-derived BPH cell organoids in 3D culture. Our findings partially support historic speculations on the etiology of BPH and provide what we believe to be new molecular targets for rational therapies directed against the underlying processes driving BPH.

Low-grade fibromyxoid sarcoma of the breast: genetic characterization and immunohistochemical comparison to morphologic mimics.

Spindle cell lesions of the breast elicit a specific, relatively limited differential diagnosis, and accurate classification often requires careful morphologic evaluation and immunohistochemical workup. Low-grade fibromyxoid sarcoma (LGFMS) is a rare malignant fibroblastic tumor with deceptively bland spindle cell morphology. Involvement of the breast is exceedingly rare. We examined the clinicopathologic and molecular characteristics of three cases of breast/axillary LGFMS. In addition, we interrogated the immunohistochemical expression of MUC4, a commonly used marker of LGFMS, in other breast spindle cell lesions. LGFMS presented in women at 23, 33, and 59 years of age. Tumor size ranged from 0.9 to 4.7 cm. Microscopically, they were circumscribed nodular masses composed of bland spindle cells with fibromyxoid stroma. Immunohistochemically, tumors were diffusely positive for MUC4 and negative for keratin, CD34, S100 protein, and nuclear beta-catenin. Fluorescence in-situ hybridization demonstrated FUS (n = 2) or EWSR1 (n = 1) rearrangements. Next-generation sequencing identified FUS::CREB3L2 and EWSR1::CREB3L1 fusions. MUC4 immunohistochemistry performed on 162 additional breast lesions demonstrated only weak and limited expression in a subset of cases of fibromatosis (10/20, ≤30% staining), scar (5/9, ≤10%), metaplastic carcinoma (4/23, ≤5%), and phyllodes tumor (3/74, ≤10%). MUC4 was entirely negative in cases of pseudoangiomatous stromal hyperplasia (n = 9), myofibroblastoma (n = 6), periductal stromal tumor (n = 3), and cellular/juvenile fibroadenoma (n = 21). LGFMS can rarely occur in the breast and should be considered in the differential diagnosis of breast spindle cell lesions. Strong and diffuse MUC4 expression is highly specific in this histologic context. Detection of an FUS or EWSR1 rearrangement can confirm the diagnosis.

A Pilot Study of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for Biopsy Guidance in Patients with Suspected Prostate Cancer.

Targeting of lesions seen on multiparametric MRI (mpMRI) improves prostate cancer (PC) detection at biopsy. However, 20%-65% of highly suspicious lesions on mpMRI (PI-RADS [Prostate Imaging-Reporting and Data System] 4 or 5) are false-positives (FPs), while 5%-10% of clinically significant PC (csPC) are missed. Prostate-specific membrane antigen (PSMA) and gastrin-releasing peptide receptors (GRPRs) are both overexpressed in PC. We therefore aimed to evaluate the potential of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for biopsy guidance in patients with suspected PC. Methods: A highly selective cohort of 13 men, aged 58.0 ± 7.1 y, with suspected PC (persistently high prostate-specific antigen [PSA] and PSA density) but negative or equivocal mpMRI results or negative biopsy were prospectively enrolled to undergo 68Ga-PSMA11 and 68Ga-RM2 PET/MRI. PET/MRI included whole-body and dedicated pelvic imaging after a delay of 20 min. All patients had targeted biopsy of any lesions seen on PET followed by standard 12-core biopsy. The SUVmax of suspected PC lesions was collected and compared with gold standard biopsy. Results: PSA and PSA density at enrollment were 9.8 ± 6.0 (range, 1.5-25.5) ng/mL and 0.20 ± 0.18 (range, 0.06-0.68) ng/mL2, respectively. Standardized systematic biopsy revealed a total of 14 PCs in 8 participants: 7 were csPC and 7 were nonclinically significant PC (ncsPC). 68Ga-PSMA11 identified 25 lesions, of which 11 (44%) were true-positive (TP) (5 csPC). 68Ga-RM2 showed 27 lesions, of which 14 (52%) were TP, identifying all 7 csPC and also 7 ncsPC. There were 17 concordant lesions in 11 patients versus 14 discordant lesions in 7 patients between 68Ga-PSMA11 and 68Ga-RM2 PET. Incongruent lesions had the highest rate of FP (12 FP vs. 2 TP). SUVmax was significantly higher for TP than FP lesions in delayed pelvic imaging for 68Ga-PSMA11 (6.49 ± 4.14 vs. 4.05 ± 1.55, P = 0.023) but not for whole-body images, nor for 68Ga-RM2. Conclusion: Our results show that 68Ga-PSMA11 and 68Ga-RM2 PET/MRI are feasible for biopsy guidance in suspected PC. Both radiopharmaceuticals detected additional clinically significant cancers not seen on mpMRI in this selective cohort. 68Ga-RM2 PET/MRI identified all csPC confirmed at biopsy.

A Pilot Study of 68Ga-PSMA11 and 68Ga-RM2 PET/MRI for Evaluation of Prostate Cancer Response to High-Intensity Focused Ultrasound Therapy.

Focal therapy for localized prostate cancer (PC) using high-intensity focused ultrasound (HIFU) is gaining in popularity as it is noninvasive and associated with fewer side effects than standard whole-gland treatments. However, better methods to evaluate response to HIFU ablation are an unmet need. Prostate-specific membrane antigen (PSMA) and gastrin-releasing peptide receptors are both overexpressed in PC. In this study, we evaluated a novel approach of using both 68Ga-RM2 and 68Ga-PSMA11 PET/MRI in each patient before and after HIFU to assess the accuracy of target tumor localization and response to treatment. Methods: Fourteen men, 64.5 ± 8.0 y old (range, 48-78 y), with newly diagnosed PC were prospectively enrolled. Before HIFU, the patients underwent prostate biopsy, multiparametric MRI, 68Ga-PSMA11, and 68Ga-RM2 PET/MRI. Response to treatment was assessed at a minimum of 6 mo after HIFU with prostate biopsy (n = 13), as well as 68Ga-PSMA11 and 68Ga-RM2 PET/MRI (n = 14). The SUVmax and SUVpeak of known or suspected PC lesions were collected. Results: Pre-HIFU biopsy revealed 18 cancers, of which 14 were clinically significant (Gleason score ≥ 3 + 4). Multiparametric MRI identified 18 lesions; 14 of them were at least score 4 in the Prostate Imaging-Reporting and Data System. 68Ga-PSMA11 and 68Ga-RM2 PET/MRI each showed 23 positive intraprostatic lesions; 21 were congruent in 13 patients, and 5 were incongruent in 5 patients. Before HIFU, 68Ga-PSMA11 identified all target tumors, whereas 68Ga-RM2 PET/MRI missed 2 tumors. After HIFU, 68Ga-RM2 and 68Ga-PSMA11 PET/MRI both identified clinically significant residual disease in 1 patient. Three significant ipsilateral recurrent lesions were identified, whereas 1 was missed by 68Ga-PSMA11. The pretreatment level of prostate-specific antigen decreased significantly after HIFU, by 66%. Concordantly, the pretreatment SUVmax decreased significantly after HIFU for 68Ga-PSMA11 (P = 0.001) and 68Ga-RM2 (P = 0.005). Conclusion: This pilot study showed that 68Ga-PSMA11 and 68Ga-RM2 PET/MRI identified the target tumor for HIFU in 100% and 86% of cases, respectively, and accurately verified response to treatment. PET may be a useful tool in the guidance and monitoring of treatment success in patients receiving focal therapy for PC. These preliminary findings warrant larger studies for validation.

A review of artificial intelligence in prostate cancer detection on imaging.

A multitude of studies have explored the role of artificial intelligence (AI) in providing diagnostic support to radiologists, pathologists, and urologists in prostate cancer detection, risk-stratification, and management. This review provides a comprehensive overview of relevant literature regarding the use of AI models in (1) detecting prostate cancer on radiology images (magnetic resonance and ultrasound imaging), (2) detecting prostate cancer on histopathology images of prostate biopsy tissue, and (3) assisting in supporting tasks for prostate cancer detection (prostate gland segmentation, MRI-histopathology registration, MRI-ultrasound registration). We discuss both the potential of these AI models to assist in the clinical workflow of prostate cancer diagnosis, as well as the current limitations including variability in training data sets, algorithms, and evaluation criteria. We also discuss ongoing challenges and what is needed to bridge the gap between academic research on AI for prostate cancer and commercial solutions that improve routine clinical care.

GRM1 Immunohistochemistry Distinguishes Chondromyxoid Fibroma From its Histologic Mimics.

Chondromyxoid fibroma (CMF) is a rare benign bone neoplasm that manifests histologically as a lobular proliferation of stellate to spindle-shaped cells in a myxoid background, exhibiting morphologic overlap with other cartilaginous and myxoid tumors of bone. CMF is characterized by recurrent genetic rearrangements that place the glutamate receptor gene GRM1 under the regulatory control of a constitutively active promoter, leading to increased gene expression. Here, we explore the diagnostic utility of GRM1 immunohistochemistry as a surrogate marker for GRM1 rearrangement using a commercially available monoclonal antibody in a study of 230 tumors, including 30 CMF cases represented by 35 specimens. GRM1 was positive by immunohistochemistry in 97% of CMF specimens (34/35), exhibiting moderate to strong staining in more than 50% of neoplastic cells; staining was diffuse (>95% of cells) in 25 specimens (71%). Among the 9 CMF specimens with documented exposure to acid decalcification, 4 (44%) exhibited diffuse immunoreactivity (>95%) for GRM1, whereas all 15 CMF specimens (100%) with lack of exposure to decalcification reagents were diffusely immunoreactive ( P =0.003). High GRM1 expression at the RNA level was previously observed by quantitative reverse transcription polymerase chain reaction in 9 CMF cases that were also positive by immunohistochemistry; low GRM1 expression was observed by quantitative reverse transcription polymerase chain reaction in the single case of CMF that was negative by immunohistochemistry. GRM1 immunohistochemistry was negative (<5%) in histologic mimics of CMF, including conventional chondrosarcoma, enchondroma, chondroblastoma, clear cell chondrosarcoma, giant cell tumor of the bone, fibrous dysplasia, chondroblastic osteosarcoma, myoepithelial tumor, primary aneurysmal bone cyst, brown tumor, phosphaturic mesenchymal tumor, CMF-like osteosarcoma, and extraskeletal myxoid chondrosarcoma. These results indicate that GRM1 immunohistochemistry may have utility in distinguishing CMF from its histologic mimics.

Computational Detection of Extraprostatic Extension of Prostate Cancer on Multiparametric MRI Using Deep Learning.

The localization of extraprostatic extension (EPE), i.e., local spread of prostate cancer beyond the prostate capsular boundary, is important for risk stratification and surgical planning. However, the sensitivity of EPE detection by radiologists on MRI is low (57% on average). In this paper, we propose a method for computational detection of EPE on multiparametric MRI using deep learning. Ground truth labels of cancers and EPE were obtained in 123 patients (38 with EPE) by registering pre-surgical MRI with whole-mount digital histopathology images from radical prostatectomy. Our approach has two stages. First, we trained deep learning models using the MRI as input to generate cancer probability maps both inside and outside the prostate. Second, we built an image post-processing pipeline that generates predictions for EPE location based on the cancer probability maps and clinical knowledge. We used five-fold cross-validation to train our approach using data from 74 patients and tested it using data from an independent set of 49 patients. We compared two deep learning models for cancer detection: (i) UNet and (ii) the Correlated Signature Network for Indolent and Aggressive prostate cancer detection (CorrSigNIA). The best end-to-end model for EPE detection, which we call EPENet, was based on the CorrSigNIA cancer detection model. EPENet was successful at detecting cancers with extraprostatic extension, achieving a mean area under the receiver operator characteristic curve of 0.72 at the patient-level. On the test set, EPENet had 80.0% sensitivity and 28.2% specificity at the patient-level compared to 50.0% sensitivity and 76.9% specificity for the radiologists. To account for spatial location of predictions during evaluation, we also computed results at the sextant-level, where the prostate was divided into sextants according to standard systematic 12-core biopsy procedure. At the sextant-level, EPENet achieved mean sensitivity 61.1% and mean specificity 58.3%. Our approach has the potential to provide the location of extraprostatic extension using MRI alone, thus serving as an independent diagnostic aid to radiologists and facilitating treatment planning.

Immunofluorescent and molecular characterization of effusion tumor cells reveal cancer site-of-origin and disease-driving mutations.

BACKGROUND: Effective cancer treatment relies on precision diagnostics. In cytology, an accurate diagnosis facilitates the determination of proper therapeutics for patients with cancer. Previously, the authors developed a multiplexed immunofluorescent panel to detect epithelial malignancies from pleural effusion specimens. Their assay reliably distinguished effusion tumor cells (ETCs) from nonmalignant cells; however, it lacked the capacity to reveal specific cancer origin information. Furthermore, DNA profiling of ETCs revealed some, but not all, cancer-driver mutations. METHODS: The authors developed a new multiplex immunofluorescent panel that detected both malignancy and pulmonary origin by incorporating the thyroid transcription factor-1 (TTF-1) biomarker. Evaluation for TTF-1-positive ETCs (T-ETCs) was performed on 12 patient samples. T-ETCs and parallel ETCs from selected patients were collected and subjected to DNA profiling to identify pathogenic mutations. All samples were obtained with Institutional Review Board approval. RESULTS: Malignancy was detected in all samples. T-ETCs were identified in 9 of 10 patients who had clinically reported TTF-1 positivity (90% sensitivity and 100% specificity). Furthermore, DNA profiling of as few as five T-ETCs identified pathogenic mutations with equal or greater sensitivity compared with profiling of ETCs, both of which showed high concordance with clinical findings. CONCLUSIONS: The findings suggest that the immunofluorescent and molecular characterization of tumor cells from pleural effusion specimens can provide reliable diagnostic information, even with very few cells. The integration of site-specific biomarkers like TTF-1 into ETC analysis may facilitate better refined diagnosis and improve patient care.

The genetic landscape of germline DDX41 variants predisposing to myeloid neoplasms.

Germline DDX41 variants are the most common mutations predisposing to acute myeloid leukemia (AML)/myelodysplastic syndrome (MDS) in adults, but the causal variant (CV) landscape and clinical spectrum of hematologic malignancies (HMs) remain unexplored. Here, we analyzed the genomic profiles of 176 patients with HM carrying 82 distinct presumably germline DDX41 variants among a group of 9821 unrelated patients. Using our proposed DDX41-specific variant classification, we identified features distinguishing 116 patients with HM with CV from 60 patients with HM with variant of uncertain significance (VUS): an older age (median 69 years), male predominance (74% in CV vs 60% in VUS, P = .03), frequent concurrent somatic DDX41 variants (79% in CV vs 5% in VUS, P < .0001), a lower somatic mutation burden (1.4 ± 0.1 in CV vs 2.9 ± 0.04 in VUS, P = .012), near exclusion of canonical recurrent genetic abnormalities including mutations in NPM1, CEBPA, and FLT3 in AML, and favorable overall survival (OS) in patients with AML/MDS. This superior OS was determined independent of blast count, abnormal karyotypes, and concurrent variants, including TP53 in patients with AML/MDS, regardless of patient's sex, age, or specific germline CV, suggesting that germline DDX41 variants define a distinct clinical entity. Furthermore, unrelated patients with myeloproliferative neoplasm and B-cell lymphoma were linked by DDX41 CV, thus expanding the known disease spectrum. This study outlines the CV landscape, expands the phenotypic spectrum in unrelated DDX41-mutated patients, and underscores the urgent need for gene-specific diagnostic and clinical management guidelines.

Bridging the gap between prostate radiology and pathology through machine learning.

BACKGROUND: Prostate cancer remains the second deadliest cancer for American men despite clinical advancements. Currently, magnetic resonance imaging (MRI) is considered the most sensitive non-invasive imaging modality that enables visualization, detection, and localization of prostate cancer, and is increasingly used to guide targeted biopsies for prostate cancer diagnosis. However, its utility remains limited due to high rates of false positives and false negatives as well as low inter-reader agreements. PURPOSE: Machine learning methods to detect and localize cancer on prostate MRI can help standardize radiologist interpretations. However, existing machine learning methods vary not only in model architecture, but also in the ground truth labeling strategies used for model training. We compare different labeling strategies and the effects they have on the performance of different machine learning models for prostate cancer detection on MRI. METHODS: Four different deep learning models (SPCNet, U-Net, branched U-Net, and DeepLabv3+) were trained to detect prostate cancer on MRI using 75 patients with radical prostatectomy, and evaluated using 40 patients with radical prostatectomy and 275 patients with targeted biopsy. Each deep learning model was trained with four different label types: pathology-confirmed radiologist labels, pathologist labels on whole-mount histopathology images, and lesion-level and pixel-level digital pathologist labels (previously validated deep learning algorithm on histopathology images to predict pixel-level Gleason patterns) on whole-mount histopathology images. The pathologist and digital pathologist labels (collectively referred to as pathology labels) were mapped onto pre-operative MRI using an automated MRI-histopathology registration platform. RESULTS: Radiologist labels missed cancers (ROC-AUC: 0.75-0.84), had lower lesion volumes (~68% of pathology lesions), and lower Dice overlaps (0.24-0.28) when compared with pathology labels. Consequently, machine learning models trained with radiologist labels also showed inferior performance compared to models trained with pathology labels. Digital pathologist labels showed high concordance with pathologist labels of cancer (lesion ROC-AUC: 0.97-1, lesion Dice: 0.75-0.93). Machine learning models trained with digital pathologist labels had the highest lesion detection rates in the radical prostatectomy cohort (aggressive lesion ROC-AUC: 0.91-0.94), and had generalizable and comparable performance to pathologist label-trained-models in the targeted biopsy cohort (aggressive lesion ROC-AUC: 0.87-0.88), irrespective of the deep learning architecture. Moreover, machine learning models trained with pixel-level digital pathologist labels were able to selectively identify aggressive and indolent cancer components in mixed lesions on MRI, which is not possible with any human-annotated label type. CONCLUSIONS: Machine learning models for prostate MRI interpretation that are trained with digital pathologist labels showed higher or comparable performance with pathologist label-trained models in both radical prostatectomy and targeted biopsy cohort. Digital pathologist labels can reduce challenges associated with human annotations, including labor, time, inter- and intra-reader variability, and can help bridge the gap between prostate radiology and pathology by enabling the training of reliable machine learning models to detect and localize prostate cancer on MRI.

Correlation of 68Ga-RM2 PET with Postsurgery Histopathology Findings in Patients with Newly Diagnosed Intermediate- or High-Risk Prostate Cancer.

68Ga-RM2 targets gastrin-releasing peptide receptors (GRPRs), which are overexpressed in prostate cancer (PC). Here, we compared preoperative 68Ga-RM2 PET to postsurgery histopathology in patients with newly diagnosed intermediate- or high-risk PC. Methods: Forty-one men, 64.0 ± 6.7 y old, were prospectively enrolled. PET images were acquired 42-72 min (median ± SD, 52.5 ± 6.5 min) after injection of 118.4-247.9 MBq (median ± SD, 138.0 ± 22.2 MBq) of 68Ga-RM2. PET findings were compared with preoperative multiparametric MRI (mpMRI) (n = 36) and 68Ga-PSMA11 PET (n = 17) and correlated to postprostatectomy whole-mount histopathology (n = 32) and time to biochemical recurrence. Nine participants decided to undergo radiation therapy after study enrollment. Results: All participants had intermediate- (n = 17) or high-risk (n = 24) PC and were scheduled for prostatectomy. Prostate-specific antigen was 8.8 ± 77.4 (range, 2.5-504) and 7.6 ± 5.3 ng/mL (range, 2.5-28.0 ng/mL) when participants who ultimately underwent radiation treatment were excluded. Preoperative 68Ga-RM2 PET identified 70 intraprostatic foci of uptake in 40 of 41 patients. Postprostatectomy histopathology was available in 32 patients in which 68Ga-RM2 PET identified 50 of 54 intraprostatic lesions (detection rate = 93%). 68Ga-RM2 uptake was recorded in 19 nonenlarged pelvic lymph nodes in 6 patients. Pathology confirmed lymph node metastases in 16 lesions, and follow-up imaging confirmed nodal metastases in 2 lesions. 68Ga-PSMA11 and 68Ga-RM2 PET identified 27 and 26 intraprostatic lesions, respectively, and 5 pelvic lymph nodes each in 17 patients. Concordance between 68Ga-RM2 and 68Ga-PSMA11 PET was found in 18 prostatic lesions in 11 patients and 4 lymph nodes in 2 patients. Noncongruent findings were observed in 6 patients (intraprostatic lesions in 4 patients and nodal lesions in 2 patients). Sensitivity and accuracy rates for 68Ga-RM2 and 68Ga-PSMA11 (98% and 89% for 68Ga-RM2 and 95% and 89% for 68Ga-PSMA11) were higher than those for mpMRI (77% and 77%, respectively). Specificity was highest for mpMRI with 75% followed by 68Ga-PSMA11 (67%) and 68Ga-RM2 (65%). Conclusion: 68Ga-RM2 PET accurately detects intermediate- and high-risk primary PC, with a detection rate of 93%. In addition, 68Ga-RM2 PET showed significantly higher specificity and accuracy than mpMRI and a performance similar to 68Ga-PSMA11 PET. These findings need to be confirmed in larger studies to identify which patients will benefit from one or the other or both radiopharmaceuticals.