Interpretable deep learning insights: Unveiling the role of 1 Gy volume on lymphopenia after radiotherapy in breast cancer.

BACKGROUND: Lymphopenia is known for its significance on poor survivals in breast cancer (BC) patients. Considering full dosimetric data, this study aimed to develop and validate predictive models for lymphopenia after radiotherapy (RT) in BC. MATERIAL AND METHODS: BC patients treated with adjuvant RT were eligible in this multicenter study. The study endpoint was lympopenia, defined as the reduction in absolute lymphocytes and graded lymphopenia after RT. The dose-volume histogram (DVH) data of related critical structures and clinical factors were taken into account for the development of dense neural network (DNN) predictive models. The developed DNN models were validated using external patient cohorts. RESULTS: Totally 918 consecutive patients with invasive BC enrolled. The training, testing, and external validating datasets consisted of 589, 203, and 126 patients, respectively. Treatment volumes at nearly all dose levels of the DVH were significant predictors for lymphopenia following RT, including volumes at very low-dose 1 Gy (V1) of organs at risk (OARs) including lung, heart and body, especially ipsilateral-lung V1. A final DNN model, combining full DVH dosimetric parameters of OARs and three key clinical factors, achieved a predictive accuracy of 75 % or higher. CONCLUSION: This study demonstrated and externally validated the significance of full dosimetric data, particularly the volume of low dose at as low as 1 Gy of critical structures on lymphopenia after radiation in BC patients. The significance of V1 deserves special attention, as modern VMAT RT technology often has a relatively high value of this parameter. Further study warranted for RT plan optimization.

Enhancing cardiovascular risk prediction through AI-enabled calcium-omics.

Whole-heart coronary calcium Agatston score is a well-established predictor of major adverse cardiovascular events (MACE), but it does not account for individual calcification features related to the pathophysiology of the disease (e.g., multiple-vessel disease, spread of the disease along the vessel, stable calcifications, numbers of lesions, and density). We used novel, hand-crafted calcification features (calcium-omics); Cox time-to-event modeling; elastic net; and up and down synthetic sampling methods for imbalanced data, to assess MACE risk. We used 2457 CT calcium score (CTCS) images enriched for MACE events from our large no-cost CLARIFY program (ClinicalTrials.gov Identifier: NCT04075162). Among calcium-omics features, numbers of calcifications, LAD mass, and diffusivity (a measure of spatial distribution) were especially important determinants of increased risk, with dense calcification (> 1000HU, stable calcifications) associated with reduced risk Our calcium-omics model with (training/testing, 80/20) gave C-index (80.5%/71.6%) and 2-year AUC (82.4%/74.8%). Although the C-index is notoriously impervious to model improvements, calcium-omics compared favorably to Agatston and gave a significant difference (P < 0.001). The calcium-omics model identified 73.5% of MACE cases in the high-risk group, a 13.2% improvement as compared to Agatston, suggesting that calcium-omics could be used to better identity candidates for intensive follow-up and therapies. The categorical net-reclassification index was NRI = 0.153. Our findings from this exploratory study suggest the utility of calcium-omics in improved risk prediction. These promising results will pave the way for more extensive, multi-institutional studies of calcium-omics.

Patients on Antithrombotic Agents with Small Bowel Bleeding -Yield of Small Bowel Capsule Endoscopy and Subsequent Management.

BACKGROUND AND AIMS: Small bowel gastrointestinal bleeding (GIB) is associated with multiple blood transfusions, prolonged and/or multiple hospital admissions, utilization of significant healthcare resources, and negative effects on patient quality of life. There is a well-recognized association between antithrombotic medications and small bowel GIB. We aimed to identify the diagnostic yield of small bowel capsule endoscopy (SBCE) in patients on antithrombotic medications and the impact of SBCE on treatment course. METHODS: The electronic medical records of nineteen hundred eighty-six patients undergoing SBCE were retrospectively reviewed. RESULTS: The diagnostic yield for detecting stigmata of recent bleeding and/or actively bleeding lesions in SBCE was higher in patients that were on antiplatelet agents (21.6%), patients on anticoagulation (22.5%), and in patients that had their SBCE performed while they were inpatient (21.8%), when compared to the patients not on antiplatelet agents (12.1%), patients not on anticoagulation (13.5%), and with patients that had their SBCE performed in the outpatient setting (12%). Of 318 patients who had stigmata of recent bleeding and/or actively bleeding lesion(s) identified on SBCE, SBCE findings prompted endoscopic evaluation (small bowel enteroscopy, esophagogastroduodenoscopy (EGD), and/or colonoscopy) in 25.2%, with endoscopic hemostasis attempted in 52.5%. CONCLUSIONS: Our study, the largest conducted to date, emphasizes the importance of performing SBCE as part of the evaluation for suspected small bowel bleeding, particularly in patients taking antithrombotic therapy, and especially during their inpatient hospital stay.

Neoadjuvant Dual Checkpoint Inhibitors vs Anti-PD1 Therapy in High-Risk Resectable Melanoma: A Pooled Analysis.

Importance: Despite the clear potential benefits of neoadjuvant therapy, the optimal neoadjuvant regimen for patients with high-risk resectable melanoma (HRRM) is not known. Objective: To compare the safety and efficacy of dual checkpoint inhibitors with anti-programmed cell death protein-1 (anti-PD1) therapy in a neoadjuvant setting among patients with HRRM. Design, Setting, and Participants: In this pooled analysis of clinical trials, studies were selected provided they investigated immune checkpoint inhibitor treatment, were published between January 2018 and March 2023, and were phase 1, 2, or 3 clinical trials. Participant data included in the analysis were derived from trials evaluating the efficacy and safety of anti-PD1 monotherapy and the combination of anti-cytotoxic T lymphocyte-associated protein-4 with anti-PD1 in the neoadjuvant setting, specifically among patients with HRRM. Interventions: Patients were treated with either anti-PD1 monotherapy; dual checkpoint inhibition (DCPI) with a conventional dose of 3-mg/kg ipilimumab and 1-mg/kg nivolumab; or DCPI with an alternative-dose regimen of 1-mg/kg ipilimumab and 3-mg/kg nivolumab. Main Outcomes and Measures: The main outcomes were radiologic complete response (rCR), radiologic overall objective response (rOOR), and radiologic progressive disease. Also, pathologic complete response (pCR), the proportion of patients undergoing surgical resection, and occurrence of grade 3 or 4 immune-related adverse events (irAEs) were considered. Results: Among 573 patients enrolled in 6 clinical trials, neoadjuvant therapy with DCPI was associated with higher odds of achieving pCR compared with anti-PD1 monotherapy (odds ratio [OR], 3.16; P < .001). DCPI was associated with higher odds of grade 3 or 4 irAEs compared with anti-PD1 monotherapy (OR, 3.75; P < .001). When comparing the alternative-dose ipilimumab and nivolumab (IPI-NIVO) regimen with conventional-dose IPI-NIVO, no statistically significant difference in rCR, rOOR, radiologic progressive disease, or pCR was noted. However, the conventional-dose IPI-NIVO regimen was associated with increased grade 3 or 4 irAEs (OR, 4.76; P < .001). Conventional-dose IPI-NIVO was associated with greater odds of achieving improved rOOR (OR, 1.95; P = .046) and pCR (OR, 2.99; P < .001) compared with anti-PD1 monotherapy. The alternative dose of IPI-NIVO also was associated with higher odds of achieving rCR (OR, 2.55; P = .03) and pCR (OR, 3.87; P < .001) compared with anti-PD1 monotherapy. The risk for grade 3 or 4 irAEs is higher with both the conventional-dose (OR, 9.59; P < .001) and alternative-dose IPI-NIVO regimens (OR, 2.02; P = .02) compared with anti-PD1 monotherapy. Conclusion and Relevance: In this pooled analysis of 6 clinical trials, although DCPI was associated with increased likelihood of achieving pathological and radiologic responses, the associated risk for grade 3 or 4 irAEs was significantly lower with anti-PD1 monotherapy in the neoadjuvant setting for HRRM. Additionally, compared with alternative-dose IPI-NIVO, the conventional dose of IPI-NIVO was associated with increased risk for grade 3 or 4 irAEs, with no significant distinctions in radiologic or pathologic efficacy.

Failing to Make the Grade: Conventional Cardiac Allograft Rejection Grading Criteria Are Inadequate for Predicting Rejection Severity.

BACKGROUND: Cardiac allograft rejection is the leading cause of early graft failure and is a major focus of postheart transplant patient care. While histological grading of endomyocardial biopsy samples remains the diagnostic standard for acute rejection, this standard has limited diagnostic accuracy. Discordance between biopsy rejection grade and patient clinical trajectory frequently leads to both overtreatment of indolent processes and delayed treatment of aggressive ones, spurring the need to investigate the adequacy of the current histological criteria for assessing clinically important rejection outcomes. METHODS: N=2900 endomyocardial biopsy images were assigned a rejection grade label (high versus low grade) and a clinical trajectory label (evident versus silent rejection). Using an image analysis approach, n=370 quantitative morphology features describing the lymphocytes and stroma were extracted from each slide. Two models were constructed to compare the subset of features associated with rejection grades versus those associated with clinical trajectories. A proof-of-principle machine learning pipeline-the cardiac allograft rejection evaluator-was then developed to test the feasibility of identifying the clinical severity of a rejection event. RESULTS: The histopathologic findings associated with conventional rejection grades differ substantially from those associated with clinically evident allograft injury. Quantitative assessment of a small set of well-defined morphological features can be leveraged to more accurately reflect the severity of rejection compared with that achieved by the International Society of Heart and Lung Transplantation grades. CONCLUSIONS: Conventional endomyocardial samples contain morphological information that enables accurate identification of clinically evident rejection events, and this information is incompletely captured by the current, guideline-endorsed, rejection grading criteria.

A multicenter study of posttransplantation low-dose inotuzumab ozogamicin to prevent relapse of acute lymphoblastic leukemia.

ABSTRACT: The curative potential of allogeneic hematopoietic transplantation (allo-HCT) in patients with acute lymphoblastic leukemia (ALL) is hampered by relapse. Inotuzumab ozogamicin (INO) is an anti-CD22 monoclonal antibody bound to calicheamicin, which has significant activity against ALL. We hypothesized that low-dose INO would be safe and feasible after allo-HCT. Therefore, we conducted a phase 1 study to determine the dose and safety in this setting. Patients were eligible if they were aged 16 to 75 years, had undergone allo-HCT for CD22+ ALL, were in complete remission (CR) after allo-HCT, had high risk of recurrence, were between day 40 and 100 after allo-HCT with adequate graft function, and did not have a history of sinusoidal obstruction syndrome (SOS). The objectives of this trial were to define INO maximum tolerated dose (MTD), to determine post-allo-HCT INO safety, and to measure 1-year progression-free survival (PFS). The trial design followed a "3+3" model. The treatment consisted of INO given on day 1 of 28-day cycles. Dose levels were 0.3 mg/m2, 0.4 mg/m2, 0.5 mg/m2, and 0.6 mg/m2. Median age was 44 years (range, 17-66 years; n = 18). Disease status at transplantation was first CR (n = 14) or second CR or beyond (n = 4). Preparative regimen was of reduced intensity in 72% of patients who received transplantation. Most common toxicity was thrombocytopenia. There were no instances of SOS; the MTD was 0.6 mg/m2. One-year nonrelapse mortality was 5.6%. With a median follow-up of 18.1 months (range, 8.6-59 months) 1-year post-allo-HCT PFS and overall survival is 89% and 94%, respectively. Low-dose INO has a favorable safety profile and was associated with high rates of 1-year PFS. This trial was registered at www.clinicaltrials.gov as #NCT03104491.

Impact of Visceral Obesity on Clinical Outcome and Quality of Life for Patients with Multiple Myeloma: A Secondary Data Analysis of STaMINA (BMT CTN 0702) Trial.

Obesity is a common health problem in patients with multiple myeloma (MM) that has been linked to poor clinical outcomes and quality of life (QoL). We conducted a secondary analysis of the BMT CTN 0702, a randomized, controlled trial comparing outcomes of 3 treatment interventions after a single hematopoietic cell transplantation (HCT) (n = 758), to investigate the impact of visceral obesity, as measured by waist-to-hip ratio (WHR), on clinical outcomes and QoL in MM patients. A total of 549 MM patients, median age 55.5 years, were enrolled in the study. The majority of patients received triple-drug antimyeloma initial therapy before enrollment, and 29% had high-risk disease according to cytogenetic assessment. The median duration of follow-up was 6 years. There was no significant association between WHR and progression-free survival (PFS) or overall survival (OS) in MM patients undergoing HCT. Similarly, body mass index (BMI) did not significantly predict PFS or OS. Furthermore, there was no significant correlation between WHR and QoL measures. This study suggests that visceral obesity, as measured by WHR, might not have a significant impact on clinical outcomes in MM patients undergoing HCT. These findings add to the existing literature on the topic and provide valuable information for healthcare professionals and MM patients. Further studies are needed to confirm these results and to investigate other potential factors that may affect clinical outcomes and QoL in this patient population using modern imaging technologies to assess visceral obesity.

Rank acquisition impact on radiomics estimation (AсquIRE) in chest CT imaging: A retrospective multi-site, multi-use-case study.

BACKGROUND: Radiomics is a method within medical image analysis that involves the extraction of quantitative data from radiologic scans, often in conjunction with machine learning algorithms to phenotype disease appearance, prognosticate disease outcome, and predict treatment response. However, variance in CT scanner acquisition parameters, such as convolution kernels or pixel spacing, can impact radiomics texture feature values. PURPOSE: The extent to which the parameters influence radiomics features continues to be an active area of investigation. In this study, we describe a novel approach, Acquisition Impact on Radiomics Estimation (AcquIRE), to rank the impact of CT acquisition parameters on radiomic texture features. METHODS: In this work, we used three chest CT imaging datasets (n = 749 patients) from nine sites comprising: i) lung granulomas and adenocarcinomas (D1) (10 and 52 patients, respectively); ii) minimal and frank invasive adenocarcinoma (D2) (74 and 145 patients); and iii) early-stage NSCLC patients (D3) (315 patients). Datasets D2 and D3 were collected from four sites each, and D1 from a single site. For each patient, 744 texture features and nine acquisition parameters were extracted and utilized to evaluate which parameters impact radiomic features the most. The AcquIRE method establishes a relative assessment between acquisition parameters and radiomic texture featuresa through the creation of a classification model, which is then utilized to assess the rank of the acquisition parameters. RESULTS: Across the use cases, CT software version and convolution kernel parameters were found to have the most variance. In D1, it was observed that the Haralick texture feature family was the least affected by variations in acquisition parameters, while the Gabor feature family was the most impacted. However, in datasets D2 and D3, the Gabor features were found to be the least affected. Our findings suggest that the impact on radiomic parameters is as much a function of the problem in question as it is acquisition parameters. CONCLUSIONS: The software version and convolution kernel parameters impacted the radiomics feature the most.

Computational pathology identifies immune-mediated collagen disruption to predict clinical outcomes in gynecologic malignancies.

BACKGROUND: The role of immune cells in collagen degradation within the tumor microenvironment (TME) is unclear. Immune cells, particularly tumor-infiltrating lymphocytes (TILs), are known to alter the extracellular matrix, affecting cancer progression and patient survival. However, the quantitative evaluation of the immune modulatory impact on collagen architecture within the TME remains limited. METHODS: We introduce CollaTIL, a computational pathology method that quantitatively characterizes the immune-collagen relationship within the TME of gynecologic cancers, including high-grade serous ovarian (HGSOC), cervical squamous cell carcinoma (CSCC), and endometrial carcinomas. CollaTIL aims to investigate immune modulatory impact on collagen architecture within the TME, aiming to uncover the interplay between the immune system and tumor progression. RESULTS: We observe that an increased immune infiltrate is associated with chaotic collagen architecture and higher entropy, while immune sparse TME exhibits ordered collagen and lower entropy. Importantly, CollaTIL-associated features that stratify disease risk are linked with gene signatures corresponding to TCA-Cycle in CSCC, and amino acid metabolism, and macrophages in HGSOC. CONCLUSIONS: CollaTIL uncovers a relationship between immune infiltration and collagen structure in the TME of gynecologic cancers. Integrating CollaTIL with genomic analysis offers promising opportunities for future therapeutic strategies and enhanced prognostic assessments in gynecologic oncology.

The role of cells that are part of our immune system in altering the structure of the protein collagen within cancers is not fully understood, particularly within cancers that affect women such as ovarian, cervical and uterine cancers. Here, we developed a computer-based method called CollaTIL to explore how immune cells influence collagen in these tumors and affect their growth. We found that a higher presence of immune cells leads to less organized collagen in the tumor. Conversely, when there are fewer immune cells, the collagen tends to be more structured. Additionally, CollaTIL identifies patterns that predict patient outcomes in these cancers. These findings not only enhance our understanding of tumor biology but also may be useful in helping clinicians to predict which patients are at risk of their disease progressing.

Phase II Clinical Trial of Pembrolizumab and Chemotherapy Reveals Distinct Transcriptomic Profiles by Radiologic Response in Metastatic Triple-Negative Breast Cancer.

PURPOSE: A single arm, phase II trial of carboplatin, nab-paclitaxel, and pembrolizumab (CNP) in metastatic triple-negative breast cancer (mTNBC) was designed to evaluate overall response rate (ORR), progression-free survival (PFS), duration of response (DOR), safety/tolerability, overall survival (OS), and identify pathologic and transcriptomic correlates of response to therapy. PATIENTS AND METHODS: Patients with ≤2 prior therapies for metastatic disease were treated with CNP regardless of tumor programmed cell death-ligand 1 status. Core tissue biopsies were obtained prior to treatment initiation. ORR was assessed using a binomial distribution. Survival was analyzed via the Kaplan-Meier method. Bulk RNA sequencing was employed for correlative studies. RESULTS: Thirty patients were enrolled. The ORR was 48.0%: 2 (7%) complete responses (CR), 11 (41%) partial responses (PR), and 8 (30%) stable disease (SD). The median DOR for patients with CR or PR was 6.4 months [95% confidence interval (CI), 4-8.5 months]. For patients with CR, DOR was >24 months. Overall median PFS and OS were 5.8 (95% CI, 4.7-8.5 months) and 13.4 months (8.9-17.3 months), respectively. We identified unique transcriptomic landscapes associated with each RECIST category of radiographic treatment response. In CR and durable PR, IGHG1 expression was enriched. IGHG1high tumors were associated with improved OS (P = 0.045) and were concurrently enriched with B cells and follicular helper T cells, indicating IGHG1 as a promising marker for lymphocytic infiltration and robust response to chemo-immunotherapy. CONCLUSIONS: Pretreatment tissue sampling in mTNBC treated with CNP reveals transcriptomic signatures that may predict radiographic responses to chemo-immunotherapy.

Dosimetric Effect of Thymus and Thoracic Duct on Radiation-Induced Lymphopenia in Patients With Primary Lung Cancer Who Received Thoracic Radiation.

Purpose: Radiation-induced lymphopenia is a well-recognized factor for tumor control and survival in patients with cancer. This study aimed to determine the role of radiation dose to the thymus and thoracic duct on radiation-induced lymphopenia. Methods and Materials: Patients with primary lung cancer treated with thoracic radiation therapy between May 2015 and February 2020 with whole blood count data were eligible. Clinical characteristics, including age, gender, histology, stage, chemotherapy regimen, radiation dosimetry, and absolute lymphocyte count (ALC) were collected. The thymus and thoracic duct were contoured by one investigator for consistency and checked by one senior physician. The primary endpoint was radiation-induced decrease in lymphocytes, defined as the difference in ALC (DALC) before and after radiation therapy. Results: The data of a total of 116 consecutive patients were retrospectively retrieved. Significant correlations were found between DALC and several clinical factors. These factors include stage, chemotherapy or concurrent chemoradiation, biologically effective dose (BED), mean lung dose, mean body dose, effective dose to immune cells (EDIC), mean thymus dose (MTD), and mean thoracic duct dose (MTDD) (all P < .05). Ridge regression showed that DALC = 0.0063 × BED + 0.0172 × EDIC + 0.0002 × MTD + 0.0147 × MTDD + 0.2510 (overall P = .00025 and F = 5.85). The combination model has the highest area under the curve of 0.77 (P < .001) when fitting the logistic regression model on DALC categorized as binary endpoint. The sensitivity and specificity of the combined model were 89% and 58%, respectively. Conclusions: This study demonstrated for the first time that radiation doses to the thymus and thoracic duct are strongly associated with radiation-induced lymphopenia patients with lung cancer. Further validation studies are needed to implement thymus and thoracic duct as organs at risk.

The Impact of Prophylactic Cranial Irradiation and Consolidative Thoracic Radiation Therapy for Extensive Stage Small-Cell Lung Cancer in the Transition to the Chemo-Immunotherapy Era: A Single Institution Series.

INTRODUCTION: Extensive-stage small-cell lung cancer (ES-SCLC) continues to have poor survival due to its aggressive behavior, despite improvements with incorporation of immunotherapy with standard chemotherapy. Controversy exists regarding the role of consolidative thoracic radiation therapy (TRT) and prophylactic cranial irradiation (PCI) in ES-SCLC due to high recurrence rates. We report our institutional result of the benefit of PCI and TRT in ES-SCLC. METHODS: Patients with ES-SCLC without intracranial metastasis at diagnosis (N = 163) were included. All patients completed systemic therapy with or without immunotherapy based on time of standard of care. Cohorts were divided by systemic therapy use and further subdivided by treatment with PCI and TRT. Overall survival (OS) and progression-free survival (PFS) were estimated by the Kaplan-Meier method with log-rank test for comparison. The effects of TRT and PCI were estimated by multivariable (MVA) Cox regression. RESULTS: Seventy-four patients (45.4%) received TRT, and 33.1% (n = 54) received PCI. The median follow-up was 11 months (3-85 months). PCI improved median OS to 15 months from 10 months, P = .02) and median PFS to 8.5 months from 5 months (P = .02) which remained significant on MVA, P = .02 and P = .02, respectively. TRT improved OS on UVA (P = 0.002) but was not significant on MVA. TRT did not improve PFS. CONCLUSION: This study including chemotherapy and chemo-immunotherapy suggests improved outcomes with addition of PCI in patients with ES-SCLC while TRT did not show benefit to either OS or PFS. A future trial is needed to evaluate the role of TRT and PCI in the era of chemo-immunotherapy.

Impact of Visceral Obesity on Clinical Outcome and Quality of Life for Patients with Multiple Myeloma: A Secondary Data Analysis of STaMINA (BMT CTN 0702) Trial.

Obesity is a common health problem among multiple myeloma (MM) patients, and it has been linked to poor clinical outcomes and quality of life (QOL). We conducted a secondary analysis of the BMT CTN 0702, a randomized, controlled trial comparing outcomes of three treatment interventions after a single hematopoietic cell transplant (HCT), to investigate the impact of visceral obesity, as measured by waist-to-hip ratio (WHR), on clinical outcomes and QOL in MM patients. 549 MM patients, median age 55.5 years, were enrolled in the study. The majority of patients received triple-drug antimyeloma initial therapy before enrollment, and 29% had high-risk disease according to cytogenetic assessment. The median follow-up time was six years. There was no significant association between WHR and progression-free survival (PFS) or overall survival (OS) in MM patients undergoing HCT. Similarly, body mass index (BMI) did not significantly predict PFS or OS. Furthermore, there was no significant correlation between WHR and QOL measures. In conclusion, this study suggests that visceral obesity, as measured by WHR, may not significantly impact clinical outcomes in MM patients undergoing HCT. Further studies utilizing imaging technologies to assess the impact of visceral obesity distribution are warranted.

Enhancing cardiovascular risk prediction through AI-enabled calcium-omics.

Background: Coronary artery calcium (CAC) is a powerful predictor of major adverse cardiovascular events (MACE). Traditional Agatston score simply sums the calcium, albeit in a non-linear way, leaving room for improved calcification assessments that will more fully capture the extent of disease. Objective: To determine if AI methods using detailed calcification features (i.e., calcium-omics) can improve MACE prediction. Methods: We investigated additional features of calcification including assessment of mass, volume, density, spatial distribution, territory, etc. We used a Cox model with elastic-net regularization on 2457 CT calcium score (CTCS) enriched for MACE events obtained from a large no-cost CLARIFY program (ClinicalTrials.gov Identifier: NCT04075162). We employed sampling techniques to enhance model training. We also investigated Cox models with selected features to identify explainable high-risk characteristics. Results: Our proposed calcium-omics model with modified synthetic down sampling and up sampling gave C-index (80.5%/71.6%) and two-year AUC (82.4%/74.8%) for (80:20, training/testing), respectively (sampling was applied to the training set only). Results compared favorably to Agatston which gave C-index (71.3%/70.3%) and AUC (71.8%/68.8%), respectively. Among calcium-omics features, numbers of calcifications, LAD mass, and diffusivity (a measure of spatial distribution) were important determinants of increased risk, with dense calcification (>1000HU) associated with lower risk. The calcium-omics model reclassified 63% of MACE patients to the high risk group in a held-out test. The categorical net-reclassification index was NRI=0.153. Conclusions: AI analysis of coronary calcification can lead to improved results as compared to Agatston scoring. Our findings suggest the utility of calcium-omics in improved prediction of risk.

Outcomes of Antineoplastic Immunotherapy at a Large Healthcare Organization: Impact of Provider, Race and Socioeconomic Status.

Purpose: Disparities in cancer care delivery remain a pressing health-care crisis within the United States (US). The use of immune checkpoint inhibitors (ICIs) and their management may be a disparity generator that impacts survival. This retrospective study assessed disparities in a cohort of patients with a variety of solid tumors treated with ICIs within a single health-care organization focusing on the impact of race, socioeconomic status (SES) and site of care delivery on survival and the development of severe immune-related adverse events (irAEs). Patients and Methods: Manual chart review was performed on all patients with solid tumors treated with ICIs within a health-care organization from 2012 to 2018. Care delivery was dichotomized as DOP (disease-oriented provider at academic center) and COP (community oncology provider). Primary and secondary outcomes were overall survival (OS) and rates of grade 3-4 irAEs, respectively. Relationships with covariates of interest, including race, socioeconomic status and type of care delivery, were assessed among both outcomes. Results: A total of 1070 eligible patients were identified. Of those, 11.4% were of Black race, 59.7% had either non-small cell lung cancer (NSCLC) or melanoma and 82.8% had stage IV disease. Patients of Black race and lower SES were more likely to be treated by DOPs (p<0.0001). A superior OS was associated with care delivered by DOPs when compared to COPs (HR 0.68; 95% CI 0.56-0.84; p=0.0002), which was durable after accounting for race, SES, histopathologic diagnosis and disease stage. Melanoma patients experienced higher rates of severe irAEs (HR 2.37; 95% CI 1.42-3.97; p=0.001). Race, SES and site of care delivery were not related to rates of severe irAEs. Conclusion: In a large health-care organization, patients treated with checkpoint inhibitors by DOPs benefited from a significant OS advantage that was durable after controlling for racial and socioeconomic factors, providing evidence that disease-oriented care has the potential to mitigate racial and socioeconomic disparities.

Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer.

Background: around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─). Objective: To quantify the differences between MR visible (MRI+) and MRI─ CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI). Methods: This retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI─ CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (Dv) comprised 52 patients from a single institution, the remaining 112 patients were used for training (Dt). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI.Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on Dt to identify radiomic features associated with MRI─ and MRI+ CsPCa to generate corresponding risk scores RMRI─ and RMRI+. RbpMRI was further generated by integrating RMRI─ and RMRI+. Statistical significance was determined using the Wilcoxon signed-rank test. Results: Both intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI─ CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI─ and MRI+ CsPCa (p < 0.05). RbpMRI yielded the highest AUC of 0.82 (95 % CI 0.72-0.91) compared to AUCs of RMRI+ 0.76 (95 % CI 0.63-0.89), and PI-RADS 0.58 (95 % CI 0.50-0.72) on Dv. RbpMRI correctly reclassified 10 out of 14 MRI─ CsPCa on Dv. Conclusion: Our preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI─ CsPCa. These features could assist in CsPCa identification on bpMRI.

CT radiomic signature predicts survival and chemotherapy benefit in stage I and II HPV-associated oropharyngeal carcinoma.

Chemoradiation is a common therapeutic regimen for human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPSCC). However, not all patients benefit from chemotherapy, especially patients with low-risk characteristics. We aim to develop and validate a prognostic and predictive radiomic image signature (pRiS) to inform survival and chemotherapy benefit using computed tomography (CT) scans from 491 stage I and II HPV-associated OPSCC, which were divided into three cohorts D1-D3. The prognostic performance of pRiS was evaluated on two test sets (D2, n = 162; D3, n = 269) using concordance index. Patients from D2 and D3 who received either radiotherapy alone or chemoradiation were used to validate pRiS as predictive of added benefit of chemotherapy. Seven features were selected to construct pRiS, which was found to be prognostic of overall survival (OS) on univariate analysis in D2 (hazard ratio [HR] = 2.14, 95% confidence interval [CI], 1.1-4.16, p = 0.02) and D3 (HR = 2.74, 95% CI, 1.34-5.62, p = 0.006). Chemotherapy was associated with improved OS for high-pRiS patients in D2 (radiation vs chemoradiation, HR = 4.47, 95% CI, 1.73-11.6, p = 0.002) and D3 (radiation vs chemoradiation, HR = 2.99, 95% CI, 1.04-8.63, p = 0.04). In contrast, chemotherapy did not improve OS for low-pRiS patients, which indicates these patients did not derive additional benefit from chemotherapy and could be considered for treatment de-escalation. The proposed radiomic signature was prognostic of patient survival and informed benefit from chemotherapy for stage I and II HPV-associated OPSCC patients.

Deep computational image analysis of immune cell niches reveals treatment-specific outcome associations in lung cancer.

The tumor immune composition influences prognosis and treatment sensitivity in lung cancer. The presence of effective adaptive immune responses is associated with increased clinical benefit after immune checkpoint blockers. Conversely, immunotherapy resistance can occur as a consequence of local T-cell exhaustion/dysfunction and upregulation of immunosuppressive signals and regulatory cells. Consequently, merely measuring the amount of tumor-infiltrating lymphocytes (TILs) may not accurately reflect the complexity of tumor-immune interactions and T-cell functional states and may not be valuable as a treatment-specific biomarker. In this work, we investigate an immune-related biomarker (PhenoTIL) and its value in associating with treatment-specific outcomes in non-small cell lung cancer (NSCLC). PhenoTIL is a novel computational pathology approach that uses machine learning to capture spatial interplay and infer functional features of immune cell niches associated with tumor rejection and patient outcomes. PhenoTIL's advantage is the computational characterization of the tumor immune microenvironment extracted from H&E-stained preparations. Association with clinical outcome and major non-small cell lung cancer (NSCLC) histology variants was studied in baseline tumor specimens from 1,774 lung cancer patients treated with immunotherapy and/or chemotherapy, including the clinical trial Checkmate 057 (NCT01673867).

Computational pathology improves risk stratification of a multi-gene assay for early stage ER+ breast cancer.

Prognostic markers currently utilized in clinical practice for estrogen receptor-positive (ER+) and lymph node-negative (LN-) invasive breast cancer (IBC) patients include the Nottingham grading system and Oncotype Dx (ODx). However, these biomarkers are not always optimal and remain subject to inter-/intra-observer variability and high cost. In this study, we evaluated the association between computationally derived image features from H&E images and disease-free survival (DFS) in ER+ and LN- IBC. H&E images from a total of n = 321 patients with ER+ and LN- IBC from three cohorts were employed for this study (Training set: D1 (n = 116), Validation sets: D2 (n = 121) and D3 (n = 84)). A total of 343 features relating to nuclear morphology, mitotic activity, and tubule formation were computationally extracted from each slide image. A Cox regression model (IbRiS) was trained to identify significant predictors of DFS and predict a high/low-risk category using D1 and was validated on independent testing sets D2 and D3 as well as within each ODx risk category. IbRiS was significantly prognostic of DFS with a hazard ratio (HR) of 2.33 (95% confidence interval (95% CI) = 1.02-5.32, p = 0.045) on D2 and a HR of 2.94 (95% CI = 1.18-7.35, p = 0.0208) on D3. In addition, IbRiS yielded significant risk stratification within high ODx risk categories (D1 + D2: HR = 10.35, 95% CI = 1.20-89.18, p = 0.0106; D1: p = 0.0238; D2: p = 0.0389), potentially providing more granular risk stratification than offered by ODx alone.

Focal adhesion kinase activation is involved in contractile stimulation-induced detrusor muscle contraction in mice.

Recent studies suggested smooth muscle contraction may involve mechanisms besides the myosin regulatory light chain (MLC) phosphorylation-induced actomyosin crossbridge cycling. This study aims to determine if focal adhesion kinase (FAK) activation is involved in mouse detrusor muscle contraction. The mouse detrusor muscle strips were preincubated with PF-573228 (2 µM), latrunculin B (1 µM), or the same volume of vehicle (DMSO) for 30 min. The contractile responses to KCl (90 mM), electrical field stimulation (EFS, 2-32 Hz), or carbachol (CCh, 10-7.5-10-4.5 M) were measured. In a separate experiment, the phosphorylated FAK (p-FAK) and MLC (p-MLC) levels were measured in the detrusor strips stimulated with CCh (10 µM) after incubation with PF-573228 or vehicle (DMSO) compared to those with vehicle incubation but without CCh stimulation. KCl-induced contractile responses decreased significantly after incubation with PF-573228 or latrunculin B compared to the corresponding vehicle-treated strips (p < 0.0001). The contractile responses induced by EFS were markedly inhibited by preincubation with PF-573228 at 8, 16, and 32 Hz (p < 0.05) or latrunculin B at 16 and 32 Hz (p < 0.01). Following the application of PF-573228 or Latrunculin B, CCh-induced dose-response contractions were lower than the corresponding vehicle group (p = 0.0021 and 0.0003, respectively). Western blot examination showed that CCh stimulation enhanced the expression of p-FAK and p-MLC, while preincubation with PF-573228 prevented the increase of p-FAK but not p-MLC. In conclusion, FAK activation involves tension development induced by contractile stimulation in the mouse detrusor muscle. This effect is likely caused by promoting actin polymerization rather than elevating MLC phosphorylation.