Citations

Background: Establishing imaging registries for large patient cohorts is challenging because manual labeling is tedious and relying solely on DICOM (digital imaging and communications in medicine) metadata can result in errors. We endeavored to establish an automated hip and pelvic radiography registry of total hip arthroplasty (THA) patients by utilizing deep-learning pipelines. The aims of the study were (1) to utilize these automated pipelines to identify all pelvic and hip radiographs with appropriate annotation of laterality and presence or absence of implants, and (2) to automatically measure acetabular component inclination and version for THA images. Methods: We retrospectively retrieved 846,988 hip and pelvic radiography DICOM files from 20,378 patients who underwent primary or revision THA performed at our institution from 2000 to 2020. Metadata for the files were screened followed by extraction of imaging data. Two deep-learning algorithms (an EfficientNetB3 classifier and a YOLOv5 object detector) were developed to automatically determine the radiographic appearance of all files. Additional deep-learning algorithms were utilized to automatically measure the acetabular angles on anteroposterior pelvic and lateral hip radiographs. Algorithm performance was compared with that of human annotators on a random test sample of 5,000 radiographs. Results: Deep-learning algorithms enabled appropriate exclusion of 209,332 DICOM files (24.7%) as misclassified non-hip/pelvic radiographs or having corrupted pixel data. The final registry was automatically curated and annotated in <8 hours and included 168,551 anteroposterior pelvic, 176,890 anteroposterior hip, 174,637 lateral hip, and 117,578 oblique hip radiographs. The algorithms achieved 99.9% accuracy, 99.6% precision, 99.5% recall, and a 99.6% F1 score in determining the radiograph appearance. Conclusions: We developed a highly accurate series of deep-learning algorithms to rapidly curate and annotate THA patient radiographs. This efficient pipeline can be utilized by other institutions or registries to construct radiography databases for patient care, longitudinal surveillance, and large-scale research. The stepwise approach for establishing a radiography registry can further be utilized as a workflow guide for other anatomic areas. Level of Evidence: Diagnostic Level IV . See Instructions for Authors for a complete description of levels of evidence.

The analysis and interpretation of cardiac magnetic resonance (CMR) images are often time-consuming. The automated segmentation of cardiac structures can reduce the time required for image analysis. Spatial similarities between different CMR image types were leveraged to jointly segment multiple sequences using a segmentation model termed a multi-image type UNet (MI-UNet). This model was developed from 72 exams (46% female, mean age 63 ± 11 years) performed on patients with hypertrophic cardiomyopathy. The MI-UNet for steady-state free precession (SSFP) images achieved a superior Dice similarity coefficient (DSC) of 0.92 ± 0.06 compared to 0.87 ± 0.08 for a single-image type UNet (p < 0.001). The MI-UNet for late gadolinium enhancement (LGE) images also had a superior DSC of 0.86 ± 0.11 compared to 0.78 ± 0.11 for a single-image type UNet (p = 0.001). The difference across image types was most evident for the left ventricular myocardium in SSFP images and for both the left ventricular cavity and the left ventricular myocardium in LGE images. For the right ventricle, there were no differences in DCS when comparing the MI-UNet with single-image type UNets. The joint segmentation of multiple image types increases segmentation accuracy for CMR images of the left ventricle compared to single-image models. In clinical practice, the MI-UNet model may expedite the analysis and interpretation of CMR images of multiple types.

Abstract Breast cancer metastases are most commonly found in bone, an indication of poor prognosis. Pathway-based biomarkers identification may help elucidate the cellular signature of breast cancer metastasis in bone, further characterizing the etiology and promoting new therapeutic approaches. We extracted gene expression profiles from mouse macrophages from the GEO dataset, GSE152795 using the GEO2R webtool. The differentially expressed genes (DEGs) were filtered by log2 fold-change with threshold 1.5 (FDR < 0.05). STRING database and Enrichr were used for GO-term analysis, miRNA and TF analysis associated with DEGs. Autodock Vienna was exploited to investigate interaction of anti-cancer drugs, Actinomycin-D and Adriamycin. Sensitivity and specificity of DEGs was assessed using receiver operating characteristic (ROC) analyses. A total of 61 DEGs, included 27 down-regulated and 34 up-regulated, were found to be significant in breast cancer bone metastasis. Major DEGs were associated with lipid metabolism and immunological response of tumor tissue. Crucial DEGs, Bcl3, ADGRG7, FABP4, VCAN, and IRF4 were regulated by miRNAs, miR-497, miR-574, miR-138 and TFs, CCDN1, STAT6, IRF8. Docking analysis showed that these genes possessed strong binding with the drugs. ROC analysis demonstrated Bcl3 is specific to metastasis. DEGs Bcl3, ADGRG7, FABP4, IRF4, their regulating miRNAs and TFs have strong impact on proliferation and metastasis of breast cancer in bone tissues. In conclusion, present study revealed that DEGs are directly involved in of breast tumor metastasis in bone tissues. Identified genes, miRNAs, and TFs can be possible drug targets that may be used for the therapeutics. However, further experimental validation is necessary.

There is a growing demand for high-resolution (HR) medical images for both clinical and research applications. Image quality is inevitably traded off with acquisition time, which in turn impacts patient comfort, examination costs, dose, and motion-induced artifacts. For many image-based tasks, increasing the apparent spatial resolution in the perpendicular plane to produce multi-planar reformats or 3D images is commonly used. Single-image super-resolution (SR) is a promising technique to provide HR images based on deep learning to increase the resolution of a 2D image, but there are few reports on 3D SR. Further, perceptual loss is proposed in the literature to better capture the textural details and edges versus pixel-wise loss functions, by comparing the semantic distances in the high-dimensional feature space of a pre-trained 2D network (e.g., VGG). However, it is not clear how one should generalize it to 3D medical images, and the attendant implications are unclear. In this paper, we propose a framework called SOUP-GAN: Super-resolution Optimized Using Perceptual-tuned Generative Adversarial Network (GAN), in order to produce thinner slices (e.g., higher resolution in the ‘Z’ plane) with anti-aliasing and deblurring. The proposed method outperforms other conventional resolution-enhancement methods and previous SR work on medical images based on both qualitative and quantitative comparisons. Moreover, we examine the model in terms of its generalization for arbitrarily user-selected SR ratios and imaging modalities. Our model shows promise as a novel 3D SR interpolation technique, providing potential applications for both clinical and research applications.

TPS234 Background: Total neoadjuvant therapy (TNT) followed by total mesorectal excision (TME) is one of the standard treatment options for patients with locally advanced rectal cancer (LARC). A commonly employed TNT protocol consists of 8 biweekly cycles of oxaliplatin-based chemotherapy (CT) followed by radiation concurrent with fluoropyrimidine-based chemotherapy (CRT) for about 6 weeks. During the TNT, patients undergo tumor response assessments periodically with standard modalities (SM) consisting of pelvic magnetic resonance imaging (MRI) and proctoscopic/endoscopic examination. The objective of the current protocol is to evaluate the feasibility of tumor response assessment by ctDNA in patients with LARC undergoing TNT. The present feasibility study is designed to collect preliminary data to evaluate if a subsequent larger validation study is justified. If ctDNA-based response assessment is validated, ctDNA can potentially replace at least some components of the SM (for example, MRI) as tumor response assessment by SM is often time-consuming, expensive, and poses logistical challenges. Methods: Patients with LARC undergoing TNT will be enrolled. After obtaining informed consent, venous blood samples will be obtained for ctDNA level measurements at the following time points: baseline (within 1 week before the CT begins), after 4 cycles of CT within +/- 5 days of the MRI study, after 8 cycles of CT within +/- 5 days of the MRI study, and 1 to 14 days before TME. ctDNA levels will be measured by a commercially available ctDNA assay (Signatera by Natera), and ctDNA response is defined as >90% drop in the ctDNA level after treatment compared to the baseline level. Tumor response will be evaluated after 4 and 8 cycles of CT by SM. Primary endpoint: correlation between the response rate (RR) assessed by ctDNA and by SM after 4 cycles of CT. Secondary endpoints: 1) correlation between the RR assessed by ctDNA and by SM after 8 cycles of CT, and 2) correlation between the ctDNA defined RR and the complete pathological response (pCR) rate. The trial will enroll 30 patients. To evaluate the primary endpoint, differences in ctDNA levels between the baseline and 4-cycles post-CT will be computed. The differences will then be expressed as a proportion of each patient’s baseline level, D. This relative change, D, will be compared between the responder and non-responder groups using a two-sample Welch’s t-test. Similar methods will be applied for the secondary endpoints. All analyses will use the nominal type I error level of 0.05 and two-sided tests. Clinical trial information: NCT04670588.

596 Background: Genomic alterations (GA) that drive cancer development and predict therapeutic response remain elusive in patients (pts) with KRAS WT PDAC. We interrogated our institutional database to identify actionable GAs in pts with metastatic, KRAS WT PDAC and analyzed the therapeutic impact of matched TT. Methods: We reviewed electronic medical records of KRAS WT PDAC pts (n=24) who underwent comprehensive genomic profiling (CGP) utilizing Foundation One CDx (25.0%) or Tempus (75.0%) between 2015-2021. Duration of response (DOR) was calculated from date of treatment (Tx) initiation to Tx discontinuation. Overall survival (OS) was measured from the date of the diagnosis (Dx) of advanced disease (AD) to death or last follow-up. OS was estimated using the Kaplan-Meier method, with at-risk periods left-truncated at the time of CGP. The effect of covariates on survival was evaluated using Cox proportional hazards regression. Results: Of the 24 KRAS WT pts, 14 (58%) had AD: 8 (57%) pts had metastatic disease at or shortly after Dx, 6 (43%) pts developed metachronous recurrence. Median age at Dx for pts with AD was 65, and 57% were female. Seven of 14 pts with AD (50%) had highly actionable GA (HAGA), (Table). Pts with HAGA demonstrated durable responses to TT (Table) with manageable toxicities. Pts with HAGA had a median OS of 28 mo compared to 5.9 mo for those without (Hazard Ratio = 0.47, p = 0.33). Conclusions: The sustained therapeutic benefit noted with TT matched to HAGA in pts with KRAS WT PDAC underscores the need for systematic interrogation of the somatic genome in PDAC pts. Optimal sequencing of cytotoxic therapy with TT and its impact on modulating clonal selection pressure in pts with KRAS WT PDAC merits prospective evaluation.[Table: see text]