Abstract 715: Robust segmentation-free stain quality concordance metrics in the SpaceIQ™ multi-omic analysis platform.

Feature matching in transformed images is critical to many fields of computer science, from autonomous robots to video analysis. However, most widely used feature matching algorithms vary in their ability to track features depending on whether rigid or non-rigid image transformations occur. This makes it critical, especially in real-time calculations, to be able to identify what kind of transformation is taking place quickly in order to deploy the best feature matching algorithm for that type of transformation. The proposed research uses a combined autoencoder and neural network classification model to classify rigid or non-rigid transformations in order to improve feature matching on the image pairs. This system is the first to perform this kind of analysis with representation learning and opens new ways to improving feature matching performance. We show that using this method improves the amount of feature matches found between correctly identified image pairs.

BackgroundTumor infiltrated lymphocytes (TIL), namely CD8+ TILs play a major role in antitumor immunity and tumor cell eradication. High-density infiltration of CD8+ cells in the tumor, in contrast to CD8+...

Backgrounds: Antibody-drug conjugate (ADC) has emerged as treatment option for breast cancer (BC). The ASCENT and TROPiCS-02 trial of Sacituzumab Govitecan, a Trop2 ADC, gained great success in TNBC and HR+ BC. Other targets, such as LIV-1, are being investigated for TNBC and HR+ BC. The clinical trials of Ladiratuzumab, an ADC of LIV-1 Ab and MMAE, are ongoing. However, unlike Her2 protein, the predictive and prognostic role of LIV-1 and Trop-2 has not been fully investigated. Therefore, we aimed to analyze the relationship between expression level and clinicopathological features and explore the value of the markers among subtypes of BC. Methods: TMA were selected from 1,349 breast cancer specimen of patients who received curative surgery from 2008 to 2012 at Seoul National University Hospital and IHC staining was performed on the TMA using LIV-1 antibody (HPA042377 manufactured by Sigma-Aldrich, St. Louis, MO, dilution ratio of 1:300) and Trop2 antibody(HPA055067, dilution ratio of 1:75). All IHC slides were carefully evaluated by trained pathologists. IHC expression was assessed as intensity (negative:0, weak:1, moderate:2, and strong:3). A modified histochemical score(H-score) was calculated from the intensity multiplied by the percentage of positive cells. Results: A total of 1119 patients from selected samples were included. The median age was 49 (range 25-90). Most patients had early T stage disease (n=513, 569, 29, 7, for pT1, pT2, pT3, pT4, respectively). The percentage of nodal metastasis (N=687 vs 432 in pN0 vs ≥pN1, 61.4 vs 38.6%) and LVI (N= 678 vs 441 in neg vs pos, 60.6% vs 38.6%). 713 pts (63.7%) were HR+ subtype, 200(17.9%) of Her2+ and 206(18.4%) of TNBC. We divided patients into negative/low/high expression groups according to LIV-1 expression by median expression level (cutoff H-score = 100): 479 of 1119 (42.8%) LIV-1-negative; 270 (42.2%) LIV-1-low expression and 370 (57.8%) LIV-1-high. Patients with LIV-1-low or -high tumors showed better DFS (156.2 vs 158.8 vs 159.95 mo for LIV-1-negative, -low, -high, respectively; P=0.0072) and OS(157.6 vs 163 vs 165.4 mo, P=0.0029) . HR+ subgroup, (N= 193 vs 228 vs 354 for neg vs low vs high), followed overall tendency (153.4vs 158.3 vs 159.9mo, P=0.0571 in DFS, 155.6vs160.2 vs165.4mo, P=0.0627 in OS, respectively) In contrast, for patients with TNBC, LIV-1-high expression showed the worst DFS and OS. (N = 183 vs 18 vs 5 in neg vs low vs high group, 159.7 vs 160.7 vs 93.1mo, P value=0.1854 for DFS, 160.8 vs 160.7 vs 93.1 mo, P=0.0334 for OS, respectively) LIV-1 expression failed to prove a prognostic value in Her2+ BC. We also analyzed Trop2 expression by dividing patients into low/intermediate/high by the method used previously in ASCENT trial. 1009 of 1119 (n=341 in low, 363 in intermediate, 305 in high expression) patients had Trop2 expression. There was no statistically significant difference in DFS and OS among all subtypes. In multivariate analysis, neither LIV-1 or Trop-2 had a prognostic role. Conclusion: The analysis of clinicopathological findings of LIV-1 protein indicates their values for prognosis markers, especially in HR+ BC and TNBC. Trop2 expression has no prognostic role in line with previous research. Further studies are warranted to explore targetable biomarkers for the development of appropriate ADCs. Citation Format: Yeonjoo Choi, Han Suk Ryu, Jiwon Koh, Dae-Won Lee, Kyung-hun Lee, Seock-Ah Im. LIV-1 and Trop2 expression using Immunohistochemistry as prognostic markers in early breast cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO1-13-07.

Reliable and rapid identification of tumor in the margins of breast specimens during breast-conserving surgery to reduce repeat surgery rates is an active area of investigation. Dual-stain difference imaging (DDSI) is one of many approaches under evaluation for this application. This technique aims to topically apply fluorescent stain pairs (one targeted to a receptor-of-interest and the other a spectrally distinct isotype), image both stains, and compute a normalized difference image between the two channels. Prior evaluation and optimization in a variety of preclinical models produced encouraging diagnostic performance. Herein, we report on a pilot clinical study which evaluated HER2-targeted DDSI on 11 human breast specimens. Gross sections from 11 freshly excised mastectomy specimens were processed using a HER2-receptor-targeted DDSI protocol shortly after resection. After staining with the dual-probe protocol, specimens were imaged on a fluorescence scanner, followed by tissue fixation for hematoxylin and eosin and anti-HER2 immunohistochemical staining. Receiver operator characteristic curves and area under the curve (AUC) analysis were used to assess diagnostic performance of the resulting images. Performance values were also compared to expression level determined from IHC staining. Eight of the 11 specimens presented with distinguishable invasive ductal carcinoma and/or were not affected by an imaging artifact. In these specimens, the DDSI technique provided an AUC = 0.90 ± 0.07 for tumor-to-adipose tissue and 0.81 ± 0.15 for tumor-to-glandular tissue, which was significantly higher than AUC values recovered from images of the targeted probe alone. DDSI values and diagnostic performance did not correlate with HER2 expression level, and tumors with low HER2 expression often produced high AUC, suggesting that even the low expression levels were enough to help distinguish tumor. The results from this preliminary study of rapid receptor-specific staining in human specimens were consistent with prior preclinical results and demonstrated promising diagnostic potential.

Feature matching, which refers to the establishment of accurate correspondence between two sets of feature points, plays an important role in the field of computer vision and remote sensing. Focusing on the characteristics of remote sensing images, this paper proposes a new algorithm for robust feature matching based on non-rigid transformation, which formulates the feature matching problem as a probabilistic model. Specifically, we first utilize the scale-invariant feature transform to establish the initial feature correspondences between an image pair, and the thin-plate spline is adopted for non-rigid transformation modeling, where a local geometric constraint is introduced to maintain local structures of neighboring feature points after the transformation. Under the Bayesian framework, we seek a maximum a posteriori solution of our model by using the expectation-maximization algorithm. In addition, without sacrificing the matching accuracy, we provide a fast implementation to reduce the computational complexity of the algorithm based on sparse approximation. We verify the performance of our method on a large number of remote sensing images, and the qualitative and quantitative results reveal its superiority over the state-of-the-art.

Feature matching is critical in analyzing remote sensing images, aiming to find the optimal mapping between correspondences. Regularization technology is essential to ensure the well-posedness of feature matching. However, current regularization-based methods scarcely consider the geometry structure of the image, which is beneficial for estimating the mapping, especially when the image pairs have a large view or scale change and local distortion. In this article, we introduce manifold regularization to overcome this limit and formulate feature matching as a unified semisupervised latent variable mixture model for both rigid and nonrigid transformations. Especially, we apply a Bayesian model with latent variables indicating whether matches in the putative correspondences are outliers or inliers. Moreover, we employ all the feature points, only part of which have correct matches, to express the intrinsic structure, which is preserved by manifold regularization. Finally, we combine manifold regularization with three different transformation models (e.g., rigid, affine, and thin-plate spline) to estimate the corresponding mappings. Experimental results on four remote sensing image datasets demonstrate that our method can significantly outperform the state of the art.

Feature matching is the foundation and key task of remote sensing image registration, which is to establish a reliable point corresponding relationship between the feature points of two images. In this article, a simple and effective local consensus method for rigid and nonrigid feature matching is proposed and applied to solve the problem of high outliers ratio caused by nonrigid transformation, nonlinear radiation difference, and speckle noise in the remote sensing image registration task. We first establish the putative feature correspondences according to the similarity between local descriptors and then use local consensus constraints (including neighborhood consensus and motion vector consensus) to remove outliers. The specific steps are given as follows. First, we use the neighborhood consensus constraint of feature points to carry out preliminary filtering to remove outliers with obvious errors and retain a large number of inliers, so as to obtain a clean reliable set. Then, the reliable set space is grided into several nonoverlapping cells, and the estimated motion vector is calculated for each cell. By taking the comprehensive deviation between the ordinary motion vectors and estimated motion vectors, we transform the matching problem into a mathematical optimization model and derive a closed-form solution with linear time and linear space complexities. In this way, our method can also significantly increase the speed of operation without sacrificing accuracy. A large number of feature matching experiments on remote sensing prove that our method is superior to existing methods and also has good results in the general scene.

3125 Background: The Cancer Immune Monitoring and Analysis Centers Cancer Immunology Data Commons (CIMAC-CIDC) network is a NCI Cancer Moonshots initiative to provide state-of-the-art technology and expertise for immunotherapy clinical trials. Multiplex tissue immunostaining is an integral assay provided that examines density and spatial distribution of immune cells and markers in tissues, for their prognostic or predictive value. Two approaches were evaluated for sensitivity, specificity, and reproducibility and subsequently harmonized: chromogenic-based Multiplex Immunohistochemical Consecutive Staining on Single Slide (MICSSS) and Multiplex Immunofluorescence (mIF) based tyramide signal amplification system. Methods: Harmonization was performed across CIMACs (Mount Sinai, Dana Farber Cancer Institute, MD Anderson Cancer Center) in multiple steps to prove that comparable data can be generated independent of site and platform. Goals: 1) harmonize image analysis platforms alone using tissues pre-stained with single chromogenic IHC for CD3 (membrane), Ki67 (nuclear), and CD68 (cytoplasmic), 2) compare image acquisition platforms, 3) streamline Antibody (Ab) clones and assess PD-L1 detection in relation to CLIA- assays, 4) harmonize staining protocols, image acquisition, and analysis platforms on 2 test head and neck tumor samples using MICSSS and mIF, 5) validate harmonization results with a tissue microarray on 27 tissues representing multiple tumors. For last steps, each CIMAC used their platforms for PD-L1, PD-1, CD3, CD8, and pan-cytokeratin (PanCK) staining on one of three consecutive slides from serial sections and compared densities of each marker. Results: Variables as PD-1 Ab clone, positive control reference tissues, sigma value for nuclear segmentation, and use of machine-learning based cell classifier were found to be key to produce accurate, reliable, comparable data. After visual quality control assessment and comparisons of each Region Of Interest (ROI), an overall inter-site Spearman correlation coefficient of ≥0.85 was achieved per marker within each tissue and across tissue types (expect pan-Cytokeratin, ≥0.7), with average coefficient of variation ≤0.1. Conclusions: These results show for the first time that two platforms can deliver harmonized data, despite differences in protocols, platforms, reagents, and analysis tools. Data resulting from retrospective and prospective CIMAC-CIDC analyses may be used with confidence for statistical associations with clinical parameters and outcome.

Feature matching, which refers to establishing reliable correspondence between two sets of features (particularly point features), is a critical prerequisite in feature-based registration. In this paper, we propose a flexible and general algorithm, which is called locally linear transforming (LLT), for both rigid and nonrigid feature matching of remote sensing images. We start by creating a set of putative correspondences based on the feature similarity and then focus on removing outliers from the putative set and estimating the transformation as well. We formulate this as a maximum-likelihood estimation of a Bayesian model with hidden/latent variables indicating whether matches in the putative set are outliers or inliers. To ensure the well-posedness of the problem, we develop a local geometrical constraint that can preserve local structures among neighboring feature points, and it is also robust to a large number of outliers. The problem is solved by using the expectation–maximization algorithm (EM), and the closed-form solutions of both rigid and nonrigid transformations are derived in the maximization step. In the nonrigid case, we model the transformation between images in a reproducing kernel Hilbert space (RKHS), and a sparse approximation is applied to the transformation that reduces the method computation complexity to linearithmic. Extensive experiments on real remote sensing images demonstrate accurate results of LLT, which outperforms current state-of-the-art methods, particularly in the case of severe outliers (even up to 80%).

Introduction: The Destiny Breast-04 Trial (DB-04) demonstrated the survival benefits of Trastuzumab Deruxtecan (T-DXd) for women with metastatic HER2 Low breast cancer, characterised by 1+ or 2+ IHC staining without amplification. While the DB-04 study applied the standard 2018 ASCO CAP IHC scoring criteria, in clinical practice, distinguishing HER2 0 from 1+ cancers is challenging as i) HER2 Low is not a biologically distinct subset of breast cancer, ii) there are no reference standards for HER2 Low cancers, iii) second-tier test, like ISH, are not applicable, and iv) there are no known controls for cases that have 0 or 1+ HER2 scores. For two decades this distinction was clinically immaterial, but now differentiating between HER2 0 and 1+ has now become crucial for determining patient eligibility for T-DXd therapy. Concerns regarding the subjectivity, imprecision and poor concordance between pathologists in scoring IHC in HER2 Low cancers raise the potential for misalignments in patient treatment. Ensuring pathologists have access to focused training for interpreting IHC scores at the low end of the HER2 expression spectrum, quality assurance procedures and reference sets are essential steps to help pathologists assess HER2 Low breast cancers more accurately and consistently. Design: In this study, a group of 9 experienced breast pathologists compiled a deidentified set of 60 breast cancer core biopsies from 3 laboratories. The Ventana 4B5 HER2 assay had been used for evaluation and the local laboratories had scored the samples as HER2 0 or 1+. We teased out the ASCO CAP 2018 criteria and used our collective expertise of reporting HER2 IHC for many years to specify HER2 Low-focused scoring conventions, including some potential pitfalls. Subsequently, using these conventions, each pathologist reviewed digitized whole slide images of the IHC slides and scored HER2 expression for each case. At a consensus workshop, the cases were jointly reviewed to establish consensus scores and determine the percentage of HER2-expressing tumor cells in each case. We then evaluated the concordance between individual pathologists' HER2 scores and the consensus opinion and ascertained reasons for discordance. Results: Among the cases discussed during the consensus conference, 43 out of 60 (71.7%) were classified as HER2 Low, with 40 cases designated as 1+ and three as 2+ (known to be not amplified). The consensus score matched the majority opinion of the pathologists' independent scores in 93.3% (56 out of 60) of the cases. Utilizing the HER2 Low-focused IHC scoring conventions, 7 out of 17 (41.2%) cases locally reported as HER2 0 were reclassified as HER2 Low. Conversely, among the 32 cases with local scores of 1+, 7 (21.8%) were reclassified as ultralow or null. When compared to the consensus score, individual pathologists' scores demonstrated concordance levels ranging from 71.7% to 91.7%, with a mean concordance rate of 81.3%. Cases with less than 20% of tumor cells expressing HER2 had lower inter observer concordance. This reference set of cases with expert consensus HER2 scores obtained through our study will be invaluable for peer training and the development of external quality assurance programs for HER2 Low cancers, including the quality assurance program of the Royal College of Pathologists of Australasia. Conclusion: This study revealed that when breast pathologists were provided explicit instructions on scoring pitfalls and HER2 Low-focused scoring conventions, their HER2 scores were concordant with expert consensus scores in 71.7% to 91.7% of cases. Discordant cases primarily involved cases with less than 20% of tumor cells expressing HER2. Utilising such an approach, peer training and quality assurance procedures will improve the accuracy and consistency of HER2 IHC assessment for better patient care. Reassessing older cases using HER2 Low focused scoring conventions may result in revisions of HER2 scores from HER2 Low to zero, and vice versa. Table. Individual pathologists' concordance with the consensus HER2 IHC score Applying our HER2 Low-focused IHC scoring conventions in a set of 60 core biopsies of invasive breast cancer with low or 0 HER2 protein expression. Citation Format: Gelareh Farshid, Beena Kumar, Nirmala Pathmanathan, Hema Mahajan, Ben Dessauvagie, Jane Armes, Cameron Snell, Amardeep Gilhotra. Improving HER2 Low Scoring Consistency and Accuracy: Insights from the Australian HER2 Low Concordance Study for Invasive Breast Cancer [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-25-12.

Accurate and automatic registration of multimodal retinal images such as fluorescein angiography (FA) and optical coherence tomography (OCT) enables utilization of supplementary information. FA is a gold standard imaging modality that depicts neurovascular structure of retina and is used for diagnosing neurovascular-related diseases such as diabetic retinopathy (DR). Unlike FA, OCT is non-invasive retinal imaging modality that provides cross-sectional data of retina. Due to differences in contrast, resolution and brightness of multimodal retinal images, the images resulted from vessel extraction of image pairs are not exactly the same. Also, prevalent feature detection, extraction and matching schemes do not result in perfect matches. In addition, the relationships between retinal image pairs are usually modeled by affine transformation, which cannot generate accurate alignments due to the non-planar retina surface. In this paper, a precise registration scheme is proposed to align FA and OCT images via scanning laser ophthalmoscopy (SLO) photographs as intermediate images. For this purpose, first a retinal vessel segmentation is applied to extract main blood vessels from the FA and SLO images. Next, a novel global registration is proposed based on the Gaussian model for curved surface of retina. For doing so, first a global rigid transformation is applied to FA vessel-map image using a new feature-based method to align it with SLO vessel-map photograph, in a way that outlier matched features resulted from not-perfect vessel segmentation are completely eliminated. After that, the transformed image is globally registered again considering Gaussian model for curved surface of retina to improve the precision of the previous step. Eventually a local non-rigid transformation is exploited to register two images perfectly. The experimental results indicate the presented scheme is more precise compared to other registration methods.

Purpose: In image-guided spine surgery, mapping 3D preoperative images to 2D intraoperative images via 3D-2D registration can provide valuable assistance in target localization. However, the presence of surgical instrumentation, hardware implants, and soft-tissue resection/displacement causes mismatches in image content, confounding existing registration methods. Manual/semi-automatic methods to mask such extraneous content is time consuming, user-dependent, error prone, and disruptive to clinical workflow. We developed and evaluated 2 novel similarity metrics within a robust registration framework to overcome such challenges in target localization. Methods: An IRB-approved retrospective study in 19 spine surgery patients included 19 preoperative 3D CT images and 50 intraoperative mobile radiographs in cervical, thoracic, and lumbar spine regions. A neuroradiologist provided truth definition of vertebral positions in CT and radiography. 3D-2D registration was performed using the CMA-ES optimizer with 4 gradient-based image similarity metrics: (1) gradient information (GI); (2) gradient correlation (GC); (3) a novel variant referred to as gradient orientation (GO); and (4) a second variant referred to as truncated gradient correlation (TGC). Registration accuracy was evaluated in terms of the projection distance error (PDE) of the vertebral levels. Results: Conventional similarity metrics were susceptible to gross registration error and failure modes associated with the presence of surgical instrumentation: for GI, the median PDE and interquartile range was 33.0±43.6 mm; similarly for GC, PDE = 23.0±92.6 mm respectively. The robust metrics GO and TGC, on the other hand, demonstrated major improvement in PDE (7.6 ±9.4 mm and 8.1± 18.1 mm, respectively) and elimination of gross failure modes. Conclusion: The proposed GO and TGC similarity measures improve registration accuracy and robustness to gross failure in the presence of strong image content mismatch. Such registration capability could offer valuable assistance in target localization without disruption of clinical workflow. G. Kleinszig and S. Vogt are employees of Siemens Healthcare.

Line feature matching is a fundamental task in computer vision, with wide applications in 3D reconstruction, image registration, and visual positioning. Traditional methods, often reliant on local feature descriptors or pre-defined geometric models, frequently struggle in the presence of large-scale scaling, non-rigid transformations, or sparse texture scenes. This paper proposes a robust line feature matching method that combines spatial clustering of point features with point-line geometric invariants. First, an improved RFM-SCAN algorithm is employed to spatially cluster initial point feature matches, effectively purifying them by enforcing motion consistency. Subsequently, for the line feature matching, the core innovation is introduced: a dual-invariant construction comprising a point-to-line distance ratio invariant and a direction vector invariant. High-accuracy line correspondences are then achieved by leveraging these dual invariants in conjunction with rigorous geometric consistency constraints. Experimental results demonstrate that our method maintains high matching accuracy and robustness across various challenging conditions—including scale and rotation changes, occlusion, illumination variation, and low-texture scenes—without relying on GPU acceleration or large-scale training data.

This letter proposes a remote sensing (RS) image registration method based on adjustable threshold and variational mixture transformation (VMT). The main contributions of our method are: 1) an adjustable threshold strategy proposed to guarantee sufficient inlier pairs for image spatial transformation and 2) a VMT, which achieves a coarse-to-fine process, consisting of three main steps as follows: a) a rigid transformation is employed to achieve approximate correspondence; b) a guided Gaussian mixture model is proposed to better distinguish outliers; and c) a nonrigid transformation is applied to achieve an accurate registration. We test the performance of our algorithm in feature matching and RS image registration and compare it with the six state-of-the-art methods. Our method shows the best performances in most scenarios.

BACKGROUND CT imaging is commonly used by physicians to monitor the development of pathological conditions, e.g. brain tumours. Accurate monitoring of a unique point in the brain over consecutive CT scans in between which a patient’s head may have moved requires determination of the relative position and orientation of the skull coordinate system with respect to the imager coordinate system, known as registration. A configuration of fiducial markers can be attached to the skull to provide means for registration by fitting of its known geometry with image data obtained from CT scanning. Typical requirements on fiducial based registration systems are related to fiducial and target registration errors and the extent to which the surrounding image is unaffected. In [1], six 0.80 mm tantalum spherical fiducials were placed in phantom bones to register data from CT and roentgen stereogrammetric analysis, achieving a root mean square fiducial registration error of 0.152 mm. Some reconstruction artefacts in the CT images are reported due to the high absorption rate of tantalum. In [2] and [3], registration is performed based on a single image using a configuration of obliquely placed aluminium rods. In [2], an average 3D position accuracy better than 1.2 mm is obtained with 50% of outliers in the data. An average displacement error at the instrument tip of 0.630 mm over 63 trials was reported in [3] with 95% of the errors under 1.0 mm. Both registration systems require all rods to intersect with the image plane, limiting the range of rotation of the connected instrument for which registration is possible.