Development and validation of a deep learning-based microsatellite instability predictor from prostate cancer whole-slide images.

Microsatellite instability-high (MSI-H) is a tumor-agnostic biomarker for immune checkpoint inhibitor therapy. However, MSI status is not routinely tested in prostate cancer, in part due to low prevalence and assay cost. As such, prediction of MSI status from hematoxylin and eosin (H&E) stained whole-slide images (WSIs) could identify prostate cancer patients most likely to benefit from confirmatory testing to evaluate their eligibility for immunotherapy and need for Lynch syndrome testing. Prostate biopsies and surgical resections from prostate cancer patients referred to our institution were analyzed. MSI status was determined by next-generation sequencing. Patients sequenced before a cutoff date formed an algorithm development set (n = 4015, MSI-H 1.8%) and a paired validation set (n = 173, MSI-H 19.7%) that consisted of two serial sections from each sample, one stained and scanned internally and the other at an external site. Patients sequenced after the cutoff date formed a temporally independent validation set (n = 1350, MSI-H 2.3%). Attention-based multiple instance learning models were trained to predict MSI-H from H&E WSIs. The predictor achieved area under the receiver operating characteristic curve values of 0.78 (95% CI [0.69-0.86]), 0.72 (95% CI [0.63-0.81]), and 0.72 (95% CI [0.62-0.82]) on the internally prepared, externally prepared, and temporal validation sets, respectively, showing effective predictability and generalization to both external staining/scanning processes and temporally independent samples. While MSI-H status is significantly correlated with Gleason score, the model remained predictive within each Gleason score subgroup.

Changes in Maternal Heart Rate Variability and Photoplethysmography Morphology after Corticosteroid Administration: A Prospective, Observational Study.

Background: Owing to the association between dysfunctional maternal autonomic regulation and pregnancy complications, assessing non-invasive features reflecting autonomic activity-e.g., heart rate variability (HRV) and the morphology of the photoplethysmography (PPG) pulse wave-may aid in tracking maternal health. However, women with early pregnancy complications typically receive medication, such as corticosteroids, and the effect of corticosteroids on maternal HRV and PPG pulse wave morphology is not well-researched. Methods: We performed a prospective, observational study assessing the effect of betamethasone (a commonly used corticosteroid) on non-invasively assessed features of autonomic regulation. Sixty-one women with an indication for betamethasone were enrolled and wore a wrist-worn PPG device for at least four days, from which five-minute measurements were selected for analysis. A baseline measurement was selected either before betamethasone administration or sufficiently thereafter (i.e., three days after the last injection). Furthermore, measurements were selected 24, 48, and 72 h after betamethasone administration. HRV features in the time domain and frequency domain and describing heart rate (HR) complexity were calculated, along with PPG morphology features. These features were compared between the different days. Results: Maternal HR was significantly higher and HRV features linked to parasympathetic activity were significantly lower 24 h after betamethasone administration. Features linked to sympathetic activity remained stable. Furthermore, based on the PPG morphology features, betamethasone appears to have a vasoconstrictive effect. Conclusions: Our results suggest that administering betamethasone affects maternal autonomic regulation and cardiovasculature. Researchers assessing maternal HRV in complicated pregnancies should schedule measurements before or sufficiently after corticosteroid administration.

Prediction of MET Overexpression in Lung Adenocarcinoma from Hematoxylin and Eosin Images.

Mesenchymal epithelial transition (MET) protein overexpression is a targetable event in non-small cell lung cancer and is the subject of active drug development. Challenges in identifying patients for these therapies include lack of access to validated testing, such as standardized immunohistochemistry assessment, and consumption of valuable tissue for a single gene/protein assay. Development of prescreening algorithms using routinely available digitized hematoxylin and eosin (H&E)-stained slides to predict MET overexpression could promote testing for those who will benefit most. Recent literature reports a positive correlation between MET protein overexpression and RNA expression. In this work, a large database of matched H&E slides and RNA expression data were leveraged to train a weakly supervised model to predict MET RNA overexpression directly from H&E images. This model was evaluated on an independent holdout test set of 300 overexpressed and 289 normal patients, demonstrating a receiver operating characteristic area under curve of 0.70 (95th percentile interval: 0.66 to 0.74) with stable performance characteristics across different patient clinical variables and robust to synthetic noise on the test set. These results suggest that H&E-based predictive models could be useful to prioritize patients for confirmatory testing of MET protein or MET gene expression status.

Signatures of quantum phases in a dissipative system.

Lindbladian formalism, as tuned to dissipative and open systems, has been all-pervasive to interpret non-equilibrium steady states of quantum many-body systems. We study the fate of free fermionic and superconducting phases in a dissipative one-dimensional Kitaev model-where the bath acts both as a source and a sink of fermionic particles with different coupling rates. As a function of these two couplings, we investigate the steady state, its entanglement content, and its approach from varying initial states. Interestingly, we find that the steady state phase diagram retains decipherable signatures of ground state critical physics. We also show that early-time fidelity is a useful marker to find a subclass of phase transitions in such situations. Moreover, we show that the survival of critical signatures at late-times, strongly depend on the thermal nature of the steady state. This connection hints at a correspondence between quantum observables and classical magnetism in the steady state of such systems. Our work uncovers interesting connections between dissipative quantum many-body systems, thermalization of a classical spin and many-body quantum critical phenomena.

Quantitative assessment of carotid ultrasound diameter measurements in the operating room: a comparable analysis of long-axis versus rotated and tilted orientation.

Objective. Carotid ultrasound (US) has been studied as a non-invasive alternative for hemodynamic monitoring. A long-axis (LA) view is traditionally employed but is difficult to maintain and operator experience may impact the diameter estimates, making it unsuitable for monitoring. Preliminary results show that a new, i.e. rotated and tilted (RT) view is more robust to motion and less operator-dependent. This study aimed to quantitatively assess common carotid diameter estimates obtained in a clinical setting from an RT view and compare those to corresponding estimates obtained using other views.Approach. Carotid US measurements were performed in 30 adult cardiac-surgery patients (26 males, 4 females) with short-axis (SA), LA, and RT probe orientations, the first being used as a reference for measuring the true vessel diameter. Per 30 s acquisition, the median and spread in diameter values were computed, the latter representing a measure of robustness, and were statistically compared between views.Main results. The median (IQR) over all the patients of the median diameter per 30 s acquisition was 7.15 (1.15) mm for the SA view, 7.03 (1.51) mm for the LA view, and 6.99 (1.72) mm for the RT view. The median spread in diameter values was 0.18 mm for the SA view, 0.16 mm for the LA view, and 0.18 mm for the RT view. There were no statistically significant differences between views in the median diameter values (p= 0.088) or spread (p= 0.122).Significance. The RT view results in comparable and equally robust median carotid diameter values compared to the reference. These findings open the path for future studies investigating the use of the RT view in new applications, such as in wearable ultrasound devices.

Modeling meibum secretion: Alternatives for obstructive Meibomian Gland Dysfunction (MGD).

PURPOSE: While changes in meibum quality are correlated with severity of meibomian gland dysfunction (MGD) and dry eye disease, little is known regarding the mechanics of meibum secretion. The purpose of this study was to develop a finite element model of meibum secretion and evaluate the effect of various factors that might impact meibum delivery to the ocular surface. METHODS: A finite element analysis in COMSOL 6.0 was used to simulate the flow of meibum within the gland's terminal excretory duct. Historical normal human meibum rheology data taken over the meibum melting range from fluid (35-40 °C) to solid (25-30 °C) were then used to calculate the minimum yield stress and plastic viscosity of meibum. The effects of meibum melting state, eyelid pressure and terminal duct diameter on meibum flow rates were then systematically investigated. RESULTS: The melting state of meibum from liquid to solid was associated with an increase in the minimum yield stress and plastic viscosity that caused an exponential decrease in meibum flow. Modeling also established that there was a linear correlation between meibum flow rate and eyelid pressure needed to express meibum and the 4th power of the terminal duct radius. CONCLUSIONS: Our results suggest that changes in the melting state of meibum from fluid to solid, as well as changes in the radius of the terminal excretory duct and the force exerted by the eyelid can lead to dramatic decreases in the flow of meibum. Together these findings suggest alternative mechanisms for meibomian gland obstruction.

Maternal cardiorespiratory coupling: differences between pregnant and nonpregnant women are further amplified by sleep-stage stratification.

Pregnancy complications are associated with abnormal maternal autonomic regulation. Subsequently, thoroughly understanding maternal autonomic regulation during healthy pregnancy may enable the earlier detection of complications, in turn allowing for the improved management thereof. Under healthy autonomic regulation, reciprocal interactions occur between the cardiac and respiratory systems, i.e., cardiorespiratory coupling (CRC). Here, we investigate, for the first time, the differences in CRC between healthy pregnant and nonpregnant women. We apply two algorithms, namely, synchrograms and bivariate phase-rectified signal averaging, to nighttime recordings of ECG and respiratory signals. We find that CRC is present in both groups. Significantly less (P < 0.01) cardiorespiratory synchronization occurs in pregnant women (11% vs. 15% in nonpregnant women). Moreover, there is a smaller response in the heart rate of pregnant women corresponding to respiratory inhalations and exhalations. In addition, we stratified these analyses by sleep stages. As each sleep stage is governed by different autonomic states, this stratification not only amplified some of the differences between groups but also brought out differences that remained hidden when analyzing the full-night recordings. Most notably, the known positive relationship between CRC and deep sleep is less prominent in pregnant women than in their nonpregnant counterparts. The decrease in CRC during healthy pregnancy may be attributable to decreased maternal parasympathetic activity, anatomical changes to the maternal respiratory system, and the increased physiological stress accompanying pregnancy. This work offers novel insight into the physiology of healthy pregnancy and forms part of the base knowledge needed to detect abnormalities in pregnancy.NEW & NOTEWORTHY We compare CRC, i.e., the reciprocal interaction between the cardiac and respiratory systems, between healthy pregnant and nonpregnant women for the first time. Although CRC is present in both groups, CRC is reduced during healthy pregnancy; there is less synchronization between maternal cardiac and respiratory activity and a smaller response in maternal heart rate to respiratory inhalations and exhalations. Stratifying this analysis by sleep stages reveals that differences are most prominent during deep sleep.

Iridocorneal angle imaging of a human donor eye by spectral-domain optical coherence tomography.

Iridocorneal angle (ICA) details particularly the trabecular meshwork (TM), Schlemm's canal (SC), and collector channels (CCs) play crucial roles in the regulation of the aqueous outflow in the eyes and are closely associated with glaucoma. Current clinical gonioscopy imaging provides no depth information, and studies of 3D high-resolution optical coherence tomography (OCT) imaging of these structures are limited. We developed a custom-built spectral-domain (SD-) OCT imaging system to fully characterize the angle details. Imaging of a human cadaver eye reveals the visibility of details in the TM/SC/CC region via a 'crossline' scanning and a series of image processing. This shows that ICA imaging can be used for preoperative glaucoma inspections in the clinical setting with the proposed prototype.

Evidence and clinical relevance of maternal-fetal cardiac coupling: A scoping review.

BACKGROUND: Researchers have long suspected a mutual interaction between maternal and fetal heart rhythms, referred to as maternal-fetal cardiac coupling (MFCC). While several studies have been published on this phenomenon, they vary in terms of methodologies, populations assessed, and definitions of coupling. Moreover, a clear discussion of the potential clinical implications is often lacking. Subsequently, we perform a scoping review to map the current state of the research in this field and, by doing so, form a foundation for future clinically oriented research on this topic. METHODS: A literature search was performed in PubMed, Embase, and Cochrane. Filters were only set for language (English, Dutch, and German literature were included) and not for year of publication. After screening for the title and the abstract, a full-text evaluation of eligibility followed. All studies on MFCC were included which described coupling between heart rate measurements in both the mother and fetus, regardless of the coupling method used, gestational age, or the maternal or fetal health condition. RESULTS: 23 studies remained after a systematic evaluation of 6,672 studies. Of these, 21 studies found at least occasional instances of MFCC. Methods used to capture MFCC are synchrograms and corresponding phase coherence indices, cross-correlation, joint symbolic dynamics, transfer entropy, bivariate phase rectified signal averaging, and deep coherence. Physiological pathways regulating MFCC are suggested to exist either via the autonomic nervous system or due to the vibroacoustic effect, though neither of these suggested pathways has been verified. The strength and direction of MFCC are found to change with gestational age and with the rate of maternal breathing, while also being further altered in fetuses with cardiac abnormalities and during labor. CONCLUSION: From the synthesis of the available literature on MFCC presented in this scoping review, it seems evident that MFCC does indeed exist and may have clinical relevance in tracking fetal well-being and development during pregnancy.

Survival differences of low-grade versus high-grade head and neck pleomorphic dermal sarcomas and a review of a scalp case.

Objective: To examine survival by tumor grade of pleomorphic dermal sarcomas (PDS) of the head and neck (H&N) and review a scalp PDS case. Methods: Patients in the Surveillance, Epidemiology, and End Results (SEER) database were included from 1980 to 2016 based on a diagnosis of H&N PDS. Survival estimates were performed using Kaplan-Meier analysis. Additionally, a case of a grade III H&N PDS is presented. Results: Two hundred-seventy cases of PDS were identified. The mean age at diagnosis was 75.1 years (SD: 13.5). Two hundred-thirty-four (86.7%) patients were male. Eighty-seven percent of patients received surgery as a part of their care. The 5-year overall survival rates for grades I, II, III, and IV PDSs were 69%, 60%, 50%, and 42%, respectively (P = 0.03). Conclusions: H&N PDS occurs most commonly in older-age males. Surgical management is frequently a part of H&N PDS care. Survival rates significantly decline based on tumor grade.

Changes in Maternal Heart Rate and Autonomic Regulation following the Antenatal Administration of Corticosteroids: A Secondary Analysis.

While the effect of antenatally administered corticosteroids on fetal heart rate (HR) and heart rate variability (HRV) is well established, little information is available on how these drugs affect maternal physiology. In this secondary analysis of a prospective, observational cohort study, we quantify how corticosteroids affect maternal HR and HRV, which serve as a proxy measure for autonomic regulation. Abdominal ECG measurements were recorded before and in the five days following the administration of betamethasone­a corticosteroid commonly used for fetal maturation­in 46 women with singleton pregnancies. Maternal HR and HRV were determined from these recordings and compared between these days. HRV was assessed with time- and frequency-domain features, as well as non-linear and complexity features. In the 24 h after betamethasone administration, maternal HR was significantly increased (p < 0.01) by approximately 10 beats per minute, while HRV features linked to parasympathetic activity and HR complexity were significantly decreased (p < 0.01 and p < 0.001, respectively). Within four days after the initial administration of betamethasone, HR decreases and HRV features increase again, indicating a diminishing effect of betamethasone a few days after administration. We conclude that betamethasone administration results in changes in maternal HR and HRV, despite the heterogeneity of the studied population. Therefore, its recent administration should be considered when evaluating these cardiovascular metrics.

Laryngectomy: Social media analysis of patient perception.

BACKGROUND: Social media continues to grow as a relevant information source for the lay public and medical professionals. METHODS: A search of posts on Facebook and Instagram was conducted using the hashtag #laryngectomy. Posts were categorized based upon perspective, media type, timeframe, topic, tone, and popularity. RESULTS: Final analysis included 929 Instagram posts and 355 Facebook posts. Most Facebook posts were made by companies (38%) and physicians (17%) with information (30%) and advertisements (22%) being common topics. Patients (40%) were the largest group of Instagram authors with lifestyle (39%) being the most common topic. Greater than 90% of posts were either neutral or positive in tone across both platforms. CONCLUSIONS: Patient perspective was most commonly represented on Instagram, whereas Facebook more commonly included posts by physicians and companies. The majority of posts carried a neutral or positive tone, which is consistent with positive quality of life patients have shown postoperatively.

Artificial intelligence-augmented histopathologic review using image analysis to optimize DNA yield from formalin-fixed paraffin-embedded slides.

To achieve minimum DNA input requirements for next-generation sequencing (NGS), pathologists visually estimate macrodissection and slide count decisions. Unfortunately, misestimation may cause tissue waste and increased laboratory costs. We developed an artificial intelligence (AI)-augmented smart pathology review system (SmartPath) to empower pathologists with quantitative metrics for accurately determining tissue extraction parameters. SmartPath uses two deep learning architectures, a U-Net based network for cell segmentation and a multi-field-of-view convolutional network for tumor area segmentation, to extract features from digitized H&E-stained formalin-fixed paraffin-embedded slides. From the segmented tumor area, SmartPath suggests a macrodissection area. To predict DNA yield per slide, the extracted features from within the macrodissection area are correlated with known DNA yields to fit a regularized linear model (R = 0.85). Then, a pathologist-defined target yield divided by the predicted DNA yield per slide gives the number of slides to scrape. Following model development, an internal validation trial was conducted within the Tempus Labs molecular sequencing laboratory. We evaluated our system on 501 clinical colorectal cancer slides, where half received SmartPath-augmented review and half traditional pathologist review. The SmartPath cohort had 25% more DNA yields within a desired target range of 100-2000 ng. The number of extraction attempts was statistically unchanged between cohorts. The SmartPath system recommended fewer slides to scrape for large tissue sections, saving tissue in these cases. Conversely, SmartPath recommended more slides to scrape for samples with scant tissue sections, especially those with degraded DNA, helping prevent costly re-extraction due to insufficient extraction yield. A statistical analysis was performed to measure the impact of covariates on the results, offering insights on how to improve future applications of SmartPath. With these improvements, AI-augmented histopathologic review has the potential to decrease tissue waste, sequencing time, and laboratory costs by optimizing DNA yields, especially for samples with scant tissue and/or degraded DNA.

Longitudinally Tracking Maternal Autonomic Modulation During Normal Pregnancy With Comprehensive Heart Rate Variability Analyses.

Changes in the maternal autonomic nervous system are essential in facilitating the physiological changes that pregnancy necessitates. Insufficient autonomic adaptation is linked to complications such as hypertensive diseases of pregnancy. Consequently, tracking autonomic modulation during progressing pregnancy could allow for the early detection of emerging deteriorations in maternal health. Autonomic modulation can be longitudinally and unobtrusively monitored by assessing heart rate variability (HRV). Yet, changes in maternal HRV (mHRV) throughout pregnancy remain poorly understood. In previous studies, mHRV is typically assessed only once per trimester with standard HRV features. However, since gestational changes are complex and dynamic, assessing mHRV comprehensively and more frequently may better showcase the changing autonomic modulation over pregnancy. Subsequently, we longitudinally (median sessions = 8) assess mHRV in 29 healthy pregnancies with features that assess sympathetic and parasympathetic activity, as well as heart rate (HR) complexity, HR responsiveness and HR fragmentation. We find that vagal activity, HR complexity, HR responsiveness, and HR fragmentation significantly decrease. Their associated effect sizes are small, suggesting that the increasing demands of advancing gestation are well tolerated. Furthermore, we find a notable change in autonomic activity during the transition from the second to third trimester, highlighting the dynamic nature of changes in pregnancy. Lastly, while we saw the expected rise in mean HR with gestational age, we also observed increased autonomic deceleration activity, seemingly to counter this rising mean HR. These results are an important step towards gaining insights into gestational physiology as well as tracking maternal health via mHRV.

Synchronous tonsillar tumors with differing histopathology: A case report and review of the literature.

BACKGROUND: Tonsillar squamous cell carcinoma (TSCC) due to human papillomavirus (HPV) infection has seen a dramatic increase in recent years. Bilateral tonsillar squamous cell carcinoma (biTSCC) has a much lower incidence than unilateral TSCC and three main hypotheses of biTSCC pathogenesis prevail: field carcinogenesis, single-clone, and multiple HPV infections. CASE: A 49-year-old Male with a remote history of chewing tobacco presented with symptoms of spitting up tissue and occasional hemoptysis. Physical exam showed a sole left tonsillar mass which was confirmed to be TSCC on biopsy. The patient's computed tomographic (CT) scan was consistent with this finding; however, positron emission tomography (PET) scan indicated a second tumor in the contralateral right tonsil. Surgical resection of both masses and selective neck dissection was performed, and the specimens were sent for further pathological analysis. No complications of surgery were noted and the final diagnosis of synchronous biTSCC was made. The tumors were a T2N0M0 left poorly differentiated TSCC (p16+, EGFR+, bcl2+) with basaloid features, and a T1N0M0 right well to moderately differentiated TSCC (p16+, EGFR+, bcl2-). CONCLUSION: Our present case was notable for differing tumor pathology and karyotype analysis between the right and left masses, directly supporting the multiple HPV infections hypothesis of biTSCC pathogenesis. Further genetic characterization of tonsillar tumors is needed to better characterize TSCC and best guide medical/surgical therapy.

Combined large cell neuroendocrine carcinoma and squamous cell carcinoma of the oropharynx: A collision course of tumors.

Combined large cell neuroendocrine carcinoma (LCNEC) and squamous cell carcinoma (SCC) of the H&N are exceptionally rare. We present the case of combined p16 negative SCC and LCNEC of the oropharynx treated with combination chemotherapy. This is the third reported case of combined neuroendocrine carcinoma and SCC of the oropharynx.

Novel Use of Hypoxia-Inducible Polymerizable Protein to Augment Chemotherapy for Pancreatic Cancer.

Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive malignancies and is the fourth leading cause of cancer-related deaths in the United States. Unfortunately, 80-85% of patients are diagnosed with unresectable, advanced stage tumors. These tumors are incurable and result in a median survival less than approximately six months and an overall 5-year survival rate of less than 7%. Whilst chemotherapy is a critical treatment, cure is not possible without surgical resection. The poor clinical outcomes in PDAC can be partially attributed to its dense desmoplastic stroma, taking up roughly 80% of the tumor mass. The stroma surrounding the tumor disrupts the normal architecture of pancreatic tissue leading to poor vascularization, high intratumoral pressure along with hypoxia and an acidic tumor microenvironment. This complicated microenvironment presents a significant challenge for drug delivery. The current manuscript discusses a novel approach to overcome many of these various obstacles. A complex of gemcitabine (GEM) and hemoglobin S (HbS) was formulated, which self-polymerizes under hypoxic and acidic conditions. When polymerized, HbS has the potential to break the tumor stroma, decrease intratumoral pressure, and therefore improve the treatment efficacy of standard therapy. Intratumoral injection of HbS with a fluorescent small molecule surrogate for GEM into a pancreatic tumor xenograft resulted in improved dissemination of the small molecule throughout the pancreatic tumor. The self-polymerization of HbS + GEM was significantly more effective than either agent individually at decreasing tumor size in an in vivo PDAC mouse model. These findings would suggest a clinical benefit from delivering the complex of GEM and HbS via direct injection by endoscopic ultrasound (EUS). With such a treatment option, patients with locally advanced disease would have the potential to become surgical candidates, offering them a chance for cure.

Kimura Disease: A Rare and Difficult to Diagnose Entity.

Kimura disease (KD) is a rare inflammatory disorder which involves the head and neck. Due to its rarity and various findings, definitive diagnosis can be difficult to ascertain. Kimura disease is distinguished from other conditions, including angiolymphoid hyperplasia, by histopathological features including follicular hyperplasia, reactive germinal centers, abundant eosinophilia, eosinophilic microabscesses, preserved nodal architecture, Warthin-Finkeldy polykaryocytes, and capsular fibrosis. Herein, we describe the clinical presentation, pathology, and diagnosis of a single case of a 39-year-old treated at an academic center in Texas.

W-Net: Dense and diagnostic semantic segmentation of subcutaneous and breast tissue in ultrasound images by incorporating ultrasound RF waveform data.

We study the use of raw ultrasound waveforms, often referred to as the "Radio Frequency" (RF) data, for the semantic segmentation of ultrasound scans to carry out dense and diagnostic labeling. We present W-Net, a novel Convolution Neural Network (CNN) framework that employs the raw ultrasound waveforms in addition to the grey ultrasound image to semantically segment and label tissues for anatomical, pathological, or other diagnostic purposes. To the best of our knowledge, this is also the first deep-learning or CNN approach for segmentation that analyzes ultrasound raw RF data along with the grey image. We chose subcutaneous tissue (SubQ) segmentation as our initial clinical goal for dense segmentation since it has diverse intermixed tissues, is challenging to segment, and is an underrepresented research area. SubQ potential applications include plastic surgery, adipose stem-cell harvesting, lymphatic monitoring, and possibly detection/treatment of certain types of tumors. Unlike prior work, we seek to label every pixel in the image, without the use of a background class. A custom dataset consisting of hand-labeled images by an expert clinician and trainees are used for the experimentation, currently labeled into the following categories: skin, fat, fat fascia/stroma, muscle, and muscle fascia. We compared W-Net and attention variant of W-Net (AW-Net) with U-Net and Attention U-Net (AU-Net). Our novel W-Net's RF-Waveform encoding architecture outperformed regular U-Net and AU-Net, achieving the best mIoU accuracy (averaged across all tissue classes). We study the impact of RF data on dense labeling of the SubQ region, which is followed by the analyses of the generalization capability of the networks to patients and analysis on the SubQ tissue classes, determining that fascia tissues, especially muscle fascia in particular, are the most difficult anatomic class to recognize for both humans and AI algorithms. We present diagnostic semantic segmentation, which is semantic segmentation carried out for the purposes of direct diagnostic pixel labeling, and apply it to breast tumor detection task on a publicly available dataset to segment pixels into malignant tumor, benign tumor, and background tissue class. Using the segmented image we diagnose the patient by classifying the breast lesion as either benign or malignant. We demonstrate the diagnostic capability of RF data with the use of W-Net, which achieves the best segmentation scores across all classes.

Spatial proteomic characterization of HER2-positive breast tumors through neoadjuvant therapy predicts response.

The addition of HER2-targeted agents to neoadjuvant chemotherapy has dramatically improved pathological complete response (pCR) rates in early-stage, HER2-positive breast cancer. Nonetheless, up to 50% of patients have residual disease after treatment, while others are likely overtreated. Here, we performed multiplex spatial proteomic characterization of 122 samples from 57 HER2-positive breast tumors from the neoadjuvant TRIO-US B07 clinical trial sampled pre-treatment, after 14-21 d of HER2-targeted therapy and at surgery. We demonstrated that proteomic changes after a single cycle of HER2-targeted therapy aids the identification of tumors that ultimately undergo pCR, outperforming pre-treatment measures or transcriptomic changes. We further developed and validated a classifier that robustly predicted pCR using a single marker, CD45, measured on treatment, and showed that CD45-positive cell counts measured via conventional immunohistochemistry perform comparably. These results demonstrate robust biomarkers that can be used to enable the stratification of sensitive tumors early during neoadjuvant HER2-targeted therapy, with implications for tailoring subsequent therapy.