Node Sections Research Articles

Departure delay prediction and analysis based on node sequence data of ground support services for transit flights

Delays frequently occur during ground support services for transit flights. Due to the limitation of related data acquisition, the delay occurred during this process has seldom been explored. Toward the purpose of departure delay mitigation, the present research provides the node sequence data to identify the critical ground support service nodes that associate with departure delay. Machine learning techniques are used for accurate departure delay prediction of transit flights. First, the topological structure of the neural network is constructed according to the ground service support procedure of transit flights. The flight data from Shanghai Pudong and Kunming Changshui International airports are collected for delay description and model evaluation. Then, similarity of delay scenarios are illustrated and the typical delay patterns are explored based on clustering methods. It is found that there are some node sections that delays routinely occur. Third, a Bayesian network is constructed for delay probability analysis. The conditional probability table describing the impact of delay occurred during each section on the departure delay for transit flights is provided. Finally, the performance of two classes of approaches to predict departure delays are constructed and compared, including three traditional machining learning methods denoted as random forest, decision tree, XGBoost models, and four graph convolutional neural network models namely Graph convolutional network (GCN), Graph attention network (GAT), Graph sample and aggregate (GraphSAGE) and integrated Graph convolutional network and Graph sample and aggregate (GCN-GraphSAGE) models. In general, the proposed GCN-GraphSAGE method achieves the most stable and satisfactory performance for departure delay prediction. The research results can support the dynamic and accurate prediction of departure delays and the refined management of transit flights for delay alleviation.

Contralateral lymph node metastasis: A rare skip pattern

Neck lymph node metastasis is the most critical factor influencing the survival and prognosis of oral squamous cell carcinoma. The outcome of patients with lymph node metastases occurring after excision or radiotherapy of the primary tumor is poor. In the absence of ipsilateral nodal metastases, contralateral lymph neck metastasis is extremely rare. Reports of skip metastases have been recorded for lesions of the tongue and floor of the mouth as there is free communication between the two sides of the tongue. Intraoperative frozen sections of neck nodes have been used as a modality for the detection of occult metastases and to guide the extent of neck dissection but have not provided satisfactory results. The case described in this report is a rare phenomenon that demonstrates a well-lateralized clinically advanced buccal mucosa carcinoma with histologically proven node-negative neck but exhibited contralateral positive neck after a span of 1 month.

Using Artificial Intelligence to Identify Tumor Microenvironment Heterogeneity in Non–Small Cell Lung Cancers

Lung cancer heterogeneity is a major barrier to effective treatments and encompasses not only the malignant epithelial cell phenotypes and genetics but also the diverse tumor-associated cell types. Current techniques used to investigate the tumor microenvironment can be time-consuming, expensive, complicated to interpret, and often involves destruction of the sample. Here we use standard hematoxylin and eosin–stained tumor sections and the HALO AI nuclear phenotyping software to characterize 6 distinct cell types (epithelial, mesenchymal, macrophage, neutrophil, lymphocyte, and plasma cells) in both murine lung cancer models and human lung cancer samples. CD3 immunohistochemistry and lymph node sections were used to validate lymphocyte calls, while F4/80 immunohistochemistry was used for macrophage validation. Consistent with numerous prior studies, we demonstrated that macrophages predominate the adenocarcinomas, whereas neutrophils predominate the squamous cell carcinomas in murine samples. In human samples, we showed a strong negative correlation between neutrophils and lymphocytes as well as between mesenchymal cells and lymphocytes and that higher percentages of mesenchymal cells correlate with poor prognosis. Taken together, we demonstrate the utility of this AI software to identify, quantify, and compare distributions of cell types on standard hematoxylin and eosin–stained slides. Given the simplicity and cost-effectiveness of this technique, it may be widely beneficial for researchers designing new therapies and clinicians working to select favorable treatments for their patients.

Quantitative analysis of dual-phase enhanced CT in cervical lymph node metastasis of papillary thyroid carcinoma: a comparative study along with pathological manifestations.

This study aimed to investigate the diagnostic value of dual-phase enhanced computed tomography (CT) in the cervical lymph node metastasis (LNM) of papillary thyroid carcinoma (PTC) by analyzing the dual-phase enhanced Hounsfield units (HUs) of lymph node and sternocleidomastoid muscle, and the ratio and difference. The CT arterial-phase and venous-phase imaging data of 143 metastasis-positive lymph nodes (MPLNs) in 88 cases and 172 metastasis-negative lymph nodes (MNLNs) in 128 cases with PTC were retrospectively analyzed. All lymph nodes were confirmed by surgical pathology. The arterial-phase HU of lymph nodes (ANHU), venous-phase HU of lymph nodes (VNHU), arterial-phase HU of the sternocleidomastoid muscle (AMHU) and venous-phase HU of the sternocleidomastoid muscle (VMHU) were measured, and their difference and ratio (ANHU-AMHU, ANHU/AMHU, VNHU-VMHU, VNHU/VMHU) were calculated. The cutoff values and corresponding diagnostic efficacy for diagnosing LNM in PTC were sought by performing the receiver operating characteristic curves. The maximum pathological diameter (MPD) measured on pathological sections of lymph nodes was compared with the maximum transverse diameter (MTD) and maximum sagittal diameter (MSD) and their average values on CT images. The ANHU, and VNHU of MPLNs and MNLNs were 111.89 ± 33.26 and 66.12 (56.81-76.86) (P < 0.001), and 99.07 ± 23.27 and 75.47 ± 13.95 (P < 0.001), respectively. The area under the curve, sensitivity, and specificity of the arterial-phase three parameters (ANHU, ANHU-AMHU, ANHU/AMHU) for diagnosing LNM were (0.877-0.880), (0.755-0.769), and (0.901-0.913), respectively, and the venous-phase three parameters (VNHU, VNHU-VMHU, VNHU/VMHU) were (0.801-0.817), (0.650-0.678), and (0.826-0.901), respectively. Compared with MPD, MTD (Z = -2.686, P = 0.007) and MSD (Z = -3.539, P < 0.001) were significantly different, while (MTD + MSD)/2 was not statistically different (Z = -0.038b, P = 0.969). In the differential diagnosis of cervical LNM of PTC by dual-phase enhanced CT angiography, the arterial phase had higher diagnostic efficacy.

Lipid metabolism marker CD36 is associated with 18FDG-PET/CT false negative lymph nodes in head and neck squamous cell carcinoma.

Lymph node metastasis frequently occurs in head and neck squamous cell carcinoma (HNSCC) patients, and [18F] fluorodeoxyglucose positron emission tomography with computed tomography (18FDG-PET/CT) examination for lymph node metastasis could result in false negativity and delay following treatment. However, the mechanism and resolution for 18FDG-PET/CT false negatives remain unclear. Our study was aim to found biomarkers for false negativity and true positivity from a metabolic perspective. Ninety-two patients diagnosed with HNSCC who underwent preoperative 18FDG-PET/CT and subsequent surgery in our institution were reviewed. Immunohistochemistry (IHC) examinations of glucose metabolism (GLUT1 and GLUT5), amino acid metabolism4 (GLS and SLC1A5), and lipid metabolism (CPT1A and CD36) markers were conducted on their primary lesion and lymph node sections. We identified specific metabolic patterns of the false-negative group. Significantly, CD36 IHC score of primary lesions was higher in false-negative group than true-positive group. Moreover, we validated pro-invasive biological effects of CD36 by bioinformatics analysis as well as experiments. Conclusion: IHC examination of CD36 expression, which is a lipid metabolism marker, in primary lesions could distinguish HNSCC patients' lymph nodes false negatives in 18FDG-PET/CT.

DESCRIPTIVE STUDY OF SENTINEL LYMPH NODES /AXILLARY SAMPLING ON FROZEN SECTION IN CASES OF CARCINOMA OF BREAST

Background: The frozen section provides rapid diagnosis to guide intra or perioperative patient management. Intraoperative frozen sections of sentinel lymph nodes can be used to identify metastatic disease, allowing immediate axillary lymph node dissection. To Study Sentinel Aims: Lymph node /Axillary Sampling on Frozen Section in Cases of Carcinoma of the Breast and to assess the accuracy of frozen section diagnosis. Materials and Methods: - An observational descriptive study was carried out in the department of pathology. A total of 33 patients were evaluated during January 2021 to July 2022. SLNs were examined using standard frozen section procedure and sections were stained with rapid H &amp;E. Patients with positive SLN on FS underwent ALND. The remaining frozen tissue was processed for routine histopathology processing. Results: - Out of 33 cases, 9 (27.27%) cases are positive on the frozen section and 24 (72.72 %) cases are negative on the frozen section. However, on the parafn section, 14 (42.42%) cases are positive and 19 (57.57 %) are negative. There was no false positive case (specicity-100%). 14 cases show tumour deposit in sentinel lymph node. 13 cases had macro-metastatic tumour deposit and 01 case shows micro-metastatic tumour deposit. The diagnostic accuracy is 84.84% and sensitivity 64.28%. Intraoperative frozen section diagnosi Conclusions: - s of sentinel lymph nodes in cases of carcinoma of breast can identify metastatic disease, allowing immediate axillary dissection, if necessary, thus avoiding the need for reoperation. Arm and shoulder morbidity caused by axillary lymph node dissection (ALND) can be avoided in cases where it was not indicated on frozen section.

Spatially resolved immune receptor repertoires from Visium transcriptomic libraries

Abstract Recent advances have enabled the integration of T cell receptor (TCR) sequencing into spatial transcriptomics. Current approaches yield critical information about in situ T cell responses directly from relevant tissues, yet are largely limited to alpha/beta TCRs, leaving the clonal dynamics of B cells and gamma/delta T cells underexplored. We therefore modified our previously reported ultra-efficient immune receptor repertoire sequencing (IRR-seq) method, Framework Region 3 AmplifiKation Sequencing (FR3AK-seq), for compatibility with the 10X Genomics Visium spatial transcriptomics platform. Here we report simultaneous acquisition of alpha/beta TCR, gamma/delta TCR, and immunoglobulin (B cell receptor, BCR) heavy/light chain sequences from a single multiplexed FR3AK-seq reaction using Visium transcriptomics-generated cDNA libraries. More specifically, we used the Visium spatial transcriptomics protocol to generate cDNA from serial sections of a lymph node with a metastatic lesion obtained from a patient with pancreatic ductal adenocarcinoma previously treated with immunotherapy. Notably, we detected sequences from all IRR chains as expected from the abundant immune infiltrates within these sections. Furthermore, we found that multiplexed FR3AK-seq yields technically reproducible repertoires, with the TCR beta chain repertoires also comparable to those obtained using a previously published method. We anticipate that this simple extension of the Visium technology will accelerate the simultaneous and comprehensive examination of in situ IRR dynamics beyond alpha/beta T cells.

Deep learning detection of melanoma metastases in lymph nodes

BackgroundIn melanoma patients, surgical excision of the first draining lymph node, the sentinel lymph node (SLN), is a routine procedure to evaluate lymphogenic metastases. Metastasis detection by histopathological analysis assesses multiple tissue levels with hematoxylin and eosin and immunohistochemically stained glass slides. Considering the amount of tissue to analyze, the detection of metastasis can be highly time-consuming for pathologists. The application of artificial intelligence in the clinical routine has constantly increased over the past few years. MethodsIn this multi-center study, a deep learning method was established on histological tissue sections of sentinel lymph nodes collected from the clinical routine. The algorithm was trained to highlight potential melanoma metastases for further review by pathologists, without relying on supplementary immunohistochemical stainings (e.g. anti-S100, anti-MelanA). ResultsThe established method was able to detect the existence of metastasis on individual tissue cuts with an area under the curve of 0.9630 and 0.9856 respectively on two test cohorts from different laboratories. The method was able to accurately identify tumour deposits>0.1 mm and, by automatic tumour diameter measurement, classify these into 0.1 mm to −1.0 mm and>1.0 mm groups, thus identifying and classifying metastasis currently relevant for assessing prognosis and stratifying treatment. ConclusionsOur results demonstrate that AI-based SLN melanoma metastasis detection has great potential and could become a routinely applied aid for pathologists. Our current study focused on assessing established parameters; however, larger future AI-based studies could identify novel biomarkers potentially further improving SLN-based prognostic and therapeutic predictions for affected patients.

IMPLEMENTASI TEKNOLOGI LORA DAN NODEMCU ESP8266 PADA ALAT EARLY WARNING SYSTEM UNTUK PEMANTAUAN KUALITAS UDARA

Good air quality is important for the health and comfort of the people living in that environment. Air quality conditions at a location can be determined from the levels of pollutants and harmful gases. The most easily known air quality parameters are temperature, humidity, and levels of harmful gases present. This research presents an air quality monitoring instrument that utilizes Long Range (LoRa) wireless technology for data transmission. This tool consists of a sensor node section that functions to detect air quality in a certain area, as well as a gateway section that functions to receive data from the sensor node to be forwarded to the operator. Each set of sections is equipped with a LoRa SX1276 module that works at a frequency of 915 MHz for data communication and NodeMCU ESP8266 for data processing. The sensor node is equipped with a DHT22 sensor to detect temperature and humidity and an MQ7 sensor to detect carbon monoxide (CO) levels. The reading results of these sensors are forwarded by the sensor node to the gateway to be displayed on a 0.96” OLED. The gateway is also equipped with a buzzer that will sound if a temperature reading value exceeds 40 oC is found, humidity does not meet the 45-65% RH range, and CO levels exceed 12 ppm. The test results showed that the buzzer function can work properly according to the specified sensor reading value and the maximum distance between the sensor node and the gateway for optimal data communication is a radius of 400 m when tested at the Politeknik Penerbangan Surabaya.

Role of Sentinel Lymph Node Drainage Mapping for Localization of Contralateral Lymph Node Metastasis in Locally Advanced Oral Squamous Cell Carcinoma - A Prospective Pilot Study.

Sentinel lymph node biopsy (SLNB) has become the standard of care for nodal staging in early-stage oral squamous cell carcinoma (OSCC) as an alternative to elective neck dissection. However, the role of sentinel lymph node (SLN) and lymphatic drainage mapping with image-guided surgery has not been studied in locally advanced OSCC. Therefore, this study was undertaken to evaluate the role of lymphatic drainage mapping in the identification of contralateral cervical lymph node metastasis in locally advanced OSCC (Stage III-IVb). We have prospectively analyzed treatment-naïve patients of locally advanced, lateralized OSCC (n = 20). All patients underwent SLN imaging using peritumoral injection 0.5-1.0 mCi of 99 mTc-Sulfur colloid (Filtered) and intraoperative identification of contralateral neck nodes using a handheld gamma probe (Crystal Photonics). A total of 20 patients (18 males and 2 females) with a median age of 52.5 (33-70 years) were included. Ipsilateral SLN was localized in 18 (90%) patients. Bilateral cervical nodes were visualized only in 7 (35%) patients on lymphoscintigraphy (LSG). Out of the seven patients, 5 patients underwent bilateral neck dissection and 2 patients had unilateral neck dissection with LSG-guided exploration of contralateral cervical node and intraoperative frozen section examination. Six out of these seven patients had one or other risk factor for contralateral metastasis (patients had either primary in the tongue, involvement of floor of mouth, or tumor thickness >3.75 mm). On postoperative HPE, only 1/20 (5%) patient showed metastasis in the contralateral cervical lymph node. Correct identification of metastatic disease in contralateral neck directly influences clinical management, as it can reduce contralateral neck failure rate and limit the morbidity associated with unnecessary contralateral neck dissection, and it is also crucial in radiotherapy planning in locally advanced OSCC. In the current study, lymphatic drainage mapping showed a metastatic rate of 5% in the contralateral neck nodes in locally advanced, lateralized OSCC. However, the role of SLNB and lymphatic drainage mapping in this subgroup of OSCC needs to be studied in larger population to validate these findings.

Artificial intelligence-based model for lymph node metastases detection on whole slide images in bladder cancer: a retrospective, multicentre, diagnostic study.

Accurate lymph node staging is important for the diagnosis and treatment of patients with bladder cancer. We aimed to develop a lymph node metastases diagnostic model (LNMDM) on whole slide images and to assess the clinical effect of an artificial intelligence-assisted (AI) workflow. In this retrospective, multicentre, diagnostic study in China, we included consecutive patients with bladder cancer who had radical cystectomy and pelvic lymph node dissection, and from whom whole slide images of lymph node sections were available, for model development. We excluded patients with non-bladder cancer and concurrent surgery, or low-quality images. Patients from two hospitals (Sun Yat-sen Memorial Hospital of Sun Yat-sen University and Zhujiang Hospital of Southern Medical University, Guangzhou, Guangdong, China) were assigned before a cutoff date to a training set and after the date to internal validation sets for each hospital. Patients from three other hospitals (the Third Affiliated Hospital of Sun Yat-sen University, Nanfang Hospital of Southern Medical University, and the Third Affiliated Hospital of Southern Medical University, Guangzhou, Guangdong, China) were included as external validation sets. A validation subset of challenging cases from the five validation sets was used to compare performance between the LNMDM and pathologists, and two other datasets (breast cancer from the CAMELYON16 dataset and prostate cancer from the Sun Yat-sen Memorial Hospital of Sun Yat-sen University) were collected for a multi-cancer test. The primary endpoint was diagnostic sensitivity in the four prespecified groups (ie, the five validation sets, a single-lymph-node test set, the multi-cancer test set, and the subset for a performance comparison between the LNMDM and pathologists). Between Jan 1, 2013 and Dec 31, 2021, 1012 patients with bladder cancer had radical cystectomy and pelvic lymph node dissection and were included (8177 images and 20 954 lymph nodes). We excluded 14 patients (165 images) with concurrent non-bladder cancer and also excluded 21 low-quality images. We included 998 patients and 7991 images (881 [88%] men; 117 [12%] women; median age 64 years [IQR 56-72]; ethnicity data not available; 268 [27%] with lymph node metastases) to develop the LNMDM. The area under the curve (AUC) for accurate diagnosis of the LNMDM ranged from 0·978 (95% CI 0·960-0·996) to 0·998 (0·996-1·000) in the five validation sets. Performance comparisons between the LNMDM and pathologists showed that the diagnostic sensitivity of the model (0·983 [95% CI 0·941-0·998]) substantially exceeded that of both junior pathologists (0·906 [0·871-0·934]) and senior pathologists (0·947 [0·919-0·968]), and that AI assistance improved sensitivity for both junior (from 0·906 without AI to 0·953 with AI) and senior (from 0·947 to 0·986) pathologists. In the multi-cancer test, the LNMDM maintained an AUC of 0·943 (95% CI 0·918-0·969) in breast cancer images and 0·922 (0·884-0·960) in prostate cancer images. In 13 patients, the LNMDM detected tumour micrometastases that had been missed by pathologists who had previously classified these patients' results as negative. Receiver operating characteristic curves showed that the LNMDM would enable pathologists to exclude 80-92% of negative slides while maintaining 100% sensitivity in clinical application. We developed an AI-based diagnostic model that did well in detecting lymph node metastases, particularly micrometastases. The LNMDM showed substantial potential for clinical applications in improving the accuracy and efficiency of pathologists' work. National Natural Science Foundation of China, the Science and Technology Planning Project of Guangdong Province, the National Key Research and Development Programme of China, and the Guangdong Provincial Clinical Research Centre for Urological Diseases.

Enhancement of Immune Response of Bioconjugate Nanovaccine by Loading of CpG through Click Chemistry

CpG is a widely used adjuvant that enhances the cellular immune response by entering antigen-presenting cells and binding with receptors. The traditional physical mixing of the antigen and CpG adjuvant results in a low adjuvant utilization rate. Considering the efficient delivery capacity of nanovaccines, we developed an attractive strategy to covalently load CpG onto the nanovaccine, which realized the co-delivery of both CpG and the antigen. Briefly, the azide-modified CpG was conjugated to a bioconjugate nanovaccine (NP-OPS) against Shigella flexneri through a simple two-step reaction. After characterization of the novel vaccine (NP-OPS-CpG), a series of in vitro and in vivo experiments were performed, including in vivo imaging, lymph node sectioning, and dendritic cell stimulation, and the results showed that more CpG reached the lymph nodes after covalent coupling. Subsequent flow cytometry analysis of lymph nodes from immunized mice showed that the cellular immune response was greatly promoted by the nanovaccine coupled with CpG. Moreover, by analyzing the antibody subtypes of immunized mice, NP-OPS-CpG was found to further promote a Th1-biased immune response. Thus, we developed an attractive method to load CpG on a nanovaccine that is simple, convenient, and is especially suitable for immune enhancement of vaccines against intracellular bacteria.

Abstract P5-01-03: Evaluation of novel diagnostic kits using the semi-dry dot-blot method combined with an automatic reader for detecting metastases in sentinel lymph nodes of patients with breast cancer: a multi-center prospective study

Abstract Background: The semi-dry dot-blot (SDB) method, a diagnostic procedure for detecting lymph node (LN) metastases using an anti-cytokeratin (CK) antibody, is based on the theory that epithelial components, such as CK, are not found in normal LNs. Thus, metastases are diagnosed according to the presence of CK in the lavage fluid of sectioned LNs. We prospectively evaluated novel SDB kits that use a newly developed anti-CK19 antibody and an automatic reader for diagnosing sentinel LN metastases in patients with breast cancer as a multi-center study. Methods: We obtained 924 sentinel LNs dissected from 405 patients with breast cancer between January 2021 and December 2021 at six institutes in Japan. We excluded patients who underwent neoadjuvant chemotherapy and neoadjuvant endocrine therapy. LNs were sectioned at 2-mm intervals and washed with phosphate-buffered saline. Cells suspended in the lavage fluid of sectioned LNs were centrifuged and lysed to extract protein. The extracted protein was applied to the SDB kit to diagnose LN metastasis using an automatic absorbance reader. Hematoxylin and eosin (H&amp;E) stained and washed LNs were blindly examined by pathologists using intraoperative and permanent histological examination. Diagnoses based on SDB kit and automatic reader findings were compared with diagnoses made by permanent histological examination of paraffin-embedded H&amp;E-stained sections of LNs. Primary endpoints were the sensitivity, specificity, and overall agreement of the SDB kit for distinguishing macrometastases from non-macrometastases. Results: Ninety-four of the 924 LNs were assessed as macrometastases, 40 as micrometastases, and 790 as isolated tumor cells by histological examination. Compared with patients with non-macrometastases, those with macrometastases had significantly younger age (p&amp;lt; 0.01), larger primary tumor (p&amp;lt; 0.01), higher nuclear grade (p=0.04), increased lymphatic invasion (p&amp;lt; 0.01), and increased venous invasion (p=0.01). Using a borderline CK19 absorbance of 11.9 milli-absorbance for detecting macrometastases with an area under the curve of 0.989, the sensitivity, specificity, and overall agreement of the SDB kit were 94.7%, 98.3%, and 97.9%, respectively. Moreover, the sensitivity, specificity, and overall agreement of the intraoperative histological examination compared with permanent histological examination for distinguishing macrometastases from non-macrometastases were 91.4%, 99.1%, and 98.3%, respectively. Furthermore, the kits and automatic reader yielded diagnoses within approximately 20 min at a cost of &amp;lt; 30 USD for the SDB kit and &amp;lt; 3,000 USD for the automatic reader. Conclusions: The kits with an automatic reader used in our study were accurate, quick, and cost-effective in diagnosing LN metastases without the loss of LN tissue and were particularly useful for distinguishing macrometastases. We plan to make the SDB kit and automatic reader commercially available worldwide soon. Citation Format: Megumi Matsumoto, Masaaki Baba, Aya Tanaka, Sayaka Kuba, Michi Morita, Fujiko Kaseida, Hiroko Hayashi, Shigeto Maeda, Hiroshi Yano, Eiko Inamasu, Akiko Ogiya, Kenta Sekiya, Masahiro Nakashima, Hideki Ikari, Shinji Ohno, Hiroyuki Takei, Katsunori Yanagihara, Susumu Eguchi, Takeshi Nagayasu, Ryota Otsubo. Evaluation of novel diagnostic kits using the semi-dry dot-blot method combined with an automatic reader for detecting metastases in sentinel lymph nodes of patients with breast cancer: a multi-center prospective study [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P5-01-03.

Category-aware feature attribution for Self-Optimizing medical image classification

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance for automatic medical image classification. Although remarkable advancement has been made, they have not demonstrated sufficiently accurate and robust results for clinical use. In addition, they are limited by the unavoidable hard samples and minority class samples. Meanwhile, it is hard to understand the prediction mechanism and debug the wrong prediction. To address these issues, this paper proposes a Self-Optimizing medical image classification framework based on category-aware feature attribution, which automatically performs model diagnosis, repairing, and enhancement. On one hand, we introduce selective filter restraining to alleviate the disturbance of misclassified features for hard samples. On the other hand, we introduce sample-specific fine-tuning to promote category-wise feature learning, especially for minority classes. The Self-Optimizing framework is a versatile module for other medical image classifiers based on mainstream CNN structures. We extensively validated the proposed method on three typical yet challenging medical image classification tasks: (i) skin lesion classification from dermoscopic images in the International Skin Imaging Collaboration (ISIC) 2019 dataset, (ii) breast cancer classification from ultrasound images in Breast Ultrasound Images (BUSI) dataset, and (iii) breast tumour classification from histopathologic scans of lymph node sections in PatchCamelyon (PCam) dataset. Experimental results demonstrate that the proposed framework achieves 1%∼5% performance gain for various classifiers, brings better explainability, and can be applied to incremental learning scenarios.

MRI/PET multimodal imaging of the innate immune response in skeletal muscle and draining lymph node post vaccination in rats.

The goal of this study was to utilize a multimodal magnetic resonance imaging (MRI) and positron emission tomography (PET) imaging approach to assess the local innate immune response in skeletal muscle and draining lymph node following vaccination in rats using two different vaccine platforms (AS01 adjuvanted protein and lipid nanoparticle (LNP) encapsulated Self-Amplifying mRNA (SAM)). MRI and 18FDG PET imaging were performed temporally at baseline, 4, 24, 48, and 72 hr post Prime and Prime-Boost vaccination in hindlimb with Cytomegalovirus (CMV) gB and pentamer proteins formulated with AS01, LNP encapsulated CMV gB protein-encoding SAM (CMV SAM), AS01 or with LNP carrier controls. Both CMV AS01 and CMV SAM resulted in a rapid MRI and PET signal enhancement in hindlimb muscles and draining popliteal lymph node reflecting innate and possibly adaptive immune response. MRI signal enhancement and total 18FDG uptake observed in the hindlimb was greater in the CMV SAM vs CMV AS01 group (↑2.3 - 4.3-fold in AUC) and the MRI signal enhancement peak and duration were temporally shifted right in the CMV SAM group following both Prime and Prime-Boost administration. While cytokine profiles were similar among groups, there was good temporal correlation only between IL-6, IL-13, and MRI/PET endpoints. Imaging mass cytometry was performed on lymph node sections at 72 hr post Prime and Prime-Boost vaccination to characterize the innate and adaptive immune cell signatures. Cell proximity analysis indicated that each follicular dendritic cell interacted with more follicular B cells in the CMV AS01 than in the CMV SAM group, supporting the stronger humoral immune response observed in the CMV AS01 group. A strong correlation between lymph node MRI T2 value and nearest-neighbor analysis of follicular dendritic cell and follicular B cells was observed (r=0.808, P<0.01). These data suggest that spatiotemporal imaging data together with AI/ML approaches may help establish whether in vivo imaging biomarkers can predict local and systemic immune responses following vaccination.

A Deep Neural Network–Based Decision Support Tool for the Detection of Lymph Node Metastases in Colorectal Cancer Specimens

The identification of lymph node metastases in colorectal cancer (CRC) specimens is crucial for the planning of postoperative treatment and can be a time-consuming task for pathologists. In this study, we developed a deep neural network (DNN) algorithm for the detection of metastatic CRC in digitized histologic sections of lymph nodes and evaluated its performance as a diagnostic support tool. First, the DNN algorithm was trained using pixel-level annotations of cancerous areas on 758 whole slide images (360 with cancerous areas). The algorithm’s performance was evaluated on 74 whole slide images (43 with cancerous areas). Second, the algorithm was evaluated as a decision support tool on 288 whole slide images covering 1517 lymph node sections, randomized in 16 batches. Two senior pathologists (C.K. and C.O.) assessed each batch with and without the help of the algorithm in a 2 × 2 crossover design, with a washout period of 1 month in between. The time needed for the evaluation of each node section was recorded. The DNN algorithm achieved a median pixel-level accuracy of 0.952 on slides with cancerous areas and 0.996 on slides with benign samples. N+ disease (metastases, micrometastases, or tumor deposits) was present in 103 of the 1517 sections. The algorithm highlighted cancerous areas in 102 of these sections, with a sensitivity of 0.990. Assisted by the algorithm, the median time needed for evaluation was significantly shortened for both pathologists (median time for pathologist 1, 26 vs 14 seconds; P < .001; 95% CI, 11.0-12.0; median time for pathologist 2, 25 vs 23 seconds; P < .001; 95% CI, 2.0-4.0). Our DNN showed high accuracy for detecting metastatic CRC in digitized histologic sections of lymph nodes. This decision support tool has the potential to improve the diagnostic workflow by shortening the time needed for the evaluation of lymph nodes in CRC specimens without impairing diagnostic accuracy.

Robotic upper lobe segmentectomy: technical pearls

: Minimally invasive approaches to segmentectomy have grown in popularity as sublobar resection has been increasingly offered as a parenchyma-sparing alternative to lobectomy for amenable lesions. Both video-assisted thoracic surgery and robotic surgery offer advantages over traditional thoracotomy, with fewer complications, shortened hospital stay, and less pain. While segmentectomy has been traditionally performed by video-assisted thoracic surgery, the robotic approach represents a growing subset of minimally invasive sublobar resections. Patient selection for robotic segmentectomy involves a standard preoperative evaluation including pulmonary function tests, cardiac evaluation, and complete staging. Preoperative axial imaging is essential in choosing patients with lesions amenable to segmentectomy, and evaluating the segmental anatomy. Safe robotic segmentectomy centers around thorough knowledge of the segmental vascular and bronchial anatomy and its variants, and preoperative imaging can help the surgeon anticipate variant anatomy intraoperatively. The operative technique generally involves a mediastinal lymph node dissection with frozen section of the N1 nodes and conversion to lobectomy if positive. The segmental resection then proceeds depending on the individual segment to be resected, but generally involves dissection and division of the vessels and bronchus, followed by division of the parenchyma along the intersegmental plane. For most patients, postoperative recovery is short and uncomplicated, with most patients being discharged on the first or second postoperative day.

Tensile strength of various bamboo species tested with different shape of test specimens

Bamboo has a different tensile strength at the bottom, middle and top, both at the node and internode part of the bamboo. Tensile strength obtained by tension test with several standard testing methods that use different specimen shapes in the testing process. This study compared standard test methods that use dog bone-shaped specimens and strip-shaped specimens to see the correction of the tensile strength of bamboo from the same culm but tested differently. The test specimens are carried out from the area of Asahan Regency (including Tanjung Balai City), Batubara Regency, and Simalungun Regency, which are located in the eastern region of Sumatera Utara. The tension tests are carried out from the bottom, middle, and top section of the bamboo culm, and tested using a Universal Testing Machine. The average water content from bamboo species tested in this study is 14%. The strength ratio of the bottom, middle, and top section (B:M:T ratio) of dog bone-shaped specimens is 1.57: 1.24: 1, while B:M:T ratio of the strip-shaped specimen is 1.15: 1.05: 1. The tensile strength difference of dog bone-specimens from node and internode section is 31.89%, while the difference from the strip-shaped specimen is 13.81%. These results indicate that the bottom part of the bamboo culm has greater tensile strength, regardless of the shape of the specimens, followed by the middle part, and the top part respectively.

Detection of micro-metastasis using cytokeratins (AE1/AE3) in haematoxylin & eosin-stained N0 lymph nodes of oral squamous cell carcinoma.

Oral squamous cell carcinoma (OSCC) is one of the most common malignancies affecting the head-and-neck region, regional lymph nodes being an important prognostication factor dictating the survival rate. Despite an array of modalities used, clinically, radiographically and routine histopathologically, the detection of micro-metastasis (2-3 mm tumour cell deposits) in the lymph nodes often escapes identification. The presence of few of these tumour epithelial cells in the lymph nodes drastically increases mortality and alters treatment plan. Hence, the identification of these cells is of major prognostic significance for a patient. Thus, the present study was aimed to evaluate and detect the efficacy of the immunohistochemical (IHC) marker [cytokeratin (CK) AE1/AE3] over routine Hematoxylin & eosin (H & E) staining in detecting micro-metastasis in the lymph nodes of OSCC cases. Hundred H & E-stained N0 lymph nodes of OSCC cases treated with radical neck dissection were subjected to IHC with marker AE1/AE3 antibody cocktail for detecting micro-metastasis. The IHC marker CK cocktail (AE1/AE3) did not demonstrate any positive reactivity for the target antigen in all the 100 H & E stained lymph node sections evaluated in the present study. This study was undertaken to check the efficacy of IHC (CK cocktail AE1/AE3) in the detection of micro-metastasis in lymph nodes that are found to be negative in routine H&E stained sections. The findings of this study suggest that the IHC marker AE1/AE3 did not prove to be useful to detect micro-metastasis in this study population.

Micrometastasis detection using modified papanicolaou stain in nodal tissues of oral squamous cell carcinoma - A histological study.

Cervical lymph node metastasis is the most important prognostic factor in Squamous Cell Carcinoma of Head and Neck (SCCHN). Detection and evaluation of micro-metastasis forms the basis for diagnosis, staging, treatment options and prognosis. Lymph node prognostic factors are extremely important for the survival and recurrence in the patient. Assessing lymph node metastasis in the absence of clinical enlargement is challenging. To evaluate micrometastasis and individual tumor cells (ITC) in regional lymph nodes of oral squamous cell carcinoma (OSCC) by modified papanicolaou (PAP) stain and re-evaluate the tumor staging. The retrospective study was executed at MS Ramaiah University of Applied Sciences. The current study constituted a total of 40 lymph nodes from OSCC patients, metastatic (n=20) and non-metastatic lymph nodes (n=20). All sections were stained with H & E followed by modified PAP stain. Modified PAP was used for identification of micrometastasis deposits. The Chi square test was employed to analyze significance. Modified PAP stain proved to be more accurate (p = 0.006) than H and E stain in detecting micrometastasis which accounted for 15% of non-metastatic lymph node sections used in our study. Special stain like modified PAP stain is valuable and sensitive in detecting micro-metastasis over H and E stain. Detection of micrometastasis in OSCC patients is advantageous for the patient as it influences staging, it modifies the treatment plan in terms of both radiotherapy and chemotherapy.