Deformed graphene FET biosensor on textured glass coupled with dielectrophoretic trapping for ultrasensitive detection of GFAP

Numerous efforts have been undertaken to mitigate the Debye screening effect of FET biosensors for achieving higher sensitivity. There are few reports that show sub-femtomolar detection of biomolecules by FET mechanisms but they either suffer from significant background noise or lack robust control. In this aspect, deformed/crumpled graphene has been recently deployed by other researchers for various biomolecule detection like DNA, COVID-19 spike proteins and immunity markers like IL-6 at sub-femtomolar levels. However, the chemical vapor deposition (CVD) approach for graphene fabrication suffers from various surface contamination while the transfer process induces structural defects. In this paper, an alternative fabrication methodology has been proposed where glass substrate has been initially texturized by wet chemical etching through the sacrificial layer of synthesized silver nanoparticles, obtained by annealing of thin silver films leading to solid state dewetting. Graphene has been subsequently deposited by thermal reduction technique from graphene oxide solution. The resulting deformed graphene structure exhibits higher sensor response towards glial fibrillary acidic protein (GFAP) detection with respect to flat graphene owing to the combined effect of reduced Debye screening and higher surface area for receptor immobilization. Additionally, another interesting aspect of the reported work lies in the biomolecule capture by dielectrophoretic (DEP) transport on the crests of the convex surfaces of graphene in a coplanar gated topology structure which has resulted in 10 aM and 28 aM detection limits of GFAP in buffer and undiluted plasma respectively, within 15 min of application of analyte. The detection limit in buffer is almost four decades lower than that documented for GFAP using biosensors which is is expected to pave way for advancing graphene FET based sensors towards ultrasensitive point-of-care diagnosis of GFAP, a biomarker for traumatic brain injury.

Enhancing chest X-ray datasets with privacy-preserving large language models and multi-type annotations: a data-driven approach for improved classification

In chest X-ray (CXR) image analysis, rule-based systems are usually employed to extract labels from reports, but concerns exist about label quality. These datasets typically offer only presence labels, sometimes with binary uncertainty indicators, which limits their usefulness. In this work, we present MAPLEZ (Medical report Annotations with Privacy-preserving Large language model using Expeditious Zero shot answers), a novel approach leveraging a locally executable Large Language Model (LLM) to extract and enhance findings labels on CXR reports. MAPLEZ extracts not only binary labels indicating the presence or absence of a finding but also the location, severity, and radiologists' uncertainty about the finding. Over eight abnormalities from five test sets, we show that our method can extract these annotations with an increase of 5 percentage points (pp) in F1 score for categorical presence annotations and more than 30 pp increase in F1 score for the location annotations over competing labelers. Additionally, using these improved annotations in classification supervision, we demonstrate substantial advancements in model quality, with an increase of 1.7 pp in AUROC over models trained with annotations from the state-of-the-art approach. We share code and annotations.

Cryopreservation and assessment of genetic fidelity Acorus calamus Linn., an endangered medicinal plant

BACKGROUND

Acorus calamus Linn. is a medicinally valuable monocot plant belonging to the family Acoraceae. Over-exploitation and unscientific approach towards harvesting to fulfill an ever-increasing demand have placed it in the endangered list of species.

OBJECTIVE

To develop vitrification-based cryopreservation protocols for A. calamus shoot tips, using conventional vitrification and V cryo-plate.

MATERIALS AND METHODS

Shoot tips (2 mm in size) were cryopreserved with the above techniques by optimizing various parameters such as preculture duration, sucrose concentration in the preculture medium, and PVS2 dehydration time. Regenerated plantlets obtained post-cryopreservation were evaluated by random amplified polymorphic DNA (RAPD) to test their genetic fidelity.

RESULTS

The highest regrowth of 88.3% after PVS2 exposure of 60 min was achieved with V cryo-plate as compared to 75% after 90 min of PVS2 exposure using conventional vitrification. After cryopreservation, shoot tips developed into complete plantlets in 28 days on regrowth medium (0.5 mg/L BAP, 0.3 mg/L GA3, and 0.3 mg/L ascorbic acid). RAPD analysis revealed 100% monomorphism in all cryo-storage derived regenerants and in vitro donor (120-days-old) plants.

CONCLUSION

Shoot tips of A. calamus that were cryopreserved had 88.3% regrowth using V cryo-plate technique and the regerants retained genetic fidelity. https://doi.org/10.54680/fr24210110412.

Segmentation of pelvic structures in T2 MRI via MR-to-CT synthesis

Segmentation of multiple pelvic structures in MRI volumes is a prerequisite for many clinical applications, such as sarcopenia assessment, bone density measurement, and muscle-to-fat volume ratio estimation. While many CT-specific datasets and automated CT-based multi-structure pelvis segmentation methods exist, there are few MRI-specific multi-structure segmentation methods in literature. In this pilot work, we propose a lightweight and annotation-free pipeline to synthetically translate T2 MRI volumes of the pelvis to CT, and subsequently leverage an existing CT-only tool called TotalSegmentator to segment 8 pelvic structures in the generated CT volumes. The predicted masks were then mapped back to the original MR volumes as segmentation masks. We compared the predicted masks against the expert annotations of the public TCGA-UCEC dataset and an internal dataset. Experiments demonstrated that the proposed pipeline achieved Dice measures ≥65% for 8 pelvic structures in T2 MRI. The proposed pipeline is an alternative method to obtain multi-organ and structure segmentations without being encumbered by time-consuming manual annotations. By exploiting the significant research progress in CTs, it is possible to extend the proposed pipeline to other MRI sequences in principle. Our research bridges the chasm between the current CT-based multi-structure segmentation and MRI-based segmentation. The manually segmented structures in the TCGA-UCEC dataset are publicly available.

Weakly Supervised Detection of Pheochromocytomas and Paragangliomas in CT

Pheochromocytomas and Paragangliomas (PPGLs) are rare adrenal and extra-adrenal tumors which have the potential to metastasize. For the management of patients with PPGLs, CT is the preferred modality of choice for precise localization and estimation of their progression. However, due to the myriad variations in size, morphology, and appearance of the tumors in different anatomical regions, radiologists are posed with the challenge of accurate detection of PPGLs. Since clinicians also need to routinely measure their size and track their changes over time across patient visits, manual demarcation of PPGLs is quite a time-consuming and cumbersome process. To ameliorate the manual effort spent for this task, we propose an automated method to detect PPGLs in CT studies via a proxy segmentation task. As only weak annotations for PPGLs in the form of prospectively marked 2D bounding boxes on an axial slice were available, we extended these 2D boxes into weak 3D annotations and trained a 3D full-resolution nnUNet model to directly segment PPGLs. We evaluated our approach on a dataset consisting of chest-abdomen-pelvis CTs of 255 patients with confirmed PPGLs. We obtained a precision of 70% and sensitivity of 64.1% with our proposed approach when tested on 53 CT studies. Our findings highlight the promising nature of detecting PPGLs via segmentation, and furthers the state-of-the-art in this exciting yet challenging area of rare cancer management.

Automated Classification of Body MRI Sequence Type Using Convolutional Neural Networks

Multi-parametric MRI of the body is routinely acquired for the identification of abnormalities and diagnosis of diseases. However, a standard naming convention for the MRI protocols and associated sequences does not exist due to wide variations in imaging practice at institutions and myriad MRI scanners from various manufacturers being used for imaging. The intensity distributions of MRI sequences differ widely as a result, and there also exists information conflicts related to the sequence type in the DICOM headers. At present, clinician oversight is necessary to ensure that the correct sequence is being read and used for diagnosis. This poses a challenge when specific series need to be considered for building a cohort for a large clinical study or for developing AI algorithms. In order to reduce clinician oversight and ensure the validity of the DICOM headers, we propose an automated method to classify the 3D MRI sequence acquired at the levels of the chest, abdomen, and pelvis. In our pilot work, our 3D DenseNet-121 model achieved an F1 score of 99.5% at differentiating 5 common MRI sequences obtained by three Siemens scanners (Aera, Verio, Biograph mMR). To the best of our knowledge, we are the first to develop an automated method for the 3D classification of MRI sequences in the chest, abdomen, and pelvis, and our work has outperformed the previous state-of-the-art MRI series classifiers.

Automated detection of incidental abdominal aortic aneurysms on computed tomography

PURPOSE

To detect and assess abdominal aortic aneurysms (AAAs) on CT in a large asymptomatic adult patient population using fully-automated deep learning software.

MATERIALS AND METHODS

The abdominal aorta was segmented using a fully-automated deep learning model trained on 66 manually-segmented abdominal CT scans from two datasets. The axial diameters of the segmented aorta were extracted to detect the presence of AAAs-maximum axial aortic diameter greater than 3 cm were labeled as AAA positive. The trained system was then externally-validated on CT colonography scans of 9172 asymptomatic outpatients (mean age, 57 years) referred for colorectal cancer screening. Using a previously-validated automated calcified atherosclerotic plaque detector, we correlated abdominal aortic Agatston and volume scores with the presence of AAA.

RESULTS

The deep learning software detected AAA on the external validation dataset with a sensitivity, specificity, and AUC of 96%, (95% CI 89%, 100%), 96% (96%, 97%), and 99% (98%, 99%) respectively. The Agatston and volume scores of reported AAA-positive cases were statistically significantly greater than those of reported AAA-negative cases (p < 0.0001). Using plaque alone as a AAA detector, at a threshold Agatston score of 2871, the sensitivity and specificity were 84% (73%, 94%) and 87% (86%, 87%), respectively.

CONCLUSION

Fully-automated detection and assessment of AAA on CT is feasible and accurate. There was a strong statistical association between the presence of AAA and the quantity of abdominal aortic calcified atherosclerotic plaque.

Longitudinal follow-up of incidental renal calculi on computed tomography

RATIONALE AND OBJECTIVES

Measuring small kidney stones on CT is a time-consuming task often neglected. Volumetric assessment provides a better measure of size than linear dimensions. Our objective is to analyze the growth rate and prognosis of incidental kidney stones in asymptomatic patients on CT.

MATERIALS AND METHODS

This retrospective study included 4266 scans from 2030 asymptomatic patients who underwent two or more nonenhanced CT scans for colorectal screening between 2004 and 2016. The DL software identified and measured the volume, location, and attenuation of 883 stones. The corresponding scans were manually evaluated, and patients without follow-up were excluded. At each follow-up, the stones were categorized as new, growing, persistent, or resolved. Stone size (volume and diameter), attenuation, and location were correlated with the outcome and growth rates of the stones.

RESULTS

The stone cohort comprised 407 scans from 189 (M: 124, F: 65, median age: 55.4 years) patients. The median number of stones per scan was 1 (IQR: [1, 2]). The median stone volume was 17.1 mm3 (IQR: [7.4, 43.6]) and the median peak attenuation was 308 HU (IQR: [204, 532]. The 189 initial scans contained 291stones; 91 (31.3%) resolved, 142 (48.8%) grew, and 58 (19.9) remained persistent at the first follow-up. At the second follow-up (for 27 patients with 2 follow-ups), 14/44 (31.8%) stones had resolved, 19/44 (43.2%) grew and 11/44 (25%) were persistent. The median growth rate of growing stones was 3.3 mm3/year, IQR: [1.4,7.4]. Size and attenuation had a moderate correlation (Spearman rho 0.53, P < .001 for volume, and 0.50 P < .001 for peak attenuation) with the growth rate. Growing and persistent stones had significantly greater maximum axial diameter (2.7 vs 2.3 mm, P =.047) and peak attenuation (300 vs 258 HU, P =.031) CONCLUSION: We report a 12.7% prevalence of incidental kidney stones in asymptomatic adults, of which about half grew during follow-up with a median growth rate of about 3.3 mm3/year.

Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports

Despite the reduction in turn-around times in radiology reporting with the use of speech recognition software, persistent communication errors can significantly impact the interpretation of radiology reports. Pre-filling a radiology report holds promise in mitigating reporting errors, and despite multiple efforts in literature to generate comprehensive medical reports, there lacks approaches that exploit the longitudinal nature of patient visit records in the MIMIC-CXR dataset. To address this gap, we propose to use longitudinal multi-modal data, i.e., previous patient visit CXR, current visit CXR, and the previous visit report, to pre-fill the "findings" section of the patient's current visit. We first gathered the longitudinal visit information for 26,625 patients from the MIMIC-CXR dataset, and created a new dataset called Longitudinal-MIMIC. With this new dataset, a transformer-based model was trained to capture the multi-modal longitudinal information from patient visit records (CXR images + reports) via a cross-attention-based multi-modal fusion module and a hierarchical memory-driven decoder. In contrast to previous works that only uses current visit data as input to train a model, our work exploits the longitudinal information available to pre-fill the "findings" section of radiology reports. Experiments show that our approach outperforms several recent approaches. Code will be published at https://github.com/CelestialShine/Longitudinal-Chest-X-Ray.

Utilizing Longitudinal Chest X-Rays and Reports to Pre-fill Radiology Reports

Despite the reduction in turn-around times in radiology reporting with the use of speech recognition software, persistent communication errors can significantly impact the interpretation of radiology reports. Pre-filling a radiology report holds promise in mitigating reporting errors, and despite multiple efforts in literature to generate comprehensive medical reports, there lacks approaches that exploit the longitudinal nature of patient visit records in the MIMIC-CXR dataset. To address this gap, we propose to use longitudinal multi-modal data, i.e., previous patient visit CXR, current visit CXR, and the previous visit report, to pre-fill the "findings" section of the patient's current visit. We first gathered the longitudinal visit information for 26,625 patients from the MIMIC-CXR dataset, and created a new dataset called Longitudinal-MIMIC. With this new dataset, a transformer-based model was trained to capture the multi-modal longitudinal information from patient visit records (CXR images + reports) via a cross-attention-based multi-modal fusion module and a hierarchical memory-driven decoder. In contrast to previous works that only uses current visit data as input to train a model, our work exploits the longitudinal information available to pre-fill the "findings" section of radiology reports. Experiments show that our approach outperforms several recent approaches by ≥3% on F1 score, and ≥2% for BLEU-4, METEOR and ROUGE-L respectively. Code will be published at https://github.com/CelestialShine/Longitudinal-Chest-X-Ray.

Feasibility of Using the Privacy-preserving Large Language Model Vicuna for Labeling Radiology Reports

Background Large language models (LLMs) such as ChatGPT, though proficient in many text-based tasks, are not suitable for use with radiology reports due to patient privacy constraints. Purpose To test the feasibility of using an alternative LLM (Vicuna-13B) that can be run locally for labeling radiography reports. Materials and Methods Chest radiography reports from the MIMIC-CXR and National Institutes of Health (NIH) data sets were included in this retrospective study. Reports were examined for 13 findings. Outputs reporting the presence or absence of the 13 findings were generated by Vicuna by using a single-step or multistep prompting strategy (prompts 1 and 2, respectively). Agreements between Vicuna outputs and CheXpert and CheXbert labelers were assessed using Fleiss κ. Agreement between Vicuna outputs from three runs under a hyperparameter setting that introduced some randomness (temperature, 0.7) was also assessed. The performance of Vicuna and the labelers was assessed in a subset of 100 NIH reports annotated by a radiologist with use of area under the receiver operating characteristic curve (AUC). Results A total of 3269 reports from the MIMIC-CXR data set (median patient age, 68 years [IQR, 59-79 years]; 161 male patients) and 25 596 reports from the NIH data set (median patient age, 47 years [IQR, 32-58 years]; 1557 male patients) were included. Vicuna outputs with prompt 2 showed, on average, moderate to substantial agreement with the labelers on the MIMIC-CXR (κ median, 0.57 [IQR, 0.45-0.66] with CheXpert and 0.64 [IQR, 0.45-0.68] with CheXbert) and NIH (κ median, 0.52 [IQR, 0.41-0.65] with CheXpert and 0.55 [IQR, 0.41-0.74] with CheXbert) data sets, respectively. Vicuna with prompt 2 performed at par (median AUC, 0.84 [IQR, 0.74-0.93]) with both labelers on nine of 11 findings. Conclusion In this proof-of-concept study, outputs of the LLM Vicuna reporting the presence or absence of 13 findings on chest radiography reports showed moderate to substantial agreement with existing labelers. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Cai in this issue.

SCOPE: predicting future diagnoses in office visits using electronic health records

We propose an interpretable and scalable model to predict likely diagnoses at an encounter based on past diagnoses and lab results. This model is intended to aid physicians in their interaction with the electronic health records (EHR). To accomplish this, we retrospectively collected and de-identified EHR data of 2,701,522 patients at Stanford Healthcare over a time period from January 2008 to December 2016. A population-based sample of patients comprising 524,198 individuals (44% M, 56% F) with multiple encounters with at least one frequently occurring diagnosis codes were chosen. A calibrated model was developed to predict ICD-10 diagnosis codes at an encounter based on the past diagnoses and lab results, using a binary relevance based multi-label modeling strategy. Logistic regression and random forests were tested as the base classifier, and several time windows were tested for aggregating the past diagnoses and labs. This modeling approach was compared to a recurrent neural network based deep learning method. The best model used random forest as the base classifier and integrated demographic features, diagnosis codes, and lab results. The best model was calibrated and its performance was comparable or better than existing methods in terms of various metrics, including a median AUROC of 0.904 (IQR [0.838, 0.954]) over 583 diseases. When predicting the first occurrence of a disease label for a patient, the median AUROC with the best model was 0.796 (IQR [0.737, 0.868]). Our modeling approach performed comparably as the tested deep learning method, outperforming it in terms of AUROC (p < 0.001) but underperforming in terms of AUPRC (p < 0.001). Interpreting the model showed that the model uses meaningful features and highlights many interesting associations among diagnoses and lab results. We conclude that the multi-label model performs comparably with RNN based deep learning model while offering simplicity and potentially superior interpretability. While the model was trained and validated on data obtained from a single institution, its simplicity, interpretability and performance makes it a promising candidate for deployment.

Cryopreservation of zygotic embryos of Podophyllum hexandrum Royle, an endangered medicinal plant, by vitrification and v cryo-plate techniques

BACKGROUND

Podophyllum hexandrum is a highly endangered valuable medicinal plant of the Himalayas belonging to family Berberidaceae. This plant needs conservation efforts due to the over-exploitation and unscrupulous harvesting from the wild because of its ever-increasing demand.

OBJECTIVE

To establish a long-term cryopreservation method for Podophyllum hexandrum using two techniques: Vitrification and V Cryo-plate.

MATERIALS AND METHODS

Zygotic embryos were cryopreserved using vitrification and V cryo-plate by optimization of parameters including preculture time, loading time and PVS2 dehydration time. Recovery of zygotic embryos was performed on different regrowth media for plantlet formation.

RESULTS

With V cryo-plate, 90% regrowth was obtained as compared to 73.3% with vitrification. V Cryo-plate conditions were pre-culture of zygotic embryos in 0.3 M sucrose for 4 days, treatment in loading solution with 0.8 M sucrose for 20 min, dehydration in PVS2 for 50 min, LN exposure, unloading in 1.2 M sucrose for 20 min and transfer of zygotic embryos to regrowth medium for recovery. During recovery, the maximum number of shoots (4.2) and highest shoot length (5.1 cm) were observed on regrowth medium with 1.5 mg per liter BAP and 0.1 mg per liter IAA (R7).

CONCLUSION

Zygotic embryos of Podophyllum hexandrum were cryopreserved with 90% regrowth using a V cryoplate technique and plantlets were produced directly after cryopreservation. Doi: 10.54680/fr23410110712.

Performance of alternative manual and automated deep learning segmentation techniques for the prediction of benign and malignant lung nodules

Purpose

We aim to evaluate the performance of radiomic biopsy (RB), best-fit bounding box (BB), and a deep-learning-based segmentation method called no-new-U-Net (nnU-Net), compared to the standard full manual (FM) segmentation method for predicting benign and malignant lung nodules using a computed tomography (CT) radiomic machine learning model.

Materials and Methods

A total of 188 CT scans of lung nodules from 2 institutions were used for our study. One radiologist identified and delineated all 188 lung nodules, whereas a second radiologist segmented a subset (n = 20 ) of these nodules. Both radiologists employed FM and RB segmentation methods. BB segmentations were generated computationally from the FM segmentations. The nnU-Net, a deep-learning-based segmentation method, performed automatic nodule detection and segmentation. The time radiologists took to perform segmentations was recorded. Radiomic features were extracted from each segmentation method, and models to predict benign and malignant lung nodules were developed. The Kruskal-Wallis and DeLong tests were used to compare segmentation times and areas under the curve (AUC), respectively.

Results

For the delineation of the FM, RB, and BB segmentations, the two radiologists required a median time (IQR) of 113 (54 to 251.5), 21 (9.25 to 38), and 16 (12 to 64.25) s, respectively (p = 0.04 ). In dataset 1, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.964 (0.96 to 0.968), 0.985 (0.983 to 0.987), 0.961 (0.956 to 0.965), and 0.878 (0.869 to 0.888). In dataset 2, the mean AUC (95% CI) of the FM, RB, BB, and nnU-Net model were 0.717 (0.705 to 0.729), 0.919 (0.913 to 0.924), 0.699 (0.687 to 0.711), and 0.644 (0.632 to 0.657).

Conclusion

Radiomic biopsy-based models outperformed FM and BB models in prediction of benign and malignant lung nodules in two independent datasets while deep-learning segmentation-based models performed similarly to FM and BB. RB could be a more efficient segmentation method, but further validation is needed.

Fully Automated Longitudinal Assessment of Renal Stone Burden on Serial CT Imaging Using Deep Learning

Use deep learning (DL) to automate the measurement and tracking of kidney stone burden over serial computed tomography (CT) scans. Materials and Methods This retrospective study included 259 scans from 113 symptomatic patients being treated for urolithiasis at a single medical center between 2006 and 2019. These patients underwent a standard low-dose (SLD) non-contrast CT scan followed by ultra-low dose (ULD) CT scans limited to the level of the kidneys. A DL model was used to detect, segment, and measure the volume of all stones in both initial and follow-up scans. The stone burden was characterized by the total volume of all stones in a scan (SV). The absolute and relative change of SV, (SVA and SVR, respectively) over serial scans were computed. The automated assessments were compared with manual assessments using Concordance Correlation Coefficient (CCC), and their agreement was visualized using Bland-Altman and scatter plots. Results 228/233 scans with stones were identified by the automated pipeline; per-scan sensitivity was 97.8% (95% CI: [96.0 - 99.7]). The per-scan positive predictive value was 96.6% (95% CI: [94.4 - 98.8]). The median SV, SVA and SVR were 476.5 mm3, -10 mm3 and 0.89, respectively. After removing outliers outside the 5th and 95th percentiles, the CCC measuring agreement on SV, SVA and SVR were 0.995 (0.992 - 0.996), 0.980 (0.972 - 0.986), and 0.915 (0.881 - 0.939), respectively. The mean effective dose was 4.1 mSv for the ULD compared to 13.4 mSv for the SLD (p<0.01). Conclusions The automated DL-based measurements showed good agreement with the manual assessments of the stone burden and its interval change on serial CT scans.

Abstract 5618: Multi-institutional validation of a radiomics-based artificial intelligence method for predicting response to PD-1/PD-L1 immune checkpoint inhibitor (ICI) therapy in stage IV NSCLC

There is an urgent clinical need to identify patients likely to benefit from immune checkpoint inhibitor ICI treatment. Approaches available in the clinic today, such as PD-L1 immunohistochemistry (IHC) and tumor mutation burden (TMB), are insufficient for this task, in part as differences in microenvironments expressed by individual tumors may lead to heterogeneous response patterns. Recent efforts exploring the utility of quantitative imaging (radiomic) biomarkers to predict response to ICIs have shown promise to provide a more accurate and scalable method. In contrast to previously published models, our work focuses on generalizable models for predicting individual lesion-level as well as patient-level response at 3-month follow-up per RECIST criteria, using a large multi-institutional “real-world” dataset. The models combine radiomics features with demographic, molecular, and laboratory values routinely available in patients’ electronic medical records. We analyzed radiomic characteristics of 6,295 primary and metastatic lesions from 1,206 metastatic NSCLC patients treated with anti-PD-1/anti-PD-L1 ICIs from 8 institutions across the US and Europe. Patients with unavailable PD-L1 IHC, imaging follow-up, or with oncogenic driver mutations were excluded from analysis, resulting in a total dataset of 766 subjects randomly assigned to training (N=514) and validation sets (N=252). Using gradient-boosted decision tree algorithms, we developed a multi-modal predictive model to identify patients responding to ICI therapy at 3-months and evaluated its performance against an imaging-only CT radiomics model and the clinical standard of care, biopsy-based PD-L1 IHC. The multi-modal model contains CT radiomic features capturing lesion heterogeneity and spicularity, patient demographics, PD-L1 TPS, and tumor burden volume in the lung, lymph nodes, and the liver. Under the two-tailed DeLong test, the multi-modal model demonstrated statistically significant benefit over the current standard of care (PD-L1 IHC) in predicting multi-lesion 3-month response: 0.81 (P=.005) area under the receiver operating characteristic curve (ROC-AUC) in first-line ICI monotherapy patients, 0.72 (P=.044) in all-lines ICI monotherapy, and 0.71 (P=.025) in all-lines ICI-chemotherapy combination. The imaging-only model demonstrated predictive performance comparable to PD-L1 IHC: 0.71 (P=.226), 0.61 (P=.905), 0.62 (P=.674) on the same cohorts respectively. A multi-modal CT radiomics-based approach demonstrated predictive accuracy benefit over the current clinical standard and may provide an opportunity for more personalized patient management, such as risk-based escalation/de-escalation of concurrent chemotherapy in NSCLC patients. We will evaluate this methodology in prospective studies.

Citation Format: Ravi B. Parikh, Petr Jordan, Rita J. Ciaravino, Ryan A. Beasley, Arpan A. Patel, Dwight H. Owen, Arya Amini, Brendan D. Curti, Ray Page, Aurelie Swalduz, Jean-Paul Beregi, Jan Chrusciel, Eric Snyder, Pritam Mukherjee, Heather M. Selby, Soohee Lee, Roshanthi Weerasinghe, Shwetha Pindikuri, Jakob B. Weiss, Andrew L. Wentland, Anish Kirpalani, An Liu, Olivier Gevaert, George Simon, Hugo JWL Aerts. Multi-institutional validation of a radiomics-based artificial intelligence method for predicting response to PD-1/PD-L1 immune checkpoint inhibitor (ICI) therapy in stage IV NSCLC. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5618.

Multimodal deep learning to predict prognosis in adult and pediatric brain tumors

BACKGROUND

The introduction of deep learning in both imaging and genomics has significantly advanced the analysis of biomedical data. For complex diseases such as cancer, different data modalities may reveal different disease characteristics, and the integration of imaging with genomic data has the potential to unravel additional information than when using these data sources in isolation. Here, we propose a DL framework that combines these two modalities with the aim to predict brain tumor prognosis.

METHODS

Using two separate glioma cohorts of 783 adults and 305 pediatric patients we developed a DL framework that can fuse histopathology images with gene expression profiles. Three strategies for data fusion were implemented and compared: early, late, and joint fusion. Additional validation of the adult glioma models was done on an independent cohort of 97 adult patients.

RESULTS

Here we show that the developed multimodal data models achieve better prediction results compared to the single data models, but also lead to the identification of more relevant biological pathways. When testing our adult models on a third brain tumor dataset, we show our multimodal framework is able to generalize and performs better on new data from different cohorts. Leveraging the concept of transfer learning, we demonstrate how our pediatric multimodal models can be used to predict prognosis for two more rare (less available samples) pediatric brain tumors.

CONCLUSIONS

Our study illustrates that a multimodal data fusion approach can be successfully implemented and customized to model clinical outcome of adult and pediatric brain tumors.

Early Detection of Lung Cancer in the NLST Dataset

Lung Cancer is the leading cause of cancer mortality in the U.S. The effectiveness of standard treatments, including surgery, chemotherapy or radiotherapy, depends on several factors like type and stage of cancer, with the survival rate being much worse for later cancer stages. The National Lung Screening Trial (NLST) established that patients screened using low-dose Computed Tomography (CT) had a 15 to 20 percent lower risk of dying from lung cancer than patients screened using chest X-rays. While CT excelled at detecting small early stage malignant nodules, a large proportion of patients (> 25%) screened positive and only a small fraction (< 10%) of these positive screens actually had or developed cancer in the subsequent years. We developed a model to distinguish between high and low risk patients among the positive screens, predicting the likelihood of having or developing lung cancer at the current time point or in subsequent years non-invasively, based on current and previous CT imaging data. However, most of the nodules in NLST are very small, and nodule segmentations or even precise locations are unavailable. Our model comprises two stages: the first stage is a neural network model trained on the Lung Image Database Consortium (LIDC-IDRI) cohort which detects nodules and assigns them malignancy scores. The second part of our model is a boosted tree which outputs a cancer probability for a patient based on the nodule information (location and malignancy score) predicted by the first stage. Our model, built on a subset of the NLST cohort (n = 1138) shows excellent performance, achieving an area under the receiver operating characteristics curve (ROC AUC) of 0.85 when predicting based on CT images from all three time points available in the NLST dataset.

Cancer trends and burden among Armed Forces personnel, veterans and their families: Cancer registry data analysis from tertiary care hospital

Background

Cancer incidence is rising across the globe. The incidence and patterns of various cancers among Armed Forces Personnel and Veterans is not known. We did the analysis of registry data maintained at our hospital.

Methods

A retrospective analysis was performed of all patients registered at our hospital cancer registry between 01st January 2017 and 31st December 2019. Patients were registered with unique identification number. Baseline demographics and cancer subtype data were retrieved. Patients with histopathologically proven diagnosis and age ≥18 years were studied. Armed Forces Personnel (AFP) were defined as those who are in active service, and Veterans as those who had retired from service at the time of registration. Patients with Acute and Chronic Leukemias were excluded.

Results

New cases registered were 2023, 2856 and 3057 in year 2017, 2018, 2019 respectively. AFP, Veterans and dependents among them were 9.6%, 17.8%, and 72.6% respectively. Haryana, Uttar Pradesh and Rajasthan represented 55% of all cases with male to female ratio 1.14:1 and median age was 59 years. The median age among AFP was 39 years. Among AFP as well as veterans, Head and Neck cancer was the most common malignancy. Cancer incidence was significantly higher in adults >40 years as compared to <40 years.

Conclusion

Seven percent rise per year of new cases in this cohort is alarming. Tobacco-related cancers were the most common. There is an unmet need to establish a prospective centralized Cancer Registry to better understand the risk factors, outcomes of treatment and strengthen the policy matters.

Machine intelligence for radiation science: summary of the Radiation Research Society 67th annual meeting symposium

The era of high-throughput techniques created big data in the medical field and research disciplines. Machine intelligence (MI) approaches can overcome critical limitations on how those large-scale data sets are processed, analyzed, and interpreted. The 67^th Annual Meeting of the Radiation Research Society featured a symposium on MI approaches to highlight recent advancements in the radiation sciences and their clinical applications. This article summarizes three of those presentations regarding recent developments for metadata processing and ontological formalization, data mining for radiation outcomes in pediatric oncology, and imaging in lung cancer.

Identifying key multifunctional components shared by critical cancer and normal liver pathways via SparseGMM

Despite the abundance of multimodal data, suitable statistical models that can improve our understanding of diseases with genetic underpinnings are challenging to develop. Here, we present SparseGMM, a statistical approach for gene regulatory network discovery. SparseGMM uses latent variable modeling with sparsity constraints to learn Gaussian mixtures from multiomic data. By combining coexpression patterns with a Bayesian framework, SparseGMM quantitatively measures confidence in regulators and uncertainty in target gene assignment by computing gene entropy. We apply SparseGMM to liver cancer and normal liver tissue data and evaluate discovered gene modules in an independent single-cell RNA sequencing (scRNA-seq) dataset. SparseGMM identifies PROCR as a regulator of angiogenesis and PDCD1LG2 and HNF4A as regulators of immune response and blood coagulation in cancer. Furthermore, we show that more genes have significantly higher entropy in cancer compared with normal liver. Among high-entropy genes are key multifunctional components shared by critical pathways, including p53 and estrogen signaling.

Topological data analysis of thoracic radiographic images shows improved radiomics-based lung tumor histology prediction

Topological data analysis provides tools to capture wide-scale structural shape information in data. Its main method, persistent homology, has found successful applications to various machine-learning problems. Despite its recent gain in popularity, much of its potential for medical image analysis remains undiscovered. We explore the prominent learning problems on thoracic radiographic images of lung tumors for which persistent homology improves radiomic-based learning. It turns out that our topological features well capture complementary information important for benign versus malignant and adenocarcinoma versus squamous cell carcinoma tumor prediction while contributing less consistently to small cell versus non-small cell-an interesting result in its own right. Furthermore, while radiomic features are better for predicting malignancy scores assigned by expert radiologists through visual inspection, we find that topological features are better for predicting more accurate histology assessed through long-term radiology review, biopsy, surgical resection, progression, or response.

ACR White Paper on Magnetoencephalography and Magnetic Source Imaging: A Report from the ACR Commission on Neuroradiology

Magnetoencephalography, the extracranial detection of tiny magnetic fields emanating from intracranial electrical activity of neurons, and its source modeling relation, magnetic source imaging, represent a powerful functional neuroimaging technique, able to detect and localize both spontaneous and evoked activity of the brain in health and disease. Recent years have seen an increased utilization of this technique for both clinical practice and research, in the United States and worldwide. This report summarizes current thinking, presents recommendations for clinical implementation, and offers an outlook for emerging new clinical indications.

A comparative meta-analysis of membraneless organelle-associated proteins with age related proteome of C. elegans

Proteome imbalance can lead to protein misfolding and aggregation which is associated with pathologies. Protein aggregation can also be an active, organized process and can be exploited by cells as a survival strategy. In adverse conditions, it is beneficial to deposit the proteins in a condensate rather degrading and resynthesizing. Membraneless organelles (MLOs) are biological condensates formed through liquid-liquid phase separation (LLPS), involving cellular components such as nucleic acids and proteins. LLPS is a regulated process, which when perturbed, can undergo a transition from a physiological liquid condensate to pathological solid-like protein aggregates. To understand how the MLO-associated proteins (MLO-APs) behave during aging, we performed a comparative meta-analysis with age-related proteome of C. elegans. We found that the MLO-APs are highly abundant throughout the lifespan in wild-type and long-lived daf-2 mutant animals. Interestingly, they are aggregating more in long-lived mutant animals compared to the age matched wild-type and short-lived daf-16 and hsf-1 mutant animals. GO term analysis revealed that the cell cycle and embryonic development are among the top enriched processes in addition to RNP components in aggregated proteome. Considering antagonistic pleotropic nature of these developmental genes and post mitotic status of C. elegans, we assume that these proteins phase transit during post development. As the organism ages, these MLO-APs either mature to become more insoluble or dissolve in uncontrolled manner. However, in the long-lived daf-2 mutant animals, the MLOs may attain protective states due to extended availability and association of molecular chaperones.

Automated Assessment of Renal Calculi in Serial Computed Tomography Scans

An automated pipeline is developed for the serial assessment of renal calculi using computed tomography (CT) scans obtained at multiple time points. This retrospective study included 722 scans from 330 patients chosen from 8544 asymptomatic patients who underwent two or more CTC (CT colonography) or non-enhanced abdominal CT scans between 2004 and 2016 at a single medical center. A pre-trained deep learning (DL) model was used to segment the kidneys and the calculi on the CT scans at each time point. Based on the output of the DL, 330 patients were identified as having a stone candidate on at least one time point. Then, for every patient in this group, the kidneys from different time points were registered to each other, and the calculi present at multiple time points were matched to each other using proximity on the registered scans. The automated pipeline was validated by having a blinded radiologist assess the changes manually. New graph-based metrics are introduced in order to evaluate the performance of our pipeline. Our method shows high fidelity in tracking changes in renal calculi over multiple time points.

Disparities in dermatology AI performance on a diverse, curated clinical image set

An estimated 3 billion people lack access to dermatological care globally. Artificial intelligence (AI) may aid in triaging skin diseases and identifying malignancies. However, most AI models have not been assessed on images of diverse skin tones or uncommon diseases. Thus, we created the Diverse Dermatology Images (DDI) dataset-the first publicly available, expertly curated, and pathologically confirmed image dataset with diverse skin tones. We show that state-of-the-art dermatology AI models exhibit substantial limitations on the DDI dataset, particularly on dark skin tones and uncommon diseases. We find that dermatologists, who often label AI datasets, also perform worse on images of dark skin tones and uncommon diseases. Fine-tuning AI models on the DDI images closes the performance gap between light and dark skin tones. These findings identify important weaknesses and biases in dermatology AI that should be addressed for reliable application to diverse patients and diseases.

Role of animal models in biomedical research: a review

The animal model deals with the species other than the human, as it can imitate the disease progression, its’ diagnosis as well as a treatment similar to human. Discovery of a drug and/or component, equipment, their toxicological studies, dose, side effects are in vivo studied for future use in humans considering its’ ethical issues. Here lies the importance of the animal model for its enormous use in biomedical research. Animal models have many facets that mimic various disease conditions in humans like systemic autoimmune diseases, rheumatoid arthritis, epilepsy, Alzheimer’s disease, cardiovascular diseases, Atherosclerosis, diabetes, etc., and many more. Besides, the model has tremendous importance in drug development, development of medical devices, tissue engineering, wound healing, and bone and cartilage regeneration studies, as a model in vascular surgeries as well as the model for vertebral disc regeneration surgery. Though, all the models have some advantages as well as challenges, but, present review has emphasized the importance of various small and large animal models in pharmaceutical drug development, transgenic animal models, models for medical device developments, studies for various human diseases, bone and cartilage regeneration model, diabetic and burn wound model as well as surgical models like vascular surgeries and surgeries for intervertebral disc degeneration considering all the ethical issues of that specific animal model. Despite, the process of using the animal model has facilitated researchers to carry out the researches that would have been impossible to accomplish in human considering the ethical prohibitions.

Abstract 6341: ImaGene: A robust AI-based software platform for tumor radiogenomic evaluation and reporting

The field of radiomics has undergone several advancements in approaches to uncovering hidden quantitative features from tumor imaging data for use in guiding clinical decision-making for cancer patients. Radiographic imaging techniques provide insight into the imaging features of tumor regions of interest (ROIs), while immunohistochemistry and sequencing techniques performed on biopsy samples yield omics data. These imaging and omics feature data can then be correlated and modeled using artificial intelligence (AI) techniques to highlight notable associations between tumor genotype and phenotype. Currently, however, the radiogenomics field lacks a unified and robust software platform capable of algorithmically analyzing imaging and omics features using modifiable parameters, detecting significant relationships among these features, and subjecting them to AI-based analysis. To address this gap, we developed ImaGene, a robust AI-based platform that uses omics and imaging features as inputs for different tumor types, performs statistical analyses of the correlations between these data types, and constructs AI models based upon significantly correlated features. It has several modifiable configuration parameters that provide users with complete control over their experiments. For each run, ImaGene produces comprehensive reports that can contribute to the construction of a novel radiogenomic knowledge base, in addition to enabling the deployment and sharing of AI models. To demonstrate the utility of ImaGene, we acquired imaging and omics datasets pertaining to Invasive Breast Cancer (IBC) and Head and Neck Squamous Cell Carcinoma (HNSCC) from public databases and analyzed them with this platform using specific parameters. In both cases, we uncovered significant associations between several imaging features and 11 genes: CRABP1, VRTN, SMTNL2, FABP1, HAND2, HAS1, C4BPA, FAM163A, DSG1, SMTNL2 and KCNJ16 for IBC, and 10 genes: CEACAM6, IGLL1, SERPINA1, NANOG, OCA2, PRLR, ACSM2B, CYP11B1, and VPREB1 for HNSCC. Overall, our software platform is capable of identifying, analyzing, and correlating important features from tumor scans, thereby providing researchers with a reliable and accurate tool for their radiogenomics experiments. We anticipate that ImaGene will become the gold standard for tumor analyses in the field of radiogenomics owing to its ease of use, flexibility, and reproducibility.

Citation Format: Shrey S. Sukhadia, Aayush Tyagi, Vivek Venkatraman, Pritam Mukherjee, Prathosh A.P., Mayur Divate, Olivier Gevaert, Shivashankar H. Nagaraj. ImaGene: A robust AI-based software platform for tumor radiogenomic evaluation and reporting [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6341.

Strategies to Address the Lack of Labeled Data for Supervised Machine Learning Training With Electronic Health Records: Case Study for the Extraction of Symptoms From Clinical Notes

BACKGROUND

Automated extraction of symptoms from clinical notes is a challenging task owing to the multidimensional nature of symptom description. The availability of labeled training data is extremely limited owing to the nature of the data containing protected health information. Natural language processing and machine learning to process clinical text for such a task have great potential. However, supervised machine learning requires a great amount of labeled data to train a model, which is at the origin of the main bottleneck in model development.

OBJECTIVE

The aim of this study is to address the lack of labeled data by proposing 2 alternatives to manual labeling for the generation of training labels for supervised machine learning with English clinical text. We aim to demonstrate that using lower-quality labels for training leads to good classification results.

METHODS

We addressed the lack of labels with 2 strategies. The first approach took advantage of the structured part of electronic health records and used diagnosis codes (International Classification of Disease-10th revision) to derive training labels. The second approach used weak supervision and data programming principles to derive training labels. We propose to apply the developed framework to the extraction of symptom information from outpatient visit progress notes of patients with cardiovascular diseases.

RESULTS

We used >500,000 notes for training our classification model with International Classification of Disease-10th revision codes as labels and >800,000 notes for training using labels derived from weak supervision. We show that the dependence between prevalence and recall becomes flat provided a sufficiently large training set is used (>500,000 documents). We further demonstrate that using weak labels for training rather than the electronic health record codes derived from the patient encounter leads to an overall improved recall score (10% improvement, on average). Finally, the external validation of our models shows excellent predictive performance and transferability, with an overall increase of 20% in the recall score.

CONCLUSIONS

This work demonstrates the power of using a weak labeling pipeline to annotate and extract symptom mentions in clinical text, with the prospects to facilitate symptom information integration for a downstream clinical task such as clinical decision support.

Precision of MRI radiomics features in the liver and hepatocellular carcinoma

OBJECTIVES

To assess the precision of MRI radiomics features in hepatocellular carcinoma (HCC) tumors and liver parenchyma.

METHODS

The study population consisted of 55 patients, including 16 with untreated HCCs, who underwent two repeat contrast-enhanced abdominal MRI exams within 1 month to evaluate: (1) test-retest repeatability using the same MRI system (n = 28, 10 HCCs); (2) inter-platform reproducibility between different MRI systems (n = 27, 6 HCCs); (3) inter-observer reproducibility (n = 16, 16 HCCs). Shape and 1st- and 2nd-order radiomics features were quantified on pre-contrast T1-weighted imaging (WI), T1WI portal venous phase (pvp), T2WI, and ADC (apparent diffusion coefficient), on liver regions of interest (ROIs) and HCC volumes of interest (VOIs). Precision was assessed by calculating intraclass correlation coefficient (ICC), concordance correlation coefficient (CCC), and coefficient of variation (CV).

RESULTS

There was moderate to excellent test-retest repeatability of shape and 1st- and 2nd-order features for all sequences in HCCs (ICC: 0.53-0.99; CV: 3-29%), and moderate to good test-retest repeatability of 1st- and 2nd-order features for T1WI sequences, and 2nd-order features for T2WI in the liver (ICC: 0.53-0.73; CV: 12-19%). There was poor inter-platform reproducibility for all features and sequences, except for shape and 1st-order features on T1WI in HCCs (CCC: 0.58-0.99; CV: 3-15%). Good to excellent inter-observer reproducibility was found for all features and sequences in HCCs (CCC: 0.80-0.99; CV: 4-15%) and moderate to good for liver (CCC: 0.45-0.86; CV: 6-25%).

CONCLUSIONS

MRI radiomics features have acceptable repeatability in the liver and HCC when using the same MRI system and across readers but have low reproducibility across MR systems, except for shape and 1st-order features on T1WI. Data must be interpreted with caution when performing multiplatform radiomics studies.

KEY POINTS

• MRI radiomics features have acceptable repeatability when using the same MRI system but less reproducible when using different MRI platforms. • MRI radiomics features extracted from T1 weighted-imaging show greater stability across exams than T2 weighted-imaging and ADC. • Inter-observer reproducibility of MRI radiomics features was found to be good in HCC tumors and acceptable in liver parenchyma.

ImaGene: a web-based software platform for tumor radiogenomic evaluation and reporting

Summary

Radiographic imaging techniques provide insight into the imaging features of tumor regions of interest, while immunohistochemistry and sequencing techniques performed on biopsy samples yield omics data. Relationships between tumor genotype and phenotype can be identified from these data through traditional correlation analyses and artificial intelligence (AI) models. However, the radiogenomics community lacks a unified software platform with which to conduct such analyses in a reproducible manner. To address this gap, we developed ImaGene, a web-based platform that takes tumor omics and imaging datasets as inputs, performs correlation analysis between them, and constructs AI models. ImaGene has several modifiable configuration parameters and produces a report displaying model diagnostics. To demonstrate the utility of ImaGene, we utilized data for invasive breast carcinoma (IBC) and head and neck squamous cell carcinoma (HNSCC) and identified potential associations between imaging features and nine genes (WT1, LGI3, SP7, DSG1, ORM1, CLDN10, CST1, SMTNL2, and SLC22A31) for IBC and eight genes (NR0B1, PLA2G2A, MAL, CLDN16, PRDM14, VRTN, LRRN1, and MECOM) for HNSCC. ImaGene has the potential to become a standard platform for radiogenomic tumor analyses due to its ease of use, flexibility, and reproducibility, playing a central role in the establishment of an emerging radiogenomic knowledge base.

Availability and implementation

www.ImaGene.pgxguide.org, https://github.com/skr1/Imagene.git.

Supplementary information

Supplementary data are available at https://github.com/skr1/Imagene.git.

87 PREDICTIVE VALIDITY OF SCREENING TOOLS USED BY A FRAILTY INTERVENTION TEAM IN AN IRISH EMERGENCY DEPARTMENT: A RETROSPECTIVE COHORT STUDY

Background

Various screening tools exist to identify frail and at-risk older adults in the emergency department (ED). This can facilitate targeted assessment and management, leading to improve outcomes. This study evaluated the predictive validity of four screening tools used by an ED-based team of allied health professionals.

Methods

The Variable Indicative of Placement (VIP) tool, Think Frailty Tool, Clinical Frailty Scale (CFS) and 4AT were administered to adults aged ≥75 years as part of assessment by the Frailty Intervention Therapy Team in an Irish ED. Outcomes were hospital admission; re-attendance within 28 or 90 days; and death within 28 or 365 days. Scores were dichotomised, and for each outcome, relative risks and sensitivity, specificity, positive and negative predictive values were calculated.

Results

Over the six-month period, 429 individuals (median age:82 years) were assessed. Of these, 59% were VIP-positive, 81% screened at-risk of frailty on the Think Frailty Tool, 56% screened positive for frailty on the CFS, and 16% screened positive on the 4AT. Hospital admission, re-attendance at 28 and 90 days, and death within 28 and 365 days were 56%, 12%, 27%, 5%, and 23%, respectively. Positive screens on the VIP, Think Frailty Tool, CFS and 4AT were associated with significantly increased risk of hospital admission and death within 28 or 365 days (p &lt; 0.05). Positive screens on the Think Frailty Tool and CFS were also associated with increased risk of 90-day re-attendance (p &lt; 0.05). Of the four tools, the Think Frailty Tool had the highest sensitivity (86%–100%) for all outcomes. The CFS showed high sensitivity for detecting death within 28 or 365 days (95% and 84%, respectively), but lower sensitivity (68%–75%) for other outcomes. The 4AT demonstrated the lowest sensitivity for all outcomes (20%–46%).

Conclusion

The Think Frailty Tool and CFS were the most useful for predicting adverse outcomes in this group.

Cryopreservation of a threatened medicinal plant, Valeriana jatamansi Jones, using vitrification and assessment of biosynthetic stability of regenerants

BACKGROUND

Valeriana jatamansi Jones is a medicinal plant of the Himalayan region with high trade value. Since overexploitation of this wild species led it to be listed as threatened, a comprehensive conservation strategy is needed. Cryopreservation would be a useful complementary method to conventional conservation methods.

OBJECTIVE

To develop a cryopreservation protocol for V. jatamansi with maintenance of biosynthetic stability of regenerants.

MATERIALS AND METHODS

In vitro shoot tips were cryopreserved using vitrification with either PVS2 or PVS3 and the efficacy of the two cryoprotectant mixtures compared. Regenerated plantlets were evaluated by HPLC analysis for contents of four valepotriates viz. valtrate, acevaltrate, didrovaltrate and IVHD valtrate.

RESULTS

The highest shoot recovery (91.6%) after transfer to liquid nitrogen was obtained when shoot tips were treated with PVS2 at 0°C for 110 min, which was significantly higher than the highest recovery (73.3%) obtained using PVS3 for any duration tested. Evaluation of biosynthetic stability showed no variation in valepotriate contents between in vitro maintained and cryopreserved derived plantlets.

CONCLUSION

This protocol will be useful for the long-term conservation of this species as high frequency recovery and biosynthetic stability after cryopreservation were obtained.

Structuring clinical text with AI: Old versus new natural language processing techniques evaluated on eight common cardiovascular diseases

Free-text clinical notes in electronic health records are more difficult for data mining while the structured diagnostic codes can be missing or erroneous. To improve the quality of diagnostic codes, this work extracts diagnostic codes from free-text notes: five old and new word vectorization methods were used to vectorize Stanford progress notes and predict eight ICD-10 codes of common cardiovascular diseases with logistic regression. The models showed good performance, with TF-IDF as the best vectorization model showing the highest AUROC (0.9499-0.9915) and AUPRC (0.2956-0.8072). The models also showed transferability when tested on MIMIC-III data with AUROC from 0.7952 to 0.9790 and AUPRC from 0.2353 to 0.8084. Model interpretability was shown by the important words with clinical meanings matching each disease. This study shows the feasibility of accurately extracting structured diagnostic codes, imputing missing codes, and correcting erroneous codes from free-text clinical notes for information retrieval and downstream machine-learning applications.

Machine Learning Radiomics Model for Early Identification of Small-Cell Lung Cancer on Computed Tomography Scans

PURPOSE

Small-cell lung cancer (SCLC) is the deadliest form of lung cancer, partly because of its short doubling time. Delays in imaging identification and diagnosis of nodules create a risk for stage migration. The purpose of our study was to determine if a machine learning radiomics model can detect SCLC on computed tomography (CT) among all nodules at least 1 cm in size.

MATERIALS AND METHODS

Computed tomography scans from a single institution were selected and resampled to 1 × 1 × 1 mm. Studies were divided into SCLC and other scans comprising benign, adenocarcinoma, and squamous cell carcinoma that were segregated into group A (noncontrast scans) and group B (contrast-enhanced scans). Four machine learning classification models, support vector classifier, random forest (RF), XGBoost, and logistic regression, were used to generate radiomic models using 59 quantitative first-order and texture Imaging Biomarker Standardization Initiative compliant PyRadiomics features, which were found to be robust between two segmenters with minimum Redundancy Maximum Relevance feature selection within each leave-one-out-cross-validation to avoid overfitting. The performance was evaluated using a receiver operating characteristic curve. A final model was created using the RF classifier and aggregate minimum Redundancy Maximum Relevance to determine feature importance.

RESULTS

A total of 103 studies were included in the analysis. The area under the receiver operating characteristic curve for RF, support vector classifier, XGBoost, and logistic regression was 0.81, 0.77, 0.84, and 0.84 in group A, and 0.88, 0.87, 0.85, and 0.81 in group B, respectively. Nine radiomic features in group A and 14 radiomic features in group B were predictive of SCLC. Six radiomic features overlapped between groups A and B.

CONCLUSION

A machine learning radiomics model may help differentiate SCLC from other lung lesions.

Abstract PO-036: A sophisticated bioinformatics framework for integrative study of radiomics and genomics profiles of tumors

The potential for radiomics to support oncology decision-making has grown substantially in recent years, as these scanning techniques have been found to offer unique information regarding the tumor phenotype and microenvironment that is distinct from that provided by genomic or proteomic assays. Radiomic and genomic (or proteomic) data can be correlated with one another, thereby facilitating radiogenomic efforts. Radiogenomically-informed biopsies have the potential to yield better pathological outcomes and can aid in the planning of more appropriate treatment strategies for cancer patients. However, the field lacks a unified software platform wherein radiomic and genomics/proteomic data could be brought together to conduct a variety of correlational analyses and build robust artificial intelligence models that would aid the prediction of genomic/proteomic profiles of tumors from their radiological images. We have built such a comprehensive platform that could be utilized by scientists and clinicians globally to conduct radiogenomic studies for a variety of cancer types, and further validate and deploy it in clinics to aid effective monitoring, diagnosis, and treatment of cancer patients.

Citation Format: Shrey S. Sukhadia, Shivashankar H. Nagaraj, Olivier Gevaert, Sivakumaran Theru Arumugam, Aayush Tyagi, Pritam Mukherjee, A.P. Prathosh. A sophisticated bioinformatics framework for integrative study of radiomics and genomics profiles of tumors [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-036.

Inhibition of growth and virulence of Vibrio cholerae by carvacrol, an essential oil component of Origanum spp

AIMS

In the age where bacterial resistance to conventional antibiotics is increasing at an alarming rate, the use of the traditional plant, herb extracts or other bioactive constituents is gradually becoming popular as an anti-virulence agent to treat pathogenic diseases. Carvacrol, a major essential oil fraction of Oregano, possesses a wide range of bioactivities. Therefore, we aimed to study the effect of sub-inhibitory concentrations of carvacrol on major virulence traits of Vibrio cholerae.

METHODS AND RESULTS

We have used in vitro as well as ex vivo models to access the anti-pathogenic role of carvacrol. We found that the sub-inhibitory concentration of carvacrol significantly repressed bacterial mucin penetrating ability. Carvacrol also reduced the adherence and fluid accumulation in the rabbit ileal loop model. Reduction in virulence is associated with the downregulated expression of tcpA, ctxB, hlyA and toxT. Furthermore, carvacrol inhibits flagellar synthesis by downregulating the expression of flrC and most of the class III genes.

CONCLUSIONS

Carvacrol exhibited anti-virulence activity against V. cholerae, which involved many events including the inhibition of mucin penetration, adhesion, reduced expression of virulence-associated genes culminating in reduced fluid accumulation.

SIGNIFICANCE AND IMPACT OF THE STUDY

These findings indicate that carvacrol possesses inhibitory activity against V. cholerae pathogenesis and might be considered as a potential bio-active therapeutic alternative to combat cholera.

The evolution of white matter microstructural changes after mild traumatic brain injury: A longitudinal DTI and NODDI study

Neuroimaging biomarkers that can detect white matter (WM) pathology after mild traumatic brain injury (mTBI) and predict long-term outcome are needed to improve care and develop therapies. We used diffusion tensor imaging (DTI) and neurite orientation dispersion and density imaging (NODDI) to investigate WM microstructure cross-sectionally and longitudinally after mTBI and correlate these with neuropsychological performance. Cross-sectionally, early decreases of fractional anisotropy and increases of mean diffusivity corresponded to WM regions with elevated free water fraction on NODDI. This elevated free water was more extensive in the patient subgroup reporting more early postconcussive symptoms. The longer-term longitudinal WM changes consisted of declining neurite density on NODDI, suggesting axonal degeneration from diffuse axonal injury for which NODDI is more sensitive than DTI. Therefore, NODDI is a more sensitive and specific biomarker than DTI for WM microstructural changes due to mTBI that merits further study for mTBI diagnosis, prognosis, and treatment monitoring.

CT-based Radiomic Signatures for Predicting Histopathologic Features in Head and Neck Squamous Cell Carcinoma

Purpose

To determine the performance of CT-based radiomic features for noninvasive prediction of histopathologic features of tumor grade, extracapsular spread, perineural invasion, lymphovascular invasion, and human papillomavirus status in head and neck squamous cell carcinoma (HNSCC).

Materials and Methods

In this retrospective study, which was approved by the local institutional ethics committee, CT images and clinical data from patients with pathologically proven HNSCC from The Cancer Genome Atlas (n = 113) and an institutional test cohort (n = 71) were analyzed. A machine learning model was trained with 2131 extracted radiomic features to predict tumor histopathologic characteristics. In the model, principal component analysis was used for dimensionality reduction, and regularized regression was used for classification.

Results

The trained radiomic model demonstrated moderate capability of predicting HNSCC features. In the training cohort and the test cohort, the model achieved a mean area under the receiver operating characteristic curve (AUC) of 0.75 (95% confidence interval [CI]: 0.68, 0.81) and 0.66 (95% CI: 0.45, 0.84), respectively, for tumor grade; a mean AUC of 0.64 (95% CI: 0.55, 0.62) and 0.70 (95% CI: 0.47, 0.89), respectively, for perineural invasion; a mean AUC of 0.69 (95% CI: 0.56, 0.81) and 0.65 (95% CI: 0.38, 0.87), respectively, for lymphovascular invasion; a mean AUC of 0.77 (95% CI: 0.65, 0.88) and 0.67 (95% CI: 0.15, 0.80), respectively, for extracapsular spread; and a mean AUC of 0.71 (95% CI: 0.29, 1.0) and 0.80 (95% CI: 0.65, 0.92), respectively, for human papillomavirus status.

Conclusion

Radiomic CT models have the potential to predict characteristics typically identified on pathologic assessment of HNSCC.Supplemental material is available for this article.© RSNA, 2020.

A Shallow Convolutional Neural Network Predicts Prognosis of Lung Cancer Patients in Multi-Institutional CT-Image Data

Lung cancer is the most common fatal malignancy in adults worldwide, and non-small cell lung cancer (NSCLC) accounts for 85% of lung cancer diagnoses. Computed tomography (CT) is routinely used in clinical practice to determine lung cancer treatment and assess prognosis. Here, we developed LungNet, a shallow convolutional neural network for predicting outcomes of NSCLC patients. We trained and evaluated LungNet on four independent cohorts of NSCLC patients from four medical centers: Stanford Hospital (n = 129), H. Lee Moffitt Cancer Center and Research Institute (n = 185), MAASTRO Clinic (n = 311) and Charité - Universitätsmedizin (n=84). We show that outcomes from LungNet are predictive of overall survival in all four independent survival cohorts as measured by concordance indices of 0.62, 0.62, 0.62 and 0.58 on cohorts 1, 2, 3, and 4, respectively. Further, the survival model can be used, via transfer learning, for classifying benign vs malignant nodules on the Lung Image Database Consortium (n = 1010), with improved performance (AUC=0.85) versus training from scratch (AUC=0.82). LungNet can be used as a noninvasive predictor for prognosis in NSCLC patients and can facilitate interpretation of CT images for lung cancer stratification and prognostication.

International Nosocomial Infection Control Consortium (INICC) report, data summary of 45 countries for 2012-2017: Device-associated module

BACKGROUND

We report the results of International Nosocomial Infection Control Consortium (INICC) surveillance study from January 2012 to December 2017 in 523 intensive care units (ICUs) in 45 countries from Latin America, Europe, Eastern Mediterranean, Southeast Asia, and Western Pacific.

METHODS

During the 6-year study period, prospective data from 532,483 ICU patients hospitalized in 242 hospitals, for an aggregate of 2,197,304 patient days, were collected through the INICC Surveillance Online System (ISOS). The Centers for Disease Control and Prevention-National Healthcare Safety Network (CDC-NHSN) definitions for device-associated health care-associated infection (DA-HAI) were applied.

RESULTS

Although device use in INICC ICUs was similar to that reported from CDC-NHSN ICUs, DA-HAI rates were higher in the INICC ICUs: in the medical-surgical ICUs, the pooled central line-associated bloodstream infection rate was higher (5.05 vs 0.8 per 1,000 central line-days); the ventilator-associated pneumonia rate was also higher (14.1 vs 0.9 per 1,000 ventilator-days,), as well as the rate of catheter-associated urinary tract infection (5.1 vs 1.7 per 1,000 catheter-days). From blood cultures samples, frequencies of resistance, such as of Pseudomonas aeruginosa to piperacillin-tazobactam (33.0% vs 18.3%), were also higher.

CONCLUSIONS

Despite a significant trend toward the reduction in INICC ICUs, DA-HAI rates are still much higher compared with CDC-NHSN's ICUs representing the developed world. It is INICC's main goal to provide basic and cost-effective resources, through the INICC Surveillance Online System to tackle the burden of DA-HAIs effectively.

Predicting the tumor response to chemoradiotherapy for rectal cancer: Model development and external validation using MRI radiomics

BACKGROUND

In well-responding patients to chemoradiotherapy for locally advanced rectal cancer (LARC), a watch-and-wait strategy can be considered. To implement organ-sparing strategies, accurate patient selection is needed. We investigate the use of MRI-based radiomics models to predict tumor response to improve patient selection.

MATERIALS AND METHODS

Models were developed in a cohort of 70 patients and validated in an external cohort of 55 patients. Patients received chemoradiation followed by surgery and underwent T2-weighted and diffusion-weighted MRI (DW-MRI) before and after chemoradiation. The outcome measure was (near-)complete pathological tumor response (ypT0-1N0). Tumor segmentation was done on T2-images and transferred to b800-images and ADC maps, after which quantitative and four semantic features were extracted. We combined features using principal component analysis and built models using LASSO regression analysis. The best models based on precision and performance were selected for validation.

RESULTS

21/70 patients (30%) achieved ypT0-1N0 in the development cohort versus 13/55 patients (24%) in the validation cohort. Three models (t2_dwi_pre_post, semantic_dwi_adc_pre, semantic_dwi_post) were identified with an area-under-the-curve (AUC) of 0.83 (95% CI 0.70-0.95), 0.86 (95% CI 0.75-0.98) and 0.84 (95% CI 0.75-0.94) respectively. Two models (t2_dwi_pre_post, semantic_dwi_post) validated well in the external cohort with AUCs of 0.83 (95% CI 0.70-0.95) and 0.86 (95% CI 0.76-0.97). These models however did not outperform a previously established four-feature semantic model.

CONCLUSION

Prediction models based on MRI radiomics non-invasively predict tumor response after chemoradiation for rectal cancer and can be used as an additional tool to identify patients eligible for an organ-preserving treatment.

Emergent magnetic order and correlated disorder in formate metal-organic frameworks

Magnetic materials with strong local interactions but lacking long-range order have long been a curiosity of physicists. Probing their magnetic interactions is crucial for understanding the unique properties they can exhibit. Metal-organic frameworks have recently gathered more attention as they can produce more exotic structures, allowing for controlled design of magnetic properties not found in conventional metal-oxide materials. Historically, magnetic diffuse scattering in such materials has been overlooked but has attracted greater attention recently, with advances in techniques. In this study, we investigate the magnetic structure of metal-organic formate frameworks, using heat capacity, magnetic susceptibility and neutron diffraction. In Tb(DCO₂)₃, we observe emergent magnetic order at temperatures below 1.2 K, consisting of two k-vectors. Ho(DCO₂)₃ shows diffuse scattering above 1.6 K, consistent with ferromagnetic chains packed in a frustrated antiferromagnetic triangular lattice, also observed in Tb(DCO₂)₃ above 1.2 K. The other lanthanides show no short- or long-range order down to 1.6 K. The results suggest an Ising-like one-dimensional magnetic order associated with frustration is responsible for the magnetocaloric properties, of some members in this family, improving at higher temperatures. This article is part of the theme issue 'Mineralomimesis: natural and synthetic frameworks in science and technology'.

Halomonas Rhizobacteria of Avicennia marina of Indian Sundarbans Promote Rice Growth Under Saline and Heavy Metal Stresses Through Exopolysaccharide Production

The Halomonas species isolated from the rhizosphere of the true mangrove Avicennia marina of Indian Sundarbans showed enhanced rice growth promotion under combined stress of salt and arsenic in pot assay. Interestingly, under abiotic stress conditions, Halomonas sp. Exo1 was observed as an efficient producer of exopolysaccharide. The study revealed that salt triggered exopolysaccharide production, which in turn, increased osmotic tolerance of the strain. Again, like salt, presence of arsenic also caused increased exopolysaccharide production that in turn sequestered arsenic showing a positive feedback mechanism. To understand the role of exopolysaccharide in salt and arsenic biosorption, purified exopolysaccharide mediated salt and arsenic sequestration were studied both under in vivo and in vitro conditions and the substrate binding properties were characterized through FT-IR and SEM-EDX analyses. Finally, observation of enhanced plant growth in pot assay in the presence of the strain and pure exopolysaccharide separately, confirmed direct role of exopolysaccharide in plant growth promotion.