Life Sciences Commons^™

Cross-Facility Reliable Deep Learning Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression, Samuel Vinson

Biological and Agricultural Engineering Undergraduate Honors Theses

Inconsistent quality grading in beef production leads to inefficiencies, economic disparity, and consumer mistrust. While USDA meat grading traditionally relies on skilled visual inspectors, these human evaluations suffer from cross-facility variability and subjectivity. This paper introduces the first known application of unsupervised domain adaptation regression for cross-facility beef marbling score prediction—an innovation that improves generalization across diverse environments in the beef supply chain. Utilizing numerical scores ranging from 100-900, the research employed convolutional neural networks (CNNs), including ResNet, VGG, and AlexNet architectures. The study specifically introduced and validated a unified unsupervised domain adaptation regression method using the ResNet-50 architecture to …

Classification Of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, And Thickness With A Deep And A Shallow Learning Model, Roberto Goya-Maldonado, Tracy Erwin-Grabner, Ling-Li Zeng, Christopher R K Ching, Andre Aleman, Alyssa R Amod, Zeynep Basgoze, Francesco Benedetti, Bianca Besteher, Katharina Brosch, Robin Bülow, Romain Colle, Colm G Connolly, Emmanuelle Corruble, Baptiste Couvy-Duchesne, Kathryn Cullen, Udo Dannlowski, Christopher G Davey, Annemiek Dols, Jan Ernsting, Jennifer W Evans, Lukas Fisch, Paola Fuentes-Claramonte, Ali Saffet Gonul, Ian H Gotlib, Hans J Grabe, Nynke A Groenewold, Dominik Grotegerd, Tim Hahn, J Paul Hamilton, Laura K M Han, Ben J Harrison, Tiffany C Ho, Neda Jahanshad, Alec J Jamieson, Andriana Karuk, Tilo Kircher, Bonnie Klimes-Dougan, Sheri-Michelle Koopowitz, Thomas Lancaster, Ramona Leenings, Meng Li, David E J Linden, Frank P Macmaster, David M A Mehler, Susanne Meinert, Elisa Melloni, Bryon A Mueller, Benson Mwangi, Igor Nenadić, Amar Ojha, Yasumasa Okamoto, Mardien L Oudega, Brenda W J H Penninx, Sara Poletti, Edith Pomarol-Clotet, Maria J Portella, Joaquim Radua, Elena Rodríguez-Cano, Matthew D Sacchet, Raymond Salvador, Anouk Schrantee, Kang Sim, Jair C Soares, Aleix Solanes, Dan J Stein, Frederike Stein, Aleks Stolicyn, Sophia I Thomopoulos, Yara J Toenders, Aslihan Uyar-Demir, Eduard Vieta, Yolanda Vives-Gilabert, Henry Völzke, Martin Walter, Heather C Whalley, Sarah Whittle, Nils Winter, Katharina Wittfeld, Margaret J Wright, Mon-Ju Wu, Tony T Yang, Carlos Zarate, Dick J Veltman, Lianne Schmaal, Paul M Thompson, Enigma Major Depressive Disorder Working Group

Faculty, Staff and Student Publications

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. In this study, we used …

A Hybrid Object Detection And Temporal Attention Framework For Intelligent Video Surveillance, Sudheer Reddy Bandi, Eswari Vanaparthi, Yakshini Edapalli, Roshan Kavuri

Mansoura Engineering Journal

The rapid growth of urban areas has greatly heightened the need for smart video surveillance systems that can automatically process extensive amounts of CCTV footage. Traditional surveillance methods largely depend on human monitoring, which is not only inefficient but also susceptible to human mistakes, especially in intricate and crowded environments. To tackle these issues, this paper introduces a combined object detection and temporal attention for intelligent video surveillance that concurrently analyzes spatial and temporal data from video streams. The proposed system analyzes real-time CCTV footage utilising a multi-pathway frame extraction technique that includes slow, fast, and full-frame sampling to capture …

Dcpr: A Deep Learning Framework For Circadian Phase Reconstruction, Xiao Han, Xiaochen Cen, Zhijin Li, Xiaobo Zhou, Zhiwei Ji

Faculty, Staff and Student Publications

Background: The circadian clock is an evolutionarily conserved system that orchestrates 24-h physiological rhythms through transcriptional and translational feedback loops. Mounting evidence suggests a bidirectional relationship between circadian rhythm alteration and disease progression, positioning the circadian clock as a potential therapeutic target. Due to the scarcity of high-resolution temporal omics data, it remains very challenging to elucidate the underlying regulatory mechanisms of the circadian system. As a practical alternative, public untimed transcriptomic datasets offer the potential to infer gene expression oscillations retrospectively. However, existing computational approaches for circadian phase estimation often suffer from limited predictive accuracy, reducing their ability to …

Deciphering Rna Modification And Post-Transcriptional Regulation With Netrnapan, Haodong Xu, Wankun Deng, Ruifeng Hu, Binfeng Liu, Wenchao Zhang, Lujuan Wang, Lin Qi, Xiaolei Ren, Chao Tu, Zhihong Li, Zhongming Zhao

Faculty, Staff and Student Publications

RNA modification, which is evolutionarily conserved, is crucial for modulating various biological functions and disease pathogenesis. High resolution transcriptome-wide mapping of RNA modifications has facilitated both data resources and computational prediction of RNA modification. While these prediction algorithms are promising, they are limited in interpretability or generalizability, or the capacity for discovering novel post-transcriptional regulations. Here, we present NetRNApan, a deep learning framework for RNA modification site prediction, motif discovery and trans-regulatory factor identification. Using m5U profiles generated by FICC-seq and miCLIP-seq technologies and single-base resolution m6A sites from multiple experiments as cases, we demonstrated the accuracy of NetRNApan with …

Intentional Creation Of Suboptimal, Realistic Dose Distributions, Skylar S Gay, Mary P Gronberg, Raymond Mumme, Beth M Beadle, Anuja Jhingran, Tze Yee Lim, Zhiqian H Yu, Christine Chung, Meena Khan, Chelsea Pinnix, Sanjay Shete, Brent Parker, Tucker J Netherton, Carlos E Cardenas, Laurence E Court

Faculty, Staff and Student Publications

Background: Radiation oncology residents report a lack of understanding and confidence in assessing radiotherapy plan quality. A contributing factor is the environment in which plan review is taught during residency, that is, routine clinical practice, which does not provide ample time for self-guided practice in a low-stakes setting. Expertise in plan review requires diverse case presentation and many examples, which are often not achievable in smaller programs and for less common cancer types. As plan quality affects patient outcomes, it is important to address these pitfalls in the education of residents on plan review.

Purpose: To address the identified pitfalls …

Advancing Modified Barium Swallow Pre-Sorting With Deep Learning: A New Paradigm For The First Step Analysis In X-Ray Swallowing Study, Shitong Mao, Mohamed A Naser, Sheila Buoy, Kristy K Brock, Katherine A Hutcheson

Faculty, Staff and Student Publications

Purpose: Modified barium swallow (MBS) exams are pivotal for assessing swallowing function and include diagnostic video segments imaged in various planes, such as anteroposterior (AP or coronal plane) and lateral (or mid-sagittal plane), alongside non-diagnostic 'scout' image segments used for anatomic reference and image set-up that do not include bolus swallows. These variations in imaging files necessitate manual sorting and labeling, complicating the pre-analysis workflow.

Methods: Our study introduces a deep learning approach to automate the categorization of swallow videos in MBS exams, distinguishing between the different types of diagnostic videos and identifying non-diagnostic scout videos to streamline the MBS …

Interactive 3d Segmentation For Primary Gross Tumor Volume In Oropharyngeal Cancer, Mikko Saukkoriipi, Jaakko Sahlsten, Joel Jaskari, Lotta Orsmaa, Jari Kangas, Nastaran Rasouli, Roope Raisamo, Jussi Hirvonen, Helena Mehtonen, Jorma Järnstedt, Antti Mäkitie, Mohamed Naser, Clifton Fuller, Benjamin Kann, Kimmo Kaski

Faculty, Staff and Student Publications

Radiotherapy is the main treatment modality of oropharyngeal cancer (OPC), in which an accurate segmentation of primary gross tumor volume (GTVt) is essential but also challenging due to significant interobserver variability and the time consumed in manual tumor delineation. For such a challenge an interactive deep learning (DL) based approach offers the advantage of automatic high-performance segmentation with the flexibility for user correction when necessary. In this study, we investigate an interactive DL for GTVt segmentation in OPC by introducing a novel two-stage Interactive Click Refinement (2S-ICR) framework and implementing state-of-the-art algorithms. Using the 2021 HEad and neCK TumOR dataset …

Evolution Of Esophageal Adenocarcinoma From Precursor Lesion Stem Cells, Wa Xian, Shan Wang, Jingzhong Xie, Yusuke Yamamoto, Melina Khorrami, Yanting Zhang, Raul Caballero Montes, Caycel Desales, Melika Khorrami, Zaal Mory, Ashley Hoffman, Amber Su, Crystal Nguyen, Peter J A Davies, Clifford Stephan, Shuang Pan, Wengen Wu, Yuxin Liu, Jeremy Siegelman, Rebecca E Waters, William A Ross, Shumei Song, Mark Metersky, David G Beer, Christopher P Crum, Alexander J Stewart, Matthew Vincent, Richard Russell, Robert A Izard, Khek Yu Ho, Jack Hung-Sen Lai, William W Bachovchin, Jaffer A Ajani, Frank D Mckeon

Faculty, Staff and Student Publications

Background & aims: Metastatic cancers arise from a decades-long succession of increasingly virulent precursor lesions, each of which represents prospective targets for therapeutic intervention. This evolutionary process has been particularly vivid in esophageal adenocarcinoma (EAC), as this cancer and associated precursor lesions, including Barrett's esophagus (BE), low-grade dysplasia (LGD), and high-grade dysplasia (HGD), coexist in an accessible, 2-dimensional pattern in esophageal mucosa. Given the durability of these precursor lesions, it is likely that they, like EAC, rely on stem cells for their regenerative growth. To assess the role of stem cells in the evolution of EAC, we apply technology that …

Dr Kinase: Predicting The Drug-Resistance Hotspots Of Protein Kinases, Shaofeng Lin, Chao Tu, Ruifeng Hu, Haiji Wang, Zongcheng Dong, Hui Luo, Lan Kuang, Tao Wang, Liming Wang, Zhongming Zhao, Zhihong Li, Haodong Xu

Faculty, Staff and Student Publications

Protein kinases (PKs) regulate various cellular functions, and are targeted by small-molecule kinase inhibitors (KIs) in cancers and other diseases. However, drug resistance (DR) of KIs occurs through critical mutations in four types of representative hotspots, including gatekeeper, G-loop, αC-helix, and A-loop. KI DR has become a common clinical complication affecting multiple cancers, targeted kinases, and drugs. To tackle this challenge, we report an upgraded web server, namely Dr. Kinase, for predicting the loci of four DR hotspots and assessing effects of mutations on DR hotspots for PKs in our previous studies, by utilizing multimodal features and deep hybrid learning. …

Deep Learning Based Rapid X-Ray Fluorescence Signal Extraction And Image Reconstruction For Preclinical Benchtop X-Ray Fluorescence Computed Tomography Applications, Amrit Kaphle, Sandun Jayarathna, Sang Hyun Cho

Faculty, Staff and Student Publications

Recent research advances have resulted in an experimental benchtop X-ray fluorescence computed tomography (XFCT) system that likely meets the imaging dose/scan time constraints for benchtop XFCT imaging of live mice injected with gold nanoparticles (GNPs). For routine in vivo benchtop XFCT imaging, however, additional challenges, most notably the need for rapid/near-real-time handling of X-ray fluorescence (XRF) signal extraction and XFCT image reconstruction, must be successfully addressed. Here we propose a novel end-to-end deep learning (DL) framework that integrates a one-dimensional convolutional neural network (1D CNN) for rapid XRF signal extraction with a U-Net model for XFCT image reconstruction. We trained …

Deep Learning Based Rapid X-Ray Fluorescence Signal Extraction And Image Reconstruction For Preclinical Benchtop X-Ray Fluorescence Computed Tomography Applications, Amrit Kaphle, Sandun Jayarathna, Sang Hyun Cho

Faculty, Staff and Student Publications

Recent research advances have resulted in an experimental benchtop X-ray fluorescence computed tomography (XFCT) system that likely meets the imaging dose/scan time constraints for benchtop XFCT imaging of live mice injected with gold nanoparticles (GNPs). For routine in vivo benchtop XFCT imaging, however, additional challenges, most notably the need for rapid/near-real-time handling of X-ray fluorescence (XRF) signal extraction and XFCT image reconstruction, must be successfully addressed. Here we propose a novel end-to-end deep learning (DL) framework that integrates a one-dimensional convolutional neural network (1D CNN) for rapid XRF signal extraction with a U-Net model for XFCT image reconstruction. We trained …

Histodx: Revolutionizing Breast Cancer Diagnosis Through Advanced Imaging Techniques, Wishal Arshad, Thhreem Masrood, H. M. Shahzhad, Hassan A. Ahmed, Syed Hamza Ahmed, Hafiz Muhammad Tayyab Khushi

Business Faculty Publications

Breast cancer is the second leading cause of mortality among women worldwide, highlighting the need for efficient histopathology-based screening methods for early diagnosis. This study introduces HistoDX, a deep learning framework to classify Invasive Ductal Carcinoma (IDC) using 277,524 histopathology image patches ( 50×50 pixels) from Paul Mooney’s IDC dataset on Kaggle, comprising No Cancer and IDC(+) classes. HistoDX employs a preprocessing pipeline with normalization, data augmentation, and class balancing via oversampling and weighted loss to address the class imbalance. A customized convolutional neural network, built on EfficientNetV2-B3 with additional layers, achieves 97% accuracy and a 0.91 ROC-AUC score on …

Skin Cancer Diagnosis Utilizing Hybrid Discrete Cosine Transform And High-Performance Convolutional Neural Networks, Mohammed M. Abo-Zahhad, Mohammed Abo-Zahhad

Mansoura Engineering Journal

Detecting skin cancer early and accurately is crucial for successfully treating this potentially fatal disease. Enhancing the accuracy of visual inspection techniques is often necessary to improve clinical decision-making and increase the chance of successful treatment outcomes. In this research, high-performance deep learning (DL) models for automated skin cancer categorization and early skin cancer diagnosis screening are developed and evaluated in conjunction with the discrete cosine transform (DCT). For this purpose, features are extracted from medical images using both techniques. The DCT is used for feature extraction and dimensionality reduction, while deep learning (DL) trains fully connected models for classification …

A Framework For Establishing An Automated Traffic Violation Detection System In New Assiut City Using Ordinary Cctv Units, Mahmoud Owais, Ali Shehata, Abdou Shaband, Ghada S. Moussa

Mansoura Engineering Journal

Violating traffic rules in transport networks is a genuine concern for operators as it is one of the most important causes of fatal accidents. With the increasing number of residents in the new cities in the Arab Republic of Egypt, and the incompleteness of the transportation system in those cities, including traffic signs, light signals, and control points, the possibility of committing such violations increases. The study aims to propose the framework for establishing an intelligent monitoring system in the new city of Assiut consisting of high-resolution cameras optimally distributed on the traffic network points in the city. They will …

Igtp: Learning Interpretable Cellular Embedding For Inferring Biological Mechanisms Underlying Single-Cell Transcriptomics, Kang-Lin Hsieh, Kai Zhang, Yan Chu, Lishan Yu, Xiaoyang Li, Nuo Hu, Isha Kawosa, Patrick G Pilié, Pratip K Bhattacharya, Degui Zhi, Xiaoqian Jiang, Zhongming Zhao, Yulin Dai

Faculty, Staff and Student Publications

Deep-learning models like Variational AutoEncoder have enabled low dimensional cellular embedding representation for large-scale single-cell transcriptomes and shown great flexibility in downstream tasks. However, biologically meaningful latent space is usually missing if no specific structure is designed. Here, we engineered a novel interpretable generative transcriptional program (iGTP) framework that could model the importance of transcriptional program (TP) space and protein-protein interactions (PPI) between different biological states. We demonstrated the performance of iGTP in a diverse biological context using gene ontology, canonical pathway, and different PPI curation. iGTP not only elucidated the ground truth of cellular responses but also surpassed other …

Dose Prediction Via Deep Learning To Enhance Treatment Planning Of Lung Radiotherapy Including Simultaneous Integrated Boost Techniques, Wenhua Cao, Mary Gronberg, Stephen Bilton, Hana Baroudi, Skylar Gay, Christopher Peeler, Zhongxing Liao, Thomas J Whitaker, Karen Hoffman, Laurence E Court

Faculty, Staff and Student Publications

Background: Recent studies have shown deep learning techniques are able to predict three-dimensional (3D) dose distributions of radiotherapy treatment plans. However, their use in dose prediction for treatments with varied prescription doses including simultaneous integrated boost (SIB), that is, using multiple prescription doses within the same plan, and benefit in improving plan quality should be validated.

Purpose: To investigate the feasibility and potential benefit of using deep learning to predict dose distribution of volumetric modulated arc therapy (VMAT) including SIB techniques and improve treatment planning for patients with lung cancer.

Methods: The dose prediction model was trained with 93 retrospective …

T2-Weighted Imaging Of Rectal Cancer Using A 3d Fast Spin Echo Sequence With And Without Deep Learning Reconstruction: A Reader Study, Dan Nguyen, Sarah Palmquist, Ken-Pin Hwang, Jingfei Ma, Usama Salem, Jia Sun, Xinzeng Wang, Jong Bum Son, Randy Ernst, Peng Wei, Harmeet Kaur, Nir Stanietzky

Faculty, Staff and Student Publications

Purpose: To compare image quality and clinical utility of a T2-weighted (T2W) 3-dimensional (3D) fast spin echo (FSE) sequence using deep learning reconstruction (DLR) versus conventional reconstruction for rectal magnetic resonance imaging (MRI).

Methods: The study included 50 patients with rectal cancer who underwent rectal MRI consecutively between July 7, 2020 and January 20, 2021 using a T2W 3D FSE sequence with DLR and conventional reconstruction. Three radiologists reviewed the two sets of images, scoring overall SNR, motion artifacts, and overall image quality on a 3-point scale and indicating clinical preference for DLR or conventional reconstruction based on those three …

A Pioneering Artificial Intelligence Tool To Predict Treatment Outcomes In Ovarian Cancer Via Diagnostic Laparoscopy, Xiaotian Ma, Yu-Chun Hsu, Amma Asare, Kai Zhang, Deanna Glassman, Katelyn F Handley, Katherine Foster, Khwahish Sharma, Shannon Westin, Amir Jazaeri, Nicole D Fleming, Pratip K Bhattacharya, Xiaoqian Jiang, Anil K Sood, Shayan Shams

Faculty, Staff and Student Publications

Ovarian cancer is associated with high rates of patient mortality and morbidity. Laparoscopic assessment of tumor localization can be used for treatment planning in newly diagnosed high-grade serous ovarian carcinoma (HGSOC). While spread to multiple intra-abdominal areas is correlated with worse outcomes, whether other morphological tumor differences are also associated with patient outcomes is unknown. Given the large volume of visual information in laparoscopic videos, we investigated whether deep-learning models can capture implicit features and predict treatment outcomes. We developed a novel deep-learning framework using pre-treatment laparoscopic images to assess clinical outcomes following upfront standard treatment, defined as short progression-free …

Deep Learning-Based Automatic Segmentation Of Cerebral Infarcts On Diffusion Mri, Wi-Sun Ryu, Dawid Schellingerhout, Jonghyeok Park, Jinyong Chung, Sang-Wuk Jeong, Dong-Seok Gwak, Beom Joon Kim, Joon-Tae Kim, Keun-Sik Hong, Kyung Bok Lee, Tai Hwan Park, Sang-Soon Park, Jong-Moo Park, Kyusik Kang, Yong-Jin Cho, Hong-Kyun Park, Byung-Chul Lee, Kyung-Ho Yu, Mi Sun Oh, Soo Joo Lee, Jae Guk Kim, Jae-Kwan Cha, Dae-Hyun Kim, Jun Lee, Man Seok Park, Dongmin Kim, Oh Young Bang, Eung Yeop Kim, Chul-Ho Sohn, Hosung Kim, Hee-Joon Bae, Dong-Eog Kim

Faculty, Staff and Student Publications

We explored effects of (1) training with various sample sizes of multi-site vs. single-site training data, (2) cross-site domain adaptation, and (3) data sources and features on the performance of algorithms segmenting cerebral infarcts on Magnetic Resonance Imaging (MRI). We used 10,820 annotated diffusion-weighted images (DWIs) from 10 university hospitals. Algorithms based on 3D U-net were trained using progressively larger subsamples (ranging from 217 to 8661), while internal testing employed a distinct set of 2159 DWIs. External validation was conducted using three unrelated datasets (n = 2777, 50, and 250). For domain adaptation, we utilized 50 to 1000 subsamples from …

Enhancing State-Of-The-Art Motor Imagery Classification With Reinforcement Learning, Anton Shepelev

USF Tampa Graduate Theses and Dissertations

One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to …

Age-Associated Proteins Explain The Role Of Medial Temporal Lobe Networks In Alzheimer’S Disease, Adam Turnbull, Yejin Kim, Kai Zhang, Xiaoqian Jiang, Zihuai He, Victor W Henderson, F Vankee Lin

Faculty, Staff and Student Publications

The structural connectivity (SC) of the medial temporal lobe and its associated cortical anterior temporal and posterior medial networks (MTL-AT-PM) is linked to pathologies and memory decline in Alzheimer's disease (AD). However, neuroimaging analyses cannot tell us how SC changes occur in AD at the molecular level and do not provide a means of intervening to slow/prevent pathology-related changes in MTL-AT-PM SC. The current study aimed to understand how and where AD-related changes occur within MTL-AT-PM using proteomics. We used a 4-step approach in 101 older adults from a local sample, aiming to understand how proteins and SC in combination …

Leveraging Large Language Models For Knowledge-Free Weak Supervision In Clinical Natural Language Processing, Enshuo Hsu, Kirk Roberts

Faculty, Staff and Student Publications

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled …

A Deep Learning-Based System For Automatic Detection Of Emesis With High Accuracy In Suncus Murinus, Zengbing Lu, Yimeng Qiao, Xiaofei Huang, Dexuan Cui, Julia Y H Liu, Man Piu Ngan, Luping Liu, Zhixin Huang, Zi-Tong Li, Lingqing Yang, Aleena Khalid, Yingyi Deng, Sze Wa Chan, Longlong Tu, John A Rudd

Children’s Nutrition Research Center Staff Publications

Quantifying emesis in Suncus murinus (S. murinus) has traditionally relied on direct observation or reviewing recorded behaviour, which are laborious, time-consuming processes that are susceptible to operator error. With rapid advancements in deep learning, automated animal behaviour quantification tools with high accuracy have emerged. In this study, we pioneere the use of both three-dimensional convolutional neural networks and self-attention mechanisms to develop the Automatic Emesis Detection (AED) tool for the quantification of emesis in S. murinus, achieving an overall accuracy of 98.92%. Specifically, we use motion-induced emesis videos as training datasets, with validation results demonstrating an accuracy of 99.42% for …

Emr-Lip: A Lightweight Framework For Standardizing The Preprocessing Of Longitudinal Irregular Data In Electronic Medical Records, Jiawei Luo, Shixin Huang, Lan Lan, Shu Yang, Tingqian Cao, Jin Yin, Jiajun Qiu, Xiaoyan Yang, Yingqiang Guo, Xiaobo Zhou

Faculty, Staff and Student Publications

Objective: Longitudinal data from Electronic Medical Records (EMRs) are increasingly utilized to construct predictive models for various clinical tasks, offering enhanced insights into patient health. However, significant discrepancies exist in preprocessing the irregular and intricate EMR data across studies due to the absence of universally accepted tools and standardization methods. This study introduces the Electronic Medical Record Longitudinal Irregular Data Preprocessing (EMR-LIP) framework, a lightweight approach for optimizing the preprocessing of longitudinal, irregular EMR data, aiming to enhance research efficiency, consistency, reproducibility, and comparability.

Materials and methods: EMR-LIP modularizes the preprocessing of longitudinal irregular EMR data, offering tools with a …

Spatial Transcriptome Reveals Histology-Correlated Immune Signature Learnt By Deep Learning Attention Mechanism On H&E-Stained Images For Ovarian Cancer Prognosis, Chun Wai Ng, Kwong-Kwok Wong, Barrett C Lawson, Sammy Ferri-Borgogno, Samuel C Mok

Faculty, Staff and Student Publications

Background: The ability to predict the prognosis of patients with ovarian cancer can greatly improve disease management. However, the knowledge on the mechanism of the prediction is limited. We sought to deconvolute the attention feature learnt by a deep learning convolutional neural networks trained with whole-slide images (WSIs) of hematoxylin-and-eosin (H&E)-stained tumor samples using spatial transcriptomic data.

Methods: In this study, 773 WSIs of H&E-stained tumor sections from 335 patients with treatment naïve high-grade serous ovarian cancer who were included in The Cancer Genome Atlas (TCGA) Pan-Cancer study were used to train, and validate, and to test a ResNet101 CNN …

Real-Time Cbct Imaging And Motion Tracking Via A Single Arbitrarily-Angled X-Ray Projection By A Joint Dynamic Reconstruction And Motion Estimation (Dreme) Framework, Hua-Chieh Shao, Tielige Mengke, Tinsu Pan, You Zhang

Faculty, Staff and Student Publications

Objective: Real-time cone-beam computed tomography (CBCT) provides instantaneous visualization of patient anatomy for image guidance, motion tracking, and online treatment adaptation in radiotherapy. While many real-time imaging and motion tracking methods leveraged patient-specific prior information to alleviate under-sampling challenges and meet the temporal constraint (< 500 ms), the prior information can be outdated and introduce biases, thus compromising the imaging and motion tracking accuracy. To address this challenge, we developed a framework dynamic reconstruction and motion estimation (DREME) for real-time CBCT imaging and motion estimation, without relying on patient-specific prior knowledge.

Approach: DREME incorporates a deep learning-based real-time CBCT imaging and motion estimation method into a dynamic CBCT reconstruction framework. The reconstruction framework reconstructs a dynamic sequence of CBCTs in a data-driven manner from a standard pre-treatment scan, without requiring patient-specific prior knowledge. Meanwhile, a convolutional neural network-based motion encoder is jointly trained during the reconstruction …

Theoretical Analysis Of Cnns For Automatic Seizure Detection In Eeg Signals, Jackson T. Small

Honors Undergraduate Theses

Epilepsy is a common brain disorder where neurons in the brain rapidly fire, causing recurring seizures. The brain activity during a seizure can be detected by electroencephalogram (EEG) signals; however, this process is not only labor-intensive and time-consuming but is also subject to inter-rater variability, with a study showing only moderate agreement when diagnosing patients, even among experts. Convolutional Neural Networks (CNNs) are often proposed to detect seizures automatically, achieving high performance. The focus on performance comes at a cost of losing interpretability, leaving the model as effective but seen as a ’black box’. This thesis confronts the interpretability knowledge …

Combining Biology-Based And Mri Data-Driven Modeling To Predict Response To Neoadjuvant Chemotherapy In Patients With Triple-Negative Breast Cancer, Casey E Stowers, Chengyue Wu, Zhan Xu, Sidharth Kumar, Clinton Yam, Jong Bum Son, Jingfei Ma, Jonathan I Tamir, Gaiane M Rauch, Thomas E Yankeelov

Faculty, Staff and Student Publications

Purpose

To combine deep learning and biology-based modeling to predict the response of locally advanced, triple-negative breast cancer before initiating neoadjuvant chemotherapy (NAC).

Materials and Methods

In this retrospective study, a biology-based mathematical model of tumor response to NAC was constructed and calibrated on a patient-specific basis using imaging data from patients enrolled in the MD Anderson A Robust TNBC Evaluation FraMework to Improve Survival trial (ARTEMIS; ClinicalTrials.gov registration no. NCT02276443) between April 2018 and May 2021. To relate the calibrated parameters in the biology-based model and pretreatment MRI data, a convolutional neural network (CNN) was employed. The CNN …

Combining Biology-Based And Mri Data-Driven Modeling To Predict Response To Neoadjuvant Chemotherapy In Patients With Triple-Negative Breast Cancer, Casey E Stowers, Chengyue Wu, Zhan Xu, Sidharth Kumar, Clinton Yam, Jong Bum Son, Jingfei Ma, Jonathan I Tamir, Gaiane M Rauch, Thomas E Yankeelov

Faculty, Staff and Student Publications

Triple-negative breast cancer (TNBC) is an aggressive breast cancer subtype associated with limited targeted treatment options, heterogeneous treatment response, and high risk of early recurrence. Artificial intelligence (AI) has rapidly emerged as a powerful tool to address key clinical challenges in TNBC across diagnosis, treatment response assessment, and prognosis. Diagnostic and staging challenges persist due to variable imaging features in TNBC and limitations in conventional modalities, increasing the risk of delayed detection. Predicting response to neoadjuvant systemic therapy remains difficult, as patient responses are heterogeneous, and existing clinical markers provide limited early predictive value. Prognostication in TNBC is similarly constrained …