-
Digital Pathology, Deep Learning, and Cancer: A Narrative Review medRxiv. Pathol. Pub Date : 2024-03-15 Darnell K Adrian Williams, Gillian Graifman, Nowair Hussain, Maytal Amiel, Tran Priscilla, Arjun Reddy, Ali Haider, Bali Kumar Kavitesh, Austin Li, Leael Alishahian, Nichelle Perera, Corey Efros, Myoungmee Babu, Mathew Tharakan, Mill Etienne, Benson Babu
Background and Objective: Cancer is a leading cause of morbidity and mortality worldwide. The emergence of digital pathology and deep learning technologies signifies a transformative era in healthcare. These technologies can enhance cancer detection, streamline operations, and bolster patient care. A substantial gap exists between the development phase of deep learning models in controlled laboratory
-
Evaluation of ChatGPT's Usefulness and Accuracy in Diagnostic Surgical Pathology. medRxiv. Pathol. Pub Date : 2024-03-13 Vincenzo Guastafierro, Devin Nicole Corbitt, Alessandra Bressan, Bethania Fernandes, Ömer Mintemur, Francesca Magnoli, Susanna Ronchi, Stefano La Rosa, Silvia Uccella, Salvatore Lorenzo Renne
ChatGPT is an artificial intelligence capable of processing and generating human-like language. ChatGPT's role within clinical patient care and medical education has been explored; however, assessment of its potential in supporting histopathological diagnosis is lacking. In this study, we assessed ChatGPT's reliability in addressing pathology-related diagnostic questions across 10 subspecialties, as
-
Early diagnosis of transthyretin amyloidosis by detection of monomers in plasma microsamples using a protein crystal-based assay medRxiv. Pathol. Pub Date : 2024-02-29 Diogo Costa-Rodrigues, Leite Jose, Maria Joao Saraiva, Maria Rosario Almeida, Luis Gales
Amyloid diseases are frequently associated with the appearance of an aberrant form of a protein, whose detection enables early diagnosis. In the case of transthyretin amyloidosis, the aberrant protein, the monomers, constitute the smallest species of the amyloid cascade, which creates engineering opportunities for sensing that remain virtually unexplored. Here, a two-step assay is devised, combining
-
Image-Based Consensus Molecular Subtyping in Rectal Cancer Biopsies and Response to Neoadjuvant Chemoradiotherapy medRxiv. Pathol. Pub Date : 2024-02-09 Maxime W Lafarge, Enric Domingo, Korsuk Sirinukunwattana, Ruby Wood, Leslie Samuel, Graeme Murray, Susan D Richman, Andrew Blake, David Sebag-Montefiore, Simon Gollins, Eckhard Klieser, Daniel Neureiter, Florian Huemer, Richard Greil, Philip Dunne, Philip Quirke, Lukas Weiss, Jens Rittscher, Tim Maughan, Viktor H Koelzer
The development of deep learning (DL) models to predict the consensus molecular subtypes (CMS) from histopathology images (imCMS) is a promising and cost-effective strategy to support patient stratification. Here, we investigate whether imCMS calls generated from whole slide histopathology images (WSIs) of rectal cancer (RC) pre-treatment biopsies are associated with pathological complete response
-
Public evidence on AI products for digital pathology medRxiv. Pathol. Pub Date : 2024-02-06 Gillian A Matthews, Clare McGenity, Daljeet Bansal, Darren Treanor
Background: Novel products applying artificial intelligence (AI)-based approaches to digital pathology images have consistently emerged onto the commercial market, touting improvements in diagnostic accuracy, workflow efficiency, and treatment selection. However, publicly available information on these products can be variable, with few sources to obtain independent evidence. Methods: Our objective
-
Cortico-cortical connectivity is influenced by levodopa in tremor-dominant Parkinson's disease medRxiv. Pathol. Pub Date : 2024-02-06 Brittany K. Rurak, Jane Tan, Julian P. Rodrigues, Brian D. Power, Peter D Drummond, Ann-Maree Vallence
Background: Resting tremor is the most common presenting motor symptom in Parkinson's disease (PD). The supplementary motor area (SMA) is one of the main targets of the basal ganglia-thalamo-cortical circuit and has direct, facilitatory connections with the primary motor cortex (M1), which is important for the execution of voluntary movement. Dopamine potentially modulates SMA and M1 activity, and
-
Multi-V-Stain: Multiplexed Virtual Staining of Histopathology Whole-Slide Images medRxiv. Pathol. Pub Date : 2024-01-26 Sonali Andani, Boqi Chen, Joanna Ficek-Pascual, Simon Heinke, Ruben Casanova, Bettina Sobottka, Bernd Bodenmiller, The Tumor Profiler Consortium, Viktor H Kölzer, Gunnar Rätsch
Pathological assessment of Hematoxylin & Eosin (H&E) stained tissue samples is a well-established clinical routine for cancer diagnosis. While providing rich morphological data, it lacks information on protein expression patterns which is crucial for cancer prognosis and treatment recommendations. Imaging Mass Cytometry (IMC) excels in highly multiplexed protein profiling but faces challenges like
-
Atypia of Undetermined Significance and ThyroSeq v3 Positive Call Rates as Quality Control Metrics for Cytology Laboratory Performance medRxiv. Pathol. Pub Date : 2024-01-26 Odille Mejia-Mejia, Andres Bravo-Gonzalez, Monica Sanchez-Avila, Youley Tjendra, Rodrigo Santoscoy, Katherine Drews-Elger, Yiqin Zuo, Camilo Arias-Abad, Carmen Gomez, Monica Garcia-Buitrago, Mehrdad Nadji, Merce Jorda, Jaylou M. Velez-Torres, Roberto Ruiz-Cordero
Background The Bethesda system (TBS) for reporting thyroid cytopathology recommends an “atypia of undetermined significance (AUS)” rate of 10%. Recent data suggest that this category might be overused when the rate of cases with molecular positive results is low. As a quality metric, we calculated the AUS and positive call rates for our cytology lab and each cytopathologist.
-
Hemoglobin-Albumin-Lymphocyte-Platelet (HALP) score as a predictive value of Incidental prostate cancer for patients going for Transurethral resection of the prostate (TURP): A Single Center Study medRxiv. Pathol. Pub Date : 2024-01-24 Ahmed Bendari
Aims: Prostate cancer is a significant health concern worldwide, and early detection is crucial for effective treatment. This study aimed to investigate the role of the Hemoglobin-Albumin-Lymphocyte-Platelet (HALP) score in detecting prostate cancer in patients undergoing Transurethral Resection of the Prostate (TURP). Additionally, comprehensive analysis was performed to explore clinical parameters
-
The Concept of Stroma AReactive Invasion Front Areas (SARIFA) as a New Prognostic Biomarker for Lipid-driven Cancers Holds True in Pancreatic Ductal Adenocarcinoma medRxiv. Pathol. Pub Date : 2024-01-23 Przemyslaw Grochowski, Bianca Grosser, Florian Sommer, Andreas Probst, Johanna Waidhauser, Gerhard Schenkirsch, Nic Gabriel Reitsam, Bruno Maerkl
Background: Pancreatic ductal adenocarcinoma (PDAC) is a difficult-to-treat entity. To forecast its prognosis, we introduced a new biomarker, SARIFA (stroma areactive invasion front areas), which are an area at the tumour invasion front lacking desmoplastic stroma reaction upon malignant invasion in the surrounding tissue, leading to direct contact between tumour cells and adipocytes. SARIFA showed
-
Label-free virtual peritoneal lavage cytology via deep-learning-assisted single-color stimulated Raman scattering microscopy medRxiv. Pathol. Pub Date : 2024-01-17 Tinghe Fang, Zhouqiao Wu, Xun Chen, Luxin Tan, Zhongwu Li, Jiafu Ji, Yubo Fan, Ziyu Li, Shuhua Yue
Clinical guidelines for gastric cancer treatment recommend intraoperative peritoneal lavage cytology to detect free cancer cells. Patients with positive cytology require neoadjuvant chemotherapy instead of instant resection and conversion to negative cytology results in improved survival. However, the accuracy of cytological diagnosis by pathologists or artificial intelligence is disturbed by manually-produced
-
Validation of an AI-based solution for breast cancer risk stratification using routine digital histopathology images medRxiv. Pathol. Pub Date : 2024-01-16 Abhinav Sharma, Sandy Kang Lövgren, Kajsa Ledesma Eriksson, Yinxi Wang, Stephanie Robertson, Johan Hartman, Mattias Rantalainen
Background Stratipath Breast is a CE-IVD marked artificial intelligence-based solution for prognostic risk stratification of breast cancer patients into high- and low-risk groups, using haematoxylin and eosin (H&E)-stained histopathology whole slide images (WSIs). In this validation study, we assessed the prognostic performance of Stratipath Breast in two independent breast cancer cohorts.
-
How are APOE4, changes in body weight, and longevity related? Insights from a causal mediation analysis medRxiv. Pathol. Pub Date : 2024-01-02 Rachel Holmes, Hongzhe Duan, Olivia Bagley, Deqing Wu, Yury Loika, Alexander Kulminski, Anatoliy Yashin, Konstantin Arbeev, Svetlana Ukraintseva
The ε4 allele of the APOE gene (APOE4) is known for its negative association with human longevity, however, the mechanism is unclear. APOE4 was also linked to changes in body weight, and the latter changes were associated with survival in some studies. Here we explore the role of aging changes in weight in the connection between APOE4 and longevity, using a Causal Mediation Analysis (CMA) approach
-
Resistance to cortical amyloid-beta associates with cognitive health in centenarians medRxiv. Pathol. Pub Date : 2023-12-29 Susan K. Rohde, Patricia Fierro-Hernández, Annemieke J.M. Rozemuller, Netherlands Brain Bank, Linda M.C. Lorenz, Meng Zhang, Marieke Graat, Myke van der Hoorn, Dominique Daatselaar, Marc Hulsman, Philip Scheltens, Sietske A.M. Sikkes, Jeroen J.M. Hoozemans, Henne Holstege
BACKGROUND Amyloid-beta(Aβ)-plaques accumulate in non-demented individuals, particularly at advanced ages. The unclear association between Aβ-pathology and cognition in elderly raises the question whether Aβ-pathology should be considered a benign consequence of aging.
-
Development of a multi-scanner facility for data acquisition for digital pathology artificial intelligence medRxiv. Pathol. Pub Date : 2023-12-29 Matthew P. Humphries, Danny Kaye, Gaby Stankeviciute, Jacob Halliwell, Alexander I Wright, Daljeet Bansal, David Brettle, Darren Treanor
Whole slide imaging (WSI) of pathology glass slides with high-resolution scanners has enabled the large-scale application of artificial intelligence (AI) in pathology, to support the detection and diagnosis of disease, potentially increasing efficiency and accuracy in tissue diagnosis.
-
Focal Usual Interstitial Pneumonia-like Fibrosis is a Core Prognostic Factor in Progressive Pulmonary Fibrosis medRxiv. Pathol. Pub Date : 2023-12-28 Yukio Tsushima, Ethan N. Okoshi, Sousuke Ishijima, Andrey Bychkov, Kris Lami, Shimpei Morimoto, Yasuhiko Yamano, Kensuke Kataoka, Takeshi Johkoh, Yasuhiro Kondoh, Junya Fukuoka
Progressive pulmonary fibrosis (PPF) is a newly recognized clinical phenotype of interstitial lung diseases in the 2022 interstitial pulmonary fibrosis (IPF) guidelines. This category is based entirely on clinical and radiological factors, and the background histopathology is unknown. Our objective was to investigate the histopathological characteristics of PPF and to examine the correlation between
-
Method of combining multiple researches to determine non-infectious disease causes. Analysis of Depression and Celiac disease causes medRxiv. Pathol. Pub Date : 2023-12-27 Alan Olan
In this work an author is introducing a method which using a special algorithm based in math, allows to find disease causes for a specific non-infectious disease using results of multiple researches regarding risk factors of the disease. The method is based on a model presented in the article “A Connection between Factors Causing Diseases and Diseases Frequencies: Its Application in Finding Disease
-
Classifying breast cancer and fibroadenoma tissue biopsies from paraffined stain-free slides by fractal biomarkers in Fourier Ptychographic Microscopy medRxiv. Pathol. Pub Date : 2023-12-24 Vittorio Bianco, Marika Valentino, Daniele Pirone, Lisa Miccio, Pasquale Memmolo, Valentina Brancato, Luigi Coppola, Giovanni Smaldone, Massimiliano D’Aiuto, Gennaro Mossetti, Marco Salvatore, Pietro Ferraro
Breast cancer is one of the most spread and monitored pathologies in high-income countries. After breast biopsy, histological tissue is stored in paraffin, sectioned and mounted. Conventional inspection of tissue slides under benchtop light microscopes involves paraffin removal and staining, typically with H&E. Then, expert pathologists are called to judge the stained slides. However, paraffin removal
-
“Spectromics”: Holistic Optical Assessment of Human Cartilage via Complementary Vibrational Spectroscopy for Osteoarthritis Diagnosis medRxiv. Pathol. Pub Date : 2023-12-24 Hiroki Cook, Anna Crisford, Konstantinos Bourdakos, Douglas Dunlop, Richard OC Oreffo, Sumeet Mahajan
Osteoarthritis (OA) is the most common degenerative joint disease, presented as wearing down of articular cartilage and resulting in pain and limited mobility for 1 in 10 adults in the UK. 1 There is an unmet need for patient friendly paradigms for clinical assessment that do not require ionising radiation (CT), exogenous contrast enhancing dyes (MRI), biopsy, and/or instrumentation approaches (arthroscopy
-
iQC: machine-learning-driven prediction of surgical procedure uncovers systematic confounds of cancer whole slide images in specific medical centers medRxiv. Pathol. Pub Date : 2023-12-21 Andrew J Schaumberg, Michael S Lewis, Ramin Nazarian, Ananta Wadhwa, Nathanael Kane, Graham Turner, Purushotham Karnam, Poornima Devineni, Nicholas Wolfe, Randall Kintner, Matthew B Rettig, Beatrice S Knudsen, Isla P Garraway, Saiju Pyarajan
Problem: The past decades have yielded an explosion of research using artificial intelligence for cancer detection and diagnosis in the field of computational pathology. Yet, an often unspoken assumption of this research is that a glass microscopy slide faithfully represents the underlying disease. Here we show systematic failure modes may dominate the slides digitized from a given medical center,
-
Clinical evaluation of deep learning-based risk profiling in breast cancer histopathology and comparison to an established multigene assay medRxiv. Pathol. Pub Date : 2023-12-17 Yinxi Wang, Wenwen Sun, Emelie Karlsson, Sandy Kang Lövgren, Balázs Ács, Mattias Rantalainen, Stephanie Robertson, Johan Hartman
A significant proportion of oestrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative early breast cancer patients are categorised as intermediate risk based on classic clinicopathological variables, thus providing limited information to guide treatment decisions. The Prosigna assay is one of the established prognostic multigene assays in clinical practice for risk
-
Expansion of Artemisinin Partial Resistance Mutations and Lack of Histidine Rich Protein-2 and -3 Deletions in Plasmodium falciparum infections from Rukara, Rwanda medRxiv. Pathol. Pub Date : 2023-12-18 Cecile Schreidah, David Giesbrecht, Pierre Gashema, Neeva Young, Tharcisse Munyaneza, Claude Mambo Muvunyi, Kyaw Lay Thwai, Jean-Baptiste Mazarati, Jeffrey A Bailey, Jonathan J Juliano, Corine Karema
Background Emerging artemisinin resistance and diagnostic resistance are a threat to malaria control in Africa. Plasmodium falciparum kelch13 (K13) propeller-domain mutations that confer artemisinin partial resistance have emerged in Africa. K13-561H was initially described at a frequency of 7.4% from Masaka in 2014-2015 but not present in nearby Rukara. By 2018, 19.6% of isolates in Masaka and 22%
-
Fully automated histological classification of cell types and tissue regions of celiac disease is feasible and correlates with the Marsh score medRxiv. Pathol. Pub Date : 2023-12-11 Michael Griffin, Aaron M. Gruver, Chintan Shah, Qasim Wani, Darren Fahy, Archit Khosla, Christian Kirkup, Daniel Borders, Jacqueline A. Brosnan-Cashman, Angie D. Fulford, Kelly M. Credille, Christina Jayson, Fedaa Najdawi, Klaus Gottlieb
Aims Histological assessment is essential for the diagnosis and management of celiac disease. Current scoring systems, including modified Marsh (Marsh–Oberhuber) score, lack inter-pathologist agreement. To address this unmet need, we aimed to develop a fully automated, quantitative approach for histology characterisation of celiac disease.
-
Dual T-cell constant β chain (TRBC)1 and TRBC2 staining for the identification of T-cell neoplasms by flow cytometry medRxiv. Pathol. Pub Date : 2023-12-01 Pedro Horna, Matthew J Weybright, Mathieu Ferrari, Dennis Jungherz, YaYi Peng, Zulaikha Akbar, F Tudor Ilca, Gregory E Otteson, Jansen N Seheult, Janosch Ortmann, Min Shi, Paul M Maciocia, Marco Herling, Martin A Pule, Horatiu Olteanu
The diagnosis of leukemic T-cell malignancies is often challenging, due to overlapping features with reactive T-cells and limitations of currently available T-cell clonality assays. Recently developed therapeutic antibodies specific for the mutually exclusive T-cell receptor constant β chain (TRBC)1 and TRBC2 isoforms provide a unique opportunity to assess for TRBC-restriction as a surrogate of clonality
-
Development and validation of a high-throughput qPCR platform for the detection of soil-transmitted helminth infections medRxiv. Pathol. Pub Date : 2023-11-27 Nils Pilotte, Victor Omballa, Monica Voss, Leah Padgett, Malathi Manuel, Jeanne L. Goodman, Tim Littlewood, Zayina Zondervenni Manoharan, Lisette van Lieshout, Jaco Verweij, Manigandan Sekar, Ajith Kumar Muthukumar, Gretchen Walch, Andrew Gonzalez, Sean R Galagan, Sitara Swarna Rao Ajjampur, Moudachirou Ibikounlé, Steven A Williams, Doug Rains, Ushashi Dadwal, Judd L Walson
Background Historically, soil-transmitted helminth (STH) control and prevention strategies have relied on mass drug administration efforts targeting preschool and school-aged children. While these efforts have succeeded in reducing morbidity associated with STH infection, recent modeling efforts have suggested that expanding intervention to treatment of the entire community could achieve transmission
-
A Histological Assessment Tool for Breast Implant Capsules Validated in 480 Patients with and without Capsular Contracture medRxiv. Pathol. Pub Date : 2023-11-27 Andreas Larsen, Adam M Timmermann, Mikela Kring, Tim K Weltz, Mathias Ørholt, Peter Vester-Glowinski, Jens Jørgen Elberg, Jesper Trillingsgaard, Louise V Mielke, Lisbet R Hölmich, Tine E Damsgaard, Anne Roslind, Mikkel Herly
Background Capsular contracture is a severe complication to breast implants, but the pathophysiology remains unclear, and consensus is lacking on how to analyze implant capsules histologically. In this study, we developed and validated a histological semiquantitative assessment tool for analyzing breast implant capsules.
-
Generating synthetic data in digital pathology through diffusion models: a multifaceted approach to evaluation medRxiv. Pathol. Pub Date : 2023-11-22 Matteo Pozzi, Shahryar Noei, Erich Robbi, Luca Cima, Monica Moroni, Enrico Munari, Evelin Torresani, Giuseppe Jurman
Synthetic data has recently risen as a new precious item in the computational pathologist’s toolbox, supporting several tasks such as helping with data scarcity or augmenting training set in deep learning. Nonetheless, the use of such novel resources requires a carefully planned construction and evaluation, to avoid pitfalls such as the generation of clinically meaningless artifacts.
-
A panoptic segmentation approach for tumor-infiltrating lymphocyte assessment: development of the MuTILs model and PanopTILs dataset medRxiv. Pathol. Pub Date : 2023-11-20 Shangke Liu, Mohamed Amgad, Muhammad A. Rathore, Roberto Salgado, Lee A.D. Cooper
Tumor-Infiltrating Lymphocytes (TILs) have strong prognostic and predictive value in breast cancer, but their visual assessment is subjective. To improve reproducibility, the International Immuno-oncology Working Group recently released recommendations for the computational assessment of TILs that build on visual scoring guidelines. However, existing resources do not adequately address these recommendations
-
Myelin pathology in ataxia-telangiectasia is the cell autonomous effect of ATM deficiency in oligodendrocytes medRxiv. Pathol. Pub Date : 2023-11-13 Kai-Hei Tse, Aifang Cheng, Sunny Hoi-Sang Yeung, Jia-Nian Ng, Gerald Wai-Yeung Cheng, Beika Zhu, Qingyang Wang, Yong Cui, Liwen Jiang, Julia Kofler, Karl Herrup
Ataxia-telangiectasia (A-T) is a rare genetic disease caused by mutations in the gene encoding the ATM (ataxia-telangiectasia mutated) protein. Although neuronal degeneration in the cerebellum remains the most prominent sign in A-T pathology, neuroimaging studies reveal myelin abnormalities as early comorbidities. We hypothesize that these myelin defects are the direct consequence of ATM deficiencies
-
Deep learning for subtypes identification of pure seminoma of the testis medRxiv. Pathol. Pub Date : 2023-11-05 Kirill E. Medvedev, Paul H Acosta, Liwei Jia, Nick V. Grishin
The most critical step in the clinical diagnosis workflow is the pathological evaluation of each tumor sample. Deep learning is a powerful approach that is widely used to enhance diagnostic accuracy and streamline the diagnosis process. In our previous study using omics data, we identified two distinct subtypes of pure seminoma. Seminoma is the most common histological type of testicular germ cell
-
Cilostazol may be a better therapeutic agent for acute ischemic stroke because of its efficacy in preventing post-stroke depression medRxiv. Pathol. Pub Date : 2023-10-31 Yuling Zhang, Ganggang Yang, Rui Wang, Xin Wang, Xiying Tan, Chaozhi Tang
Post-stroke depression (PSD) has more than 1/3 complications in ischemic stroke (IS) patients, but there is still no specific drug that can effectively prevent the occurrence of PSD. Cilostazol, commonly used in the treatment of IS, has been found to rescue cognition impairment in recent years, but whether it has the efficacy in preventing PSD remains uncertain. In this study, a total of 431 acute
-
Federated Learning-Driven Collaborative Diagnostic System for Metastatic Breast Cancer medRxiv. Pathol. Pub Date : 2023-10-21 William Gao, Dayong Wang, Yi Huang
Metastatic breast cancer is one of the leading causes of cancer mortality. While there has been progress in developing deep learning-driven diagnostic system for metastatic breast cancer based on histopathological images, it faces a major challenge in real-world application, i.e., how to improve generalizability of the diagnostic models for diverse patient populations and variations in sample and image
-
Head-to-head comparison of composite and individual biomarkers to predict clinical benefit to PD-1 blockade in Non-Small Cell Lung Cancer medRxiv. Pathol. Pub Date : 2023-10-20 Karlijn Hummelink, Vincent van der Noort, Mirte Muller, Robert Schouten, Michel van den Heuvel, Daniela Thommen, Egbert Smit, Gerrit Meijer, Kim Monkhorst
Background Treatment with PD-(L)1 blocking agents has demonstrated durable efficacy in advanced NSCLC, but only in a minority of patients. Multiple biomarkers for predicting treatment benefit have been investigated, but their combined performance has not been extensively studied. Here, we assess the combined predictive performance of multiple biomarkers in a series of NSCLC patients treated with nivolumab
-
Feasibility of Inferring Spatial Transcriptomics from Single-Cell Histological Patterns for Studying Colon Cancer Tumor Heterogeneity medRxiv. Pathol. Pub Date : 2023-10-09 Michael Y. Fatemi, Yunrui Lu, Cyril Sharma, Eric Feng, Zarif L. Azher, Alos B. Diallo, Gokul Srinivasan, Grace M. Rosner, Kelli B. Pointer, Brock C. Christensen, Lucas A. Salas, Gregory J. Tsongalis, Scott M. Palisoul, Laurent Perreard, Fred W. Kolling, Louis J. Vaickus, Joshua J. Levy
Background. Spatial transcriptomics involves studying the spatial organization of gene expression within tissues, offering insights into the molecular diversity of tumors. While spatial gene expression is commonly amalgamated from 1-10 cells across 50-micron spots, recent methods have demonstrated the capability to disaggregate this information at subspot resolution by leveraging both expression and
-
The Overlooked Role of Specimen Preparation in Bolstering Deep Learning-Enhanced Spatial Transcriptomics Workflows medRxiv. Pathol. Pub Date : 2023-10-09 Michael Y. Fatemi, Yunrui Lu, Alos B. Diallo, Gokul Srinivasan, Zarif L. Azher, Brock C. Christensen, Lucas A. Salas, Gregory J. Tsongalis, Scott M. Palisoul, Laurent Perreard, Fred W. Kolling, Louis J. Vaickus, Joshua J. Levy
The application of deep learning methods to spatial transcriptomics has shown promise in unraveling the complex relationships between gene expression patterns and tissue architecture as they pertain to various pathological conditions. Deep learning methods that can infer gene expression patterns directly from tissue histomorphology can expand the capability to discern spatial molecular markers within
-
Evaluating AI-Assistance for Pathologists in Diagnosing and Grading Laryngeal Lesions medRxiv. Pathol. Pub Date : 2023-10-06 Yaelle Bellahsen-Harrar, Melanie Lubrano, Charles Lepine, Aurelie Beaufrere, Claire Bocciarelli, Anais Brunet, Elise Decroix, Franck Neil El-Sissy, Bettina Fabiani, Aurelien Morini, Cyprien Tilmant, Thomas Walter, Cecile Badoual
Importance: Diagnosis of head and neck squamous dysplasias and carcinomas is challenging, with a moderate inter-rater agreement. Nowadays, new artificial intelligence (AI) models are developed to automatically detect and grade lesions, but their contribution to the performance of pathologists has not been assessed. Objective: To evaluate the contribution of our AI tool in assisting pathologists in
-
Development and validation of automated methods for COVID-19 PCR MasterMix preparation. medRxiv. Pathol. Pub Date : 2023-10-05 Giorgio Fedele, Graham Hill, Amelia Sweetford, Suki Lee, Bobby Yau, Domenico R. Caputo, Denise Grovewood, Rowda Dahir, Paula Esquivias Ruiz-Dana, Anika Wisniewska, Anna Di Biase, Miles Gibson, Benita Percival, Stefan Grujic, Donald Peter Fraser
Polymerase Chain Reaction (PCR)-based assays were widely deployed during the SARS- CoV-2 pandemic for population-scale testing. High-throughput molecular diagnostic laboratories required a high degree of process automation to cope with huge testing demand, fast turn-around times and quality requirements. However, the critical step of preparing a PCR MasterMix has often been neglected by process developers
-
Evaluation of ChatGPT's Pathology Knowledge using Board-Style Questions medRxiv. Pathol. Pub Date : 2023-10-03 Saroja Devi Geetha, Anam Khan, Atif Khan, Bijun Sai Kannadath, Taisia Vitkovski
Objectives: ChatGPT is an artificial intelligence (AI) chatbot developed by OpenAI. Its extensive knowledge and unique interactive capabilities enable it to be utilized in various innovative ways in the medical field such as writing clinical notes, simplifying radiology reports. Through this study we aim to analyze its pathology knowledge to advocate its role in transforming pathology education. Methods:
-
TRENDS IN CLINICAL STAGE AT PRESENTATION FOR FOUR COMMON ADULT CANCERS IN IBADAN, NIGERIA medRxiv. Pathol. Pub Date : 2023-09-23 Akinyinka O Omigbodun, Adebayo D Agboola, Olufunke A Fayehun, Motunrayo Ajisola, Abiola Oladejo, Omolara Popoola, Richard J Lilford
Introduction Cancer outcome is largely determined by stage at diagnosis. We hypothesised that people living in Low- and Middle-Income Countries may be reaching diagnosis at an early stage, reflecting growth in awareness of the disease and its symptoms. We examined stage at diagnosis for four common cancers presenting at a referral centre in Nigeria. Methods A retrospective review of case-records from
-
Swiss Digital Pathology Recommendations: Results from a Delphi process conducted by the Swiss Digital Pathology Consortium of the Swiss Society of Pathology medRxiv. Pathol. Pub Date : 2023-09-15 Andrew Janowczyk, Inti Zlobec, Cedric Walker, Sabina Berezowska, Viola Huschauer, Marianne Tinguely, Joel Kupferschmid, Thomas Mallet, Doron Merkler, Mario Kreutzfeldt, Radivoje Gasic, Tilman T. Rau, Luca Mazzucchelli, Isagard Eyberg, Gieri Cathomas, Kirsten D. Mertz, Viktor H. Koelzer, Davide Soldini, Wolfram Jochum, Matthias Rossle, Maurice Henkel, Rainer Grobholz
Integration of digital pathology (DP) into clinical diagnostic workflows is increasingly receiving attention as new hardware and software become available. To facilitate the adoption of DP, the Swiss Digital Pathology Consortium (SDiPath) organized a Delphi process to produce a series of recommendations for DP integration within Swiss clinical environments. This process saw the creation of 4 working
-
Immunohistochemical Study of Histone Protein 3 Modification in Pediatric Osteosarcoma Identifies Reduced H3K27me3 as a Marker of Poor Treatment Response medRxiv. Pathol. Pub Date : 2023-09-15 Sebastian Kondratowski, Danielle Cohen, Rebecca Deyell, Akshdeep Sandhu, Jonathan Willard Bush
The most common pediatric primary malignant bone tumor, osteosarcoma, is often described as genetically non-recurrent and heterogeneous. Neoadjuvant chemotherapy is typically followed by resection and assessment of treatment response, which helps inform prognosis. Identifying biomarkers that may impact chemotherapy response and survival could aid in upfront risk stratification and identify patients
-
Scaling Self-Supervised Learning for Histopathology with Masked Image Modeling medRxiv. Pathol. Pub Date : 2023-09-14 Alexandre Filiot, Ridouane Ghermi, Antoine Olivier, Paul Jacob, Lucas Fidon, Alice Mac Kain, Charlie Saillard, Jean-Baptiste Schiratti
Computational pathology is revolutionizing the field of pathology by integrating advanced computer vision and machine learning technologies into diagnostic workflows. Recently, Self-Supervised Learning (SSL) has emerged as a promising solution to learn representations from histology patches, leveraging large volumes of unannotated whole slide images whole slide images (WSI). In particular, Masked Image
-
Transcriptional Signatures of Hippocampal Tau Pathology in Primary Age-Related Tauopathy and Alzheimers Disease medRxiv. Pathol. Pub Date : 2023-09-12 Genevieve L Stein-O'Brien, Ryan Palaganas, Ernest M Meyer, Javier Redding-Ochoa, Olga Pletnikova, Haidan Guo, William R Bell, Juan C Troncoso, Richard L Huganir, Meaghan Morris
Background: Tau pathology is common in age-related neurodegenerative diseases. Tau pathology in primary age-related tauopathy (PART) and in Alzheimers disease (AD) has a similar biochemical structure and anatomic distribution, which is distinct from tau pathology in other diseases. However, the molecular changes associated with intraneuronal tau pathology in PART and AD, and whether these changes are
-
Assessing the Impact of Pretraining Domain Relevance on Large Language Models Across Various Pathology Reporting Tasks medRxiv. Pathol. Pub Date : 2023-09-11 Yunrui Lu, Gokul Srinivasan, Sarah Preum, Jason Pettus, Matthew Davis, Jack Greenburg, Louis Vaickus, Joshua Levy
Deep learning (DL) algorithms continue to develop at a rapid pace, providing researchers access to a set of tools capable of solving a wide array of biomedical challenges. While this progress is promising, it also leads to confusion regarding task-specific model choices, where deeper investigation is necessary to determine the optimal model configuration. Natural language processing (NLP) has the unique
-
Dendrite: A Structured, Accessible, and Queryable Pathology Search Database for Streamlined Experiment Planning medRxiv. Pathol. Pub Date : 2023-09-10 Yunrui Lu, Robert Hamilton, Jack Greenburg, Gokul Srinivasan, Parth Shah, Sarah Preum, Jason Pettus, Louis Vaickus, Joshua Levy
Pathology reports contain vital information, yet a significant portion of this data remains underutilized in electronic medical record systems due to the unstructured and varied nature of reporting. Although synoptic reporting has introduced reporting standards, the majority of pathology text remains free-form, necessitating additional processing to enable accessibility for research and clinical applications
-
Harnessing Raman spectroscopy and Multimodal Imaging of Cartilage for Osteoarthritis Diagnosis medRxiv. Pathol. Pub Date : 2023-09-06 Anna Crisford, Hiroki Cook, Konstantinos Bourdakos, Doug Dunlop, Seshasailam Venkateswaran, Richard O. C. Oreffo, Sumeet Mahajan
Osteoarthritis (OA) is a complex disease of cartilage characterised by chronic joint pain, limitations in mobility and function leading to reduced quality of life. Current methods to diagnose OA, such as X-ray, MRI and the invasive synovial fluid analysis lack molecular specificity and are limited to detection of the late stages of the disease. A rapid minimally invasive and non-destructive approach
-
Characterizing the phenotypic and genetic structure of psychopathology in UK Biobank medRxiv. Pathol. Pub Date : 2023-09-06 Camille M Williams, Hugo Peyre, Tobias Wolfram, Younga Heather Lee, Tian Ge, Jordan W Smoller, Travis T Mallard, Franck Ramus
Mental conditions exhibit a higher-order transdiagnostic factor structure which helps to explain the widespread comorbidity observed in psychopathology. However, the phenotypic and genetic structures of psychopathology may differ, raising questions about the validity and utility of these factors. Here, we study the phenotypic and genetic factor structures of ten psychiatric conditions using UK Biobank
-
Comparison of TP53 Mutations in Myelodysplasia and Acute Leukemia Suggests Divergent Roles in Initiation and Progression medRxiv. Pathol. Pub Date : 2023-09-05 Ashwini Jambhekar, Emily E Ackerman, Berk A Alpay, Galit Lahav, Scott B Lovitch
TP53 mutation predicts adverse prognosis in many cancers, including myeloid neoplasms, but the mechanisms by which specific mutations impact disease biology, and whether they differ between disease categories, remain unknown. We analyzed TP53 mutations in four myeloid neoplasm subtypes (MDS, AML, AML with myelodysplasia-related changes (AML-MRC), and therapy-related acute myeloid leukemia (tAML)),
-
Validation of Digital Pathology Platform for Metabolic-Associated Steatohepatitis for Clinical Trials medRxiv. Pathol. Pub Date : 2023-09-01 Hanna Pulaski, Shraddha S Mehta, Laryssa C Manigat, Stephanie Kaufman, Hypatia Hou, ILKe Nalbantoglu, Xuchen Zhang, Emily Curl, Ross Taliano, Tae Hun Kim, Michael Torbenson, Jonathan N Glickman, Murray B Resnick, Neel Patel, Cristin E Taylor, Pierre Bedossa, Michael C Montalto, Andrew H Beck, Katy E Wack
Aims: Determine if pathologic assessment of disease activity in steatohepatitis, performed using Whole Slide Images (WSIs) on the AISight Clinical Trials platform, yields results that are comparable to those obtained from the analysis performed using glass slides. Methods and Results: The accuracy of scoring for steatohepatitis (NAS >4 with >1 for each feature and absence of atypical features suggestive
-
Exploring the Pitfalls of Large Language Models: Inconsistency and Inaccuracy in Answering Pathology Board Examination-Style Questions medRxiv. Pathol. Pub Date : 2023-08-28 Shunsuke Koga
In the rapidly advancing field of artificial intelligence, large language models (LLMs) such as ChatGPT and Google Bard are making significant progress, with applications extending across various fields, including medicine. This study explores their potential utility and pitfalls by assessing the performance of these LLMs in answering 150 multiple-choice questions sourced from the PathologyOutlines
-
Pattern of Cutaneous Neoplasms and Associated Factors at a Tertiary Teaching Hospital Pathology Center in Ethiopia: An Eight-Year Histopathological Review medRxiv. Pathol. Pub Date : 2023-08-28 Fuad Temam, Samia Metena Yahya, Bereket Berhane, Frehiwot Daba, Amanuel Yeneneh Teka, Indris Ahmed Yesuf, Tigist Workneh Leulseged
Background: Cancer is the leading cause of death globally and is on the rise in Africa. Cutaneous neoplasms are becoming increasingly common worldwide. Understanding the patterns of this disease is essential for developing data-driven preventive, screening, and treatment services. However, there are limited studies in Ethiopia so far. Therefore, the study aimed to assess the pattern and associated
-
Deep learning-based risk stratification of preoperative breast biopsies using digital whole slide images medRxiv. Pathol. Pub Date : 2023-08-24 Constance Boissin, Yinxi Wang, Abhinav Sharma, Philippe Weitz, Emelie Karlsson, Stephanie Robertson, Johan Hartman, Mattias Rantalainen
Introduction Nottingham histological grade (NHG) is a well established prognostic factor in breast cancer histopathology. However, manual NHG assessment of biopsies is challenging and has a large inter-assessor variability with a large proportion being classified as NHG2 (intermediate grade). Here, we evaluate whether DeepGrade, a previously developed model for the risk stratification of resected tumour
-
Accounting for intensity variation in image analysis of large-scale multiplexed clinical trial datasets medRxiv. Pathol. Pub Date : 2023-08-16 Anja Laura Frei, Anthony McGuigan, Ritik RAK Sinha, Mark A Glaire, Faiz Jabbar, Luciana Gneo, Tijana Tomasevic, Andrea Harkin, Tim Iveson, Mark Saunders, Karin Oien, Noori Maka, Francesco Pezzella, Leticia Campo, Jennifer Hay, Joanne Edwards, Owen Sansom, Caroline Kelly, Ian Tomlinson, Wanja Kildal, Rachel Kerr, David Kerr, Havard Emil Danielsen, Enric Domingo, David N Church, Viktor Hendrik Koelzer
Multiplex immunofluorescence (mIF) imaging can provide comprehensive quantitative and spatial information for multiple immune markers for tumour immunoprofiling. However, application at scale to clinical trial samples sourced from multiple institutions is challenging due to pre-analytical heterogeneity. This study reports an analytical approach to the largest multiparameter immunoprofiling study of
-
Baseline and treatment-emergent bedaquiline resistance in drug-resistant tuberculosis: A systematic review and meta-analysis medRxiv. Pathol. Pub Date : 2023-08-07 Rubeshan Perumal, Neda Bionghi, Camus Nimmo, Marothi Letsoalo, Matthew Cummings, Madeleine Hopson, Allison Wolf, Shamim Jubaer, Nesri Padayatchi, Kogielium Naidoo, Michelle Larsen, Max O'Donnell
Abstract Rationale Bedaquiline is a novel antimycobacterial agent for drug-resistant tuberculosis (DR-TB) and is classified as a World Health Organization (WHO) Group A drug due to its excellent clinical efficacy, high bactericidal activity, and potent sterilizing effect. Baseline and treatment-emergent bedaquiline resistance have been described but prevalence and incidence have not been reported,
-
Flexible and Highly-Efficient Feature Perception for Molecular Traits Prediction via Self-interactive Deep Learning medRxiv. Pathol. Pub Date : 2023-08-05 Yang Hu, Korsuk Sirinukunwattana, Bin Li, Kezia Gaitskell, Willem Bonnaffe, Marta Wojciechowska, Ruby Wood, Nasullah Khalid Alham, Stefano Malacrino, Dan Woodcock, Clare Verrill, Ahmed Ahmed, Jens Rittscher
Predicting disease-related molecular traits from histomorphology brings great opportunities for precision medicine. Despite the rich information present in histopathological images, extracting fine-grained molecular features from standard whole slide images (WSI) is non-trivial. The task is further complicated by the lack of annotations for subtyping and contextual histomorphological features that
-
Universal PCR for Bacteria, Mycobacteria, and Fungi: A 10-year Retrospective Review of Clinical Indications and Patient Outcomes medRxiv. Pathol. Pub Date : 2023-08-04 Jeffrey Kubiak, Alexandra Morgan, Andrea Kirmaier, Ramy Arnaout, Stefan Riedel
Universal PCR for bacteria, mycobacteria, and fungi can aid in the diagnosis of occult infections, especially in the case of fastidious organisms or when prior antimicrobial treatment compromises culture growth. However, the limitations of this technology, including lack of specificity, high cost, long turnaround time, and lack of susceptibility data, may limit its effect on clinical outcomes. We performed
-
Interventions to reduce peripheral blood culture contamination in acute care settings: A systematic review and meta-analysis medRxiv. Pathol. Pub Date : 2023-07-27 James A Hughes, CJ Cabilan, Julian Williams, Mercedes Ray, Fiona Coyer
Background: Blood culture contamination is a significant problem in acute care settings. Contamination of a blood sample with pathogens not present in the patient's blood leads to increases in length of stay, overuse of antimicrobials, and increases in healthcare cost. Several interventions have been reported in different settings within the literature to decrease the contamination. However, their
-
Using an Anomaly Detection Approach for the Segmentation of Colorectal Cancer Tumors in Whole Slide Images medRxiv. Pathol. Pub Date : 2023-07-23 Qiangqiang Gu, Chady Meroueh, Jacob G. Levernier, Trynda N. Kroneman, Thomas J. Flotte, Steven N Hart
Colorectal cancer (CRC) is the 2nd most commonly diagnosed cancer in the United States. Genetic testing is critical in assisting in the early detection of CRC and selection of individualized treatment plans, which have shown to improve the survival rate of CRC patients. The tissue slides review (TSR), a tumor tissue macro-dissection procedure, is a required pre-analytical step to perform genetic testing
-
Lymphoid Enhancer-Binding Factor 1 (LEF1) immunostaining as a surrogate of β-Catenin (CTNNB1) mutations medRxiv. Pathol. Pub Date : 2023-07-12 Ekkehard Hewer, Pascal Fischer, Erik Vassella, Laura Knabben, Sara Imboden, Michael D. Mueller, Tilman T. Rau, Matthias S. Dettmer
Activating mutations affecting exon 3 of the β-Catenin (CTNNB1) gene result in constitutive activation of WNT signalling and are a diagnostic hallmark of several tumour entities including desmoid-type fibromatosis or define clinically relevant subtypes such as in endometrioid carcinoma. In a diagnostic setting, β-Catenin immunohistochemistry is widely used as a surrogate of CTNNB1 mutations, but is
-
A novel approach to classification and segmentation of colon cancer imaging towards personalized medicine medRxiv. Pathol. Pub Date : 2023-07-08 Keerthi Harikrishnan, Amogh Kamat Tarcar, Neil Botelho, Amit Kenkre, Penjo Rebelo
Recent advances in the field of pathology coupled with the rapid evolution of machine learning based techniques have revolutionized healthcare practices. Colorectal cancer accounts for one of the top 5 cancers with high incidence (126,240 in 2020) with a high mortality worldwide [1] [2]. Tissue biopsy remains to be the gold standard procedure for accurate diagnosis, treatment planning and prognosis