Search

Your search keyword '"Hall, Geoff"' showing total 616 results
Start Over Author "Hall, Geoff"
616 results on '"Hall, Geoff"'

2. Predicting Ovarian Cancer Treatment Response in Histopathology using Hierarchical Vision Transformers and Multiple Instance Learning

Author

Breen, Jack, Allen, Katie, Zucker, Kieran, Hall, Geoff, Ravikumar, Nishant, and Orsi, Nicolas M.

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Artificial Intelligence, Computer Science - Computer Vision and Pattern Recognition
Abstract

For many patients, current ovarian cancer treatments offer limited clinical benefit. For some therapies, it is not possible to predict patients' responses, potentially exposing them to the adverse effects of treatment without any therapeutic benefit. As part of the automated prediction of treatment effectiveness in ovarian cancer using histopathological images (ATEC23) challenge, we evaluated the effectiveness of deep learning to predict whether a course of treatment including the antiangiogenic drug bevacizumab could contribute to remission or prevent disease progression for at least 6 months in a set of 282 histopathology whole slide images (WSIs) from 78 ovarian cancer patients. Our approach used a pretrained Hierarchical Image Pyramid Transformer (HIPT) to extract region-level features and an attention-based multiple instance learning (ABMIL) model to aggregate features and classify whole slides. The optimal HIPT-ABMIL model had an internal balanced accuracy of 60.2% +- 2.9% and an AUC of 0.646 +- 0.033. Histopathology-specific model pretraining was found to be beneficial to classification performance, though hierarchical transformers were not, with a ResNet feature extractor achieving similar performance. Due to the dataset being small and highly heterogeneous, performance was variable across 5-fold cross-validation folds, and there were some extreme differences between validation and test set performance within folds. The model did not generalise well to tissue microarrays, with accuracy worse than random chance. It is not yet clear whether ovarian cancer WSIs contain information that can be used to accurately predict treatment response, with further validation using larger, higher-quality datasets required., Comment: Submission to ATEC23 challenge at MICCAI 2023 conference

Published
2023

3. Artificial Intelligence in Ovarian Cancer Histopathology: A Systematic Review

Author

Breen, Jack, Allen, Katie, Zucker, Kieran, Adusumilli, Pratik, Scarsbrook, Andy, Hall, Geoff, Orsi, Nicolas M., and Ravikumar, Nishant

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Artificial Intelligence, Computer Science - Machine Learning
Abstract

Purpose - To characterise and assess the quality of published research evaluating artificial intelligence (AI) methods for ovarian cancer diagnosis or prognosis using histopathology data. Methods - A search of PubMed, Scopus, Web of Science, CENTRAL, and WHO-ICTRP was conducted up to 19/05/2023. The inclusion criteria required that research evaluated AI on histopathology images for diagnostic or prognostic inferences in ovarian cancer. The risk of bias was assessed using PROBAST. Information about each model of interest was tabulated and summary statistics were reported. PRISMA 2020 reporting guidelines were followed. Results - 1573 records were identified, of which 45 were eligible for inclusion. There were 80 models of interest, including 37 diagnostic models, 22 prognostic models, and 21 models with other diagnostically relevant outcomes. Models were developed using 1-1375 slides from 1-776 ovarian cancer patients. Model outcomes included treatment response (11/80), malignancy status (10/80), stain quantity (9/80), and histological subtype (7/80). All models were found to be at high or unclear risk of bias overall, with most research having a high risk of bias in the analysis and a lack of clarity regarding participants and predictors in the study. Research frequently suffered from insufficient reporting and limited validation using small sample sizes. Conclusion - Limited research has been conducted on the application of AI to histopathology images for diagnostic or prognostic purposes in ovarian cancer, and none of the associated models have been demonstrated to be ready for real-world implementation. Key aspects to help ensure clinical translation include more transparent and comprehensive reporting of data provenance and modelling approaches, as well as improved quantitative performance evaluation using cross-validation and external validations.

Published
2023

5. Efficient subtyping of ovarian cancer histopathology whole slide images using active sampling in multiple instance learning

Author

Breen, Jack, Allen, Katie, Zucker, Kieran, Hall, Geoff, Orsi, Nicolas M., and Ravikumar, Nishant

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Weakly-supervised classification of histopathology slides is a computationally intensive task, with a typical whole slide image (WSI) containing billions of pixels to process. We propose Discriminative Region Active Sampling for Multiple Instance Learning (DRAS-MIL), a computationally efficient slide classification method using attention scores to focus sampling on highly discriminative regions. We apply this to the diagnosis of ovarian cancer histological subtypes, which is an essential part of the patient care pathway as different subtypes have different genetic and molecular profiles, treatment options, and patient outcomes. We use a dataset of 714 WSIs acquired from 147 epithelial ovarian cancer patients at Leeds Teaching Hospitals NHS Trust to distinguish the most common subtype, high-grade serous carcinoma, from the other four subtypes (low-grade serous, endometrioid, clear cell, and mucinous carcinomas) combined. We demonstrate that DRAS-MIL can achieve similar classification performance to exhaustive slide analysis, with a 3-fold cross-validated AUC of 0.8679 compared to 0.8781 with standard attention-based MIL classification. Our approach uses at most 18% as much memory as the standard approach, while taking 33% of the time when evaluating on a GPU and only 14% on a CPU alone. Reducing prediction time and memory requirements may benefit clinical deployment and the democratisation of AI, reducing the extent to which computational hardware limits end-user adoption.

Published
2023

8. Literature, Challenge, and Mediation in 21st Century Language Learning

Author

Hall, Geoff

Abstract

New directions in language learning and teaching are evident today. Students bring transnational, multicultural, multilingual, and digitally mediated experiences and identities into classrooms still sometimes too much modelled on outdated one-language-one-culture-one nation ideologies. Literature's value in these new circumstances is to challenge readers to independent interpretations, learning, and creativity, with refreshed understandings of what language, culture or indeed literature might be. In this paper I review some relevant recent interventions into the foreign language education field, including a reference to the Council of Europe's (2018) Companion. I then give a brief example from my own use of a literary text in China. [For the complete volume, "Literature in Language Learning: New Approaches," see ED608008.]

Published
2020

9. The pitfalls of using open data to develop deep learning solutions for COVID-19 detection in chest X-rays

Author

Harkness, Rachael, Hall, Geoff, Frangi, Alejandro F, Ravikumar, Nishant, and Zucker, Kieran

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Since the emergence of COVID-19, deep learning models have been developed to identify COVID-19 from chest X-rays. With little to no direct access to hospital data, the AI community relies heavily on public data comprising numerous data sources. Model performance results have been exceptional when training and testing on open-source data, surpassing the reported capabilities of AI in pneumonia-detection prior to the COVID-19 outbreak. In this study impactful models are trained on a widely used open-source data and tested on an external test set and a hospital dataset, for the task of classifying chest X-rays into one of three classes: COVID-19, non-COVID pneumonia and no-pneumonia. Classification performance of the models investigated is evaluated through ROC curves, confusion matrices and standard classification metrics. Explainability modules are implemented to explore the image features most important to classification. Data analysis and model evaluations show that the popular open-source dataset COVIDx is not representative of the real clinical problem and that results from testing on this are inflated. Dependence on open-source data can leave models vulnerable to bias and confounding variables, requiring careful analysis to develop clinically useful/viable AI tools for COVID-19 detection in chest X-rays., Comment: To be published in MedInfo 21 - 18th World Congress on Medical and Health Informatics; 5 pages, 5 figures

Published
2021

15. The Battle Of The Bargain: A Case Comment On 660 Sunningdale GP Inc. v. First Source Mortgage Corp, 2024 ONCA 252

Author

Hall, Geoff

Subjects
Mortgages -- Cases, Banking industry -- Prices and rates, Contracts -- Cases, Company legal issue, Mortgages, Business, international
Abstract

Commitment fees, penalty clauses, and relief from forfeiture: the bargain prevails in the Court of Appeal for Ontario There is sometimes something of a battle in contract cases between enforcement [...]

Published
2024

18. Process Mining on the Extended Event Log to Analyse the System Usage During Healthcare Processes (Case Study: The GP Tab Usage During Chemotherapy Treatments)

Author

Kurniati, Angelina Prima, Hall, Geoff, Hogg, David, Johnson, Owen, van der Aalst, Wil, Series Editor, Mylopoulos, John, Series Editor, Rosemann, Michael, Series Editor, Shaw, Michael J., Series Editor, Szyperski, Clemens, Series Editor, Leemans, Sander, editor, and Leopold, Henrik, editor

Published
2021
Full Text
View/download PDF

20. A Multi-level Approach for Identifying Process Change in Cancer Pathways

Author

Kurniati, Angelina Prima, McInerney, Ciarán, Zucker, Kieran, Hall, Geoff, Hogg, David, Johnson, Owen, van der Aalst, Wil, Series Editor, Mylopoulos, John, Series Editor, Rosemann, Michael, Series Editor, Shaw, Michael J., Series Editor, Szyperski, Clemens, Series Editor, Di Francescomarino, Chiara, editor, Dijkman, Remco, editor, and Zdun, Uwe, editor

Published
2019
Full Text
View/download PDF

21. Mapping Cortical and Subcortical Asymmetry in Obsessive-Compulsive Disorder: Findings From the ENIGMA Consortium

Author

Kong, Xiang-Zhen, Boedhoe, Premika S.W., Abe, Yoshinari, Alonso, Pino, Ameis, Stephanie H., Anticevic, Alan, Arnold, Paul D., Assogna, Francesca, Baker, Justin T., Banaj, Nerisa, Bargalló, Nuria, Batistuzzo, Marcelo C., Benedetti, Francesco, Beucke, Jan C., Bollettini, Irene, Bose, Anushree, Brandeis, Daniel, Brem, Silvia, Brennan, Brian P., Buitelaar, Jan, Busatto, Geraldo F., Calvo, Anna, Calvo, Rosa, Cheng, Yuqi, Cho, Kang Ik K., Ciullo, Valentina, Dallaspezia, Sara, Denys, Damiaan, de Vries, Froukje E., de Wit, Stella J., Dickie, Erin, Drechsler, Renate, Ely, Benjamin A., Esteves, Madalena, Falini, Andrea, Fang, Yu, Feusner, Jamie, Figee, Martijn, Fitzgerald, Kate D., Fontaine, Martine, Fouche, Jean-Paul, Fridgeirsson, Egill A., Gruner, Patricia, Gürsel, Deniz A., Hall, Geoff, Hamatani, Sayo, Hanna, Gregory L., Hansen, Bjarne, Hauser, Tobias U., Hirano, Yoshiyuki, Hoexter, Marcelo Q., Hu, Hao, Huyser, Chaim, Ikari, Keisuke, Jahanshad, Neda, James, Anthony, Jaspers-Fayer, Fern, Kathmann, Norbert, Kaufmann, Christian, Koch, Kathrin, Kuno, Masaru, Kvale, Gerd, Kwon, Jun Soo, Lazaro, Luisa, Liu, Yanni, Lochner, Christine, Magalhães, Ricardo, Marques, Paulo, Marsh, Rachel, Martínez-Zalacaín, Ignacio, Masuda, Yasutaka, Mataix-Cols, David, Matsumoto, Koji, McCracken, James T., Menchón, José M., Miguel, Euripedes C., Minuzzi, Luciano, Moreira, Pedro S., Morer, Astrid, Morgado, Pedro, Nakagawa, Akiko, Nakamae, Takashi, Nakao, Tomohiro, Narayanaswamy, Janardhanan C., Narumoto, Jin, Nishida, Seiji, Nurmi, Erika L., O'Neill, Joseph, Pariente, Jose C., Perriello, Chris, Piacentini, John, Piras, Fabrizio, Piras, Federica, Pittenger, Christopher, Poletti, Sara, Reddy, Y.C. Janardhan, Reess, Tim, Rus-Oswald, Oana Georgiana, Sakai, Yuki, Sato, Joao R., Schmaal, Lianne, Shimizu, Eiji, Simpson, H. Blair, Soreni, Noam, Soriano-Mas, Carles, Sousa, Nuno, Spalletta, Gianfranco, Stern, Emily R., Stevens, Michael C., Stewart, S. Evelyn, Szeszko, Philip R., Takahashi, Jumpei, Tang, Jinsong, Thorsen, Anders Lillevik, Tolin, David F., Tsuchiyagaito, Aki, van Rooij, Daan, van Wingen, Guido A., van der Werf, Ysbrand D., Veltman, Dick J., Vecchio, Daniela, Venkatasubramanian, Ganesan, Walitza, Susanne, Wang, Zhen, Watanabe, Anri, Xu, Jian, Xu, Xiufeng, Yamada, Kei, Yoshida, Tokiko, Yun, Je-Yeon, Zarei, Mojtaba, Zhao, Qing, Zhou, Cong, Thompson, Paul M., Stein, Dan J., van den Heuvel, Odile A., Francks, Clyde, Glahn, David C., and Medland, Sarah E.

Published
2020
Full Text
View/download PDF

31. Maintenance olaparib in patients with platinum-sensitive relapsed ovarian cancer: Outcomes by somatic and germline BRCA and other homologous recombination repair gene mutation status in the ORZORA trial

Author

Pignata, Sandro, Oza, Amit, Hall, Geoff, Pardo, Beatriz, Madry, Radoslaw, Cibula, David, Klat, Jaroslav, Montes Worboys, Ana, Glasspool, Rosalind, Colombo, Nicoletta, Pete, Imre, Herrero Ibáñez, Ana, Romeo Marín, Margarita, Ilieva, Rumyana, Timcheva, Constanta, Maio, Massimo di, Blakeley, Christopher, Taylor, Rosie, Barnicle, Alan, Clamp, Andrew, Pignata, S, Oza, A, Hall, G, Pardo, B, Madry, R, Cibula, D, Klat, J, Montes, A, Glasspool, R, Colombo, N, Pete, I, Herrero Ibáñez, A, Marín, M, Ilieva, R, Timcheva, C, Di Maio, M, Blakeley, C, Taylor, R, Barnicle, A, and Clamp, A

Subjects
Olaparib, Oncology, Maintenance, Ovarian cancer, BRCA mutation, Càncer d'ovari, Genetics, Obstetrics and Gynecology, HRR, Genètica
Abstract

Background: The open-label, single-arm, multicenter ORZORA trial (NCT02476968) evaluated the efficacy and safety of maintenance olaparib in patients with platinum-sensitive relapsed ovarian cancer (PSR OC) who had tumor BRCA mutations (BRCAm) of germline (g) or somatic (s) origin or non-BRCA homologous recombination repair mutations (HRRm) and were in response to their most recent platinum-based chemotherapy after ≥2 lines of treatment. Methods: Patients received maintenance olaparib capsules (400mg twice daily) until disease progression. Prospective central testing at screening determined tumor BRCAm status and subsequent testing determined gBRCAm or sBRCAm status. Patients with predefined non-BRCA HRRm were assigned to an exploratory cohort. The co-primary endpoints were investigator-assessed progression-free survival (PFS; modified Response Evaluation Criteria in Solid Tumors v1.1) in BRCAm and sBRCAm cohorts. Secondary endpoints included health-related quality of life (HRQoL) and tolerability. Results: 177 patients received olaparib. At the primary data cut-off (17 April 2020), the median follow-up for PFS in the BRCAm cohort was 22.3months. The median PFS (95% CI) in BRCAm, sBRCAm, gBRCAm and non-BRCA HRRm cohorts was 18.0 (14.3-22.1), 16.6 (12.4-22.2), 19.3 (14.3-27.6) and 16.4 (10.9-19.3) months, respectively. Most patients with BRCAm reported improvements (21.8%) or no change (68.7%) in HRQoL and the safety profile was as expected. Conclusions: Maintenance olaparib had similar clinical activity in PSR OC patients with sBRCAm and those with any BRCAm. Activity was also observed in patients with a non-BRCA HRRm. ORZORA further supports use of maintenance olaparib in all patients with BRCA-mutated, including sBRCA-mutated, PSR OC.

Published
2023

32. Somatic cancer genetics in the UK: real-world data from phase I of the Cancer Research UK Stratified Medicine Programme

Author

Lindsay, Colin R., Shaw, Emily C., Blackhall, Fiona, Blyth, Kevin G., Brenton, James D., Chaturvedi, Anshuman, Clarke, Noel, Dick, Craig, Evans, Thomas R.J., Hall, Geoff, Hanby, Andrew M., Harrison, David J., Johnston, Stephen R.D., Mason, Malcolm D., Morton, Dion, Newton-Bishop, Julia, Nicholson, Andrew G., Oien, Karin A., Popat, Sanjay, Rassl, Doris, Sharpe, Rowena, Taniere, Phillipe, Walker, Ian, Wallace, William A., West, Nicholas P., Butler, Rachel, Gonzalez de Castro, David, Griffiths, Mike, Johnson, Peter W.M., Rehal, Pauline, Butler, Samantha, Smith, Matthew, Doak, Rachel, Tanska, Anna, Halford, Graham, James, Lisa, Kotara, Chris, Masson, Gareth, Clokie, Sam, Bell, Jennie, Macdonald, Fiona, De Castro, David Gonzalez, Thompson, Lisa, Mair, Debbie, Lillis, Suzanne, Wren, Dorte, Hollifield, Robert, Dover, Keeda, Maurya, Manisha, Brooks, Damian, Gomez, Belen, Grady, Lisa, Jones, Thomas, Hooper, Chantal, Webster, Daphne, Travis, Jolyon, Ogwuru, Stephanie, Gazdova, Jana, Collins, Denise, Chapman, Elaine, Leavey, Lisa, Proszek, Paula, Hulkki, Sanna, Collins, V.Peter, Ibrahim, Ash, Brown, Kat, Burge, Jo, Burnett, Karen, Devonshire, Ginny, Moseley, Ellen, Haynes, Bev, Hodgkin, Charlotte, Jimenez-linan, Merche, Jones, Linda, Kenyon, Gilly, Mahler-araujo, Betania, Payne, Karen, Piper, Jo, Richardson, Sue, Rytina, Ed, Warren, Anne, Coker, Liz, Godsall, Gemma, Arends, Mark, O’Neill, Amanda, Rintoul, Katy, Goymer, Donna, Taylor, Julie, Matthews, Claire, Bhayani, Harshil, Osalador, Tina, Niwaz, Zakiya, Higgins, Anna, Bamsey, Olivia, Salter, Janine, Renouf, Louise, Noel-Storr, Glenn, Roberts, Helen, Gierejko, Kasia, Knapman, Paola, Wotherspoon, Andrew, Stamp, Gordon, Attygailye, Ayoma, Hazell, Steve, Osin, Peter, Nerurkar, Ash, Francis, Steven, Runde, Marion, Arch, Jo, Chitnis, Xavier, Siu, Bernard, Townsend, Debra, Hennelly, Laura, Taylor, Natalie, Johnson, Bernadette, Banerjee, Susie, Pyle, Lynda, Hamill, Monica, Gyertson, Jenny, George, Angela, Patel, Krishna, Pearce, Karla, Edmonds, Kim, Sarker, Sarah, Eeles, Rosalind, Bancroft, Liz, Thomas, Sarah, Kano, Yukie, Rowland, Lisa, Brooks, Karen, O’brien, Mary, Bhosle, Jaishree, Priest, Kathy, Ayite, Bee, Severn, Jo, Beedham, Helen, Lucas, Nicky, Tye, Kim, Lorentzos, Alison, Webb, Janine, Kerr, Sarah, Corestav, Lisa, Bottero, Diego, Jell, Laura, Thomas, Janet, Marriott, Cheryl, Rajah, Neil, Cole, Andy, Ly, Dieu, Taniere, Philippe, O’sullivan, Brendan, Swift, Clare, Hughes, Frances, Neil, Desley, Hanby, Andrew, Banks, Roz, Ajayi, Dolapo, Barclay, Alison, Bishop, Julia Newton, Beirne, Debbie, Bernard, Andrew, Berry, Maxine, Bentley, Jo, Bishop, Tim, Chambers, Amy, Clarke, Jude, Crossley, Anne, Gahir, Narinder, Gibson, Debbie, Good, Rona, Grosios, Konstantina, Harnden, Pat, Hasler, Kate, Hindmarch, Damien, Jackson, Sharon, Johnstone, Colin, Jones, Anne-marie, Lambert, Gil, Lane, Sally, Mcnicholas, Nicola, Millican-Slater, Rebecca, Moriaty, Cath, Newsham, Alex, O’connell, Kara, Ripley, Lisa, Sebag-Montefiore, David, Simpson, Mary, Speirs, Val, Sugden, Joh, Tate, Lauren, Tidswell, Emma, Twelves, Chris, Walker, Christy, Waterhouse, Barry, Waugh, Martin, White, Louise, Wright, Elizabeth, Rogan, Jane, Ashton, Garry, Abbey, Caron, Greenhalgh, Michelle, Nonaka, Daisuke, Shing, Elwyn, Gibbard, Carmen, Burton, Georgina, Fawkes, Naomi, Marsden, Angela, Waddington, Rachael, Harrison, Phil, Moghadam, Shahrzad, Murray, Kate, Brown, Sarah, Mitchinson, Christy, Booton, Richard, Shah, Rajesh, Harrison, David, Oniscu, Anca, Wallace, William, Rae, Frances, Marshall, Craig, Mcleod, Linda, Charles, Morag, Sutherland, Sarah Jane, Dawson, Carol, Mitchell, Paul, Maclellan, Alex, Muir, Sandra, Johnstone, Lynne, O’connor, John, Johnstone, Shirley, Mcpherson, Jim, Hair, Jane, Pignatelli, Massimo, Armstrong, Roma, Oien, Karin, Evans, Jeff, Burgoyne, Margaret, Blessing, Karen, Duthie, Fraser, Moyes, Colin, Mallon, Elizabeth, Millan, David, Roberts, Fiona, Seywright, Morag, Fraser, Siobhan, Ford, Ian, Kean, Sharon, Flood, Marion, Grant, David, Mcdonald, Claire, Moffat, Tom, Mclelland, Hugh, Kyle, Alistair, Cameron, Graham, Wright, Martin, Kenny, Stephen, Mcauslan, Karen, Jones, Andrew, Fitzsimons, Ted, Graham, Fiona, Bell, Alexandra, Duffy, Phil, Fisher, Alec, Smith, Alexis, Shannon, Elaine, Woods, Bryan, Hutchison, Colin, Booth, Angela, Duffy, Lyndsay, Mcculloch, Gillian, Sadiq, Hudda, Deakin, Susan, Haywood, Steven, Mason, Malcolm, Chester, John, Parry-jones, Alison, Macarthur, Abby, Williams, Suzanne, Griffiths, David, Morgan, Fiona, and Bailey, Hazel

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results