2,313 research outputs found
AI-based density prediction for breast cancer prevention:Can we measure mammographic density in just one breast?
No full textBreast density is an important factor in assessing individual breast cancer risk. We aim to identify women at increased risk of developing breast cancer before they enter routine screening, using mammography in combination with known risk factors. This will enable targeting of preventive therapies and personalised screening. To reduce radiation risk, this paper examines whether density measurements in one breast or mammographic view could be used to accurately reflect individual risk. We analysed breast cancer risk using breast density in a 1:3 case-control dataset of mammograms from the Predicting Risk of Cancer at Screening Study (PROCAS). Breast density was measured using pVAS, an AI-based approach. Cancer risk in low and high breast density groups was compared using conditional logistic regression. High breast density was independently associated with increased breast cancer risk. Women in the highest breast density quintile averaged across all views had an Odds Ratio (OR) of 4.16 (95% CI 2.90-5.97) compared to those in the lowest. A similar OR was found in both the left 3.77 (95% CI 2.68-5.31) and right 4.52 (95% CI 3.12-6.55) breasts individually. ORs were also significant for each individual view: right mediolateral oblique (MLO) 4.19 (2.92–6.00), right craniocaudal (CC) 4.40 (3.09–6.27), left MLO 3.27 (2.34–4.56) and left CC 3.65 (2.60–5.11). The ability to predict breast cancer risk due to increased breast density was achieved using one breast and even one mammographic view. This provides the possibility of a pre-screening risk assessment using fewer images and therefore less radiation.</p
'Pilings of Thought Under Spoken': The Poetry of Susan Howe, 1974-1993.
No full textPhDThis thesis discusses the poetry published by contemporary American poet Susan
Howe over a period of almost two decades. The dissertation is chiefly concerned with
articulating the relationship between poetic form, history, and authority in this body
of' work. Howe's poetry dredges the past for the linguistic effects of patriarchy,
colonialism and war. My reading of the work is an exploration of the ways in which a
disjunctive poetics can address such historical trauma. The poems, rather than
attempting to reinstate voices lifted from what Howe has called "the dark side of
history", are a means of reflecting the resistance that the past offers to contemporary
investigation. It is the effacement, and not the recovery, of history's victims, that is
discernible in the contours of these highly opaque texts. Notions of authority are most
often addressed in the poetry through the figure of paternal absence, which has a
threefold function in the work, serving to represent social authority, an aporetic
conception of divinity and an autobiographical narrative. Alongside the antiauthoritarian
currents in the writing - critiques, for example, of the doctrine of
Manifest Destiny or of scapegoating versions of femininity - my thesis stresses Howe's
engagement with negative theology and with a strain of American Protestant
enthusiasm that has its roots in 17th century New England. The dissertation explores
the dissonance caused by the co-existence in the poetry of elements of political dissent
and religious mysticism. Finally, I consider Howe's engagement with literary history
and authors such as Shakespeare, Swift, Thoreau and Melville. The manner in which
Howe deploys the words of others in her work, I argue, allows for a mixture of textual
polyphony and a more conventional notion of authorial 'voice'
Maintaining high resolution information in AI-based breast cancer risk prediction
No full textThe prevention and early detection of breast cancer hinges on precise prediction of individual breast cancer risk. Whilst well-established clinical risk factors can be used to stratify the population into risk groups, the addition of genetic information and breast density has been shown to improve prediction. Deep learning based approach have been shown to automatically extract complex information from images. However, this is a challenging area of research, partly due to the lack of data within the field, therefore there is scope for novel approaches. Our method uses Multiple Instance Learning in tandem with attention in order to make accurate, short-term risk predictions from full-sized mammograms taken prior to the detection of cancer. This approach ensures small features like calcifications are not lost in a downsizing process and the whole mammogram is analysed effectively. An attention pooling mechanism is designed to highlight patches of increased importance and improve performance. We also use transfer learning in order to utilise a rich source of screen-detected cancers and evaluate whether a model trained to detect cancers in mammograms allows us also to predict risk in priors. Our model achieves an AUC of 0.620 (0.585,0.657) in cancer-free screening mammograms of women who went on to a screen-detected or interval cancer between 5 and 55 months later, including for common breast cancer risk factors. Additionally, our model is able to discriminate interval cancers at an AUC of 0.638 (0.572, 0.703) and highlights the potential for such a model to be used alongside national screening programmes.</p
Multiclass characterization of colorectal polyps under class imbalance using a calibrated cascade model
No full textColorectal cancer (CRC) is a significant g lobal h ealth i ssue, r esponsible f or n umerous a nnual cancer-related deaths. Colorectal polyps (CRPs), as precursors to CRC, necessitate early detection and precise characterization to enhance patient outcomes and decrease mortality rates. While much of the current research focuses on benign-malignant classification, t he a dvancement o f m ulti-class c haracterization f or p olyp t ypes through computer-assisted analysis is gaining critical importance in enhancing diagnostic accuracy and supporting clinical decision-making. However, a significant challenge lies in addressing class imbalances within the data, which can bias model performance towards more prevalent classes and hinder the detection of less common but potentially more dangerous polyps. To address this challenge, this study introduces a sequential binary decision-making approach for characterizing CRP pathologies, distinguishing between Adenocarcinoma, Adenoma, and Hyperplasia. This method aims to leverage the structured decision-making advantages of decision trees within a neural network-based approach by decomposing the complex task of multi-class characterization into a sequential series of binary decisions. Each binary classifier f ocuses o n d istinguishing a s pecific cl ass (o ne-vs.-all), enabling a more interpretable decision-making process. When combining this approach with calibration, the resulting performance demonstrates that the proposed calibrated cascade model achieves notable improvements over conventional multi-class CNN models and ensemble approaches, with a 2.8% improvement in F1 score compared to the state-of-the-art method. By addressing class imbalance and incorporating confidence c alibration, t his approach offers a reliable and interpretable solution for multi-class CRP characterization, contributing significantly to the advancement of computer-aided colorectal diagnostics
Red Cardinal, White Snow
No full textIn Red Cardinal, White Snow, Susan Ayres tells us in the first poem that childhood is not a meadow, and she will document the spirit shatter of mental illness and family trauma. But these stunning poems do so for the sake of talking back to ruin, showing us the beauty of love under pressure, how illumination coexists with heartache, and disorder strengthens kindness. These poems are a master class in the art of becoming human. ~Betsy Sholl
The poems in Red Cardinal, White Snow by Susan Ayres allow readers to touch “the broken membrane between sanity and terror.” That membrane has all the voltage and punch of a live wire, but the powerful, heart-heavy, and earthy, images ground us, keep us safe as we are reminded how shockingly fragile living and loving well can be. ~Tomás Q. Morín
In Red Cardinal, White Snow, the poet’s work has been to mold the mud of experience into a vase of words. And she has succeeded by calling on all the shaping devices of poetic form. From the brilliant title and perfectly chosen Octavio Paz epigraph, to the striking metaphors, and memorable diction (“susurrated stories”), Ayres’ poems transform howls of anguish into art. What an accomplishment. ~Bonnie Lyons, author of So Fa
Using an AI-based density prediction method to explore the risk of breast cancer in different ethnic groups
No full textR. Williams letter to Mrs. Susan M.Weirman, July 21, 1896
No full textResponse letter from R. Williams to Susan M. Wierman [sometimes spelled Weirman] following up on a visit from photographer M. Wooley, presumably to snap photographs of Susan and the Lundy home to accompany Williams' biographical essay on Lundy. Williams sends along Wooley's letters and requests additional information from Ms. Wierman about the life and times of some meeting houses significant in the life and times of her father, anti-slavery activist and abolitionist periodical publisher Benjamin Lundy. Benjamin Lundy (1789-1839) was a prominent Quaker abolitionist best known for his development of abolitionist periodicals. His Genius of Universal Emancipation was first published in 1821 from his home in Mt. Pleasant, Ohio, and enjoyed a wide circulation across the antebellum United States. In the 1820s, the young William Lloyd Garrison came to work for The Genius. Benjamin Lundy traveled widely seeking subscriptions to The Genius, giving talks about the anti-slavery movement, and observing and documenting the conditions of enslaved people across the Americas. He was also involved in the establishment of freed slave colonies in Mexico
AI-assisted prostate cancer detection and localisation on biparametric MR by classifying radiologist-positives
Full text linkProstate cancer diagnosis through MR imaging have currently relied on radiologists’ interpretation, whilst modern AI-based methods have been developed to detect clinically significant cancers independent of radiologists. In this study, we propose to develop deep learning models that improve the overall cancer diagnostic accuracy, by classifying radiologist-identified patients or lesions (i.e. radiologist-positives), as opposed to the existing models that are trained to discriminate over all patients. We develop a single voxel-level classification model, with a simple percentage threshold to determine positive cases, at levels of lesions, Barzell-zones and patients. Based on the presented experiments from two clinical data sets, consisting of histopathology-labelled MR images from more than 800 and 500 patients in the respective UCLA and UCL PROMIS studies, we show that the proposed strategy can improve the diagnostic accuracy, by augmenting the radiologist reading of the MR imaging. Among varying definition of clinical significance, the proposed strategy, for example, achieved a specificity of 44.1% (with AI assistance) from 36.3% (by radiologists alone), at a controlled sensitivity of 80.0% on the publicly available UCLA data set. This provides measurable clinical values in a range of applications such as reducing unnecessary biopsies, lowering cost in cancer screening and quantifying risk in therapies
Subjective Versus Objective: An Exploratory Analysis of Latino Primary Care Patients With Self-Perceived Depression Who Do Not Fulfill Primary Care Evaluation of Mental Disorders Patient Health Questionnaire Criteria for Depression
No full textObjective: Identification and treatment of depression may be difficult for primary care providers when there is a mismatch between the patient’s subjective experiences of illness and objective criteria. Cultural differences in presentation of symptoms among Latino immigrants may hinder access to care for treatment of depression. This article seeks to describe the self-perceptions and symptoms of Latino primary care patients who identify themselves as depressed but do not meet screening criteria for depression.
Method: A convenience sample of Latino immigrants (N = 177) in Corona, Queens, New York, was obtained from a primary care practice from August 2008 to December 2008. The sample was divided into 3 groups according to whether participants met Patient Health Questionnaire diagnostic criteria for depression and whether or not participants had a self-perceived mental health problem and self-identified their problem as “depression” from a checklist of cultural idioms of distress. Psychosocial, demographic, and treatment variables were compared between the 3 groups.
Results: Participants’ descriptions of symptoms had a predominantly somatic component. The most common complaints were ánimo bajo (low energy) and decaimiento (weakness). Participants with “subjective” depression had mean scores of somatic symptoms and depression severity that were significantly lower than the participants with “objective” depression and significantly higher than the group with no depression (P < .0001).
Conclusions: Latino immigrants who perceive that they need help with depression, but do not meet screening criteria for depression, still have significant distress and impairment. To avoid having these patients “fall through the cracks,” it is important to take into account culturally accepted expressions of distress and the meaning of illness for the individual.Peer reviewe
- …
