Lubaina Arsiwala-Scheppach

Dr. Lubaina Arsiwala-Scheppach

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2023 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
Akhilanand ChaurasiaAkhilanand Chaurasia
Akhilanand Chaurasia
AMAnne Müller
Anne Müller
JKJoachim Krois
Joachim Krois
Falk SchwendickeFalk Schwendicke
Falk Schwendicke
Machine learning (ML) is being increasingly employed in dental research and application. We aimed to systematically compile studies using ML in dentistry and assess their methodological quality, including the risk of bias and reporting standards. We evaluated studies employing ML in dentistry published from 1 January 2015 to 31 May 2021 on MEDLINE, IEEE Xplore, and arXiv. We assessed publication trends and the distribution of ML tasks (classification, object detection, semantic segmentation, instance segmentation, and generation) in different clinical fields. We appraised the risk of bias and adherence to reporting standards, using the QUADAS-2 and TRIPOD checklists, respectively. Out of 183 identified studies, 168 were included, focusing on various ML tasks and employing a broad range of ML models, input data, data sources, strategies to generate reference tests, and performance metrics. Classification tasks were most common. Forty-two different metrics were used to evaluate model performances, with accuracy, sensitivity, precision, and intersection-over-union being the most common. We observed considerable risk of bias and moderate adherence to reporting standards which hampers replication of results. A minimum (core) set of outcome and outcome metrics is necessary to facilitate comparisons across studies.

9 June 2022 in Journal of Dental Research
Verified
Journal Article
Open access
LSL. Schneider
L. Schneider
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
JKJoachim Krois
Joachim Krois
HMH. Meyer-Lueckel
H. Meyer-Lueckel
KBK.K. Bressem
K.K. Bressem
Falk SchwendickeFalk Schwendicke
Falk Schwendicke
A wide range of deep learning (DL) architectures with varying depths are available, with developers usually choosing one or a few of them for their specific task in a nonsystematic way. Benchmarking (i.e., the systematic comparison of state-of-the art architectures on a specific task) may provide guidance in the model development process and may allow developers to make better decisions. However, comprehensive benchmarking has not been performed in dentistry yet. We aimed to benchmark a range of architecture designs for 1 specific, exemplary case: tooth structure segmentation on dental bitewing radiographs. We built 72 models for tooth structure (enamel, dentin, pulp, fillings, crowns) segmentation by combining 6 different DL network architectures (U-Net, U-Net++, Feature Pyramid Networks, LinkNet, Pyramid Scene Parsing Network, Mask Attention Network) with 12 encoders from 3 different encoder families (ResNet, VGG, DenseNet) of varying depth (e.g., VGG13, VGG16, VGG19). On each model design, 3 initialization strategies (ImageNet, CheXpert, random initialization) were applied, resulting overall into 216 trained models, which were trained up to 200 epochs with the Adam optimizer (learning rate = 0.0001) and a batch size of 32. Our data set consisted of 1,625 human-annotated dental bitewing radiographs. We used a 5-fold cross-validation scheme and quantified model performances primarily by the F1-score. Initialization with ImageNet or CheXpert weights significantly outperformed random initialization ( P < 0.05). Deeper and more complex models did not necessarily perform better than less complex alternatives. VGG-based models were more robust across model configurations, while more complex models (e.g., from the ResNet family) achieved peak performances. In conclusion, initializing models with pretrained weights may be recommended when training models for dental radiographic analysis. Less complex model architectures may be competitive alternatives if computational resources and training time are restricting factors. Models developed and found superior on nondental data sets may not show this behavior for dental domain-specific tasks.

26 November 2023 in Journal of Dentistry
Verified
Journal Article
Closed access
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
NCNora J. Castner
Nora J. Castner
CRCsaba Rohrer
Csaba Rohrer
SMSarah Mertens
Sarah Mertens
EKEnkelejda Kasneci
Enkelejda Kasneci
FSFalk Schwendicke
Falk Schwendicke

29 November 2023 in Ophthalmology Retina
Verified
Journal Article
Closed access
YSYesha S. Shah
Yesha S. Shah
MAMuhammad Abidi
Muhammad Abidi
IAIshrat Ahmed
Ishrat Ahmed
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
SOSally Ong
Sally Ong
JHJames T Handa
James T Handa

17 November 2021 in Journal of Periodontology
Verified
Journal Article
Closed access
PDF file
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
YMYejin Mok
Yejin Mok
CYChao Yang
Chao Yang
JIJunichi Ishigami
Junichi Ishigami
ESElizabeth Selvin
Elizabeth Selvin
KMKunihiro Matsushita
Kunihiro Matsushita

20 November 2021 in The Journals of Gerontology, Series A: Biological Sciences and Medical Sciences
Verified
Journal Article
Closed access
PDF file
LALubaina Arsiwala-Scheppach
Lubaina Arsiwala-Scheppach
XGXinxing Guo
Xinxing Guo
PRPradeep Y Ramulu
Pradeep Y Ramulu
ASA Richey Sharrett
A Richey Sharrett
AMAleksandra Mihailovic
Aleksandra Mihailovic
AAAlison G Abraham
Alison G Abraham
Given the detrimental impacts of visual and cognitive impairment separately, in older adults, understanding their coexistence could inform strategies against age-related cognitive changes. Participants from Washington County (White) and Jackson (Black) sites of the Atherosclerosis Risk in Communities Study were recruited who differed on racial, regional, urbanicity, and community-based factors. Presenting distance visual acuity (DVA; representing vision loss due to disease or lack of eye-care), corrected DVA (representing optimal correction for refractive loss of vision), and contrast sensitivity were measured. Factor scores for global cognition, memory, executive function, and language domains were calculated for 3 visits. We quantified the associations of vision measures with change in cognitive scores, stratified by community/race, using generalized estimating equations. In 982 participants, mean (standard deviation [SD]) baseline age was 74 (4) years, with 37% males and 45% Jackson/Black participants. As hypothesized, after accounting for potential confounders, in the better-eye, worse presenting DVA was associated with greater 10-year decline rate in global cognition, memory, and executive function in Washington County/White participants (eg, global cognition: −0.08 SD [95% confidence interval: −0.12, −0.04]). Worse corrected DVA was associated with greater 10-year decline rate in executive function in Washington County/White participants (−0.10 SD [−0.15, −0.04]). Better contrast sensitivity was associated with lower 10-year decline rate in global cognition and executive function in Washington County/White participants (eg, global cognition: 0.10 SD [0.06,0.14]). None of these associations were confirmed in Jackson/Black participants. Our study supports a functional link between some vision measures and cognition in older adults, but in only 1 of the 2 communities studied.