Tal Schuster

Tal Schuster

Auto-generated profile, based on publicly available information

Tal Schuster

Department of Electrical Engineering and Computer Science, CSAIL, MIT, Cambridge, MA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 July 2019 in Radiology
Verified
Journal Article
Closed access
AYAdam Yala
Adam Yala
CLConstance Lehman
Constance Lehman
TSTal Schuster
Tal Schuster
TPTally Portnoi
Tally Portnoi
RBRegina Barzilay
Regina Barzilay
We developed a deep learning model that uses full-field mammograms and traditional risk factors, and found that our model was more accurate than the Tyrer-Cusick model (version 8), a current clinic... Background Mammographic density improves the accuracy of breast cancer risk models. However, the use of breast density is limited by subjective assessment, variation across radiologists, and restri...

1 October 2019 in Radiology
Verified
Journal Article
Closed access
AYAdam Yala
Adam Yala
TSTal Schuster
Tal Schuster
RMRandy Miles
Randy Miles
RBRegina Barzilay
Regina Barzilay
CLConstance Lehman
Constance Lehman
Background Recent deep learning (DL) approaches have shown promise in improving sensitivity but have not addressed limitations in radiologist specificity or efficiency. Purpose To develop a DL model to triage a portion of mammograms as cancer free, improving performance and workflow efficiency. Materials and Methods In this retrospective study, 223 109 consecutive screening mammograms performed in 66 661 women from January 2009 to December 2016 were collected with cancer outcomes obtained through linkage to a regional tumor registry. This cohort was split by patient into 212 272, 25 999, and 26 540 mammograms from 56 831, 7021, and 7176 patients for training, validation, and testing, respectively. A DL model was developed to triage mammograms as cancer free and evaluated on the test set. A DL-triage workflow was simulated in which radiologists skipped mammograms triaged as cancer free (interpreting them as negative for cancer) and read mammograms not triaged as cancer free by using the original interpreting radiologists' assessments. Sensitivities, specificities, and percentage of mammograms read were calculated, with and without the DL-triage-simulated workflow. Statistics were computed across 5000 bootstrap samples to assess confidence intervals (CIs). Specificities were compared by using a two-tailed t test (P < .05) and sensitivities were compared by using a one-sided t test with a noninferiority margin of 5% (P < .05). Results The test set included 7176 women (mean age, 57.8 years ± 10.9 [standard deviation]). When reading all mammograms, radiologists obtained a sensitivity and specificity of 90.6% (173 of 191; 95% CI: 86.6%, 94.7%) and 93.5% (24 625 of 26 349; 95% CI: 93.3%, 93.9%). In the DL-simulated workflow, the radiologists obtained a sensitivity and specificity of 90.1% (172 of 191; 95% CI: 86.0%, 94.3%) and 94.2% (24 814 of 26 349; 95% CI: 94.0%, 94.6%) while reading 80.7% (21 420 of 26 540) of the mammograms. The simulated workflow improved specificity (P = .002) and obtained a noninferior sensitivity with a margin of 5% (P < .001). Conclusion This deep learning model has the potential to reduce radiologist workload and significantly improve specificity without harming sensitivity. © RSNA, 2019 Online supplemental material is available for this article. See also the editorial by Kontos and Conant in this issue.

1 January 2020
Verified
Conference Paper
Open access
PDF file
BPBeatrice Portelli
Beatrice Portelli
JZJason Zhao
Jason Zhao
TSTal Schuster
Tal Schuster
GSGiuseppe Serra
Giuseppe Serra
ESEnrico Santus
Enrico Santus
Beatrice Portelli, Jason Zhao, Tal Schuster, Giuseppe Serra, Enrico Santus. Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER). 2020.

1 November 2020 in JCO Clinical Cancer Informatics
Verified
Journal Article
Closed access
ESEnrico Santus
Enrico Santus
TSTal Schuster
Tal Schuster
ATAmir M. Tahmasebi
Amir M. Tahmasebi
CLClara Li
Clara Li
AYAdam Yala
Adam Yala
KHKevin Hughes
Kevin Hughes
Literature on clinical note mining has highlighted the superiority of machine learning (ML) over hand-crafted rules. Nevertheless, most studies assume the availability of large training sets, which is rarely the case. For this reason, in the clinical setting, rules are still common. We suggest 2 methods to leverage the knowledge encoded in pre-existing rules to inform ML decisions and obtain high performance, even with scarce annotations. We collected 501 prostate pathology reports from 6 American hospitals. Reports were split into 2,711 core segments, annotated with 20 attributes describing the histology, grade, extension, and location of tumors. The data set was split by institutions to generate a cross-institutional evaluation setting. We assessed 4 systems, namely a rule-based approach, an ML model, and 2 hybrid systems integrating the previous methods: a Rule as Feature model and a Classifier Confidence model. Several ML algorithms were tested, including logistic regression (LR), support vector machine (SVM), and eXtreme gradient boosting (XGB). When training on data from a single institution, LR lags behind the rules by 3.5% (F1 score: 92.2% v 95.7%). Hybrid models, instead, obtain competitive results, with Classifier Confidence outperforming the rules by +0.5% (96.2%). When a larger amount of data from multiple institutions is used, LR improves by +1.5% over the rules (97.2%), whereas hybrid systems obtain +2.2% for Rule as Feature (97.7%) and +2.6% for Classifier Confidence (98.3%). Replacing LR with SVM or XGB yielded similar performance gains. We developed methods to use pre-existing handcrafted rules to inform ML algorithms. These hybrid systems obtain better performance than either rules or ML models alone, even when training data are limited.