Manisha Palta

Overview:

Clinical research in gastrointestinal malignancies, lymphomas and breast malignancies.

Positions:

Associate Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

M.D. 2007

University of Florida, College of Medicine

Intern, Internal Medicine

University of North Carolina - Chapel Hill

Resident, Radiation Oncology

Duke University School of Medicine

Grants:

PROCEED

Administered By
Radiation Oncology
Awarded By
Merck Sharp & Dohme
Role
Principal Investigator
Start Date
End Date

GTI-4711-201 GRECO-2: A Randomized, Phase 2 Study of Stereotactic Body Radiation Therapy (SBRT) in combination with GC4711

Administered By
Radiation Oncology
Awarded By
Galera Therapeutics, Inc.
Role
Principal Investigator
Start Date
End Date

Publications:

Deep Learning-Based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost.

Purpose: Treatment planning for pancreas stereotactic body radiation therapy (SBRT) is a challenging task, especially with simultaneous integrated boost treatment approaches. We propose a deep learning (DL) framework to accurately predict fluence maps from patient anatomy and directly generate intensity modulated radiation therapy plans. Methods and Materials: The framework employs 2 convolutional neural networks (CNNs) to sequentially generate beam dose prediction and fluence map prediction, creating a deliverable 9-beam intensity modulated radiation therapy plan. Within the beam dose prediction CNN, axial slices of combined structure contour masks are used to predict 3-dimensional (3D) beam doses for each beam. Each 3D beam dose is projected along its beam's-eye-view to form a 2D beam dose map, which is subsequently used by the fluence map prediction CNN to predict its fluence map. Finally, the 9 predicted fluence maps are imported into the treatment planning system to finalize the plan by leaf sequencing and dose calculation. One hundred patients receiving pancreas SBRT were retrospectively collected for this study. Benchmark plans with unified simultaneous integrated boost prescription (25/33 Gy) were manually optimized for each case. The data set was split into 80/20 cases for training and testing. We evaluated the proposed DL framework by assessing both the fluence maps and the final predicted plans. Further, clinical acceptability of the plans was evaluated by a physician specializing in gastrointestinal cancer. Results: The DL-based planning was, on average, completed in under 2 minutes. In testing, the predicted plans achieved similar dose distribution compared with the benchmark plans (-1.5% deviation for planning target volume 33 V33Gy), with slightly higher planning target volume maximum (+1.03 Gy) and organ at risk maximum (+0.95 Gy) doses. After renormalization, the physician rated 19 cases clinically acceptable and 1 case requiring minor improvement. Conclusions: The DL framework can effectively plan pancreas SBRT cases within 2 minutes. The predicted plans are clinically deliverable, with plan quality approaching that of manual planning.
Authors
Wang, W; Sheng, Y; Palta, M; Czito, B; Willett, C; Hito, M; Yin, F-F; Wu, Q; Ge, Y; Wu, QJ
MLA Citation
Wang, Wentao, et al. “Deep Learning-Based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy With Simultaneous Integrated Boost.Adv Radiat Oncol, vol. 6, no. 4, July 2021, p. 100672. Pubmed, doi:10.1016/j.adro.2021.100672.
URI
https://scholars.duke.edu/individual/pub1481730
PMID
33997484
Source
pubmed
Published In
Advances in Radiation Oncology
Volume
6
Published Date
Start Page
100672
DOI
10.1016/j.adro.2021.100672

Maximizing Tumor Control and Limiting Complications With Stereotactic Body Radiation Therapy for Pancreatic Cancer.

PURPOSE: Stereotactic body radiation therapy (SBRT) and stereotactic ablative body radiation therapy is being increasingly used for pancreatic cancer (PCa), particularly in patients with locally advanced and borderline resectable disease. A wide variety of dose fractionation schemes have been reported in the literature. This HyTEC review uses tumor control probability models to evaluate the comparative effectiveness of the various SBRT treatment regimens used in the treatment of patients with localized PCa. METHODS AND MATERIALS: A PubMed search was performed to review the published literature on the use of hypofractionated SBRT (usually in 1-5 fractions) for PCa in various clinical scenarios (eg, preoperative [neoadjuvant], borderline resectable, and locally advanced PCa). The linear quadratic model with α/β= 10 Gy was used to address differences in fractionation. Logistic tumor control probability models were generated using maximum likelihood parameter fitting. RESULTS: After converting to 3-fraction equivalent doses, the pooled reported data and associated models suggests that 1-year local control (LC) without surgery is ≈79% to 86% after the equivalent of 30 to 36 Gy in 3 fractions, showing a dose response in the range of 25 to 36 Gy, and decreasing to less than 70% 1-year LC at doses below 24 Gy in 3 fractions. The 33 Gy in 5 fraction regimen (Alliance A021501) corresponds to 28.2 Gy in 3 fractions, for which the HyTEC pooled model had 77% 1-year LC without surgery. Above an equivalent dose of 28 Gy in 3 fractions, with margin-negative resection the 1-year LC exceeded 90%. CONCLUSIONS: Pooled analyses of reported tumor control probabilities for commonly used SBRT dose-fractionation schedules for PCa suggests a dose response. These findings should be viewed with caution given the challenges and limitations of this review. Additional data are needed to better understand the dose or fractionation-response of SBRT for PCa.
Authors
Mahadevan, A; Moningi, S; Grimm, J; Li, XA; Forster, KM; Palta, M; Prior, P; Goodman, KA; Narang, A; Heron, DE; Lo, SS; Urbanic, J; Herman, JM
MLA Citation
Mahadevan, Anand, et al. “Maximizing Tumor Control and Limiting Complications With Stereotactic Body Radiation Therapy for Pancreatic Cancer.Int J Radiat Oncol Biol Phys, vol. 110, no. 1, May 2021, pp. 206–16. Pubmed, doi:10.1016/j.ijrobp.2020.11.017.
URI
https://scholars.duke.edu/individual/pub1470064
PMID
33358561
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
110
Published Date
Start Page
206
End Page
216
DOI
10.1016/j.ijrobp.2020.11.017

An Interpretable Planning Bot for Pancreas Stereotactic Body Radiation Therapy.

PURPOSE: Pancreas stereotactic body radiation therapy (SBRT) treatment planning requires planners to make sequential, time-consuming interactions with the treatment planning system to reach the optimal dose distribution. We sought to develop a reinforcement learning (RL)-based planning bot to systematically address complex tradeoffs and achieve high plan quality consistently and efficiently. METHODS AND MATERIALS: The focus of pancreas SBRT planning is finding a balance between organ-at-risk sparing and planning target volume (PTV) coverage. Planners evaluate dose distributions and make planning adjustments to optimize PTV coverage while adhering to organ-at-risk dose constraints. We formulated such interactions between the planner and treatment planning system into a finite-horizon RL model. First, planning status features were evaluated based on human planners' experience and defined as planning states. Second, planning actions were defined to represent steps that planners would commonly implement to address different planning needs. Finally, we derived a reward system based on an objective function guided by physician-assigned constraints. The planning bot trained itself with 48 plans augmented from 16 previously treated patients, and generated plans for 24 cases in a separate validation set. RESULTS: All 24 bot-generated plans achieved similar PTV coverages compared with clinical plans while satisfying all clinical planning constraints. Moreover, the knowledge learned by the bot could be visualized and interpreted as consistent with human planning knowledge, and the knowledge maps learned in separate training sessions were consistent, indicating reproducibility of the learning process. CONCLUSIONS: We developed a planning bot that generates high-quality treatment plans for pancreas SBRT. We demonstrated that the training phase of the bot is tractable and reproducible, and the knowledge acquired is interpretable. As a result, the RL planning bot can potentially be incorporated into the clinical workflow and reduce planning inefficiencies.
Authors
Zhang, J; Wang, C; Sheng, Y; Palta, M; Czito, B; Willett, C; Zhang, J; Jensen, PJ; Yin, F-F; Wu, Q; Ge, Y; Wu, QJ
MLA Citation
Zhang, Jiahan, et al. “An Interpretable Planning Bot for Pancreas Stereotactic Body Radiation Therapy.Int J Radiat Oncol Biol Phys, vol. 109, no. 4, Mar. 2021, pp. 1076–85. Pubmed, doi:10.1016/j.ijrobp.2020.10.019.
URI
https://scholars.duke.edu/individual/pub1464387
PMID
33115686
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
109
Published Date
Start Page
1076
End Page
1085
DOI
10.1016/j.ijrobp.2020.10.019

Ipilimumab and Radiation in Patients with High-risk Resected or Regionally Advanced Melanoma.

PURPOSE: In this prospective trial, we sought to assess the feasibility of concurrent administration of ipilimumab and radiation as adjuvant, neoadjuvant, or definitive therapy in patients with regionally advanced melanoma. PATIENTS AND METHODS: Twenty-four patients in two cohorts were enrolled and received ipilimumab at 3 mg/kg every 3 weeks for four doses in conjunction with radiation; median dose was 4,000 cGy (interquartile range, 3,550-4,800 cGy). Patients in cohort 1 were treated adjuvantly; patients in cohort 2 were treated either neoadjuvantly or as definitive therapy. RESULTS: Adverse event profiles were consistent with those previously reported with checkpoint inhibition and radiation. For the neoadjuvant/definitive cohort, the objective response rate was 64% (80% confidence interval, 40%-83%), with 4 of 10 evaluable patients achieving a radiographic complete response. An additional 3 patients in this cohort had a partial response and went on to surgical resection. With 2 years of follow-up, the 6-, 12-, and 24-month relapse-free survival for the adjuvant cohort was 85%, 69%, and 62%, respectively. At 2 years, all patients in the neoadjuvant/definitive cohort and 10/13 patients in the adjuvant cohort were still alive. Correlative studies suggested that response in some patients were associated with specific CD4+ T-cell subsets. CONCLUSIONS: Overall, concurrent administration of ipilimumab and radiation was feasible, and resulted in a high response rate, converting some patients with unresectable disease into surgical candidates. Additional studies to investigate the combination of radiation and checkpoint inhibitor therapy are warranted.
Authors
Salama, AKS; Palta, M; Rushing, CN; Selim, MA; Linney, KN; Czito, BG; Yoo, DS; Hanks, BA; Beasley, GM; Mosca, PJ; Dumbauld, C; Steadman, KN; Yi, JS; Weinhold, KJ; Tyler, DS; Lee, WT; Brizel, DM
MLA Citation
Salama, April K. S., et al. “Ipilimumab and Radiation in Patients with High-risk Resected or Regionally Advanced Melanoma.Clin Cancer Res, vol. 27, no. 5, Mar. 2021, pp. 1287–95. Pubmed, doi:10.1158/1078-0432.CCR-20-2452.
URI
https://scholars.duke.edu/individual/pub1464016
PMID
33172894
Source
pubmed
Published In
Clinical Cancer Research
Volume
27
Published Date
Start Page
1287
End Page
1295
DOI
10.1158/1078-0432.CCR-20-2452

Randomized, Double-Blinded, Placebo-controlled Multicenter Adaptive Phase 1-2 Trial of GC 4419, a Dismutase Mimetic, in Combination with High Dose Stereotactic Body Radiation Therapy (SBRT) in Locally Advanced Pancreatic Cancer (PC).

Authors
Hoffe, S; Frakes, JM; Aguilera, TA; Czito, B; Palta, M; Brookes, M; Schweizer, C; Colbert, L; Moningi, S; Bhutani, MS; Pant, S; Tzeng, CW; Tidwell, RS; Thall, P; Yuan, Y; Moser, EC; Holmlund, J; Herman, J; Taniguchi, CM
URI
https://scholars.duke.edu/individual/pub1470085
PMID
33427657
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
108
Published Date
Start Page
1399
End Page
1400
DOI
10.1016/j.ijrobp.2020.09.022