Patient‐specific transfer learning for auto‐segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi‐centric evaluation

Kawula, Maria; Hadi, Ibnu; Nierer, Lukas; Vagni, M.; Cusumano, D.; Boldrini, Luca; Placidi, L.; Corradini, Stefanie; Belka, Claus; Landry, Guillaume; Kurz, Christopher

doi:10.1002/mp.16056

Cited by 31 publications

(18 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kawula et al utilized transfer learning to develop patient-specific (PS) and facility-specific (FS) models on magnetic resonance imaging. 36 The PS model reported a significant improvement, whereas the FS model did not improve the performance significantly. Feng et al implemented a transfer learning strategy to overcome the data heterogeneity problem in thoracic cases and successfully improved the sub-optimal performance for cases with abdominal compression.…”

Section: Discussionmentioning

confidence: 89%

See 1 more Smart Citation

Incremental retraining, clinical implementation, and acceptance rate of deep learning auto‐segmentation for male pelvis in a multiuser environment

et al. 2023

View full text Add to dashboard Cite

Background Deep learning auto‐segmentation (DLAS) models have been adopted in the clinic; however, they suffer from performance deterioration owing to the clinical practice variability. Some commercial DLAS software provide an incremental retraining function that enables users to train a custom model using their institutional data to account for clinical practice variability. Purpose This study was performed to evaluate and implement the commercial DLAS software with the incremental retraining function for definitive treatment of patients with prostate cancer in a multi‐user environment. Methods CT‐based target organs and organs‐at‐risk (OAR) delineation of 215 prostate cancer patients were utilized. The performance of three commercial DLAS software built‐in models was validated with 20 patients. A retrained custom model was developed using 100 patients and evaluated on the remaining data (n = 115). Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and surface DSC (SDSC) were utilized for quantitative evaluation. A multi‐rater qualitative evaluation was blindly performed with a five‐level scale. Visual inspection was performed in consensus and non‐consensus unacceptable cases to identify the failure modes. Results Three commercial DLAS vendor built‐in models achieved sub‐optimal performance in 20 patients. The retrained custom model had a mean DSC of 0.82 for prostate, 0.48 for seminal vesicles (SV), and 0.92 for rectum, respectively. This represents a significant improvement over the built‐in model with DSC of 0.73, 0.37, and 0.81 for the corresponding structures. Compared to the acceptance rate of 96.5% and consensus unacceptable rate (i.e., both reviewers rated as unacceptable) of 3.5% achieved by manual contours, the custom model achieved a 91.3% acceptance rate and 8.7% consensus unacceptable rate. The failure modes of retrained custom model were attributed to the following: cystogram (n = 2), hip prosthesis (n = 2), low dose rate brachytherapy seeds (n = 2), air in endorectal balloon(n = 1), non‐iodinated spacer (n = 2), and giant bladder(n = 1). Conclusion The commercial DLAS software with the incremental retraining function was validated and clinically adopted for prostate patients in a multi‐user environment. AI‐based auto‐delineation of the prostate and OARs is shown to achieve improved physician acceptance, overall clinical utility, and accuracy.

show abstract

Section: Discussionmentioning

confidence: 89%

“…Kawula et al. utilized transfer learning to develop patient‐specific (PS) and facility‐specific (FS) models on magnetic resonance imaging 36 . The PS model reported a significant improvement, whereas the FS model did not improve the performance significantly.…”

Section: Discussionmentioning

confidence: 99%

Incremental retraining, clinical implementation, and acceptance rate of deep learning auto‐segmentation for male pelvis in a multiuser environment

et al. 2023

View full text Add to dashboard Cite

show abstract

“…30 Recent work by Kawula et al utilized the fine-tuning approach to create patient-specific DL models in ART auto-segmentation. 31 In a study by Chun et al, they demonstrated that the intentional deep overfit learning (IDOL) approach to training a patient-specific DL model yielded statistically significant improvement over a generalized DL model in three ART tasks-auto-segmentation, super-resolution for magnetic resonance imaging (MRI), and synthetic CT reconstruction based on MRI. 32 Our previous work explored the application of the IDOL approach toward fine-tuning dose predictions in ART.…”

Section: Introductionmentioning

confidence: 99%

Single patient learning for adaptive radiotherapy dose prediction

Maniscalco,

Liang,

Lin

et al. 2023

Medical Physics

View full text Add to dashboard Cite

BackgroundThroughout a patient's course of radiation therapy, maintaining accuracy of their initial treatment plan over time is challenging due to anatomical changes‐for example, stemming from patient weight loss or tumor shrinkage. Online adaptation of their RT plan to these changes is crucial, but hindered by manual and time‐consuming processes. While deep learning (DL) based solutions have shown promise in streamlining adaptive radiation therapy (ART) workflows, they often require large and extensive datasets to train population‐based models.PurposeThis study extends our prior research by introducing a minimalist approach to patient‐specific adaptive dose prediction. In contrast to our prior method, which involved fine‐tuning a pre‐trained population model, this new method trains a model from scratch using only a patient's initial treatment data. This patient‐specific dose predictor aims to enhance clinical accessibility, thereby empowering physicians and treatment planners to make more informed, quantitative decisions in ART. We hypothesize that patient‐specific DL models will provide more accurate adaptive dose predictions for their respective patients compared to a population‐based DL model.MethodsWe selected 33 patients to train an adaptive population‐based (AP) model. Ten additional patients were selected, and their respective initial RT data served as single samples for training patient‐specific (PS) models. These 10 patients contained an additional 26 ART plans that were withheld as the test dataset to evaluate AP versus PS model dose prediction performance. We assessed model performance using Mean Absolute Percent Error (MAPE) by comparing predicted doses to the originally delivered ground truth doses. We used the Wilcoxon signed‐rank test to determine statistically significant differences in terms of MAPE between the AP and PS model results across the test dataset. Furthermore, we calculated differences between predicted and ground truth mean doses for segmented structures and determined statistical significance in the differences for each of them.ResultsThe average MAPE across AP and PS model dose predictions was 5.759% and 4.069%, respectively. The Wilcoxon signed‐rank test yielded two‐tailed p‐value = , indicating that the MAPE differences between the AP and PS model dose predictions are statistically significant, and 95% confidence interval = [−2.1610, −1.0130], indicating 95% confidence that the MAPE difference between the AP and PS models for a population lies in this range. Out of 24 total segmented structures, the comparison of mean dose differences for 12 structures indicated statistical significance with two‐tailed p‐values < 0.05.ConclusionOur study demonstrates the potential of patient‐specific deep learning models in application to ART. Notably, our method streamlines the training process by minimizing the size of the required training dataset, as only a single patient's initial treatment data is required. External institutions considering the implementation of such a technology could package such a model so that it only requires the upload of a reference treatment plan for model training and deployment. Our single patient learning strategy demonstrates promise in ART due to its minimal dataset requirement and its utility in personalization of cancer treatment.

show abstract

“…The DL model trained from popular data will not perform well when applied to new and unseen cases. [26][27][28][29] The existing DIR and DL methods are suboptimal, so the development of a reliable and efficient automatic segmentation algorithm is an urgent need of online MRI-guided prostate radiotherapy. Ding et al 27,28 developed a DL-based automatic contour refinement to correct the segmentation errors in regular method.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, significant intensity inhomogeneities among MR images across patients can be observed even with the same scanner. The DL model trained from popular data will not perform well when applied to new and unseen cases 26–29 …”

Section: Introductionmentioning

confidence: 99%

Pretreatment information–aided automatic segmentation for online magnetic resonance imaging‐guided prostate radiotherapy

et al. 2023

View full text Add to dashboard Cite

BackgroundIt is necessary to contour regions of interest (ROIs) for online magnetic resonance imaging (MRI)‐guided adaptive radiotherapy (MRIgART). These updated contours are used for online replanning to obtain maximum dosimetric benefits. Contouring can be accomplished using deformable image registration (DIR) and deep learning (DL)‐based autosegmentation methods. However, these methods may require considerable manual editing and thus prolong treatment time.PurposeThe present study aimed to improve autosegmentation performance by integrating patients’ pretreatment information in a DL‐based segmentation algorithm. It is expected to improve the efficiency of current MRIgART process.MethodsForty patients with prostate cancer were enrolled retrospectively. The online adaptive MR images, patient‐specific planning computed tomography (CT), and contours in CT were used for segmentation. The deformable registration of planning CT and MR images was performed first to obtain a deformable CT and corresponding contours. A novel DL network, which can integrate such patient‐specific information (deformable CT and corresponding contours) into the segmentation task of MR images was designed. We performed a four‐fold cross‐validation for the DL models. The proposed method was compared with DIR and DL methods on segmentation of prostate cancer. The ROIs included the clinical target volume (CTV), bladder, rectum, left femur head, and right femur head. Dosimetric parameters of automatically generated ROIs were evaluated using a clinical treatment planning system.ResultsThe proposed method enhanced the segmentation accuracy of conventional procedures. Its mean value of the dice similarity coefficient (93.5%) over the five ROIs was higher than both DIR (87.5%) and DL (87.2%). The number of patients (n = 40) that required major editing using DIR, DL, and our method were 12, 18, and 7 (CTV); 17, 4, and 1 (bladder); 8, 11, and 5 (rectum); 2, 4, and 1 (left femur head); and 3, 7, and 1 (right femur head), respectively. The Spearman rank correlation coefficient of dosimetry parameters between the proposed method and ground truth was 0.972 ± 0.040, higher than that of DIR (0.897 ± 0.098) and DL (0.871 ± 0.134).ConclusionThis study proposed a novel method that integrates patient‐specific pretreatment information into DL‐based segmentation algorithm. It outperformed baseline methods, thereby improving the efficiency and segmentation accuracy in adaptive radiotherapy.

show abstract

Patient‐specific transfer learning for auto‐segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi‐centric evaluation

Cited by 31 publications

References 36 publications

Incremental retraining, clinical implementation, and acceptance rate of deep learning auto‐segmentation for male pelvis in a multiuser environment

Incremental retraining, clinical implementation, and acceptance rate of deep learning auto‐segmentation for male pelvis in a multiuser environment

Single patient learning for adaptive radiotherapy dose prediction

Pretreatment information–aided automatic segmentation for online magnetic resonance imaging‐guided prostate radiotherapy

Contact Info

Product

Resources

About