Smart starting guesses from machine learning for phase retrieval

Paine, Scott W.; Fienup, James R.

doi:10.1117/12.2307858

Cited by 3 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the last years, deep learning-based approaches using convolutional neural networks (CNNs) have proven to be powerful and computationally efficient for image-based classification and regression tasks for microscopy images [18,19]. Recently, several studies demonstrated that deep learning-based phase retrieval can produce accurate results at fast processing speeds [20][21][22][23][24][25], however they fall short regarding their practical applicability. Some of these approaches [22][23][24] used purely simulated synthetic data, where generalizability to real microscopy images is unclear.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, several studies demonstrated that deep learning-based phase retrieval can produce accurate results at fast processing speeds [20][21][22][23][24][25], however they fall short regarding their practical applicability. Some of these approaches [22][23][24] used purely simulated synthetic data, where generalizability to real microscopy images is unclear. Others focused on specific microscopy acquisition modes (such as using biplanar PSFs [20]) or microscopy setups that allow to collect large sets of experimental ground truth data for training and prediction [21,25], thus limiting this approach in practice.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Practical sensorless aberration estimation for 3D microscopy with deep learning

et al. 2020

View full text Add to dashboard Cite

Estimation of optical aberrations from volumetric intensity images is a key step in sensorless adaptive optics for 3D microscopy. Recent approaches based on deep learning promise accurate results at fast processing speeds. However, collecting ground truth microscopy data for training the network is typically very difficult or even impossible thereby limiting this approach in practice. Here, we demonstrate that neural networks trained only on simulated data yield accurate predictions for real experimental images. We validate our approach on simulated and experimental datasets acquired with two different microscopy modalities and also compare the results to non-learned methods. Additionally, we study the predictability of individual aberrations with respect to their data requirements and find that the symmetry of the wavefront plays a crucial role. Finally, we make our implementation freely available as open source software in Python.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Practical sensorless aberration estimation for 3D microscopy with deep learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Additional body work has been done using convolutional neural nets, such as prDeep [26], leading to a separate class of architectures not versatile enough to improve the existing algorithms. In fact, some of Fienup's recent work for space telescopes take advantage of smart initializations obtained from convolutional neural nets for phase retrieval [27]. The said limitations directly relate to the two major pitfalls of data-driven approaches, i.e., (i) their need to a relatively large amount of data for training purposes and (ii) their inherent lack of interpretability, even after training.…”

Section: Introductionmentioning

confidence: 99%

Unfolded Algorithms for Deep Phase Retrieval

Naimipour,

Khobahi,

Soltanalian

2020

Preprint

View full text Add to dashboard Cite

Exploring the idea of phase retrieval has been intriguing researchers for decades, due to its appearance in a wide range of applications. The task of a phase retrieval algorithm is typically to recover a signal from linear phaseless measurements. In this paper, we approach the problem by proposing a hybrid model-based data-driven deep architecture, referred to as Unfolded Phase Retrieval (UPR), that exhibits significant potential in improving the performance of state-of-theart data-driven and model-based phase retrieval algorithms. The proposed method benefits from versatility and interpretability of well-established model-based algorithms, while simultaneously benefiting from the expressive power of deep neural networks. In particular, our proposed model-based deep architecture is applied to the conventional phase retrieval problem (via the incremental reshaped Wirtinger flow algorithm) and the sparse phase retrieval problem (via the sparse truncated amplitude flow algorithm), showing immense promise in both cases. Furthermore, we consider a joint design of the sensing matrix and the signal processing algorithm and utilize the deep unfolding technique in the process. Our numerical results illustrate the effectiveness of such hybrid model-based and data-driven frameworks and showcase the untapped potential of data-aided methodologies to enhance the existing phase retrieval algorithms.

show abstract

“…Over the last years, deep learning based approaches using convolutional neural networks (CNNs) have proven to be powerful and computationally efficient for image-based classification and regression tasks for microscopy images [17,18]. Recently, several studies demonstrated that deep learning based phase retrieval can produce accurate results at fast processing speeds [19][20][21][22], however they fall short regarding their practical applicability. Some of these approaches [21,22] used purely simulated synthetic data, where generalizability to real microscopy images is unclear.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, several studies demonstrated that deep learning based phase retrieval can produce accurate results at fast processing speeds [19][20][21][22], however they fall short regarding their practical applicability. Some of these approaches [21,22] used purely simulated synthetic data, where generalizability to real microscopy images is unclear. Others [19,20] focused on specific microscopy modalities where it is feasible to collect large sets of experimental ground truth data for training and prediction, thus limiting this approach in practice.…”

Section: Introductionmentioning

confidence: 99%

Practical sensorless aberration estimation for 3D microscopy with deep learning

Saha,

Schmidt,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Estimation of optical aberrations from volumetric intensity images is a key step in sensorless adaptive optics for 3D microscopy. Recent approaches based on deep learning promise accurate results at fast processing speeds. However, collecting ground truth microscopy data for training the network is typically very difficult or even impossible thereby limiting this approach in practice. Here, we demonstrate that neural networks trained only on simulated data yield accurate predictions for real experimental images. We validate our approach on simulated and experimental datasets acquired with two different microscopy modalities, and also compare the results to non-learned methods. Additionally, we study the predictability of individual aberrations with respect to their data requirements and find that the symmetry of the wavefront plays a crucial role. Finally, we make our implementation freely available as open source software in Python.

show abstract

Smart starting guesses from machine learning for phase retrieval

Cited by 3 publications

References 17 publications

Practical sensorless aberration estimation for 3D microscopy with deep learning

Practical sensorless aberration estimation for 3D microscopy with deep learning

Unfolded Algorithms for Deep Phase Retrieval

Practical sensorless aberration estimation for 3D microscopy with deep learning

Contact Info

Product

Resources

About