Abstract
The Solar Dynamics Observatory (SDO), a NASA multispectral decade-long mission that has been daily producing terabytes of observational data from the Sun, has been recently used as a use ...case to demonstrate the potential of machine-learning methodologies and to pave the way for future deep space mission planning. In particular, the idea of using image-to-image translation to virtually produce extreme ultraviolet channels has been proposed in several recent studies, as a way to both enhance missions with fewer available channels and to alleviate the challenges due to the low downlink rate in deep space. This paper investigates the potential and the limitations of such a deep learning approach by focusing on the permutation of four channels and an encoder–decoder based architecture, with particular attention to how morphological traits and brightness of the solar surface affect the neural network predictions. In this work we want to answer the question: can synthetic images of the solar corona produced via image-to-image translation be used for scientific studies of the Sun? The analysis highlights that the neural network produces high-quality images over 3 orders of magnitude in count rate (pixel intensity) and can generally reproduce the covariance across channels within a 1% error. However, the model performance drastically diminishes in correspondence to extremely high energetic events like flares, and we argue that the reason is related to the rareness of such events posing a challenge to model training.
Context.
Solar activity plays a quintessential role in affecting the interplanetary medium and space weather around Earth. Remote-sensing instruments on board heliophysics space missions provide a ...pool of information about solar activity by measuring the solar magnetic field and the emission of light from the multilayered, multithermal, and dynamic solar atmosphere. Extreme-UV (EUV) wavelength observations from space help in understanding the subtleties of the outer layers of the Sun, that is, the chromosphere and the corona. Unfortunately, instruments such as the Atmospheric Imaging Assembly (AIA) on board the NASA Solar Dynamics Observatory (SDO), suffer from time-dependent degradation that reduces their sensitivity. The current best calibration techniques rely on flights of sounding rockets to maintain absolute calibration. These flights are infrequent, complex, and limited to a single vantage point, however.
Aims.
We aim to develop a novel method based on machine learning (ML) that exploits spatial patterns on the solar surface across multiwavelength observations to autocalibrate the instrument degradation.
Methods.
We established two convolutional neural network (CNN) architectures that take either single-channel or multichannel input and trained the models using the SDOML dataset. The dataset was further augmented by randomly degrading images at each epoch, with the training dataset spanning nonoverlapping months with the test dataset. We also developed a non-ML baseline model to assess the gain of the CNN models. With the best trained models, we reconstructed the AIA multichannel degradation curves of 2010–2020 and compared them with the degradation curves based on sounding-rocket data.
Results.
Our results indicate that the CNN-based models significantly outperform the non-ML baseline model in calibrating instrument degradation. Moreover, multichannel CNN outperforms the single-channel CNN, which suggests that cross-channel relations between different EUV channels are important to recover the degradation profiles. The CNN-based models reproduce the degradation corrections derived from the sounding-rocket cross-calibration measurements within the experimental measurement uncertainty, indicating that it performs equally well as current techniques.
Conclusions.
Our approach establishes the framework for a novel technique based on CNNs to calibrate EUV instruments. We envision that this technique can be adapted to other imaging or spectral instruments operating at other wavelengths.
The Solar Dynamics Observatory (SDO), a NASA multi-spectral decade-long mission that has been daily producing terabytes of observational data from the Sun, has been recently used as a use-case to ...demonstrate the potential of machine learning methodologies and to pave the way for future deep-space mission planning. In particular, the idea of using image-to-image translation to virtually produce extreme ultra-violet channels has been proposed in several recent studies, as a way to both enhance missions with less available channels and to alleviate the challenges due to the low downlink rate in deep space. This paper investigates the potential and the limitations of such a deep learning approach by focusing on the permutation of four channels and an encoder--decoder based architecture, with particular attention to how morphological traits and brightness of the solar surface affect the neural network predictions. In this work we want to answer the question: can synthetic images of the solar corona produced via image-to-image translation be used for scientific studies of the Sun? The analysis highlights that the neural network produces high-quality images over three orders of magnitude in count rate (pixel intensity) and can generally reproduce the covariance across channels within a 1% error. However the model performance drastically diminishes in correspondence of extremely high energetic events like flares, and we argue that the reason is related to the rareness of such events posing a challenge to model training.
Solar activity plays a quintessential role in influencing the interplanetary medium and space-weather around the Earth. Remote sensing instruments onboard heliophysics space missions provide a pool ...of information about the Sun's activity via the measurement of its magnetic field and the emission of light from the multi-layered, multi-thermal, and dynamic solar atmosphere. Extreme UV (EUV) wavelength observations from space help in understanding the subtleties of the outer layers of the Sun, namely the chromosphere and the corona. Unfortunately, such instruments, like the Atmospheric Imaging Assembly (AIA) onboard NASA's Solar Dynamics Observatory (SDO), suffer from time-dependent degradation, reducing their sensitivity. Current state-of-the-art calibration techniques rely on periodic sounding rockets, which can be infrequent and rather unfeasible for deep-space missions. We present an alternative calibration approach based on convolutional neural networks (CNNs). We use SDO-AIA data for our analysis. Our results show that CNN-based models could comprehensively reproduce the sounding rocket experiments' outcomes within a reasonable degree of accuracy, indicating that it performs equally well compared with the current techniques. Furthermore, a comparison with a standard "astronomer's technique" baseline model reveals that the CNN approach significantly outperforms this baseline. Our approach establishes the framework for a novel technique to calibrate EUV instruments and advance our understanding of the cross-channel relation between different EUV channels.
As a part of NASA's Heliophysics System Observatory (HSO) fleet of satellites,the Solar Dynamics Observatory (SDO) has continuously monitored the Sun since2010. Ultraviolet (UV) and Extreme UV (EUV) ...instruments in orbit, such asSDO's Atmospheric Imaging Assembly (AIA) instrument, suffer time-dependent degradation which reduces instrument sensitivity. Accurate calibration for (E)UV instruments currently depends on periodic sounding rockets, which are infrequent and not practical for heliophysics missions in deep space. In the present work, we develop a Convolutional Neural Network (CNN) that auto-calibrates SDO/AIA channels and corrects sensitivity degradation by exploiting spatial patterns in multi-wavelength observations to arrive at a self-calibration of (E)UV imaging instruments. Our results remove a major impediment to developing future HSOmissions of the same scientific caliber as SDO but in deep space, able to observe the Sun from more vantage points than just SDO's current geosynchronous orbit.This approach can be adopted to perform autocalibration of other imaging systems exhibiting similar forms of degradation
Understanding and monitoring the complex and dynamic processes of the Sun is important for a number of human activities on Earth and in space. For this reason, NASA's Solar Dynamics Observatory (SDO) ...has been continuously monitoring the multi-layered Sun's atmosphere in high-resolution since its launch in 2010, generating terabytes of observational data every day. The synergy between machine learning and this enormous amount of data has the potential, still largely unexploited, to advance our understanding of the Sun and extend the capabilities of heliophysics missions. In the present work, we show that deep learning applied to SDO data can be successfully used to create a high-fidelity virtual telescope that generates synthetic observations of the solar corona by image translation. Towards this end we developed a deep neural network, structured as an encoder-decoder with skip connections (U-Net), that reconstructs the Sun's image of one instrument channel given temporally aligned images in three other channels. The approach we present has the potential to reduce the telemetry needs of SDO, enhance the capabilities of missions that have less observing channels, and transform the concept development of future missions.
Protein kinase C beta (PKCbeta) was identified by gene-expression profiling, preclinical evaluation, and independent immunohistochemical analysis as a rational therapeutic target in diffuse large ...B-cell lymphoma (DLBCL). We conducted a multicenter phase II study of a potent inhibitor of PKCbeta, enzastaurin, in patients with relapsed or refractory DLBCL.
Enzastaurin was taken orally once daily until disease progression or unacceptable toxicity occurred. Study end points included freedom from progression (FFP) for > or= two cycles (one cycle = 28 days), objective response, and toxicity.
Fifty-five patients (median age, 68 years) were enrolled. Patients had received a median number of two prior therapies (range, one to five); six patients relapsed after high-dose therapy and autologous stem-cell transplantation. Only one grade 4 toxicity (hypomagnesemia) occurred. Grade 3 toxicities included fatigue (n = 2), edema (n = 1), headache (n = 1), motor neuropathy (n = 1), and thrombocytopenia (n = 1). No grade 3 or 4 neutropenia occurred. No deaths or discontinuations due to toxicity were reported. Fifteen patients completed less than one cycle of therapy. Twelve of 55 patients (22%; 95% CI, 13% to 46%) experienced FFP for two cycles, and eight patients remained free from progression for four cycles (15%; 95% CI, 6% to 27%). Four patients (7%; 95% CI, 2% to 18%), including three complete responders and one patient with stable disease, continue to experience FFP 20+ to 50+ months after study entry.
Treatment with enzastaurin was well-tolerated and associated with prolonged FFP in a small subset of patients with relapsed or refractory DLBCL. Further studies of enzastaurin in DLBCL are warranted.
To investigate the existence of true altruism, the authors assessed the link between empathic concern and helping by (a) employing an experimental perspective-taking paradigm used previously to ...demonstrate empathy-associated helping and (b) assessing the empathy-helping relationship while controlling for a range of relevant, well-measured nonaltruistic motivations. Consistent with previous research, the authors found a significant zero-order relationship between helping and empathic concern, the purported motivator of true altruism. This empathy-helping relationship disappeared, however, when nonaltruistic motivators (oneness and negative affect) were taken into account: Only the nonaltruistic factors of oneness (merged identity with the victim) and negative affect mediated helping, whereas empathic concern did not. Evidence for true altruism remains elusive.
Abstract 4779
The Stanford V regimen is a combined modality approach for treatment of Hodgkin lymphoma (HL). E1492, an ECOG pilot study, consisted of 12 weeks of Stanford V chemotherapy followed by ...36 Gy radiation therapy (RT) to sites > 5 cm or macroscropic splenic disease at diagnosis. Efficacy results were reported previously (Horning et al. J Clin Onc 18, 2000). The study now has a median follow up of 17 years and patients have been followed for overall survival (OS) and development of second cancers.
47 eligible patients with stage bulky mediastinal (mass > one third of the maximum intrathoracic diameter) stage I-II or stage III-IV HL were enrolled between March 1992 and February 1995. Patients were followed every 3 months during the first year off therapy, every 6 months during years 2–5 and annually thereafter. The ECOG database was reviewed for OS and reported second cancers. Patient characteristics at baseline, type of second cancer and time to development of second cancer were assessed. RT summary forms were reviewed for patients with second cancers.
41 patients were treated with combined modality therapy and 6 with chemotherapy alone. The median age was 32 years (range 20–56 years). The 5 and 10 year OS are 96%, and 89% respectively. Seven second cancers were reported, as shown in the Table. The cumulative incidence for second cancers accounting for death as a competing risk is 0.02 (95% CI, 0–0.06) at 5 years, 0.07 (95% CI, 0–0.14) at 10 years, and 0.15 (95% CI, 0.04–0.27) at 15 years. Complete details of the exact location, histologic subtype and subsequent management of second cancers were not available for review.
Five of the 7 cancers 2 skin, 1 prostate, 2 acute myeloid leukemia (AML) were not radiation-related. One patient developed AML after primary therapy as reported in the initial publication. A second patient developed AML 5 years after salvage therapy followed by autologous stem cell transplant for relapsed HL. It is likely the 2 cases of breast cancer were treatment related.
Within the caveats of a retrospective analysis from a small cooperative group phase 2 trial, the mature 10 year OS of 89% and low frequency of secondary cancers are encouraging in comparison to historic treatment with combined modality treatment. Longer follow up of other Stanford V regimen data sets (i.e. United Kingdom National Cancer Research Institute Lymphoma Group Study ISRCTN 64141244 and the Eastern Cooperative Oncology Group E2496) are required to confirm these findings.TablePatientAge (y) at RxAnn Arbor StageTime (y) from study registration to Second CancerType of Second CancerRT FieldCommentTreated with combined modality (n=5)136IX10BreastMantle and left chest wallSite of breast cancer unknown.228IV12Breast (DCIS)Bilateral supraclavicular; mediastinum; bilateral lungsBoth breasts received 15 Gy RT3156III8ProstateUpper para-aortic; right mesentericNo pelvic RT437II9AMLBilateral supraclavicular; mediastinumDeveloped 5 years post ASCT for relapsed HL538III14Skin (face)Bilateral supraclavicular; mediastinum; spleenNo RT to faceTreated with chemotherapy alone (n=2)645IVNASkin (lip)—7243IV1AML—Reported in original publicationAbbreviations: radiation therapy (RT); acute myeloid leukemia (AML); autologous stem cell transplant (ASCT); Not Available (NA); Hodgkin lymphoma (HL); bulky mediastinal disease (X); ductal carcinoma in situ (DCIS).1Note: Patient also diagnosed with renal cancer 1 month before start of RT;2Patient died.
No relevant conflicts of interest to declare.
PKCβ was identified by gene expression profiling and confirmed by independent analysis as a possible rational therapeutic target for DLBCL. Therefore, we investigated the safety and anti-cancer ...activity of enzastaurin, an orally administered, potent inhibitor of PKCβ, in this disease. Patients (pts) with relapsed DLBCL, who progressed following CHOP-based (or equivalent) chemotherapy, were enrolled in this phase II, single-arm, US multicenter study. The primary objective was to determine the rate of freedom from progression ≥2 cycles (FFP). Secondary end-points included objective response rate (complete or partial response), and toxicity. Pts initially received an oral dose of 525 mg (capsules) enzastaurin, amended to 500 mg (tablets), once daily, until disease progression or unacceptable toxicity occurred. One cycle of therapy lasted for 28 days. All 55 enrolled pts received at least 1 dose of enzastaurin, and were included in the safety and efficacy analyses. Of these, 13 pts completed less than 1 cycle of therapy, which is noteworthy because enzastaurin must be administered for 14 days to achieve therapeutic levels. Of the 55 pts evaluated, 27 were men and 28 were women, 47 (85%) had an ECOG performance status of ≤1, and 28 pts had elevated LDH levels. The median age was 68 years (range: 31–87). Pts had received a median number of 2 prior therapies (range: 1–5); 6 pts had also received prior stem-cell transplantation. There were 11 dose omissions due to toxicities, 2 of which were possibly related to the study drug (fatigue and edema). There was only 1 grade 4 toxicity (hypomagnesemia), 1 grade 3 thrombocytopenia, and no grade 3 or 4 neutropenia. Other grade 3 toxicities were fatigue (2), edema (1), headache (1), and motor neuropathy (1). Twelve of 55 pts (21.8%, 95% CI: 11.8%–35.0%) were alive and free from progression at the end of 2 cycles. Two of these 12 pts had elevated LDH levels at baseline, which normalized after enzastaurin therapy. Nine pts had stable disease for at least 4 cycles, one of whom achieved a complete response; 2 of the 9 pts had relapsed after prior stem-cell therapy. Five pts with stable disease achieved a minor response (lesion shrinkage ≥25% and <50%). Three pts remain progression-free for ≥12 cycles (12+, 17+, and 32+ cycles, respectively).
Pts enrolledPts on-study for ≥1 cyclePts with FFP for ≥2 cyclesPts with FFP for ≥4 cyclesPts with FFP for ≥12 cycles55421293
In conclusion, several pts with multiple relapsed DLBCL achieved prolonged periods of stable disease following enzastaurin treatment, although the objective tumor response rate was low. In addition, enzastaurin was well tolerated. These results suggest that enzastaurin, an oral agent, has clinical activity in DLBCL that warrants further investigation.