Compensating Positron Range Effects of Ga-68 in Preclinical PET Imaging by Using Convolutional Neural Network: A Monte Carlo Simulation Study

This study aimed to investigate the feasibility of positron range correction based on three different convolutional neural network (CNN) models in preclinical PET imaging of Ga-68. The first model (CNN1) was originally designed for super-resolution recovery, while the second model (CNN2) and the third model (CNN3) were originally designed for pseudo CT synthesis from MRI. A preclinical PET scanner and 30 phantom configurations were modeled in Monte Carlo simulations, where each phantom configuration was simulated twice, once for Ga-68 (CNN input images) and once for back-to-back 511-keV gamma rays (CNN output images) with a 20 min emission scan duration. The Euclidean distance was used as the loss function to minimize the difference between CNN input and output images. According to our results, CNN3 outperformed CNN1 and CNN2 qualitatively and quantitatively. With regard to qualitative observation, it was found that boundaries in Ga-68 images became sharper after correction. As for quantitative analysis, the recovery coefficient (RC) and spill-over ratio (SOR) were increased after correction, while no substantial increase in coefficient of variation of RC (CVRC) or coefficient of variation of SOR (CVSOR) was observed. Overall, CNN3 should be a good candidate architecture for positron range correction in Ga-68 preclinical PET imaging.

Development of Range-Corrected Deep Learning Potentials for Fast, Accurate Quantum Mechanical/molecular Mechanical Simulations of Chemical Reactions in Solution

We develop a new Deep Potential - Range Correction (DPRc) machine learning potential for combined quantum mechanical/molecular mechanical (QM/MM) simulations of chemical reactions in the condensed phase. The new range correction enables short-ranged QM/MM interactions to be tuned for higher accuracy, and the correction smoothly vanishes within a specified cutoff. We further develop an active learning procedure for robust neural network training. We test the DPRc model and training procedure against a series of 6 non-enzymatic phosphoryl transfer reactions in solution that are important in mechanistic studies of RNA-cleaving enzymes. Specifically, we apply DPRc corrections to a base QM model and test its ability to reproduce free energy profiles generated from a target QM model. We perform comparisons using the MNDO/d and DFTB2 semiempirical models because they produce free energy profiles which differ significantly from each other, thereby providing us a rigorous stress test for the DPRc model and training procedure. The comparisons show that accurate reproduction of the free energy profiles requires correction of the QM/MM interactions out to 6 Å. We further find that the model's initial training benefits from generating data from temperature replica exchange simulations and including high-temperature configurations into the fitting procedure so the resulting models are trained to properly avoid high-energy regions. A single DPRc model was trained to reproduce 4 different reactions and yielded good agreement with the free energy profiles made from the target QM/MM simulations. The DPRc model was further demonstrated to be transferable to 2D free energy surfaces and 1D free energy profiles that were not explicitly considered in the training. Examination of the computational performance of the DPRc model showed that it was fairly slow when run on CPUs, but was sped up almost 100-fold when using an NVIDIA V100 GPUs, resulting in almost negligible overhead. The new DPRc model and training procedure provide a potentially powerful new tool for the creation of next-generation QM/MM potentials for a wide spectrum of free energy applications ranging from drug discovery to enzyme design.<br>

Development of Range-Corrected Deep Learning Potentials for Fast, Accurate Quantum Mechanical/molecular Mechanical Simulations of Chemical Reactions in Solution

We develop a new Deep Potential - Range Correction (DPRc) machine learning potential for combined quantum mechanical/molecular mechanical (QM/MM) simulations of chemical reactions in the condensed phase. The new range correction enables short-ranged QM/MM interactions to be tuned for higher accuracy, and the correction smoothly vanishes within a specified cutoff. We further develop an active learning procedure for robust neural network training. We test the DPRc model and training procedure against a series of 6 non-enzymatic phosphoryl transfer reactions in solution that are important in mechanistic studies of RNA-cleaving enzymes. Specifically, we apply DPRc corrections to a base QM model and test its ability to reproduce free energy profiles generated from a target QM model. We perform comparisons using the MNDO/d and DFTB2 semiempirical models because they produce free energy profiles which differ significantly from each other, thereby providing us a rigorous stress test for the DPRc model and training procedure. The comparisons show that accurate reproduction of the free energy profiles requires correction of the QM/MM interactions out to 6 Å. We further find that the model's initial training benefits from generating data from temperature replica exchange simulations and including high-temperature configurations into the fitting procedure so the resulting models are trained to properly avoid high-energy regions. A single DPRc model was trained to reproduce 4 different reactions and yielded good agreement with the free energy profiles made from the target QM/MM simulations. The DPRc model was further demonstrated to be transferable to 2D free energy surfaces and 1D free energy profiles that were not explicitly considered in the training. Examination of the computational performance of the DPRc model showed that it was fairly slow when run on CPUs, but was sped up almost 100-fold when using an NVIDIA V100 GPUs, resulting in almost negligible overhead. The new DPRc model and training procedure provide a potentially powerful new tool for the creation of next-generation QM/MM potentials for a wide spectrum of free energy applications ranging from drug discovery to enzyme design.<br>

The significance of long-range correction to the hydroperoxyl radical-scavenging reaction of trans-resveratrol and gnetin C

Density functional theory has been gaining popularity for studying the radical scavenging activity of antioxidants. However, only a few studies investigate the importance of calculation methods on the radical-scavenging reactions. In this study, we examined the significance of (i) the long-range correction on the coulombic interaction and (ii) the London dispersion correction to the hydroperoxyl radical-scavenging reaction of trans-resveratrol and gnetin C. We employed B3LYP, CAM-B3LYP, M06-2X exchange-correlation functionals and B3LYP with the D3 version of Grimme’s dispersion in the calculations. The results showed that long-range correction on the coulombic interaction had a significant effect on the increase of reaction and activation energies. The increase was in line with the change of hydroperoxyl radical’s orientation in the transition state structure. Meanwhile, the London dispersion correction only had a minor effect on the transition state structure, reaction energy and activation energy. Overall, long-range correction on the coulombic interaction had a significant impact on the radical-scavenging reaction.

Interpretasi Objek Dasar Laut Berdasarkan Nilai Hambur Balik Menggunakan Instrumen Side Scan Sonar (Studi Kasus Pipa Pertamina di Balongan)

Side scan sonar merupakan instrumen single beam yang mampu menunjukkan gambar dua dimensional permukaan dasar laut dengan kondisi kontur, topografi dan target secara bersamaan. Teknologi ini merupakan penginderaan jauh akustik untuk pemetaan sedimen dan struktur dasar laut. Side scan sonar merekam energi gelombang akustik yang dipancarkan oleh hambur balik dasar laut sehingga mampu membedakan besar kecil partikel penyusun permukaan dasar laut. Pengaruh dari intensitas hambur balik tergantung pada tipe, magnitudo dan orientasi dari kekasaran dasar perairan yang dapat mendeskripsikan dasar laut. Penelitian ini bertujuan untuk memvisualisasikan dan menginterpretasikan hasil pengolahan data dari side scan sonar pada pendeteksian target yang berupa pipa diperairan Balongan, estimasi dimensi dan posisi pipa, menentukan nilai amplitudo hambur balik pipa dan menganalisis respon hambur balik dari pipa. Pemrosesan data side scan sonar dilakukan menggunakan koreksi geometrik untuk menetapkan posisi yang sebenarnya pada pixel citra yang terdiri dari bottom tracking, slant range correction, layback correction dan koreksi radiometrik dilakukan untuk intensitas hambur balik pada digital number yang ditetapkan pada setiap pixel meliputi Beam Angle Correction (BAC), Automatic Gain Control (AGC), Time Varying Gain (TVG) dan Empirical Gain Normalization (EGN). Lokasi penelitian berada di sekitar Pelabuhan Balongan menggunakan instrumen side scan sonar C-MAX CM2 dengan frekuensi 325 kHz. Pengolahan data menggunakan perangkat lunak SonarWiz 5 dengan melakukan beberapa koreksi yang kemudian data hasil olahan di ekstrak menggunakan perangkat lunak XtfTosegy selanjutnya di ekstrak dengan perangkat lunak Seisee untuk menghasilkan data dengan format *.txt dan hasilnya diolah dengan perangkat lunak Matlab untuk menampilkan grafik yang dapat menunjukan nilai amplitudo dari target yang terdeteksi. Dimensi objek hasil dari pengukuran target yaitu Target pipa 1 memiliki lebar (diameter) 0,9 meter, tinggi 0,64 meter, nilai amplitudo sebesar 23.420 – 32.000 mV dan memiliki nilai hambur balik sebesar -2,71 dB. Target pipa 2 lebar(diameter) 0,9 meter, tinggi 0,35 meter dengan nilai amplitudo 20.104 – 31.100 mV dan memiliki nilai hambur balik sebesar -3,06 dB. Sedangkan target substrat dasar perairan memiliki amplitudo hambur balik 4.480 – 17.660 mV dan nilai hambur balik -11,91 dB. Hasil analisa dapat diartikan bahwa target pipa 1 dan pipa 2 memiliki kekerasan yang lebih dibandingkan dengan dasar laut. Dilihat dari nilai hambur balik dan bentuk secara 2D dipastikan target pipa 1 dan pipa 2 terbuat dari besi dengan nilai impedansi akustik 478,85 x 105 kg/m2s dan koefisien refleksi 0,928.

Deep-Learning Based Positron Range Correction of PET Images

Positron emission tomography (PET) is a molecular imaging technique that provides a 3D image of functional processes in the body in vivo. Some of the radionuclides proposed for PET imaging emit high-energy positrons, which travel some distance before they annihilate (positron range), creating significant blurring in the reconstructed images. Their large positron range compromises the achievable spatial resolution of the system, which is more significant when using high-resolution scanners designed for the imaging of small animals. In this work, we trained a deep neural network named Deep-PRC to correct PET images for positron range effects. Deep-PRC was trained with modeled cases using a realistic Monte Carlo simulation tool that considers the positron energy distribution and the materials and tissues it propagates into. Quantification of the reconstructed PET images corrected with Deep-PRC showed that it was able to restore the images by up to 95% without any significant noise increase. The proposed method, which is accessible via Github, can provide an accurate positron range correction in a few seconds for a typical PET acquisition.