3D CNN-based Deep Learning Model-based Explanatory Prognostication in Patients with Multiple Myeloma using Whole-body MRI.

Although magnetic resonance imaging (MRI) data of patients with multiple myeloma (MM) are used to predict prognosis, few reports have applied artificial intelligence (AI) techniques for this purpose. We aimed to analyze whole-body diffusion-weighted MRI data using three-dimensional (3D) convolutional neural networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), an explainable AI, to predict prognosis and explore the factors involved in prediction. We retrospectively analyzed the MRI data of a total of 142 patients with MM obtained from two medical centers. We defined the occurrence of progressive disease after MRI evaluation within 12 months as a poor prognosis and constructed a 3D CNN-based deep learning model to predict prognosis. Images from 111 cases were used as the training and internal validation data; images from 31 cases were used as the external validation data. Internal validation of the AI model with stratified 5-fold cross-validation resulted in a significant difference in progression-free survival (PFS) between good and poor prognostic cases (2-year PFS, 91.2% versus [vs.] 61.1%, P = 0.0002). The AI model clearly stratified good and poor prognostic cases in the external validation cohort (2-year PFS, 92.9% vs. 55.6%, P = 0.004), with an area under the receiver operating characteristic curve of 0.804. According to Grad-CAM, the MRI signals of the spleen and bones of the vertebrae and pelvis contributed to prognosis prediction. This study is the first to show that image analysis of whole-body MRI using a 3D CNN without any other clinical data is effective in predicting the prognosis of patients with MM.

Structures and Reactivities of N-Alkenyl-Substituted Anilides: The "Magic" Methyl Effect on Alkene.

Methyl substitution at the double bond of N-alkenyl anilides influences both the preferred conformation and the susceptibility to acidic hydrolysis. The R1-substituted amide favors the trans conformation, whereas amides substituted at R2 or R3 favor the cis conformation. Substitution at the R1 and R3 positions increases the ratio of the trans conformer. DFT study indicated that these conformational preferences can be explained in terms of substituent-induced torsion twisting of the N-alkenyl moiety relative to the amide plane. R1 substitution enhances the susceptibility to acidic hydrolysis, whereas R2 or R3 substitution increases the stability. The effect of the double bond on the conformational effect was showcased by contrasting the preferred conformation of R1-substituted anilide (trans) and hydrogenated N-isopropyl amide (cis).

N-Ethynylation of Anilides Decreases the Double-Bond Character of Amide Bond while Retaining trans-Conformation and Planarity.

Activated amide bonds have been attracting intense attention; however, most of the studied moieties have twisted amide character. To add a new strategy to activate amide bonds while maintaining its planarity, we envisioned the introduction of an alkynyl group on the amide nitrogen to disrupt amide resonance by nN→Csp conjugation. In this context, the conformations and properties of N-ethynyl-substituted aromatic amides were investigated by DFT calculations, crystallography, and NMR spectroscopic analysis. In contrast to the cis conformational preference of N-ethyl- and vinyl-substituted acetanilides, N-ethynyl-substituted acetanilide favors the trans conformation in the crystal and in solution. It also has a decreased double bond character of the C(O)-N bond, without twisting of the amide. N-Ethynyl-substituted acetanilides undergo selective C(O)-N bond or N-C(sp) bond cleavage reactions and have potential applications as activated amides for coupling reactions or easily cleavable tethers.

Expression, Functional Characterization, and Preliminary Crystallization of the Cochaperone Prefoldin from the Thermophilic Fungus Chaetomium thermophilum.

Prefoldin is a hexameric molecular chaperone found in the cytosol of archaea and eukaryotes. Its hexameric complex is built from two related classes of subunits, and has the appearance of a jellyfish: Its body consists of a double ß-barrel assembly with six long tentacle-like coiled coils protruding from it. Using the tentacles, prefoldin captures an unfolded protein substrate and transfers it to a group II chaperonin. Based on structural information from archaeal prefoldins, mechanisms of substrate recognition and prefoldin-chaperonin cooperation have been investigated. In contrast, the structure and mechanisms of eukaryotic prefoldins remain unknown. In this study, we succeeded in obtaining recombinant prefoldin from a thermophilic fungus, Chaetomium thermophilum (CtPFD). The recombinant CtPFD could not protect citrate synthase from thermal aggregation. However, CtPFD formed a complex with actin from chicken muscle and tubulin from porcine brain, suggesting substrate specificity. We succeeded in observing the complex formation of CtPFD and the group II chaperonin of C. thermophilum (CtCCT) by atomic force microscopy and electron microscopy. These interaction kinetics were analyzed by surface plasmon resonance using Biacore. Finally, we have shown the transfer of actin from CtPFD to CtCCT. The study of the folding pathway formed by CtPFD and CtCCT should provide important information on mechanisms of the eukaryotic prefoldin⁻chaperonin system.

Superovulation with an anti-inhibin monoclonal antibody improves the reproductive performance of rat strains by increasing the pregnancy rate and the litter size.

Rats are multiparous rodents that have been used extensively in research; however, the low reproductive performance of some rat strains hampers the broader use of rats as a biomedical model. In this study, the possibility of increasing the litter size after natural mating in rats through superovulation using an anti-inhibin monoclonal antibody (AIMA) was examined. In outbred Wistar rats, AIMA increased the number of ovulated oocytes by 1.3-fold. AIMA did not affect fertilization and subsequent embryonic development, resulting in a 1.4-fold increase in litter size and a high pregnancy rate (86%). In contrast, conventional superovulation by eCG/hCG administration decreased the pregnancy rate to 6-40% and did not increase the litter size. In inbred Brown Norway rats, AIMA increased the litter size by 1.2-fold, and the pregnancy rate increased more than twice (86% versus 38% in controls). AIMA also increased the litter size by 1.5-fold in inbred Tokai High Avoiders and Fischer 344 rats. AIMA increased the efficiency of offspring production by 1.5-, 2.7-, 1.4-, and 1.4-fold, respectively, in the four rat strains. Thus, AIMA may consistently improve the reproductive performance through natural mating in rats, which could promote the use of AIMA in biomedical research.

Prediction of prognosis using artificial intelligence-based histopathological image analysis in patients with soft tissue sarcomas.

BACKGROUND: Prompt histopathological diagnosis with accuracy is required for soft tissue sarcomas (STSs) which are still challenging. In addition, the advances in artificial intelligence (AI) along with the development of pathology slides digitization may empower the demand for the prediction of behavior of STSs. In this article, we explored the application of deep learning for prediction of prognosis from histopathological images in patients with STS. METHODS: Our retrospective study included a total of 35 histopathological slides from patients with STS. We trained Inception v3 which is proposed method of convolutional neural network based survivability estimation. F1 score which identify the accuracy and area under the receiver operating characteristic curve (AUC) served as main outcome measures from a 4-fold validation. RESULTS: The cohort included 35 patients with a mean age of 64 years, and the mean follow-up period was 34 months (2-66 months). Our deep learning method achieved AUC of 0.974 and an accuracy of 91.9% in predicting overall survival. Concerning with the prediction of metastasis-free survival, the accuracy was 84.2% with the AUC of 0.852. CONCLUSION: AI might be used to help pathologists with accurate prognosis prediction. This study could substantially improve the clinical management of patients with STS.

TDP-43 N-terminal domain dimerisation or spatial separation by RNA binding decreases its propensity to aggregate.

Aggregation of the 43 kDa TAR DNA-binding protein (TDP-43) is a pathological hallmark of amyotrophic lateral sclerosis (ALS) and frontotemporal lobar degeneration (FTLD). RNA binding and TDP-43 N-terminal domain dimerisation has been suggested to ameliorate TDP-43 aggregation. However, the relationship between these factors and the solubility of TDP-43 is largely unknown. Therefore, we developed new oligonucleotides that can recruit two TDP-43 molecules and interfere with their intermolecular interactions via spatial separation. Using these oligonucleotides and TDP-43-preferable UG-repeats, we uncovered two distinct mechanisms for modulating TDP-43 solubility by RNA binding: One is N-terminal domain dimerisation, and the other is the spatial separation of two TDP-43 molecules. This study provides new molecular insights into the regulation of TDP-43 solubility.

Evaluating tubulointerstitial compartments in renal biopsy specimens using a deep learning-based approach for classifying normal and abnormal tubules.

Renal pathology is essential for diagnosing and assessing the severity and prognosis of kidney diseases. Deep learning-based approaches have developed rapidly and have been applied in renal pathology. However, methods for the automated classification of normal and abnormal renal tubules remain scarce. Using a deep learning-based method, we aimed to classify normal and abnormal renal tubules, thereby assisting renal pathologists in the evaluation of renal biopsy specimens. Consequently, we developed a U-Net-based segmentation model using randomly selected regions obtained from 21 renal biopsy specimens. Further, we verified its performance in multiclass segmentation by calculating the Dice coefficients (DCs). We used 15 cases of tubulointerstitial nephritis to assess its applicability in aiding routine diagnoses conducted by renal pathologists and calculated the agreement ratio between diagnoses conducted by two renal pathologists and the time taken for evaluation. We also determined whether such diagnoses were improved when the output of segmentation was considered. The glomeruli and interstitium had the highest DCs, whereas the normal and abnormal renal tubules had intermediate DCs. Following the detailed evaluation of the tubulointerstitial compartments, the proximal, distal, atrophied, and degenerated tubules had intermediate DCs, whereas the arteries and inflamed tubules had low DCs. The annotation and output areas involving normal and abnormal tubules were strongly correlated in each class. The pathological concordance for the glomerular count, t, ct, and ci scores of the Banff classification of renal allograft pathology remained high with or without the segmented images. However, in terms of time consumption, the quantitative assessment of tubulitis, tubular atrophy, degenerated tubules, and the interstitium was improved significantly when renal pathologists considered the segmentation output. Deep learning algorithms can assist renal pathologists in the classification of normal and abnormal tubules in renal biopsy specimens, thereby facilitating the enhancement of renal pathology and ensuring appropriate clinical decisions.

Explainable Machine Learning for Atrial Fibrillation in the General Population Using a Generalized Additive Model　- A Cross-Sectional Study.

Background: Atrial fibrillation (AF) is the most common arrhythmia and is associated with increased thromboembolic stroke risk and heart failure. Although various prediction models for AF risk have been developed using machine learning, their output cannot be accurately explained to doctors and patients. Therefore, we developed an explainable model with high interpretability and accuracy accounting for the non-linear effects of clinical characteristics on AF incidence. Methods and Results: Of the 489,073 residents who underwent specific health checkups between 2009 and 2018 and were registered in the Kanazawa Medical Association database, data were used for 5,378 subjects with AF and 167,950 subjects with normal electrocardiogram readings. Forty-seven clinical parameters were combined using a generalized additive model algorithm. We validated the model and found that the area under the curve, sensitivity, and specificity were 0.964, 0.879, and 0.920, respectively. The 9 most important variables were the physical examination of arrhythmia, a medical history of coronary artery disease, age, hematocrit, γ-glutamyl transpeptidase, creatinine, hemoglobin, systolic blood pressure, and HbA1c. Further, non-linear relationships of clinical variables to the probability of AF diagnosis were visualized. Conclusions: We established a novel AF risk explanation model with high interpretability and accuracy accounting for non-linear information obtained at general health checkups. This model contributes not only to more accurate AF risk prediction, but also to a greater understanding of the effects of each characteristic.

Author Correction: Efficient derivation of knock-out and knock-in rats using embryos obtained by in vitro fertilization.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Bone Tunnel Placement Determination Method for 3D Images and Its Evaluation for Anterior Cruciate Ligament Reconstruction.

BACKGROUND: Anterior cruciate ligament (ACL) injury causes knee instability which affects sports activity involving cutting and twisting motions. The ACL reconstruction surgery replaces the damaged ACL with artificial one which is fixed to the bone tunnels opened by the surgeon. The outcome of the ACL reconstruction is strongly related to the placement of the bone tunnels, therefore, the optimization of tunnel drilling technique is an important factor to obtain satisfactory surgical results. AIMS: The quadrant method is used for the post-operative evaluation of the ACL reconstruction surgery, which evaluates the bone tunnel opening sites on the lateral 2D X-ray radiograph. METHODS: For the purpose of applying the quadrant method to the pre-operative knee MRI, we have synthesized the pseudo lateral 2D X-ray radiograph from the patients' knee MRI. This paper proposes a computer-aided surgical planning system for the ACL reconstruction. The proposed system estimates appropriate bone tunnel opening sites on the pseudo lateral 2D X-ray radiograph synthesized from the pre-operative knee MRI. RESULTS: In the experiment, the proposed method was applied to 98 subjects including subjects with osteoarthritis. The experimental results showed that the proposed method can estimate the bone tunnel opening sites accurately. The other experiment using 36 healthy patients showed that the proposed method is robust to the knee shape deformation caused by disease. CONCLUSION: It is verified that the proposed method can be applied to subjects with osteoarthritis.

Efficient derivation of knock-out and knock-in rats using embryos obtained by in vitro fertilization.

Rats are effective model animals and have contributed to the development of human medicine and basic research. However, the application of reproductive engineering techniques to rats is not as advanced compared with mice, and genome editing in rats has not been achieved using embryos obtained by in vitro fertilization (IVF). In this study, we conducted superovulation, IVF, and knock out and knock in using IVF rat embryos. We found that superovulation effectively occurred in the synchronized oestrus cycle and with anti-inhibin antiserum treatment in immature rats, including the Brown Norway rat, which is a very difficult rat strain to superovulate. Next, we collected superovulated oocytes under anaesthesia, and offspring derived from IVF embryos were obtained from all of the rat strains that we examined. When the tyrosinase gene was targeted by electroporation in these embryos, both alleles were disrupted with 100% efficiency. Furthermore, we conducted long DNA fragment knock in using adeno-associated virus and found that the knock-in litter was obtained with high efficiency (33.3-47.4%). Thus, in this study, we developed methods to allow the simple and efficient production of model rats.

Influence of Spatial Resolution in Three-dimensional Cine Phase Contrast Magnetic Resonance Imaging on the Accuracy of Hemodynamic Analysis.

INTRODUCTION: We aim to elucidate the effect of spatial resolution of three-dimensional cine phase contrast magnetic resonance (3D cine PC MR) imaging on the accuracy of the blood flow analysis, and examine the optimal setting for spatial resolution using flow phantoms. MATERIALS AND METHODS: The flow phantom has five types of acrylic pipes that represent human blood vessels (inner diameters: 15, 12, 9, 6, and 3 mm). The pipes were fixed with 1% agarose containing 0.025 mol/L gadolinium contrast agent. A blood-mimicking fluid with human blood property values was circulated through the pipes at a steady flow. Magnetic resonance (MR) images (three-directional phase images with speed information and magnitude images for information of shape) were acquired using the 3-Tesla MR system and receiving coil. Temporal changes in spatially-averaged velocity and maximum velocity were calculated using hemodynamic analysis software. We calculated the error rates of the flow velocities based on the volume flow rates measured with a flowmeter and examined measurement accuracy. RESULTS: When the acrylic pipe was the size of the thoracicoabdominal or cervical artery and the ratio of pixel size for the pipe was set at 30% or lower, spatially-averaged velocity measurements were highly accurate. When the pixel size ratio was set at 10% or lower, maximum velocity could be measured with high accuracy. It was difficult to accurately measure maximum velocity of the 3-mm pipe, which was the size of an intracranial major artery, but the error for spatially-averaged velocity was 20% or less. CONCLUSIONS: Flow velocity measurement accuracy of 3D cine PC MR imaging for pipes with inner sizes equivalent to vessels in the cervical and thoracicoabdominal arteries is good. The flow velocity accuracy for the pipe with a 3-mm-diameter that is equivalent to major intracranial arteries is poor for maximum velocity, but it is relatively good for spatially-averaged velocity.

Impact of pixel-based machine-learning techniques on automated frameworks for delineation of gross tumor volume regions for stereotactic body radiation therapy.

The aim of this study was to investigate the impact of pixel-based machine learning (ML) techniques, i.e., fuzzy-c-means clustering method (FCM), and the artificial neural network (ANN) and support vector machine (SVM), on an automated framework for delineation of gross tumor volume (GTV) regions of lung cancer for stereotactic body radiation therapy. The morphological and metabolic features for GTV regions, which were determined based on the knowledge of radiation oncologists, were fed on a pixel-by-pixel basis into the respective FCM, ANN, and SVM ML techniques. Then, the ML techniques were incorporated into the automated delineation framework of GTVs followed by an optimum contour selection (OCS) method, which we proposed in a previous study. The three-ML-based frameworks were evaluated for 16 lung cancer cases (six solid, four ground glass opacity (GGO), six part-solid GGO) with the datasets of planning computed tomography (CT) and 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET)/CT images using the three-dimensional Dice similarity coefficient (DSC). DSC denotes the degree of region similarity between the GTVs contoured by radiation oncologists and those estimated using the automated framework. The FCM-based framework achieved the highest DSCs of 0.79±0.06, whereas DSCs of the ANN-based and SVM-based frameworks were 0.76±0.14 and 0.73±0.14, respectively. The FCM-based framework provided the highest segmentation accuracy and precision without a learning process (lowest calculation cost). Therefore, the FCM-based framework can be useful for delineation of tumor regions in practical treatment planning.