Partial Map Research Articles

Partial Imaginary Transition State (ITS) Graphs: A Formal Framework for Research and Analysis of Atom-to-Atom Maps of Unbalanced Chemical Reactions and Their Completions

Atom-to-atom maps (AAMs) are bijections that establish the correspondence of reactant and product atoms across chemical reactions. They capture crucial features of the reaction mechanism and thus play a central role in modeling chemistry at the level of graph transformations. AAMs are equivalent to so-called “imaginary transition state” (ITS) graphs, making it possible to reduce tasks such as the computational comparison of AAMs to testing graph isomorphisms. In many application scenarios, nonetheless, only partial information is available, i.e., only partial maps or, equivalently, only subgraphs of the ITS graphs, are known. Here, we investigate whether and how, and to what extent, such partial chemical data can be completed and compared. The focus of this contribution is entirely on the development of a solid mathematical foundation for the analysis of partial AAMs and their associated partial ITS graphs.

Genome-wide copy number variation regions in indigenous (Bos indicus) cattle breeds of Tamil Nadu, India.

Identification of large scale structural polymorphisms (Copy number variations) of more than 50 bp between the individuals of a species would help in knowing genetic diversity, phenotypic variability, adaptability to tropical environment and disease resistance. Read depth-based method implemented in CNVnator was used for calling copy number variant regions on sequenced data obtained from WGS from 15 pooled samples belonging to five draught cattle breeds of Tamil Nadu. A total of 11,605 CNV regions (CNVRs) were observed covering a genome size of 18.63 percent. Among these, 11,459 were restricted to autosomes, consisting of 11,013 deletions, 353 duplications and 93 complex events. These CNVRs were annotated to 4,989 candidate genes. A total of 8,291 numbers of CNVRs were shared among the five cattle breeds as also supported by PCA and STRUCTURE analyses and 1,172 CNVRs were breed-specific. Four out of five selected breed-specific CNVRs were validated using real-time PCR. Genes with CNVRs are related to milk production (BTN1A1, ABCA1 and LAP3), disease resistance (TLR4 and DNAH8), adaptability (SOD1, CAST and SMARCAL1), growth (EGFR, NKAIN3), reproduction (BRWD1 and PDE6D), meat and carcass traits (MAP3K5 and NCAM1) and exterior (ATRN and MITF) traits. Gene enrichment analysis based on the gene list retrieved from the CNVRs disclosed over-represented terms (p<0.01) associated with milk fat production. NETWORK analysis had identified 13 putative candidate genes involved in milk fat percentage, milk fat yield, lactation persistency, milk yield, heat tolerance, calving ease, growth and conformation traits. The genome-wide CNVRs identified in the present study produced genome-wide partial CNV map in indigenous cattle breeds of Tamil Nadu.

Momordica charantia Is a Novel Host of 'Candidatus Phytoplasma malaysianum'-Related Strains Associated with Bitter Melon Stem Fasciation Disease in China.

Momordica charantia, also known as bitter melon, bitter gourd, and bitter squash, is a member of the Cucurbitaceae family and is widely grown in tropical and subtropical regions for its edible fruit and medicinal properties (Alves et al. 2017). In April 2022, bitter melon plants exhibiting stem fasciation and excessive tendril symptoms were observed in a 50-acre vegetable farm in Yijia Village, Weishan Yizu Huizu Autonomous County, Dali, Yunnan Province, China (Fig. 1). The farm primarily grew tomatoes, but around 400 bitter melon plants were planted in spots where tomatoes failed to establish. One plot had a 40% incidence rate, with four out of ten bitter melon plants showing symptoms. Scattered cases were observed in other plots, leading to an overall disease incidence rate of around 2% for the entire farm. Phytoplasma infection was suspected due to symptomatic plants growing in the same province as previously reported cases of phytoplasma diseases, such as happy tree (Camptotheca accuminata) witches'-broom disease, and the presence of phytoplasma-transmitting leafhoppers (Qiao et al. 2023). DNA was extracted from four symptomatic samples and two healthy controls collected from the abovementioned plot with a 40% disease incidence using Bioteke's Plant Genomic DNA Extraction Kit and then tested for phytoplasma infection. A nested PCR assay was conducted using primer pair P1/16S-SR followed by P1A/16S-SR to amplify the near full-length phytoplasma 16S rDNA (about 1.5kb) as previously described (Lee et al. 2004). None of the healthy controls tested positive for phytoplasma infection, while three out of four symptomatic plants showed positive results. The amplicons from the nested PCR were cloned into the pCRII-TOPO vector as previously described (Lee et al. 2004). The resulting clones were sequenced, and the representative sequence was deposited into GenBank (accession number PP489216). The iPhyClassifier (Zhao et al. 2009) was employed to determine the phytoplasma species and group/subgroup associated with the bitter melon stem fasciation (BMSF) disease. The results indicated that the diseased bitter melon plants were infected with a strain related to 'Candidatus Phytoplasma malaysianum' (EU371934), with a 98.07% sequence identity. The similarity coefficient was 1.00 compared to the reference strain of 16SrXXXII-D (GenBank accession: MW138004). The phytoplasma strain associated with BMSF disease was designated as BMSF1. In addition, the same DNA samples underwent further characterization of the BMSF strains. A nested PCR was conducted using primer pair rpL2F3/rpIR1A, followed by rp(III)-FN/rpIR1A to amplify a phytoplasma-specific rp gene segment (about 1.2 kb) (Martini et al. 2007; Davis et al. 2013). Three out of four samples tested positive, consistent with the 16S rRNA gene amplification results. Similarly, a primer pair L15F1/MapR1 followed by secYF1(III)/secYR1(III) was used to amplify a phytoplasma-specific partial spc operon (about 1.7 kb) that includes the complete secY gene and partial rpl15 and map genes, as previously described (Lee et al. 2010). The obtained rp and partial spc amplicons were cloned and sequenced (GenBank accession numbers PP464295 and PP464296). The rp and secY gene sequences were searched against the non-redundant nucleotide collection in the NCBI database using BLASTN. The top hit for the rp gene was 'Ca. Phytoplasma luffae' (CP054393), with 83.24% identity (1068/1283 base-matching). The top hit for the secY gene was also 'Ca. Phytoplasma luffae' (CP054393), with 72.53% identity (1294/1784 base-matching). The percent identity of the BMSF sequences compared to the top hit is low since no other group 16SrXXXII rp and secY gene sequences are available for comparison. A subgroup 16SrXXXII-D phytoplasma strain has been previously reported associated with Camptotheca acuminata witches'-broom (Qiao et al. 2023) and Trema tomentosa witches'-broom (Yu et al. 2021) in China. To our knowledge, bitter melon represents a new host of 'Candidatus Phytoplasma malaysianum'-related strains, and this is the first report of BMSF disease in China. The findings suggest that 'Candidatus Phytoplasma malaysianum'-related strains infect not only ornamental plants but also crops.

ROAD EXTRACTION FROM SATELLITE IMAGERY USING DEEP LEARNING VOL - I

Road extraction involves the intricate process of generating road maps automatically through deep learning algorithms. This task, particularly from satellite imagery, presents significant challenges due to various factors like occlusions, shadows, noise, and fluctuating illumination conditions. As a result, achieving complete and accurate road extraction is daunting without relying on manual annotations or imperfect road maps for guidance. One potential strategy to enhance road extraction accuracy is by incorporating partial road maps as supplementary data. These partial maps, sourced from platforms like OpenStreetMap or Google Maps, may not offer complete or pristine representations of roads but can still provide valuable additional information. By integrating these partial maps with satellite images, we can exploit their complementary nature to mitigate uncertainty in the extraction process. It's important to note that while road extraction may be relatively straightforward in some regions, such as rural areas, it becomes significantly more complex in urban or underdeveloped areas. These environments present unique challenges that require sophisticated algorithms and approaches to accurately extract roads from satellite imagery. Key Words: Road Extraction, Satellite Imagery, Google Maps, Open Street Map, Auxiliary information, Disaster management, Occlusions, Illumination, Annotation, Shadow.

RMSxAI: arginine methylation sites prediction from protein sequences using machine learning algorithms and explainable artificial intelligence

Protein methylation is a vital regulator of many biological processes at the post-translational level, and accurate prediction of protein methylation sites is essential for research and drug discovery. In this paper, we present a new method, namely RMSxAI, to predict the arginine methylation sites from primary sequences using machine learning algorithms and describe the predictions using explainable artificial intelligence (XAI) techniques. Leveraging experimentally validated methylated and unmethylated protein sequences from diverse organisms, we deduced several sequence features, encompassing physicochemical properties, amino acid composition, and evolutionary insights. Our results show that the proposed RMSxAI can predict protein methylation sites with high accuracy, bringing the F1 score up to 0.88 and overall accuracy up to 88.4%. We use various XAI methods to explain the output results. These include key features, partial occupancy maps, and local variation models that provide insight into key features and interactions that lead to predictions. Overall, our approach is relevant to research and drug discovery, and our results demonstrate the potential of machine learning algorithms and XAI methods to provide accurate and meaningful prediction of arginine methylation sites.

Unravelling the metabolomic diversity of pigmented and non-pigmented traditional rice from Tamil Nadu, India

Rice metabolomics is widely used for biomarker research in the fields of pharmacology. As a consequence, characterization of the variations of the pigmented and non-pigmented traditional rice varieties of Tamil Nadu is crucial. These varieties possess fatty acids, sugars, terpenoids, plant sterols, phenols, carotenoids and other compounds that plays a major role in achieving sustainable development goal 2 (SDG 2). Gas-chromatography coupled with mass spectrometry was used to profile complete untargeted metabolomics of Kullkar (red colour) and Milagu Samba (white colour) for the first time and a total of 168 metabolites were identified. The metabolite profiles were subjected to data mining processes, including principal component analysis (PCA), Orthogonal Partial Least Square Discrimination Analysis (OPLS-DA) and Heat map analysis. OPLS-DA identified 144 differential metabolites between the 2 rice groups, variable importance in projection (VIP) ≥ 1 and fold change (FC) ≥ 2 or FC ≤ 0.5. Volcano plot (64 down regulated, 80 up regulated) was used to illustrate the differential metabolites. OPLS-DA predictive model showed good fit (R2X = 0.687) and predictability (Q2 = 0.977). The pathway enrichment analysis revealed the presence of three distinct pathways that were enriched. These findings serve as a foundation for further investigation into the function and nutritional significance of both pigmented and non-pigmented rice grains thereby can achieve the SDG 2.

Chemical, antioxidant, and antifungal analysis of oregano and thyme essential oils from Ecuador: Effect of thyme against Lasiodiplodia theobromae and its application in banana rot

The objective of this study was to evaluate the antioxidant capacity by spectrophotometric methods, the in vitro and in vivo antifungal effect against Lasiodiplodia theobromae and the constitution of the essential oils (EO) of oregano and thyme in comparison with their commercial counterparts. The results showed by the EOs of extracted thyme (T-EO), commercial thyme (CT-EO), extracted oregano (O-EO) and commercial oregano (CO-EO), demonstrated antioxidant profiles with a radical neutralizing potential (DPPH•) of IC50: 1.11 ± 0.019; 1.08 ± 0.05; 40.56 ± 0.227 and 0.69 ± 0.004 mg/mL, respectively. They also revealed a ferric ion reducing capacity (FRAP) of 93.05 ± 0.52; 97.72 ± 0.42; 21.85 ± 0.57 and 117.24 ± 0.64 mg Eq Trolox/g. A reduction in β-carotene degradation of 65.71 ± 0.04; 51.97 ± 0.66; 43.58 ± 1.56 and 57.46 ± 1.56 %. A total phenol content (Folin-Ciocalteu) of 132.97 ± 0.77; 141.89 ± 2.56; 152.04 ± 0.10 and 25.66 ± 0.40 mg EGA/g. Chemical characterization performed by gas chromatography mass spectrometry (GC-MS) showed that the respective major components of the samples were thymol (T-EO: 45.78 %), thymol (CT-EO: 43.57 %), alloaromadendrene (O-EO: 25.17 %) and carvacrol (CO-EO: 62.06 %). Regarding antifungal activity, it was evident that at the in vitro level, both commercial EOs had a MIC of 250 ppm while the extracted thyme EO had a MIC of 500 ppm; In vivo studies demonstrated that the application of thyme EO had a behavior similar to the synthetic fungicide, slowing down rot in bananas under storage conditions. Finally, partial least squares discriminant analysis (PLS-DA) and heat maps suggest p-cymene, carvacrol, linalool, eucalyptol, 4-terpineol, (z)-β-terpineol, alkanhol, caryophyllene, β-myrcene, d-limonene, α-terpinene, α-terpineol, d-α-pinene, camphene, caryophyllene oxide, δ-cadinene, terpinolene and thymol as relevant biomarkers associated with the assessed bioactive properties demonstrating the potential of extracted essential oils for the development of a botanical biofungicide.

Semantically enhanced attention map‐driven occluded person re‐identification

AbstractOccluded person re‐identification (Re‐ID) is to identify a particular person when the person's body parts are occluded. However, challenges remain in enhancing effective information representation and suppressing background clutter when considering occlusion scenes. This paper proposes a novel attention map‐driven network (AMD‐Net) for occluded person Re‐ID. In AMD‐Net, human parsing labels are introduced to supervise the generation of partial attention maps, while a spatial‐frequency interaction module is suggested to complement the higher‐order semantic information from the frequency domain. Furthermore, a Taylor‐inspired feature filter for mitigating background disturbance and extracting fine‐grained features is proposed. Moreover, a part‐soft triplet loss, which is robust to non‐discriminative body partial features is also designed. Experimental results on Occluded‐Duke, Occluded‐Reid, Market‐1501, and Duke‐MTMC datasets show that this method outperforms existing state‐of‐the‐art methods. The code is available at: https://github.com/ISCLab‐Bistu/SA‐ReID.

Metabolomic profiling of the aqueous humor in patients with pediatric cataract

Pediatric cataract, including congenital and developmental cataract, is a kind of pediatric vision-threatening disease with extensive phenotypic heterogeneity and multiple mechanisms. We aimed to investigate the metabolite profile of aqueous humor (AH) in patients with pediatric cataracts, and identify underlying mutual correlations between differential metabolites. Metabolomic profiles of AH were analyzed and compared between pediatric cataract patients (n = 33) and age-related cataract patients without metabolic diseases (n = 29), using global untargeted metabolomics with ultra-high-performance liquid chromatography tandem mass spectrometry. Principal component analysis, partial least squares discriminant analysis and heat map were applied. Enriched pathway analysis was conducted using Kyoto Encyclopedia of Genes and Genomes. Receiver-operating characteristic (ROC) analyses were employed to select potential biomarkers. A total of 318 metabolites were identified, of which 54 differential metabolites (25 upregulated and 29 downregulated) were detected in pediatric cataract group compared with controls (variable importance of projection >1.0, fold change ≥1.5 or ≤ 0.667 and P < 0.05). A significant accumulation of N-Acetyl-Dl-glutamic acid was observed in pediatric cataract group. The differential metabolites were mainly enriched in histidine metabolism (increased L-Histidine and decreased 1-Methylhistamine) and the tryptophan metabolism (increased N-Formylkynurenine and L-Kynurenine). 5-Aminosalicylic acid showed strong positive mutual inter-correlation with L-Tyrosinemethylester and N,N-Diethylethanolamine, both of which were down-regulated in pediatric cataract group. The ROC analysis implied 11 metabolites served as potential biomarkers for pediatric cataract patients (all area under the ROC curve ≥0.900). These results illustrated novel potential metabolites and metabolic pathways in pediatric cataract, which provides new insights into the pathophysiology of pediatric cataract.

Tailored Mass Spectral Data Exploration Using the SpecXplore Interactive Dashboard.

Untargeted metabolomics promises comprehensive characterization of small molecules in biological samples. However, the field is hampered by low annotation rates and abstract spectral data. Despite recent advances in computational metabolomics, manual annotations and manual confirmation of in-silico annotations remain important in the field. Here, exploratory data analysis methods for mass spectral data provide overviews, prioritization, and structural hypothesis starting points to researchers facing large quantities of spectral data. In this research, we propose a fluid means of dealing with mass spectral data using specXplore, an interactive Python dashboard providing interactive and complementary visualizations facilitating mass spectral similarity matrix exploration. Specifically, specXplore provides a two-dimensional t-distributed stochastic neighbor embedding embedding as a jumping board for local connectivity exploration using complementary interactive visualizations in the form of partial network drawings, similarity heatmaps, and fragmentation overview maps. SpecXplore makes use of state-of-the-art ms2deepscore pairwise spectral similarities as a quantitative backbone while allowing fast changes of threshold and connectivity limitation settings, providing flexibility in adjusting settings to suit the localized node environment being explored. We believe that specXplore can become an integral part of mass spectral data exploration efforts and assist users in the generation of structural hypotheses for compounds of interest.

Drinfeld’s Lemma for F-isocrystals, I

Abstract We prove that in either the convergent or overconvergent setting, an absolutely irreducible $F$-isocrystal on the absolute product of two or more smooth schemes over perfect fields of characteristic $p$, further equipped with actions of the partial Frobenius maps, is an external product of $F$-isocrystals over the multiplicands. The corresponding statement for lisse $\overline{{\mathbb{Q}}}_{\ell }$-sheaves, for $\ell \neq p$ a prime, is a consequence of Drinfeld’s lemma on the fundamental groups of absolute products of schemes in characteristic $p$. The latter plays a key role in V. Lafforgue’s approach to the Langlands correspondence for reductive groups with $\ell $-adic coefficients; the $p$-adic analogue will be considered in subsequent work with Daxin Xu.

Middleman Minority Nation: A New Conceptualisation of the State in Singapore

ABSTRACT The Singaporean state is often conceptualised as neoliberal, but I argue that this conceptualisation is mistaken. While Singapore embraces the neoliberal ‘all you have is yourself’ ethos, I contend, the state does not apply this ethos to individuals and families, but to society as a whole: to the relation between Singapore and ‘the world’, rather than to the domestic realm within Singapore. That is, Singapore is a communalist and not an individualist society – a society in which the group is paramount, and in which the rights and responsibilities of individuals are subordinated to group interests. I introduce the term ‘middleman minority state’ (MM state) to capture this social phenomenon, whereby the state scales up the tactics of the classic middleman minority to the level of a small nation-state. I argue that the uniqueness of Singapore as a polity is not fully reflected in 20th-century economists’ views on society and economics, which provide only a partial map of Singapore. Instead, we must look to Singapore’s history as a centre for middleman minorities, whose values and behaviour patterns were transformed into a successful state strategy as the country became an independent nation-state in the 1960s.

Potential of Irrigated Agricultural Production of Corn (Zea mays L.) in Semi-Arid Region using Geoprocessing

This work aimed to evaluate and map the potential of irrigated agricultural production for corn for the watershed of the region of the middle course of the Paraíba River. Using SPRING, a map of soil irrigation potential and soil retention capacity was prepared and a partial map was generated through matrix crossing. Using average annual rainfall data, the climate condition map was prepared. After using LEGAL, the agricultural production potential map was generated through the matrix crossing between the partial map and the climate scenario. For maize, a Full climatic condition (C1) was identified in 2.02% of the basin's total; the full climatic condition with prolonged rainy season (C2) and the climatic condition moderated by excess water (C3) were not identified; the climatic condition Moderate by water deficiency (C4) in 0.86%; the unfit condition due to severe water deficit (C5) in 97.12% of the basin. The potential of irrigated agricultural production for maize did not show Very High (MA), High (A), Medium (M) and Low (B) potential, only the Very Low (MB) potential in 100% of the basin.

Wear-resistant nickel-matrix composite coatings incorporating hard chromium carbide particles

This work evaluates the influence of plating variables on the morphology, composition homogeneity, and abrasive wear resistance of metal matrix composite coatings. A set of Ni/Cr3C2 coatings were brush plated onto steel coupons modifying two key variables: particle size and brush material. Compositional maps of unprecedented detail have been produced and analysed statistically to enhance understanding of composition distribution. The use of Abbott-Firestone curves to analyse surface morphology enabled the evaluation of valley and peak features. The coating differences highlighted by previous analyses have been compared with their behaviour in abrasive environments, simulated using Taber testing. Moreover, coupling Taber testing with partial compositional maps at different wear stages enabled monitoring of coating wear evolution. This methodology has revealed the importance of particle sedimentation during plating, which increased particle incorporation in the composite coating but also increased composition heterogeneity. The smaller 1.7 μm carbides and abrasive brushes produced coatings with more homogeneous morphologies, higher particle content, and increased resistance against abrasive wear, with a 60% reduction in material loss in comparison to the standard nickel coatings.

Modes and model building in SHELXE.

Density modification is a standard step to provide a route for routine structure solution by any experimental phasing method, with single-wavelength or multi-wavelength anomalous diffraction being the most popular methods, as well as to extend fragments or incomplete models into a full solution. The effect of density modification on the starting maps from either source is illustrated in the case of SHELXE. The different modes in which the program can run are reviewed; these include less well known uses such as reading external phase values and weights or phase distributions encoded in Hendrickson-Lattman coefficients. Typically in SHELXE, initial phases are calculated from experimental data, from a partial model or map, or from a combination of both sources. The initial phase set is improved and extended by density modification and, if the resolution of the data and the type of structure permits, polyalanine tracing. As a feature to systematically eliminate model bias from phases derived from predicted models, the trace can be set to exclude the area occupied by the starting model. The trace now includes an extension into the gamma position or hydrophobic and aromatic side chains if a sequence is provided, which is performed in every tracing cycle. Once a correlation coefficient of over 30% between the structure factors calculated from such a trace and the native data indicates that the structure has been solved, the sequence is docked in all model-building cycles and side chains are fitted if the map supports it. The extensions to the tracing algorithm brought in to provide a complete model are discussed. The improvement in phasing performance is assessed using a set of tests.

An innovative orthogonal matrix based on nonlinear chaotic system for compressive sensing

Compressed sensing exploits the signal’s sparsity by non-uniform sampling to achieve high-quality signal reconstruction at low sampling rates. This work aims to show the efficient performance of chaotic binary orthogonal matrices (CBOM) in compressed sensing. The nonlinear, high dimensional, irregular, and high complexity properties of chaotic systems can provide more diverse and efficient ways of sampling and reconstructing signals. The CBOM construction method proposed in this paper is divided into two steps, in the first step, the real-valued sequence of a one-dimensional chaotic map is binarised using the proposed Threshold-Matching Symbol Algorithm (TMSA) to obtain a chaotic binary sequence (CBS). The i.i.d properties of the CBS were proved using the Perron–Frobenius operator and the properties of the joint probability. The binarized CBS conditionally preserves the pseudo-random of chaotic sequences, as evidenced by the derivation of the well-distribution measure and the k-order correlation measure. In the second step, the binarised sequence CBS was split and orthogonalized to construct CBOM, which satisfies low storage and correlation. We prove that CBOM obeys the Restricted Isometric Condition (RIP). The orthogonalization of the matrix will further reduce matrix column correlation and improve the quality of the reconstruction. Numerical simulation results show that the proposed matrix has considerable sampling efficiency, comparable to Gaussian and partial Hadamard matrices, close to the theoretical limit. Meanwhile, the generation and reconstruction time of the proposed matrix is smaller than other matrices. Our framework covers partial one-dimensional chaotic maps, including Chebyshev, Tent, Logistic, and so on. We can easily apply this paradigm to various fields.

Plectic structures in p-adic de Rham cohomology

Given a Hilbert modular form for a totally real field F, and a prime p split completely in F, the f-eigenspace in p-adic de Rham cohomology has a family of partial filtrations and partial Frobenius maps, indexed by the primes of F above p. The general plectic conjectures of Nekovář and Scholl suggest a “plectic comparison isomorphism” comparing these structures to étale cohomology. We prove this conjecture in the case [F:Q]=2 under some mild assumptions; and for general F we prove a weaker statement which is strong evidence for the conjecture, showing that the plectic Hodge filtration has a canonical splitting given by intersecting with simultaneous eigenspaces for the partial Frobenii.

Deep Learning-Based Interpretable AI for Prostate T2W MRI Quality Evaluation

Prostate MRI quality is essential in guiding prostate biopsies. However, assessment of MRI quality is subjective with variation. Quality degradation sources exert varying impacts based on the sequence under consideration, such as T2W versus DWI. As a result, employing sequence-specific techniques for quality assessment could yield more advantageous outcomes. This study aims to develop an AI tool that offers a more consistent evaluation of T2W prostate MRI quality, efficiently identifying suboptimal scans while minimizing user bias. This retrospective study included 1046 patients from threecohorts (ProstateX [n=347], All-comer in-house [n=602], enriched bad-quality MRI in-house [n=97]) scanned between January 2011 and May 2022. An expert reader assigned T2W MRIs a quality score. A train-validation-test split of 70:15:15 was applied, ensuring equal distribution of MRI scanners and protocols across all partitions. T2W quality AI classification model was based on 3D DenseNet121 architecture using MONAI framework. In addition to multiclassification, binary classification was utilized (Classes 0/1 vs. 2). A score of 0 was given to scans considered non-diagnostic or unusable, a score of 1 was given to those with acceptable diagnostic quality with some usability but with some quality distortions present, and a score of 2 was given to those considered optimal diagnostic quality and usability. Partial occlusion sensitivity maps were generated for anatomical correlation. Three body radiologists assessed reproducibility within a subgroup of 60 test cases using weighted Cohen Kappa. The best validation multiclass accuracy of 77.1% (121/157) was achieved during training. In the test dataset, multiclassification accuracy was 73.9% (116/157), whereas binary accuracy was 84.7% (133/157). Sub-class sensitivity for binary quality distortion classification for class 0 was 100% (18/18), and sub-class specificity for T2W classification of absence/minimal quality distortions for class 2 was 90.5% (95/105). All three readers showed moderate to substantial agreement with ground truth (R1-R3 κ=0.588, κ=0.649, κ=0.487, respectively), moderate to substantial agreement with each other (R1-R2 κ=0.599, R1-R3 κ=0.612, R2-R3 κ=0.685), fair to moderate agreement with AI (R1-R3 κ=0.445, κ=0.410, κ=0.292, respectively). AI showed substantial agreement with ground truth (κ=0.704). 3D quality heatmap evaluation revealed that the most critical non-diagnostic quality imaging features from an AI perspective related to obscuration of the rectoprostatic space (94.4%, 17/18). The 3D AI model can assess T2W prostate MRI quality with moderate accuracy and translate whole sequence-level classification labels into 3D voxel-level quality heatmaps for interpretation. Image quality has a significant downstream impact on ruling out clinically significant cancers. AI may be able to help with reproducible identification of MRI sequences requiring re-acquisition with explainability.

A Comparative Study on Methods for Identifying Partially Changed Objects to Detect Deleted Objects in Partial Maps

A Comparative Study on Methods for Identifying Partially Changed Objects to Detect Deleted Objects in Partial Maps

Lane-Level Map Generation and Management Framework Using Connected Car Data

This study proposes a lane-level map generation and management framework using connected sensor data to reduce the manpower and time required for producing and updating high-definition (HD) maps. Unlike previous studies that relied on the onboard processing capabilities of vehicles to collect map-constructing elements, this study offloads computing for map generation to the cloud, assigning vehicles solely the role of transmitting sensor data. For efficient data collection, we divide the space into a grid format to define it as a partial map and establish the state of each map and its transition conditions. Lastly, tailored to the characteristics of the road elements composing the map, we propose an automated map generation technique and method for selectively collecting data. The map generation method was tested using data collected from actual vehicles. By transmitting images with an average size of 350 KB, implementation was feasible even with the current 5G upload bandwidth. By utilizing 12,545 elements, we were able to achieve a position accuracy and regression RMSE of less than 0.25 m, obtaining 651 map elements to construct the map. We anticipate that this study will help reduce the manpower and time needed for deploying and updating HD maps.