Explainable lung cancer classification with ensemble transfer learning of VGG16, Resnet50 and InceptionV3 using grad-cam.

Medical imaging stands as a critical component in diagnosing various diseases, where traditional methods often rely on manual interpretation and conventional machine learning techniques. These approaches, while effective, come with inherent limitations such as subjectivity in interpretation and constraints in handling complex image features. This research paper proposes an integrated deep learning approach utilizing pre-trained models-VGG16, ResNet50, and InceptionV3-combined within a unified framework to improve diagnostic accuracy in medical imaging. The method focuses on lung cancer detection using images resized and converted to a uniform format to optimize performance and ensure consistency across datasets. Our proposed model leverages the strengths of each pre-trained network, achieving a high degree of feature extraction and robustness by freezing the early convolutional layers and fine-tuning the deeper layers. Additionally, techniques like SMOTE and Gaussian Blur are applied to address class imbalance, enhancing model training on underrepresented classes. The model's performance was validated on the IQ-OTH/NCCD lung cancer dataset, which was collected from the Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases over a period of three months in fall 2019. The proposed model achieved an accuracy of 98.18%, with precision and recall rates notably high across all classes. This improvement highlights the potential of integrated deep learning systems in medical diagnostics, providing a more accurate, reliable, and efficient means of disease detection.

Gray Matter Atrophy in a 6-OHDA-induced Model of Parkinson's Disease.

INTRODUCTION: Magnetic resonance imaging (MRI) based brain morphometric changes in unilateral 6-hydroxydopamine (6-OHDA) induced Parkinson's disease (PD) model can be elucidated using voxel-based morphometry (VBM), study of alterations in gray matter volume and Machine Learning (ML) based analyses. METHODS: We investigated gray matter atrophy in 6-OHDA induced PD model as compared to sham control using statistical and ML based analysis. VBM and atlas-based volumetric analysis was carried out at regional level. Support vector machine (SVM)-based algorithms wherein features (volume) extracted from (a) each of the 150 brain regions (b) statistically significant features (only) and (c) volumes of each cluster identified after application of VBM (VBM_Vol) were used for training the decision model. The lesion of the 6-OHDA model was validated by estimating the net contralateral rotational behaviour by the injection of apomorphine drug and motor impairment was assessed by rotarod and open field test. RESULTS AND DISCUSSION: In PD, gray matter volume (GMV) atrophy was noted in bilateral cortical and subcortical brain regions, especially in the internal capsule, substantia nigra, midbrain, primary motor cortex and basal ganglia-thalamocortical circuits in comparison with sham control. Behavioural results revealed an impairment in motor performance. SVM analysis showed 100% classification accuracy, sensitivity and specificity at both 3 and 7 weeks using VBM_Vol. CONCLUSION: Unilateral 6-OHDA induced GMV changes in both hemispheres at 7th week may be associated with progression of the disease in the PD model. SVM based approaches provide an increased classification accuracy to elucidate GMV atrophy.

Altruistic feeding and cell-cell signaling during bacterial differentiation actively enhance phenotypic heterogeneity.

Starvation triggers bacterial spore formation, a committed differentiation program that transforms a vegetative cell into a dormant spore. Cells in a population enter sporulation non-uniformly to secure against the possibility that favorable growth conditions, which puts sporulation-committed cells at a disadvantage, may resume. This heterogeneous behavior is initiated by a passive mechanism: stochastic activation of a master transcriptional regulator. Here, we identify a cell-cell communication pathway that actively promotes phenotypic heterogeneity, wherein Bacillus subtilis cells that start sporulating early utilize a calcineurin-like phosphoesterase to release glycerol, which simultaneously acts as a signaling molecule and a nutrient to delay non-sporulating cells from entering sporulation. This produced a more diverse population that was better poised to exploit a sudden influx of nutrients compared to those generating heterogeneity via stochastic gene expression alone. Although conflict systems are prevalent among microbes, genetically encoded cooperative behavior in unicellular organisms can evidently also boost inclusive fitness.

Folate Receptor Targeting Mn(II) Complex Encapsulated Porous Silica Nanoparticle as an MRI Contrast Agent for Early-State Detection of Cancer.

Cancer is recognized as one of the major causes of mortality, however, early-stage detection can increase the survival chance greatly. It is recognized that folate receptors are gradually overexpressed in the cellular membrane with the progress of cancer from stage 1 to stage 4. Utilizing the fact, herein, developed a porous silica nanoparticle system C1@SiO2-FA-NP; A) impregnated with thermodynamically stable Mn(II) complex (1) molecules within the core of the nanoparticle, and B) surface functionalized with folate units. It exhibited a high longitudinal relaxivity value r1 = 21.45 mM-1s-1 that substantially increased to r1 = 40.97 mM-1s-1 in the presence of 0.67 mM concentration of BSA under the physiological condition. The in vitro fluorescent images after surface conjugation of C1@SiO2-FA-NP with FITC (fluorescein isothiocyanate) buttressed the inclusion of the nanoparticle exclusively within the cancerous HeLa cells than that of healthy HEK293 cells. The importance of the surface-bound folate unit in the nanoparticle is further established by comparing the fluorescent images of HeLa cells in the absence of the group. Finally, the applicability of C1@SiO2-FA-NP as the T1-weighted MRI contrast agent for early-stage cancer diagnosis is established within C57BL/6 mice after infecting the mice with HeLa cells.

Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis.

Spinocerebellar ataxia type 12 is a hereditary and neurodegenerative illness commonly found in India. However, there is no established noninvasive automatic diagnostic system for its diagnosis and identification of imaging biomarkers. This work proposes a novel four-phase machine learning-based diagnostic framework to find spinocerebellar ataxia type 12 disease-specific atrophic-brain regions and distinguish spinocerebellar ataxia type 12 from healthy using a real structural magnetic resonance imaging dataset. Firstly, each brain region is represented in terms of statistics of coefficients obtained using 3D-discrete wavelet transform. Secondly, a set of relevant regions are selected using a graph network-based method. Thirdly, a kernel support vector machine is used to capture nonlinear relationships among the voxels of a brain region. Finally, the linear relationship among the brain regions is captured to build a decision model to distinguish spinocerebellar ataxia type 12 from healthy by using the regularized logistic regression method. A classification accuracy of 95% and a harmonic mean of precision and recall, i.e. F1-score of 94.92%, is achieved. The proposed framework provides relevant regions responsible for the atrophy. The importance of each region is captured using Shapley Additive exPlanations values. We also performed a statistical analysis to find volumetric changes in spinocerebellar ataxia type 12 group compared to healthy. The promising result of the proposed framework shows that clinicians can use it for early and timely diagnosis of spinocerebellar ataxia type 12.

Advanced AI-driven approach for enhanced brain tumor detection from MRI images utilizing EfficientNetB2 with equalization and homomorphic filtering.

Brain tumors pose a significant medical challenge necessitating precise detection and diagnosis, especially in Magnetic resonance imaging(MRI). Current methodologies reliant on traditional image processing and conventional machine learning encounter hurdles in accurately discerning tumor regions within intricate MRI scans, often susceptible to noise and varying image quality. The advent of artificial intelligence (AI) has revolutionized various aspects of healthcare, providing innovative solutions for diagnostics and treatment strategies. This paper introduces a novel AI-driven methodology for brain tumor detection from MRI images, leveraging the EfficientNetB2 deep learning architecture. Our approach incorporates advanced image preprocessing techniques, including image cropping, equalization, and the application of homomorphic filters, to enhance the quality of MRI data for more accurate tumor detection. The proposed model exhibits substantial performance enhancement by demonstrating validation accuracies of 99.83%, 99.75%, and 99.2% on BD-BrainTumor, Brain-tumor-detection, and Brain-MRI-images-for-brain-tumor-detection datasets respectively, this research holds promise for refined clinical diagnostics and patient care, fostering more accurate and reliable brain tumor identification from MRI images. All data is available on Github: https://github.com/muskan258/Brain-Tumor-Detection-from-MRI-Images-Utilizing-EfficientNetB2 ).

Computational analysis of anti-cancer drug hydroxyurea adsorption on nanocages of gold, silver and copper: SERS and DFT assessment.

The use of nanostructures in targeted drug delivery is effective in decreasing anticancer drug toxicity. Here, we discuss the theoretically predicted adsorption and interaction behavior of hydroxyurea [HU] with nano metal cages (nmC). HU interact the nmC through the N4 in primary amine with energies of -29.776, -30.684 and -22.105 kcal/mol for Au, Ag and Cu cage, respectively. As a result of reactivity studies, HU complexes with nmC (Au/Ag/Cu) are becoming more electrophilic and this gives the nmC system their bioactivity. It is suggested that nanocage is going to change the FMO's energy levels by means of absorption, so that it is used in drug administration. DOS and MEP were accomplished to gain additional understandings into the reactivity of proposed complexes. Method for improving the Raman signal of biomolecules is surface enhanced Raman scattering (SERS), which uses nanosized metal substrates. Chemical enhancement is evidenced by Mulliken charge distributions of all systems for detection and chemical compositions and exerts a significant role in determining them. In HU complexes containing nmC (Au/Ag/Cu), electron density was detected via ELF and LOL calculations. Based on the results of a non-covalent interaction (NCI) analysis, Van der Waals/hydrogen bonds/repulsive steric - interactions have been found. The title compound will also be analyzed in order to determine its bioactivity and drug likeness parameters, as a result, we will able to create a molecule with a highly favorable pharmacological profile and use the docking method to determine the values of the interaction energies for drug delivery. This study suggests that adsorption of drugs on nanocage surface occurs physically and functionalizing the nanocage has increased adsorption energy.

A Novel Kinematic Gait Parameter-Based Vibrotactile Cue for Freezing of Gait Mitigation among Parkinson's Patients: A Pilot Study.

Auditory and visual cues have been efficacious in laboratory-based freezing of gait (FoG) mitigation in Parkinson's disease (PD). However, real-life applications of these cues are restricted due to inconvenience to the users. Closed-loop vibrotactile cues based on temporal gait events have overcome the shortcomings of auditory and visual cueing. However, kinematic gait parameter-driven vibrotactile cueing has not been explored yet. Kinematic gait parameter-driven cueing is more effective than temporal cueing, according to FoG pathophysiology studies. Therefore, we developed and pilot-tested a novel cueing scheme in which the foot-to-ground angle at heel strike (FGA_HS) is estimated using indigenous instrumented shoes to drive vibrotactile cueing. Ten PD freezers underwent a 6-meter timed walk test in the off-medication state with and without the cue and after medication without the cue. The proposed system potentially mitigated FoG, quantified by a reduction in the ratio of time spent freezing to the total walking time and the number of FoGs. The FoG mitigation potential of the cue was further supported by increased anteroposterior center of pressure progression and FGA_HS. With a future comprehensive validation in a larger number of participants, the novel cue could likely be used in practice and commercialized.

Cell division machinery drives cell-specific gene activation during differentiation in Bacillus subtilis.

When faced with starvation, the bacterium Bacillus subtilis transforms itself into a dormant cell type called a "spore". Sporulation initiates with an asymmetric division event, which requires the relocation of the core divisome components FtsA and FtsZ, after which the sigma factor σF is exclusively activated in the smaller daughter cell. Compartment-specific activation of σF requires the SpoIIE phosphatase, which displays a biased localization on one side of the asymmetric division septum and associates with the structural protein DivIVA, but the mechanism by which this preferential localization is achieved is unclear. Here, we isolated a variant of DivIVA that indiscriminately activates σF in both daughter cells due to promiscuous localization of SpoIIE, which was corrected by overproduction of FtsA and FtsZ. We propose that the core components of the redeployed cell division machinery drive the asymmetric localization of DivIVA and SpoIIE to trigger the initiation of the sporulation program.

A Bis(Aquated) Mn(II)-Based MRI Contrast Agent with a Rigid Hydroquinazoline Unit: Synthesis, Characterization, and in Vivo MR Imaging Study.

Since the finding of nephrogenic systemic fibrosis (NFS) in patients with renal impairment and the long-term accumulation of Gd(III) ions in the central nervous system, the search for nongadolinium ion-based MRI contrast agents made of nutrient metal ions has drawn paramount attention. In this context, the development of Mn(II)-based MRI contrast agents has been a subject of interest for the last few decades. Herein, we report a pentadentate ligand (Li2[BenzPic2]) composed of two picolinate moieties and a rigid 1,2,3,4-tetrahydroquinazoline unit and the corresponding bis(aquated) Mn(II) complex (Complex 1). The complex exhibited high thermodynamic stability (log Kcond = 11.62) and kinetic inertness similar to that of the clinically approved Gd(III)-based contrast agent Magnevist. Complex 1 exerted longitudinal relaxivity (r1) of 5.32 mM-1 s-1 at 1.41 T, 37 °C, pH 7.4, and it increased by 3.6-fold in the presence of serum albumin protein, confirming a substantial rigidifying interaction (albumin association constant KA = 1.66 × 103 M-1) between the protein and the amphiphilic (log P = -0.45) contrast agent. An intravenous dose of 0.08 mmol/kg in a healthy mouse, excellent MRI signal intensity enhancement in the vasculature of the mouse liver, and brightened images of the gallbladder, kidney, and liver were realized.

Multi-oligomeric and catalytically compromised serine acetyltransferase and cysteine regulatory complex of Mycobacterium tuberculosis.

l-cysteine, a primary building block of mycothiol, plays an essential role in the defense mechanism of Mycobacterium tuberculosis (Mtb). However, it is unclear how Mtb regulates cysteine biosynthesis as no study has reported the cysteine regulatory complex (CRC) in Mtb. Serine acetyltransferase (SAT) and cysteine synthase (CS) interact to form CRC. Although MtCS has been characterized well, minimal information is available on MtSAT, which synthesizes, O-acetylserine (OAS), the precursor of cysteine. This study fills the gap and provides experimental evidence for the presence of MtCRC and a non-canonical multi-oligomeric MtSAT. We employed multiple analytical methods to characterize the oligomeric and kinetic properties of MtSAT and MtCRC. Results show that MtSAT, lacking >75 N-terminal amino acids exists in three different assembly states; trimer, hexamer, and dodecamer, compared to the single hexameric state of SAT of other bacteria. While hexamers display the highest catalytic turnover, the trimer is the least active. The predominance of trimers at low physiologically relevant concentrations suggests that MtSAT displays the lowest catalytic potential known. Further, the catalytic potential of MtSAT is also significantly reduced in CRC state, in contrast to enhanced activity of SAT in CRC of other organisms. Our study provides insights into multi-oligomeric MtSAT with reduced catalytic potential and demonstrates that both MtSAT and MtCS of Mycobacterium interact to form CRC, although with altered catalytic properties. We discuss our results in light of the altered biochemistry of the last step of canonical sulfate-dependent cysteine biosynthesis of Mycobacterium.

Gray matter biomarkers for major depressive disorder and manic disorder using logistic regression.

The study investigates morphometric changes using surface-based measures and logistic regression in Major depressive-disorder (MDD) and Manic-disorder patients as compared to controls. MDD (n = 21) and manic (n = 20) subjects were recruited from psychiatric clinics, along with 19 healthy-controls from local population, after structured and semi-structured clinical interview (DSM-IV, brief Psychotic-Rating Scale (BPRS), Young Mania Rating Scale (YMRS), Hamilton depression rating scale (HDRS), cognitive function by postgraduate Institute Battery of Brain Dysfunction (PGIBBD)). Using 3D T1-weighted images, gray matter (GM) cortical thickness and GM-based morphometric signatures (using logistic regression) were compared among MDD, manic disorder and controls using analysis of covariance (ANCOVA). No significant difference was found between the MDD and manic disorder patients. When compared to controls, cortical thinning was observed in bilateral rostral middle frontal gyrus and parsopercularis, right lateral occipital cortex, right lingual gyrus in MDD; and bilateral rostral middle frontal and superior frontal gyrus, right middle temporal gyrus, left supramarginal and left precentral gyrus in Manic disorders. Logistic regression analysis exhibited GM cortical thinning in the bilateral parsopercularis, right lateral occipital cortex and lingual gyrus in MDD; and bilateral rostral middle, superior frontal gyri, right middle temporal gyrus in Manic with a sensitivity and specificity of 85.7 % and 94.7 % and 90.0 % and 94.7 %, respectively in comparison with controls. Both groups exhibited GM loss in bilateral rostral middle frontal gyrus brain regions compared to controls. Multivariate analysis revealed common changes in GM in MDD and manic disorders associated with mood temperament, but differences when compared to controls.

Bacterial cell surface nanoenvironment requires a specialized chaperone to activate a peptidoglycan biosynthetic enzyme.

Bacillus subtilis spores are produced inside the cytosol of a mother cell. Spore surface assembly requires the SpoVK protein in the mother cell, but its function is unknown. Here, we report that SpoVK is a dedicated chaperone from a distinct higher-order clade of AAA+ ATPases that activates the peptidoglycan glycosyltransferase MurG during sporulation, even though MurG does not normally require activation by a chaperone during vegetative growth. MurG redeploys to the spore surface during sporulation, where we show that the local pH is reduced and propose that this change in cytosolic nanoenvironment necessitates a specific chaperone for proper MurG function. Further, we show that SpoVK participates in a developmental checkpoint in which improper spore surface assembly inactivates SpoVK, which leads to sporulation arrest. The AAA+ ATPase clade containing SpoVK includes other dedicated chaperones involved in secretion, cell-envelope biosynthesis, and carbohydrate metabolism, suggesting that such fine-tuning might be a widespread feature of different subcellular nanoenvironments.

Cell division machinery drives cell-specific gene activation during bacterial differentiation.

When faced with starvation, the bacterium Bacillus subtilis transforms itself into a dormant cell type called a "spore". Sporulation initiates with an asymmetric division event, which requires the relocation of the core divisome components FtsA and FtsZ, after which the sigma factor σF is exclusively activated in the smaller daughter cell. Compartment specific activation of σF requires the SpoIIE phosphatase, which displays a biased localization on one side of the asymmetric division septum and associates with the structural protein DivIVA, but the mechanism by which this preferential localization is achieved is unclear. Here, we isolated a variant of DivIVA that indiscriminately activates σF in both daughter cells due to promiscuous localization of SpoIIE, which was corrected by overproduction of FtsA and FtsZ. We propose that a unique feature of the sporulation septum, defined by the cell division machinery, drives the asymmetric localization of DivIVA and SpoIIE to trigger the initiation of the sporulation program.

Protein coopted from a phage restriction system dictates orthogonal cell division plane selection in Staphylococcus aureus.

The spherical bacterium Staphylococcus aureus, a leading cause of nosocomial infections, undergoes binary fission by dividing in two alternating orthogonal planes, but the mechanism by which S. aureus correctly selects the next cell division plane is not known. To identify cell division placement factors, we performed a chemical genetic screen that revealed a gene which we termed pcdA. We show that PcdA is a member of the McrB family of AAA+ NTPases that has undergone structural changes and a concomitant functional shift from a restriction enzyme subunit to an early cell division protein. PcdA directly interacts with the tubulin-like central divisome component FtsZ and localizes to future cell division sites before membrane invagination initiates. This parallels the action of another McrB family protein, CTTNBP2, which stabilizes microtubules in animals. We show that PcdA also interacts with the structural protein DivIVA and propose that the DivIVA/PcdA complex recruits unpolymerized FtsZ to assemble along the proper cell division plane. Deletion of pcdA conferred abnormal, non-orthogonal division plane selection, increased sensitivity to cell wall-targeting antibiotics, and reduced virulence in a murine infection model. Targeting PcdA could therefore highlight a treatment strategy for combatting antibiotic-resistant strains of S. aureus.

Structural, electronic, intermolecular interaction, reactivity, vibrational spectroscopy, charge transfer, Hirshfeld surface analysis, pharmacological and hydropathy plot on 5-Bromo nicotinic acid - Antiviral study (Hepatitis A, B, and C).

The therapeutic properties of 5-Bromonicotinatic acid (5BNA) were studied for antiviral illnesses like Hepatitis A, Hepatitis B and Hepatitis C and the influence of electron-donating and electron-withdrawing properties of functional groups on the nicotinic acid was evaluated and represented in this study using the DFT approach. The molecular parameters were determined for both gases as well as for various solvent phases. The reactive areas in the compound are examined utilising Fukui analysis. The molecular interactions are accomplished by recognising the different types of bonding found in the compound using the AIM, ELF, LOL, RDG and IRI. Solvation investigations were demonstrated to have an influence on molecular orbital energy, ESP, UV-Vis and NLO analyses. Electron-hole, NBO and Hirshfeld investigations are used to investigate the transfer of charges and interactions inside the molecule. The method of vibrational spectroscopy (IR and Raman) is used to differentiate and identify the various types of vibrations displayed by the compound. The hydropathy plots for the proteins 2A4O, 6CWD and 2OC8 associated with Hepatitis A, Hepatitis B and Hepatitis C illustrate the disquiet and attraction of the amino acids towards the water.

PGC-1α Agonist Rescues Doxorubicin-Induced Cardiomyopathy by Mitigating the Oxidative Stress and Necroptosis.

Cardiomyopathy (particularly dilated cardiomyopathy (DCM)) significantly contributes to development and progression of heart failure (HF), and inflammatory factors further deteriorate the symptoms. Morphological and functional defects of the heart in doxorubicin (DOX)-induced cardiomyopathy (cardiotoxicity) are similar to those of DCM. We used anagonist of PGC-1α (PPAR (peroxisome proliferator-activated receptor-gamma)-γ coactivator-1α) that is considered as the 'master regulator' of mitochondrial biogenesis with an aim to rescue the DOX-induced deleterious effects on the heart. Forty male C57BL/6J mice (8 weeks old) were divided in four groups, Control, DOX, ZLN005, and ZLN005 + DOX (n = 10 each group). The DOX-induced (10 mg/kg, single dose) cardiomyopathy mimics a DCM-like phenotype with marked morphologic alteration in cardiac tissue and functional derangements. Significant increased staining was observed for Masson Trichrome/Picrosirius red and α-Smooth Muscle Actinin (α-SMA) that indicated enhanced fibrosis in the DOX group compared to the control that was attenuated by (peroxisome proliferator-activated receptor-gamma (PPAR-γ) coactivator) (PGC)-1α (alpha) agonist (four doses of 2.5 mg/kg/dose; cumulative dose = 10 mg/kg). Similarly, elevated expression of necroptosis markers along with enhanced oxidative stress in the DOX group were alleviated by PGC-1α agonist. These data collectively suggested the potent therapeutic efficacy of PGC-1α agonist in mitigating the deleterious effects of DOX-induced cardiomyopathy, and it may be targeted in developing the future therapeutics for the management of DCM/HF.

Gd/hafnium oxide@gold@chitosan core-shell nanoparticles as a platform for multimodal theranostics in oncology research.

In the current study, we synthesized thiolated chitosan-stabilized gold-coated, gadolinium-doped hafnium oxide nanoparticles (CAuGH NPs) with the capability of acting as a multifunctional system to deliver anticancer drug doxorubicin (DOX), to enhance radiosensitization by ROS generation, and to provide magnetic resonance (MR) imaging contrast for biomedical applications.

Mn(II) complex impregnated porous silica nanoparticles as Zn(II)-responsive "Smart" MRI contrast agent for pancreas imaging.

Type-1 and type-2 diabetes mellitus are metabolic disorders governed by the functional efficiency of pancreatic ß-cells. The activities of the cells toward insulin production, storage, and secretion are accompanied by Zn(II) ions. Thus, for non-invasive pathology of the cell, developing Zn(II) ion-responsive MRI-contrast agents has earned considerable interest. In this report, we have synthesized a seven-coordinate, mono(aquated) Mn(II) complex (1), which is impregnated within a porous silica nanosphere of size 13.2 nm to engender the Mn(II)-based MRI contrast agent, complex 1@SiO2NP. The surface functionalization of the nanosphere by the Py2Pic organic moiety for the selective binding of Zn(II)-ions yields complex 1@SiO2-Py2PicNP, which exhibits r1 = 13.19 mM-1 s-1. The relaxivity value elevates to 20.38 mM-1 s-1 in the presence of 0.6 mM BSA protein at pH 7.4. Gratifyingly, r1 increases linearly with the increase of Zn(II) ion concentration and reaches 39.01 mM-1 s-1 in the presence of a 40 fold excess of the ions. Thus, Zn(II)-responsive contrast enhancement in vivo is envisaged by employing the nanoparticle. Indeed, a contrast enhancement in the pancreas is observed when complex 1@SiO2-Py2PicNP and a glucose stimulus are administered in fasted healthy C57BL/6 mice at 7 T.

Effect of rTMS at SMA on task-based connectivity in PD.

BACKGROUND: Transcranial magnetic stimulation (TMS) can aid in alleviating clinical symptoms in Parkinson's disease (PD). To better understand the neural mechanism of the intervention, neuroimaging modalities have been used to assess the effects of rTMS. OBJECTIVE: To study the changes in cortical connectivity and motor performance with rTMS at supplementary motor area (SMA) in PD using clinical assessment tools and task-based functional MRI. METHODOLOGY: 3000 pulses at 5 Hz TMS were delivered at the left SMA once a week for a total of 8 consecutive weeks in 4 sham sessions (week 1-4) and 4 real sessions (week 5 to week 8) in 16 subjects with PD. The outcomes were assessed with UPDRS, PDQ 39 and task-based fMRI at baseline, after sham sessions at week 4, and after real sessions at week 8. Visuo-spatial functional MRI task along with T1 weighted scans (at 3 Tesla) were used to evaluate the effects of rTMS intervention. Multivariate pattern analysis (MVPA) was used to analyse task-based fMRI using Conn toolbox. RESULTS: Improvements (p < 0.05) were observed in UPDRS II, III, Mobility and ADL of PDQ39 after real sessions of rTMS. MVPA of task-based connectivity revealed clusters of activation in right hemispheric precentral area, superior frontal gyrus, middle frontal gyrus, thalamus and cerebellum (cluster threshold pFDR=0.001). CONCLUSIONS: Weekly rTMS sessions at SMA incurred clinical motor benefits as revealed by an improvement in clinical scales and dexterity performance. These benefits could be attributed to changes in connectivity remote brain regions in the motor network.