Soumya Ghose

Dr. Soumya Ghose


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 May 2024 in Diagnostics
Verified
Journal Article
Open access
PDF file
JQJianwei Qiu
Jianwei Qiu
JMJhimli Mitra
Jhimli Mitra
SGSoumya Ghose
Soumya Ghose
CDCamille Dumas
Camille Dumas
JYJun Yang
Jun Yang
Marc JudsonMarc Judson
Marc Judson
Pulmonary sarcoidosis is a multisystem granulomatous interstitial lung disease (ILD) with a variable presentation and prognosis. The early accurate detection of pulmonary sarcoidosis may prevent progression to pulmonary fibrosis, a serious and potentially life-threatening form of the disease. However, the lack of a gold-standard diagnostic test and specific radiographic findings poses challenges in diagnosing pulmonary sarcoidosis. Chest computed tomography (CT) imaging is commonly used but requires expert, chest-trained radiologists to differentiate pulmonary sarcoidosis from lung malignancies, infections, and other ILDs. In this work, we develop a multichannel, CT and radiomics-guided ensemble network (RadCT-CNNViT) with visual explainability for pulmonary sarcoidosis vs. lung cancer (LCa) classification using chest CT images. We leverage CT and hand-crafted radiomics features as input channels, and a 3D convolutional neural network (CNN) and vision transformer (ViT) ensemble network for feature extraction and fusion before a classification head. The 3D CNN sub-network captures the localized spatial information of lesions, while the ViT sub-network captures long-range, global dependencies between features. Through multichannel input and feature fusion, our model achieves the highest performance with accuracy, sensitivity, specificity, precision, F1-score, and combined AUC of 0.93 ± 0.04, 0.94 ± 0.04, 0.93 ± 0.08, 0.95 ± 0.05, 0.94 ± 0.04, and 0.97, respectively, in a five-fold cross-validation study with pulmonary sarcoidosis (n = 126) and LCa (n = 93) cases. A detailed ablation study showing the impact of CNN + ViT compared to CNN or ViT alone, and CT + radiomics input, compared to CT or radiomics alone, is also presented in this work. Overall, the AI model developed in this work offers promising potential for triaging the pulmonary sarcoidosis patients for timely diagnosis and treatment from chest CT.

20 May 2022 in Frontiers in Oncology
Verified
Journal Article
Open access
RSRakesh Shiradkar
Rakesh Shiradkar
SGSoumya Ghose
Soumya Ghose
AMAmr Mahran
Amr Mahran
LLLin Li
Lin Li
IHIsaac Hubbard
Isaac Hubbard
Anant MadabhushiAnant Madabhushi
Anant Madabhushi
Objective: To derive and evaluate the association of prostate shape distension descriptors from T2-weighted MRI (T2WI) with prostate cancer (PCa) biochemical recurrence (BCR) post-radical prostatectomy (RP) independently and in conjunction with texture radiomics of PCa.Methods: This retrospective study comprised 133 PCa patients from two institutions who underwent 3T-MRI prior to RP and were followed up with PSA measurements for ≥3 years. A 3D shape atlas-based approach was adopted to derive prostate shape distension descriptors from T2WI, and these descriptors were used to train a random forest classifier (CS) to predict BCR. Texture radiomics was derived within PCa regions of interest from T2WI and ADC maps, and another machine learning classifier (CR) was trained for BCR. An integrated classifier CS+R was then trained using predictions from CS and CR. These models were trained on D1 (N = 71, 27 BCR+) and evaluated on independent hold-out set D2 (N = 62, 12 BCR+). CS+R was compared against pre-RP, post-RP clinical variables, and extant nomograms for BCR-free survival (bFS) at 3 years.Results: CS+R resulted in a higher AUC (0.75) compared to CR (0.70, p = 0.04) and CS (0.69, p = 0.01) on D2 in predicting BCR. On univariable analysis, CS+R achieved a higher hazard ratio (2.89, 95% CI 0.35–12.81, p < 0.01) compared to other pre-RP clinical variables for bFS. CS+R, pathologic Gleason grade, extraprostatic extension, and positive surgical margins were associated with bFS (p < 0.05). CS+R resulted in a higher C-index (0.76 ± 0.06) compared to CAPRA (0.69 ± 0.09, p < 0.01) and Decipher risk (0.59 ± 0.06, p < 0.01); however, it was comparable to post-RP CAPRA-S (0.75 ± 0.02, p = 0.07).Conclusions: Radiomic shape descriptors quantifying prostate surface distension complement texture radiomics of prostate cancer on MRI and result in an improved association with biochemical recurrence post-radical prostatectomy.

1 December 2010
Verified
Conference Paper
Closed access
SGSoumya Ghose
Soumya Ghose
AOArnau Oliver
Arnau Oliver
RMRobert Martí
Robert Martí
XLXavier Llado
Xavier Llado
JFJordi Freixenet
Jordi Freixenet
fabrice meriaudeaufabrice meriaudeau
fabrice meriaudeau
Prostate contour segmented from Trans Rectal Ultra Sound (TRUS) and Magnetic Resonance (MR) images could improve inter-modality registration accuracy and reduce computational complexity of the procedure. However, prostate segmentation in each of these modalities is a challenging task in presence of imaging artifacts, intensity heterogeneities, and large inter patient shape variabilities of the prostate. We propose to use Haar wavelet approximation coefficients to extract texture features of the prostate region in both modalities to guide a deformable parametric model to segment the prostate in a multi-resolution framework. Principal Component Analysis (PCA) of the shape and texture information of the prostate region obtained from the training data aids contour propagation of the deformable parametric model. Prior knowledge of the optimization space is utilized for optimal segmentation of the prostate. Our method achieves a mean Dice Similarity Coefficient (DSC) value of 0.95±0.01, with mean segmentation time of 0.72±0.05 seconds in a leave-one-out validation framework with 25 TRUS images grabbed from a video sequence. DSC value of 0.88±0.06 with a mean segmentation time of 0.81±0.02 seconds was recorded for MR images when validated with 15 central slice images of 15 datasets from the MICCAI prostate segmentation challenge 2009. Our proposed method performs computationally efficient accurate multi-modal prostate segmentation in presence of intensity heterogeneities and imaging artifacts.

18 August 2025 in Cancers
Verified
Journal Article
Open access
PDF file
JMJhimli Mitra
Jhimli Mitra
SGSoumya Ghose
Soumya Ghose
Rajat ThawaniRajat Thawani
Rajat Thawani
Background/Objectives: Immunotherapy is a viable therapeutic approach for non-small cell lung cancer (NSCLC). Despite the significant survival benefit of immune checkpoint inhibitors PD-1/PD-L1, on average; the objective response rate is around 20% as monotherapy and around 50% in combination with chemotherapy. While PD-L1 IHC is used as a predictive biomarker, its accuracy is subpar. Methods: In this work, we develop a machine learning (ML) method to predict response to immunotherapy in NSCLC from multimodal clinicopathological biomarkers, tumor and peritumoral radiomic biomarkers from CT images. We further learn a graph structure to understand the associations between biomarkers and treatment response. The graph is then used to create sentences with clinical hypotheses that are finally used in a Large Language Model (LLM) that explains the treatment response predicated on the biomarkers that are comprehensible to clinicians. From a retrospective study, a training dataset of NSCLC with n = 248 tumors from 140 subjects was used for feature selection, ML model training, learning the graph structure, and fine-tuning LLM. Results: An AUC = 0.83 was achieved for prediction of treatment response on a separate test dataset of n = 84 tumors from 47 subjects. Conclusions: Our study therefore not only improves the prediction of immunotherapy response in patients with NSCLC from multimodal data but also assists the clinicians in making clinically interpretable predictions by providing language-based explanations.

23 February 2012
Verified
Conference Paper
Open access
PDF file
SGSoumya Ghose
Soumya Ghose
AOArnau Oliver
Arnau Oliver
RMRobert Martí
Robert Martí
XLXavier Llado
Xavier Llado
JFJordi Freixenet
Jordi Freixenet
FMFabrice Meriaudeau
Fabrice Meriaudeau
Real-time fusion of Magnetic Resonance (MR) and Trans Rectal Ultra Sound (TRUS) images aid in the localization of malignant tissues in TRUS guided prostate biopsy. Registration performed on segmented contours of the prostate reduces computational complexity and improves the multimodal registration accuracy. However, accurate and computationally efficient 3D segmentation of the prostate in MR images could be a challenging task due to inter-patient shape and intensity variability of the prostate gland. In this work, we propose to use multiple statistical shape and appearance models to segment the prostate in 2D and a global registration framework to impose shape restriction in 3D. Multiple mean parametric models of the shape and appearance corresponding to the apex, central and base regions of the prostate gland are derived from principal component analysis (PCA) of prior shape and intensity information of the prostate from the training data. The estimated parameters are then modified with the prior knowledge of the optimization space to achieve segmentation in 2D. The 2D segmented slices are then rigidly registered with the average 3D model produced by affine registration of the ground truth of the training datasets to minimize pose variations and impose 3D shape restriction. The proposed method achieves a mean Dice similarity coefficient (DSC) value of 0.88±0.11, and mean Hausdorff distance (HD) of 3.38±2.81 mm when validated with 15 prostate volumes of a public dataset in leave-one-out validation framework. The results achieved are better compared to some of the works in the literature.

1 September 2012
Verified
Conference Paper
Closed access
JMJ. Mitra
J. Mitra
SGSoumya Ghose
Soumya Ghose
DSDESIRE SIDIBE
DESIRE SIDIBE
AOArnau Oliver
Arnau Oliver
RMRobert Martí
Robert Martí
fabrice meriaudeaufabrice meriaudeau
fabrice meriaudeau
This paper presents a novel method to identify the 2D axial Magnetic Resonance (MR) slice from a pre-acquired MR prostate volume that closely corresponds to the 2D axial Transrectal Ultrasound (TRUS) slice obtained during prostate biopsy. The shape-context representations of the segmented prostate contours in both the imaging modalities are used to establish point correspondences using Bhattacharyya distance. Thereafter, Chi-square distance is used to find the prostate shape similarities between the MR slices and the TRUS slice. Normalized mutual information and correlation coefficient between the TRUS and MR slices are computed to find the information theoretic similarities between the TRUS-MR slices. The maximum of the weighted likelihood function of the afore-mentioned statistical similarity measures finally yields the MR slice that closely resembles the TRUS slice acquired during the biopsy procedure. The method is evaluated for 20 patient datasets and close matches with the ground truth are obtained for 16 cases.