Gehad A. Saleh

Mansoura University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

An Ensemble Neural Architecture for Lung Diseases Prediction Using Chest X-rays

International Journal of Computing and Digital Systems (2024)

Abeer Abdelhamid Oluwatunmise Akinniyi Gehad A. Saleh Wael Deabes Fahmi Khalifa

Accurate diagnostic tools for disease control and treatment options is of immense importance, specially during pandemics, Coronavirus (or COVID) that drew global attention in late 2019.Early detection and seclusion are the cornerstone effective ways to prevent virus spread.Artificial intelligence (AI)-based diagnostic tools for COVID detection have surged dramatically using various diagnostic imaging techniques, among which Chest X-ray (CXR) have been extensively investigated due to its fast acquisition coupled with its superior results.We propose a hybrid, automated, and efficient approach to detect COVID-19 at an early stage using CXRs.One of the main advantages of the proposed analysis is the development of a learnable input scaling module, which accommodates various CXR with different sizes with the ability to keep prominent CXRs features while filtering out noise.Additionally, the suggested method ensembles several learning modules to extract more discriminative representation of texture and appearance cues of CXRs, thereby facilitating more accurate classification.Particularly, we integrated two sets of features (texture descriptors and deeper features) representing a rich accumulation of both local and global characteristics.In addition to learnable scaling and information-rich features, an ensemble classifier using various machine learning models is used for classification.Our classification module included support vector machine, XGBoost and extra trees modules.Extensive evaluation, supported by ablation and comparison studies, is conducted utilizing two benchmark datasets to assess the model's performance via a cross-validation strategy.Using various metrics, the results document the robustness of our ensemble classification system with higher accuracy of 98.20% and 97.85% for the two data sets, respectively.

Ensemble Learning

10.12785/ijcds/160174

Cite

Citations (0)

Diagnostic reliability of chest CT qualitative and quantitative assessment to predict survival and morbidity in oncology patients with COVID-19 infection

The Egyptian Journal of Radiology and Nuclear Medicine (2024)

Gehad A. Saleh Ahmad M. Mounir Mohammed A. Elhawary Marwa Saleh Manar Hamed

Abstract Background To estimate the diagnostic utility of chest CT qualitative assessment and chest CT total severity score (TSS) to predict mortality in oncology patients with COVID-19 infection. Methods This retrospective study included 151 oncology patients with COVID-19 infection. 67, 84 were male and female, respectively. Their mean age (years) ± SD was 49.7 ± 14.9. Two radiologists individually reviewed the chest CT and scored the pulmonary abnormalities using TSS. Inter-observer agreement was determined using the Bland–Altman plot. Correlation between TSS and COVID-19 severity, complication, mortality, cancer status and effect in anticancer therapy plan was done. Results There was a statistically significant excellent agreement between the independent observers in quantitative pulmonary assessment using TSS with interclass correlation (ICC) > 0.9 ( P < 0.001). ROC curve analysis revealed that TSS was statistically significantly higher in non-survivors using an optimum cut-off value of 5 to predict in-hospital mortality. Univariate analysis showed that age, pulmonary predominant pattern, pleural effusion, tree-in-bud, ECOG PS, tumour stage 4 and post-COVID cancer status were a statistically significant predictor of mortality. Multivariate analysis reported that consolidation versus ground-glass opacity (GGO), crazy paving pattern versus GGO and progressive versus remittent cancer diseases were statistically significant independent predictors of mortality among those patients. Conclusions TSS demonstrated excellent inter-observer agreement to assess COVID-19 in oncology patients with low cut-off value to predict in-hospital mortality, thus raising the attention to rapid proper care in this setting. There was a statistically significant positive correlation between TSS and delayed chemotherapeutic schedule.

2019-20 coronavirus outbreak

10.1186/s43055-024-01259-2

Cite

Citations (0)

Review of: "Comparing Visual and Software-Based Quantitative Assessment Scores of Lung Parenchymal Involvement Quantification in COVID-19 Patients"

Gehad A. Saleh

Potential competing interests: No potential competing interests to declare.The article is well-written, but the rapid diagnosis of COVID-19 is not a need nowadays; the gap is more about the longterm effects of post-infection fibrosis.The strength of this article is the comparison between visual and software-based assessment.Please add more demonstrative images of the visual affection and percentages given by radiologists using the total severity score.

Parenchyma

2019-20 coronavirus outbreak

10.32388/rj3h26

Cite

Citations (0)

A novel computer-aided diagnostic system for accurate detection and grading of liver tumors

Scientific Reports (2021)

Ahmed Alksas Mohamed Shehata Gehad A. Saleh Ahmed Shaffie Ahmed Soliman

Liver cancer is a major cause of morbidity and mortality in the world. The primary goals of this manuscript are the identification of novel imaging markers (morphological, functional, and anatomical/textural), and development of a computer-aided diagnostic (CAD) system to accurately detect and grade liver tumors non-invasively. A total of 95 patients with liver tumors (M = 65, F = 30, age range = 34-82 years) were enrolled in the study after consents were obtained. 38 patients had benign tumors (LR1 = 19 and LR2 = 19), 19 patients had intermediate tumors (LR3), and 38 patients had hepatocellular carcinoma (HCC) malignant tumors (LR4 = 19 and LR5 = 19). A multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) was collected to extract the imaging markers. A comprehensive CAD system was developed, which includes the following main steps: i) estimation of morphological markers using a new parametric spherical harmonic model, ii) estimation of textural markers using a novel rotation invariant gray-level co-occurrence matrix (GLCM) and gray-level run-length matrix (GLRLM) models, and iii) calculation of the functional markers by estimating the wash-in/wash-out slopes, which enable quantification of the enhancement characteristics across different CE-MR phases. These markers were subsequently processed using a two-stages random forest-based classifier to classify the liver tumor as benign, intermediate, or malignant and determine the corresponding grade (LR1, LR2, LR3, LR4, or LR5). The overall CAD system using all the identified imaging markers achieved a sensitivity of 91.8%±0.9%, specificity of 91.2%±1.9%, and F[Formula: see text] score of 0.91±0.01, using the leave-one-subject-out (LOSO) cross-validation approach. Importantly, the CAD system achieved overall accuracies of [Formula: see text], 85%±2%, 78%±3%, 83%±4%, and 79%±3% in grading liver tumors into LR1, LR2, LR3, LR4, and LR5, respectively. In addition to LOSO, the developed CAD system was tested using randomly stratified 10-fold and 5-fold cross-validation approaches. Alternative classification algorithms, including support vector machine, naive Bayes classifier, k-nearest neighbors, and linear discriminant analysis all produced inferior results compared to the proposed two stage random forest classification model. These experiments demonstrate the feasibility of the proposed CAD system as a novel tool to objectively assess liver tumors based on the new comprehensive imaging markers. The identified imaging markers and CAD system can be used as a non-invasive diagnostic tool for early and accurate detection and grading of liver cancer.

10.1038/s41598-021-91634-0

Cite

Citations (41)

Small breast Schwannoma in an old female; a case report

Breast Disease (2019)

Omar Hamdy Sara Raafat Gehad A. Saleh Mohammad Hamdy

Schwannoma is a usually benign peripheral nerve sheath tumor with rare breast incidence and few reported cases. We report a case which was presented to and managed in the Oncology center, Mansoura University in November 2017.

Breast tumor

Right breast

10.3233/bd-180329

Cite

Citations (3)

Utility of diffusion tensor imaging in differentiating benign from malignant hepatic focal lesions

European Radiology (2022)

Gehad A. Saleh Ali H. Elmokadem Ahmed Abdel Khalek Abdel Razek Ahmed Elmorsy Omar Hamdy

Neuroradiology

Interventional radiology

Cut-off

10.1007/s00330-022-09091-w

Cite

Citations (9)

The value of the apparent diffusion coefficient value in the Liver Imaging Reporting and Data System version 2018

Polish Journal of Radiology (2022)

Gehad A. Saleh Ahmed Abdel Khalek Abdel Razek Lamiaa Galal El-Serougy Walaa Shabana Rihame Abd el-wahab

To assess role of the apparent diffusion coefficient (ADC) in the Liver Imaging Reporting and Data System (LI-RADS) version 2018 for the prediction of hepatocellular carcinoma (HCC).Retrospective analysis of 137 hepatic focal lesions in 108 patients at risk of HCC, who underwent magnetic resonance imaging of the liver. Hepatic focal lesions were classified according to LI-RADS-v2018, and ADC of hepatic lesions was calculated by 2 independent blinded reviewers.The mean ADC of LR-1 and LR-2 were 2.11 ± 0.47 and 2.08 ± 0.47 × 10-3 mm2/s, LR-3 were 1.28 ± 0.12 and 1.36 ± 0.16 × 10-3 mm2/s, LR-4, LR-5 and LR-TIV were 1.07 ± 0.08 and 1.08 ± 0.12 × 10-3 mm2/s and LR-M were 1.02 ± 0.09 and 1.00 ± 0.09 × 10-3 mm2/s by both observers, respectively. There was excellent agreement of both readings for LR-1 and LR-2 (r = 0.988), LR-3 (r = 0.965), LR-4, LR-5 and LR-TIV (r = 0.889) and LR-M (r = 0.883). There was excellent correlation between ADC and LI-RADS-v2018 (r = -0.849 and -0.846). The cut-off ADC used to differentiate LR-3 from LR-4, LR-5, and LR-TIV were ≤ 1.21 and ≤ 1.23 × 10-3 mm2/s with AUC of 0.948 and 0.926.Inclusion of ADC to LI-RADS-v2018 improves differentiation variable LI-RADS categories and can helps in the prediction of HCC.

10.5114/pjr.2022.113193

Cite

Citations (4)

Extended abdominopelvic MRI versus CT at the time of adnexal mass characterization for assessing radiologic peritoneal cancer index (PCI) prior to cytoreductive surgery

Abdominal Radiology (2019)

Basma Gadelhak Ahmed M. Tawfik Gehad A. Saleh Nihal M. Batouty Donia M. Sobh

Institutional review board

Adnexal Diseases

10.1007/s00261-019-01939-y

Cite

Citations (22)

Recurrent mandibular ameloblastoma in soft tissue and rib graft 17 years after initial presentation

Journal of the Egyptian National Cancer Institute (2020)

Omar Hamdy Sara Raafat Gehad A. Saleh Shadi Awny Abdelhadi M. Shebl

Ameloblastoma is the commonest odontogenic tumour of epithelial origin with a high incidence for developing local recurrence. We present a patient who developed local recurrence in both soft tissue and bone graft 17 years after the initial presentation.A 75-year-old female with a previous history of right hemimandibulectomy and rib reconstruction for ameloblastoma in 1999 presented to our centre with a large cystic mouth floor swelling, biopsy from which revealed recurrent ameloblastoma. The patient underwent excision of the recurrent mass en bloc with the cystic swelling through oral and cervical approaches. The patient was discharged after 5 days with an uneventful postoperative course and with a free 2-year follow-up from further recurrence.Ameloblastoma is a locally aggressive tumour for which wide local excision with adequate margins is the best management approach. Recurrence of ameloblastoma even after adequate resection is not uncommon, and its management is considered a surgical challenge. A very long time may pass between the initial presentation and the development of recurrence.

Presentation (obstetrics)

Case presentation

Adamantinoma

10.1186/s43046-019-0012-1

Cite

Citations (16)

EP846 Parenchymal splenic metastasis from ovarian cancer; a report of two cases and literature review

Mohammad Zuhdy Khaled Gaballa Omar Hamdy Reham Alghandour MG Elmadawy

Introduction/Background

Worldwide, ovarian cancer accounts for 3.4% of newly diagnosed cancer cases and 4.4% of cancer related mortality among females.It spreads mainly through peritoneal dissemination, hematogenous or lymphatic routes, and is optimally managed by cytoreductive surgery.Splenic metastasis from malignant tumors are extremely rare ranging from 2.3 to 7.1% in autopsy studies, and a reported incidence of 1.3% in splenectomy studies. To the best of our knowledge, approximately 24 cases of isolated parenchymal splenic metastasis from ovarian cancer were reported in English based literature.

Methodology

We here report 2 cases with parenchymal splenic metastasis from ovarian cancer one case was operated in October 2017 and the other was operated October 2018.

Results

The 2 cases were managed by doing splenectomy followed by adjuvant chemotherapy and both now are on follow up with no evidence of recurrence or further metastasis.

Conclusion

Splenic metastasis from ovarian cancer is relatively rare. Thorough follow up of ovarian cancer cases including careful clinical examination, Computed tomography and tumor markers assessment when clinically indicated can early detect any recurrence events even isolated splenic recurrence. Splenectomy as a secondary cytoreductive surgery is a safe procedure that leads to achieving improved both survival and quality of life.

Disclosure

Nothing to disclose.

10.1136/ijgc-2019-esgo.895

Cite

Citations (0)