Haitham Kussaibi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Haitham Kussaibi has a total of 92 co-authors. Here are the top co-authors by number of shared publications:
Ayesha Ahmed
Imam Abdulrahman Bin Faisal Univ, Pathol Dept, Dammam, Saudi Arabia
3 shared publications- Khaled R. Alkharsah
Department of Microbiology, College of Medicine, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia
3 shared publications Philippe Bertheau
3 shared publicationsAnne Janin
2 shared publications- David Ameisen
Imginit SAS, 152 Boulevard du Montparnasse Paris France
2 shared publications Noor Alsafwani
Department of Pathology, College of Medicine, Imam Abdulrahman Bin Faisal University
2 shared publications
Latest Publications
- 1 January 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (01) , 1-14
LiteMIL: a computationally efficient cross-attention multiple instance learning for cancer subtyping on whole-slide images
PurposeAccurate cancer subtyping is essential for precision medicine but challenged by the computational demands of gigapixel whole-slide images (WSIs). Although transformer-based multiple instance learning (MIL) methods achieve strong performance, their quadratic complexity limits clinical deployment. We introduce LiteMIL, a computationally efficient cross-attention MIL, optimized for WSIs classification.ApproachLiteMIL employs a single learnable query with multi-head cross-attention for bag-level aggregation from extracted features. We evaluated LiteMIL against five baselines (mean/max pooling, ABMIL, MAD-MIL, and TransMIL) on four TCGA datasets (breast: n=875, kidney: n=906, lung: n=958, and TUPAC16: n=821) using nested cross-validation with patient-level splitting. Systematic ablation studies evaluated multi-query variants, attention heads, dropout rates, and architectural components.ResultsLiteMIL achieved competitive accuracy (average 83.5%), matching TransMIL, while offering substantial efficiency gains: 4.8× fewer parameters (560K versus 2.67M), 2.9× faster inference (1.6s versus 4.6s per fold), and 6.7× lower Graphics Processing Unit (GPU) memory usage (1.15 GB versus 7.77 GB). LiteMIL excelled on lung (86.3% versus 85.0%), TUPAC16 (72% versus 71.4%), and matched kidney performance (89.9% versus 89.7%). Ablation studies revealed task-dependent multi-query performance benefits: Q=4 versus Q=1 improved morphologically heterogeneous tasks (breast/lung +1.3% each, p<0.05) but degraded on grading tasks (TUPAC16: −1.6%), validating single-query optimality for focused attention scenarios.ConclusionsLiteMIL provides a resource-efficient solution for WSI classification. The cross-attention architecture matches complex transformer performance while enabling deployment on consumer GPUs. Task-dependent design insights, single query for sparse discriminating features, multi-query for heterogeneous patterns, guide practical implementation. The architecture’s efficiency, combined with compact features, makes LiteMIL suitable for clinical integration in settings with limited computational infrastructure.
- 1 January 2026
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 13 (01) , 1-14
LiteMIL: a computationally efficient cross-attention multiple instance learning for cancer subtyping on whole-slide images
PurposeAccurate cancer subtyping is essential for precision medicine but challenged by the computational demands of gigapixel whole-slide images (WSIs). Although transformer-based multiple instance learning (MIL) methods achieve strong performance, their quadratic complexity limits clinical deployment. We introduce LiteMIL, a computationally efficient cross-attention MIL, optimized for WSIs classification.ApproachLiteMIL employs a single learnable query with multi-head cross-attention for bag-level aggregation from extracted features. We evaluated LiteMIL against five baselines (mean/max pooling, ABMIL, MAD-MIL, and TransMIL) on four TCGA datasets (breast: n=875, kidney: n=906, lung: n=958, and TUPAC16: n=821) using nested cross-validation with patient-level splitting. Systematic ablation studies evaluated multi-query variants, attention heads, dropout rates, and architectural components.ResultsLiteMIL achieved competitive accuracy (average 83.5%), matching TransMIL, while offering substantial efficiency gains: 4.8× fewer parameters (560K versus 2.67M), 2.9× faster inference (1.6s versus 4.6s per fold), and 6.7× lower Graphics Processing Unit (GPU) memory usage (1.15 GB versus 7.77 GB). LiteMIL excelled on lung (86.3% versus 85.0%), TUPAC16 (72% versus 71.4%), and matched kidney performance (89.9% versus 89.7%). Ablation studies revealed task-dependent multi-query performance benefits: Q=4 versus Q=1 improved morphologically heterogeneous tasks (breast/lung +1.3% each, p<0.05) but degraded on grading tasks (TUPAC16: −1.6%), validating single-query optimality for focused attention scenarios.ConclusionsLiteMIL provides a resource-efficient solution for WSI classification. The cross-attention architecture matches complex transformer performance while enabling deployment on consumer GPUs. Task-dependent design insights, single query for sparse discriminating features, multi-query for heterogeneous patterns, guide practical implementation. The architecture’s efficiency, combined with compact features, makes LiteMIL suitable for clinical integration in settings with limited computational infrastructure.
- Open Access
LiteMIL: A Computationally Efficient Transformer-Based MIL for Cancer Subtyping on Whole Slide Images
Purpose: Accurate cancer subtyping is crucial for effective treatment; however, it presents challenges due to overlapping morphology and variability among pathologists. Although deep learning (DL) methods have shown potential, their application to gigapixel whole slide images (WSIs) is often hindered by high computational demands and the need for efficient, context-aware feature aggregation. This study introduces LiteMIL, a computationally efficient transformer-based multiple instance learning (MIL) network combined with Phikon, a pathology-tuned self-supervised feature extractor, for robust and scalable cancer subtyping on WSIs. Methods: Initially, patches were extracted from TCGA-THYM dataset (242 WSIs, six subtypes) and subsequently fed in real-time to Phikon for feature extraction. To train MILs, features were arranged into uniform bags using a chunking strategy that maintains tissue context while increasing training data. LiteMIL utilizes a learnable query vector within an optimized multi-head attention module for effective feature aggregation. The model’s performance was evaluated against established MIL methods on the Thymic Dataset and three additional TCGA datasets (breast, lung, and kidney cancer). Results: LiteMIL achieved 0.89 ± 0.01 F1 score and 0.99 AUC on Thymic dataset, outperforming other MILs. LiteMIL demonstrated strong generalizability across the external datasets, scoring the best on breast and kidney cancer datasets. Compared to TransMIL, LiteMIL significantly reduces training time and GPU memory usage. Ablation studies confirmed the critical role of the learnable query and layer normalization in enhancing performance and stability. Conclusion: LiteMIL offers a resource-efficient, robust solution. Its streamlined architecture, combined with the compact Phikon features, makes it suitable for integrating into routine histopathological workflows, particularly in resource-limited settings.
Open AccessLiteMIL: A Computationally Efficient Transformer-Based MIL for Cancer Subtyping on Whole Slide Images
Purpose: Accurate cancer subtyping is crucial for effective treatment; however, it presents challenges due to overlapping morphology and variability among pathologists. Although deep learning (DL) methods have shown potential, their application to gigapixel whole slide images (WSIs) is often hindered by high computational demands and the need for efficient, context-aware feature aggregation. This study introduces LiteMIL, a computationally efficient transformer-based multiple instance learning (MIL) network combined with Phikon, a pathology-tuned self-supervised feature extractor, for robust and scalable cancer subtyping on WSIs. Methods: Initially, patches were extracted from TCGA-THYM dataset (242 WSIs, six subtypes) and subsequently fed in real-time to Phikon for feature extraction. To train MILs, features were arranged into uniform bags using a chunking strategy that maintains tissue context while increasing training data. LiteMIL utilizes a learnable query vector within an optimized multi-head attention module for effective feature aggregation. The model’s performance was evaluated against established MIL methods on the Thymic Dataset and three additional TCGA datasets (breast, lung, and kidney cancer). Results: LiteMIL achieved 0.89 ± 0.01 F1 score and 0.99 AUC on Thymic dataset, outperforming other MILs. LiteMIL demonstrated strong generalizability across the external datasets, scoring the best on breast and kidney cancer datasets. Compared to TransMIL, LiteMIL significantly reduces training time and GPU memory usage. Ablation studies confirmed the critical role of the learnable query and layer normalization in enhancing performance and stability. Conclusion: LiteMIL offers a resource-efficient, robust solution. Its streamlined architecture, combined with the compact Phikon features, makes it suitable for integrating into routine histopathological workflows, particularly in resource-limited settings.
- Open Access
AI-Enhanced Subtyping of Thymic Tumors: Attention-based MIL with Pathology-Specific Feature Extraction
Purpose: The precise classification of thymic tumors using whole slide images (WSIs) is essential for accurate diagnosis and treatment. While traditional Convolutional Neural Networks (CNNs) are commonly used for this purpose, emerging models tailored to pathology, such as Phikon and HistoEncoder, present promising alternatives as feature extractors. Additionally, the limited availability of annotated WSIs has driven the development of weakly-supervised classifiers like multiple-instance learning (MIL) models. In this study, we evaluate nine different combinations of extractor-classifier pairs for thymic tumor subtyping, including a novel, self-developed attention-based MIL classifier, AttenMIL. Methods: The process began with curating a dataset of thymic tumor Whole Slide Images (WSIs) from the TCGA platform. Using the Yottixel method, patches were derived from these WSIs, and features were extracted from the patches using three different pathology-specific models: Phikon, HistoEncoder, and a pathology-fine-tuned ResNet50. The extracted features were then organized into small bags of instances through a chunking technique. Subsequently, three MIL classifiers AttenMIL, TransMIL, and Chowder were trained. Finally, the efficacy and generalizability of nine different combinations of extractor-classifier pairs were evaluated on unseen test images. Confusion matrices for each pair were utilized to provide insights into misclassification patterns and potential error sources. Results: The Phikon feature extractor consistently delivered the highest classification accuracies, particularly when paired with the AttenMIL and Chowder classifiers, achieving up to 99% accuracy. This combination significantly outperformed other feature extractor-classifier pairs. Confusion matrices revealed that the AB and B3 subtypes were the most commonly confused classes across the different models. Conclusions: The study demonstrates the potential of domain-specific feature extractors like Phikon, when coupled with robust MIL classifiers such as the novel AttenMIL and Chowder, in enhancing the accuracy and reliability of thymic tumor classification. The chunking-based augmentation method proved effective for thymic tumors, which are relatively homogeneous, but its applicability to heterogeneous tumors remains to be explored. Future research should address class imbalances and improve generalizability to different datasets. Statements and Declarations: Competing Interests: The author has declared no competing interest. No funding was received for conducting this study. Declaration of generative AI and AI-assisted technologies in the writing process: While preparing this work, the author used ChatGPT to improve language and readability. After using this tool/service, the author reviewed and edited the content as needed and took full responsibility for the publication’s content.
Open AccessAI-Enhanced Subtyping of Thymic Tumors: Attention-based MIL with Pathology-Specific Feature Extraction
Purpose: The precise classification of thymic tumors using whole slide images (WSIs) is essential for accurate diagnosis and treatment. While traditional Convolutional Neural Networks (CNNs) are commonly used for this purpose, emerging models tailored to pathology, such as Phikon and HistoEncoder, present promising alternatives as feature extractors. Additionally, the limited availability of annotated WSIs has driven the development of weakly-supervised classifiers like multiple-instance learning (MIL) models. In this study, we evaluate nine different combinations of extractor-classifier pairs for thymic tumor subtyping, including a novel, self-developed attention-based MIL classifier, AttenMIL. Methods: The process began with curating a dataset of thymic tumor Whole Slide Images (WSIs) from the TCGA platform. Using the Yottixel method, patches were derived from these WSIs, and features were extracted from the patches using three different pathology-specific models: Phikon, HistoEncoder, and a pathology-fine-tuned ResNet50. The extracted features were then organized into small bags of instances through a chunking technique. Subsequently, three MIL classifiers AttenMIL, TransMIL, and Chowder were trained. Finally, the efficacy and generalizability of nine different combinations of extractor-classifier pairs were evaluated on unseen test images. Confusion matrices for each pair were utilized to provide insights into misclassification patterns and potential error sources. Results: The Phikon feature extractor consistently delivered the highest classification accuracies, particularly when paired with the AttenMIL and Chowder classifiers, achieving up to 99% accuracy. This combination significantly outperformed other feature extractor-classifier pairs. Confusion matrices revealed that the AB and B3 subtypes were the most commonly confused classes across the different models. Conclusions: The study demonstrates the potential of domain-specific feature extractors like Phikon, when coupled with robust MIL classifiers such as the novel AttenMIL and Chowder, in enhancing the accuracy and reliability of thymic tumor classification. The chunking-based augmentation method proved effective for thymic tumors, which are relatively homogeneous, but its applicability to heterogeneous tumors remains to be explored. Future research should address class imbalances and improve generalizability to different datasets. Statements and Declarations: Competing Interests: The author has declared no competing interest. No funding was received for conducting this study. Declaration of generative AI and AI-assisted technologies in the writing process: While preparing this work, the author used ChatGPT to improve language and readability. After using this tool/service, the author reviewed and edited the content as needed and took full responsibility for the publication’s content.
- Open Access
Al-Powered classification of Ovarian cancers Based on Histopathological lmages
Background Ovarian cancer is the leading cause of gynecological cancer deaths due to late diagnosis and high recurrence rates. While histopathological analysis is the gold standard for diagnosis, artificial intelligence (AI) models have shown promise in accurately classifying ovarian cancer subtypes from his-topathology images. Herein, we developed an AI pipeline for automated identification of epithelial ovar-ian cancer (EOC) subtypes based on histopathology images and evaluated its performance compared to the pathologists’ diagnosis. Methods A dataset of over 2 million image tiles from 82 whole slide images (WSIs) of the major EOC subtypes (clear cell, endometrioid, mucinous, serous) was curated from public and institutional sources. A convolutional neural network (ResNet50) was used to extract features which were then input to 2 classifiers (CNN, and LightGBM) to predict the cancer subtype. Results Both AI classifiers achieved patch-level accuracy (97-98%) on the test set. Furthermore, adding a class-weighted cross-entropy loss function to the pipeline showed better discriminative performance between the subtypes. Conclusion AI models trained on histopathology image data can accurately classify EOC subtypes, potentially assisting pathologists and reducing subjectivity in ovarian cancer diagnosis.
Open AccessAl-Powered classification of Ovarian cancers Based on Histopathological lmages
Background Ovarian cancer is the leading cause of gynecological cancer deaths due to late diagnosis and high recurrence rates. While histopathological analysis is the gold standard for diagnosis, artificial intelligence (AI) models have shown promise in accurately classifying ovarian cancer subtypes from his-topathology images. Herein, we developed an AI pipeline for automated identification of epithelial ovar-ian cancer (EOC) subtypes based on histopathology images and evaluated its performance compared to the pathologists’ diagnosis. Methods A dataset of over 2 million image tiles from 82 whole slide images (WSIs) of the major EOC subtypes (clear cell, endometrioid, mucinous, serous) was curated from public and institutional sources. A convolutional neural network (ResNet50) was used to extract features which were then input to 2 classifiers (CNN, and LightGBM) to predict the cancer subtype. Results Both AI classifiers achieved patch-level accuracy (97-98%) on the test set. Furthermore, adding a class-weighted cross-entropy loss function to the pipeline showed better discriminative performance between the subtypes. Conclusion AI models trained on histopathology image data can accurately classify EOC subtypes, potentially assisting pathologists and reducing subjectivity in ovarian cancer diagnosis.
- Open Access
Trends in AI-powered classification of thyroid neoplasms based on histopathology images, a systematic review
Background: Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations. Methods: Eligibility criteria focused on peer-reviewed English papers published in the last five years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations. Results: Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed at basic tumor subtyping; however, three studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%. Discussion: The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice. Other: Funding: This study did not receive any funding. Registration: The procedural instructions for this systematic review were officially recorded within the PROSPERO database under registration number RD42023457854 https://www.crd.york.ac.uk/Prospero/
Open AccessTrends in AI-powered classification of thyroid neoplasms based on histopathology images, a systematic review
Background: Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations. Methods: Eligibility criteria focused on peer-reviewed English papers published in the last five years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations. Results: Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed at basic tumor subtyping; however, three studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%. Discussion: The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice. Other: Funding: This study did not receive any funding. Registration: The procedural instructions for this systematic review were officially recorded within the PROSPERO database under registration number RD42023457854 https://www.crd.york.ac.uk/Prospero/
- Open Access
- 1 January 2023
- Published by ScopeMed in Acta Informatica Medica
- Vol. 31 (4) , 280-286
Trends in AI-powered Classification of Thyroid Neoplasms Based on Histopathology Images - a Systematic Review
Background: Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations. Methods: Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations. Results: Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed for basic tumor subtyping; however, 3 studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%. Discussion: The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.
- 1 January 2023
- Published by ScopeMed in Acta Informatica Medica
- Vol. 31 (4) , 280-286
Open AccessTrends in AI-powered Classification of Thyroid Neoplasms Based on Histopathology Images - a Systematic Review
Background: Assessment of thyroid nodules histopathology using AI is crucial for an accurate diagnosis. This systematic review analyzes recent works employing deep learning approaches for classifying thyroid nodules based on histopathology images, evaluating their performance, and identifying limitations. Methods: Eligibility criteria focused on peer-reviewed English papers published in the last 5 years, applying deep learning to categorize thyroid histopathology images. The PubMed database was searched using relevant keyword combinations. Results: Out of 103 articles, 11 studies met inclusion criteria. They used convolutional neural networks to classify thyroid neoplasm. Most studies aimed for basic tumor subtyping; however, 3 studies targeted the prediction of tumor-associated mutation. Accuracy ranged from 77% to 100%, with most over 90%. Discussion: The findings from our analysis reveal the effectiveness of deep learning in identifying discriminative morphological patterns from histopathology images, thus enhancing the accuracy of thyroid nodule histopathological classification. Key limitations were small sample sizes, subjective annotation, and limited dataset diversity. Further research with larger diverse datasets, model optimization, and real-world validation is essential to translate these tools into clinical practice.
- Open Access
- 31 March 2021
- Published by Knowledge E DMCC in Dubai Medical Journal
- Vol. 4 (1) , 68-73
Neuroendocrine Breast Carcinoma: Case Report and Review of the Literature
Primary breast carcinoma with neuroendocrine features is an uncommon presentation of mammary cancers. The authors present a case of a rapidly growing breast mass that raised many differential diagnoses. The diagnosis in this case was challenging. Extensive clinical assessment, radiological imaging, nuclear scans, pathological evaluations, and series of multidisciplinary meetings were utilized to reach the diagnosis of neuroendocrine breast carcinoma.
- 31 March 2021
- Published by Knowledge E DMCC in Dubai Medical Journal
- Vol. 4 (1) , 68-73
Open AccessNeuroendocrine Breast Carcinoma: Case Report and Review of the Literature
Primary breast carcinoma with neuroendocrine features is an uncommon presentation of mammary cancers. The authors present a case of a rapidly growing breast mass that raised many differential diagnoses. The diagnosis in this case was challenging. Extensive clinical assessment, radiological imaging, nuclear scans, pathological evaluations, and series of multidisciplinary meetings were utilized to reach the diagnosis of neuroendocrine breast carcinoma.
- Open Access
- 24 February 2021
- Published by Armed Forces Medical Services in Saudi Medical Journal
- Vol. 42 (3) , 293-298
Correlation of prognostic and predictive indicators in breast cancer patients from the eastern province of Saudi Arabia
Objectives: To highlight and correlate demographic and histopathological features of breast cancer along with prognostic and predictive biomarkers, in Saudi patients from the Eastern Province and compare it to a cohort of non-Saudi patients. Methods: In a retrospective study between January 1998 and December 2017, data were collected from the medical records of breast cancer patients who were admitted at King Fahd University Hospital (KFHU), Dammam, Saudi Arabia. The information included demographic, histopathological, and immunohistochemical findings. Results: Out of 482 breast cancer patients, 60% (n=286) were Saudis, and 40% (n=196) were non-Saudis. Data showed a wide age distribution; however, most cases (80%) were seen in the third through fifth decades, with a median age at diagnosis of 51 ±12 years. Over years, breast cancer in Saudi patients was increasingly seen at a younger age (p=0.003). While tumors were increasingly detected at earlier stages (p=0.003); however, stage III & IV tumors (p=0.033) and human epidermal growth factor receptor-2 overexpressed tumors (p=0.035) were more frequently seen at a younger age. Interestingly, these associations were not significant in non-Saudi patients. Conclusion: Although, the current findings might help future studies to identify variables that could lead to better management of breast cancer in this region; however, a wider investigation including other centers in the eastern province is needed.
- 24 February 2021
- Published by Armed Forces Medical Services in Saudi Medical Journal
- Vol. 42 (3) , 293-298
Open AccessCorrelation of prognostic and predictive indicators in breast cancer patients from the eastern province of Saudi Arabia
Objectives: To highlight and correlate demographic and histopathological features of breast cancer along with prognostic and predictive biomarkers, in Saudi patients from the Eastern Province and compare it to a cohort of non-Saudi patients. Methods: In a retrospective study between January 1998 and December 2017, data were collected from the medical records of breast cancer patients who were admitted at King Fahd University Hospital (KFHU), Dammam, Saudi Arabia. The information included demographic, histopathological, and immunohistochemical findings. Results: Out of 482 breast cancer patients, 60% (n=286) were Saudis, and 40% (n=196) were non-Saudis. Data showed a wide age distribution; however, most cases (80%) were seen in the third through fifth decades, with a median age at diagnosis of 51 ±12 years. Over years, breast cancer in Saudi patients was increasingly seen at a younger age (p=0.003). While tumors were increasingly detected at earlier stages (p=0.003); however, stage III & IV tumors (p=0.033) and human epidermal growth factor receptor-2 overexpressed tumors (p=0.035) were more frequently seen at a younger age. Interestingly, these associations were not significant in non-Saudi patients. Conclusion: Although, the current findings might help future studies to identify variables that could lead to better management of breast cancer in this region; however, a wider investigation including other centers in the eastern province is needed.
- Open Access
- 2 January 2021
- Published by Springer Nature in BMC Surgery
- Vol. 21 (1) , 1-6
Concomitant hepatic tuberculosis and hepatocellular carcinoma: a case report and review of the literature
Background: Hepatocellular carcinoma (HCC) is the most common primary liver malignancy that is strongly associated with chronic liver disease. Isolated hepatic tuberculosis is an uncommon type of tuberculosis. Concomitant occurrence of both conditions is extremely rare. Case presentation: We report the case of a 47-year-old man who presented with fever and abdominal pain for 3 months prior to presentation. He reported a history of anorexia and significant weight loss. Abdominal examination revealed a tender, enlarged liver. Abdominal computed tomography (CT) demonstrated a solid heterogeneous hepatic mass with peripheral arterial enhancement, but no venous washout, conferring a radiological impression of suspected cholangiocarcinoma. However, a CT-guided biopsy of the lesion resulted in the diagnosis of concomitant HCC and isolated hepatic tuberculosis. Conclusion: A rapid increase in tumor size should draw attention to the possibility of a concomitant infectious process. Clinicians must have a high index of suspicion for tuberculosis, especially in patients from endemic areas, in order to initiate early and proper treatment.
- 2 January 2021
- Published by Springer Nature in BMC Surgery
- Vol. 21 (1) , 1-6
Open AccessConcomitant hepatic tuberculosis and hepatocellular carcinoma: a case report and review of the literature
Background: Hepatocellular carcinoma (HCC) is the most common primary liver malignancy that is strongly associated with chronic liver disease. Isolated hepatic tuberculosis is an uncommon type of tuberculosis. Concomitant occurrence of both conditions is extremely rare. Case presentation: We report the case of a 47-year-old man who presented with fever and abdominal pain for 3 months prior to presentation. He reported a history of anorexia and significant weight loss. Abdominal examination revealed a tender, enlarged liver. Abdominal computed tomography (CT) demonstrated a solid heterogeneous hepatic mass with peripheral arterial enhancement, but no venous washout, conferring a radiological impression of suspected cholangiocarcinoma. However, a CT-guided biopsy of the lesion resulted in the diagnosis of concomitant HCC and isolated hepatic tuberculosis. Conclusion: A rapid increase in tumor size should draw attention to the possibility of a concomitant infectious process. Clinicians must have a high index of suspicion for tuberculosis, especially in patients from endemic areas, in order to initiate early and proper treatment.
- Open Access
- 22 December 2020
- Published by PAGEPress Publications in Dermatology Reports
- Vol. 12 (3) , 79-81
Co-expression of CD34 and h-caldesmon in a benign meningioma-like dermal neoplasm, a case report
Meningioma-like dermal tumor with diffuse coexpression of CD34 and hcaldesmon is rarely reported. Herein, we report a case of a 58-years-old woman who complained of a solitary dome-shaped papule on the left hand. An ellipse of skin measuring 1 x 0.5 x 0.5 cm was excised and sent for histopathological evaluation. Upon sectioning, the specimen showed a whitish firm dermal nodule measuring 3 mm in its greatest dimension. Microscopic examination revealed a well-circumscribed barely encapsulated dermal lesion showing compact round whorled sheets formed of round to ovoid uniform cells with abundant pink cytoplasm. Occasional intranuclear vacuoles were seen. A minor capillary-sized vascular component was seen in the background. Immunohistochemical (IHC) study revealed a diffuse positivity of tumor cells to CD34 and h-caldesmon along with faint reaction to Smooth Muscle Actin (SMA) and ER. However, Desmin, S100, HMB45, EMA, Pan Cytokeratin, and Chromogranin were all negative. Ki67 was very low (1%). The main differential diagnoses of the current lesion are meningioma and glomus family tumors. While the current lesion is morphologically reminiscent of cutaneous meningioma; neither the location nor the IHC stains support that diagnosis. The glomus family is highly suggestive. However, the location, the compact nature of the proliferation, and the positivity of CD34, all are unusual in such entities.
- 22 December 2020
- Published by PAGEPress Publications in Dermatology Reports
- Vol. 12 (3) , 79-81
Open AccessCo-expression of CD34 and h-caldesmon in a benign meningioma-like dermal neoplasm, a case report
Meningioma-like dermal tumor with diffuse coexpression of CD34 and hcaldesmon is rarely reported. Herein, we report a case of a 58-years-old woman who complained of a solitary dome-shaped papule on the left hand. An ellipse of skin measuring 1 x 0.5 x 0.5 cm was excised and sent for histopathological evaluation. Upon sectioning, the specimen showed a whitish firm dermal nodule measuring 3 mm in its greatest dimension. Microscopic examination revealed a well-circumscribed barely encapsulated dermal lesion showing compact round whorled sheets formed of round to ovoid uniform cells with abundant pink cytoplasm. Occasional intranuclear vacuoles were seen. A minor capillary-sized vascular component was seen in the background. Immunohistochemical (IHC) study revealed a diffuse positivity of tumor cells to CD34 and h-caldesmon along with faint reaction to Smooth Muscle Actin (SMA) and ER. However, Desmin, S100, HMB45, EMA, Pan Cytokeratin, and Chromogranin were all negative. Ki67 was very low (1%). The main differential diagnoses of the current lesion are meningioma and glomus family tumors. While the current lesion is morphologically reminiscent of cutaneous meningioma; neither the location nor the IHC stains support that diagnosis. The glomus family is highly suggestive. However, the location, the compact nature of the proliferation, and the positivity of CD34, all are unusual in such entities.