Sahil Saraf
Biography
Dr. Sahil Ajit Saraf is an accomplished Pathologist with over 13 years of experience in diagnostic pathology, research, and medical leadership. He earned his MBBS from JJM Medical College and his MD in Pathology from Vydehi Institute of Medical Sciences, Bangalore. He is currently pursuing FRCPath (Histopathology, UK) and completed fellowship training at Singapore General Hospital, Department of Anatomical Pathology.
Dr. Saraf has worked with leading institutions including the National Cancer Center Singapore and Tata Memorial Hospital, Mumbai, and is presently serving as Senior Specialist at V.G. Saraf Memorial Hospital, Kochi. He was formerly the Medical Director at Qritive Pte. Ltd., Singapore, where he pioneered AI-driven diagnostic solutions in pathology and led international collaborations with over 450 pathologists from 22 countries.
His expertise spans cancer diagnostics, histopathology, molecular pathology, and the application of artificial intelligence in pathology. He has been an invited speaker at prestigious forums such as USCAP (USA), APCON (India), and international pathology masterclasses. His research has been published in high-impact journals including Scientific Reports and Heliyon.
Dr. Saraf received the 2024 ISBP-BCRF Larry Norton MD Trainee Abstract Award at USCAP for his innovative research on deep learning models for breast tumor pathology.
Research Interest
Experienced Pathologist working for 13 years, accomplished in analyzing tissue samples for diagnosis, disease management and research; Leadership Skills, Academics, Medical Affairs, Research & Development , Clinical Skills, Pathology, Clinical Studies, PG and UG Teaching, Scientific Research & Writing, Public Speaking, Data Analysis, Regulatory Compliance, Commercial Experience, Artificial Intelligence (AI)
Abstract
Clinical Impact of AI - Augmented Lymph Node Evaluation in Metastatic Gastric, Colorectal and Breast Cancer:
Examination of lymph nodes (LN) plays a critical role in cancer staging and prognosis, however, it remains a time-consuming and labor-intensive process in pathology. While artificial intelligence (AI) tools have shown promise in improving diagnostic accuracy, their real-world clinical utility in LN metastasis detection across multiple cancer types remains underexplored.
Objective
To evaluate the diagnostic performance and efficiency of an AI module in detecting LN metastases from gastric, colorectal, and breast cancers, and to assess its impact on pathologists' workflow.
Design
A retrospective study was conducted using 314 whole-slide images from 95 patients who underwent resection for gastric, colorectal, or breast cancer. Three board-certified pathologists reviewed the slides with and without AI assistance. Diagnostic accuracy, review time, and number of mouse clicks required to detect metastases were recorded and compared.
Results
AI assistance increased sensitivity from 91.8-3.9% to 95.9% for all pathologists, while specificity remained high (97.0-98.9%). Time to detect LN metastases reduced by up to 78% for some cancer types. The AI-guided click-based review required an average of 1.4-5.2 clicks depending on tissue type, with colorectal metastases detected most efficiently. Challenging subtypes, such as breast carcinoma with apocrine differentiation, required more extensive interaction. Micrometastases across all three cancer types were successfully identified by the AI.
Conclusions
The AI module improved pathologists' sensitivity in detecting LN metastases and significantly reduced review time, particularly for positive nodes. These findings support the integration of AI tools to enhance diagnostic efficiency and accuracy in routine pathology practice.
